mnbvc188199/Warrior_EA
Watch
1
0
Fork
You've already forked Warrior_EA
 1
forked from animatedread/Warrior_EA
Code Pull requests Activity
Warrior_EA/Expert/AIBase/Training.mqh

3549 lines
213 KiB
MQL5
Raw Permalink Normal View History

feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
//+------------------------------------------------------------------+
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
//| Warrior_EA |
//| AnimateDread |
//| |
refactor(comments): box headers to stdlib length The //| box blocks were excluded from 0b06f8e and 5efdb48 and were what remained: 160 of them ran to 10+ lines, the longest to 88. Compressed to their leading topic sentences - 5 lines for a function header, 8 for a file header - keeping the box format and the standard MQL5 name/author lines verbatim. Verified at the BYTE level this time, across every in-scope file: the list of non-comment lines is byte-identical to HEAD and braces balance. The first check compared a locale-decoded 'git show' against a UTF-8 read and flagged 25 files that had not changed at all - every BOM and every non-ASCII line mismatched. 47,696 -> 40,665 lines in scope; comment share 38% -> 26%. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:30:14 -04:00
//| Era loop, plateau ladder, checkpoint selection, deploy/finalise. |
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
//+------------------------------------------------------------------+
#ifndef WARRIOR_AIBASE_TRAINING_MQH
#define WARRIOR_AIBASE_TRAINING_MQH
//+------------------------------------------------------------------+
refactor(comments): box headers to stdlib length The //| box blocks were excluded from 0b06f8e and 5efdb48 and were what remained: 160 of them ran to 10+ lines, the longest to 88. Compressed to their leading topic sentences - 5 lines for a function header, 8 for a file header - keeping the box format and the standard MQL5 name/author lines verbatim. Verified at the BYTE level this time, across every in-scope file: the list of non-comment lines is byte-identical to HEAD and braces balance. The first check compared a locale-decoded 'git show' against a UTF-8 read and flagged 25 files that had not changed at all - every BOM and every non-ASCII line mismatched. 47,696 -> 40,665 lines in scope; comment share 38% -> 26%. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:30:14 -04:00
//| Does the checkpoint about to deploy survive having been CHOSEN? |
feat: gate deployment on the null of the MAXIMUM, not the per-era null EDGE_MIN_SIGMAS is a PER-ERA test and the deployed model is the MAXIMUM over every era a run ranks. A 2-sigma one-sided test passes on noise with probability 0.0228 per era, so over N eras the chance at least one clears it is 1-(1-0.0228)^N: 34% by era 18, 80% by era 70, 93% by era 112. The gate was near-certain to open on a long run whatever the data held. It did. HYBRID deployed 2026-08-08 at dir-precision 35.5% vs 34% chance - +1.5pp, best of 112 eras whose per-era values wandered 30%..35.5%. At the call counts these runs produce that is p_family 0.92..0.9999. Every OTHER best-of-N decision here already carries this correction, and every one REJECTS on this data: the barrier-geometry winner (null of the maximum over 6, p=0.3902), the indicator tuner (Sidak, p=1.0000), the MI lag profile (null of the maximum over 21 lags). The one decision that ships a model to a live account had none. BestCheckpointSurvivesSelection() re-tests the checkpoint that is about to deploy: z = (precision - chance)/SE, SE = sqrt(p0(1-p0)/n) p_single = P(Z >= z) p_family = 1 - (1-p_single)^N against DEPLOY_FAMILY_WISE_ALPHA. It uses the checkpoint's OWN snapshotted precision/chance/call-count, not the latest era's, because the model that ships is the one that has to clear the bar. N counts CANDIDATE eras (coverage measurable, at least one directional call) - an era that called nothing directional could never have become the best, so counting it would make the gate stricter than the search that actually happened. Conservative on purpose: consecutive eras share OOS bars and differ by one gradient step, so they are nowhere near N independent draws and the true family-wise error is below this bound. This gate decides what trades real money and the house posture is reject-unless-demonstrated. Effect at 2900 directional calls / N=112: required edge goes 1.76pp -> 2.92pp. A real edge clears it; +1.5pp does not. Applied to BOTH automatic paths - the plateau ladder's stage-3 deploy and the m_trainingComplete assignment - which must stay identical or the flag persisted into the .nnw disagrees with the decision to stop, and a reload runs inference on a model the ladder refused. NOT applied to the two operator paths (era-cap deploy, panel Deploy button). Those stay the operator's call; ReportSelectionGateVerdict() logs the verdict beside them so an authorised deploy can never later be misread as a validated one. NormalUpperTail() is A&S 26.2.17 (|err| < 7.5e-8), self-contained rather than pulling in Math\Stat. Verified against reference values to 6dp: Q(1.645)=0.049985, Q(1.96)=0.024998, Q(3.0)=0.001350. Its locals are ntB1..ntB5 because AI\Network.mqh line 79 does "#define b1 AdamBeta1". Compiles clean: 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-08 18:01:04 -04:00
//+------------------------------------------------------------------+
bool CExpertSignalAIBase::BestCheckpointSurvivesSelection(double &zObs, double &pFamily, int &nTried)
{
zObs = 0.0;
pFamily = 1.0;
nTried = MathMax(m_deployCandidateEras, 1);
//--- No ranked era yet, or a degenerate chance rate: nothing to test, so nothing to deploy.
if(m_bestDirCalls <= 0 || m_bestDirPrecPct < 0.0 || m_bestChancePrecPct <= 0.0 || m_bestChancePrecPct >= 100.0)
return false;
refactor(dry): one binomial arithmetic for every "is this edge real" test The formula p(1-p)/n was transcribed nine times across six files - the two deploy gates, the two edge floors, the collapse recall floor, the barrier rung ladder, the inference bin SE, the pooled inverse-variance weights and both detectability reports. System\BinomialStats.mqh now holds it once, as free functions with no class dependency, so the god-class declaration does not grow to host pure math. BinomialVar(p, n) p(1-p)/n BinomialSEPct(p, n) 100*sqrt(p(1-p)/n) BinomialCallsForEdge(p, edge, sigmas) the same, solved for n NormalUpperTailQ(z) Q(z), via Math\Stat\Normal.mqh SidakFamilyP(z, N) 1-(1-Q(z))^N Value-preserving by construction: rates go in as probabilities so no call site gained a *100/100 round-trip, and BinomialSEPct is written through BinomialVar so the multiply order is the one it replaced. Every degenerate guard each site carried (p<=0, p>=1, n<=0) now lives in one place and returns the 0 those sites already treated as "no bar to clear". CExpertSignalAIBase::NormalUpperTail is gone; NormalUpperTailQ replaces it. What consolidating SURFACED, and is deliberately NOT changed here: the two Sidak selection gates compute their SE on the RAW call count, while every other SE in the project deflates by EffectiveSampleSize() for triple- barrier label overlap. That makes them the most permissive test in the codebase, by ~sqrt(mean label lifespan). Correcting it tightens a live deploy bar, which is a policy decision, not a refactor - flagged in the code at both sites. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-19 19:50:24 -04:00
//--- RAW calls, not EffectiveSampleSize(): alone among the SEs in this project this one is not
//--- deflated for label overlap, which makes it the most permissive test here. Left as measured
//--- rather than corrected in passing - tightening a live deploy bar is a policy change.
double se = BinomialSEPct(m_bestChancePrecPct / 100.0, (double)m_bestDirCalls);
feat: gate deployment on the null of the MAXIMUM, not the per-era null EDGE_MIN_SIGMAS is a PER-ERA test and the deployed model is the MAXIMUM over every era a run ranks. A 2-sigma one-sided test passes on noise with probability 0.0228 per era, so over N eras the chance at least one clears it is 1-(1-0.0228)^N: 34% by era 18, 80% by era 70, 93% by era 112. The gate was near-certain to open on a long run whatever the data held. It did. HYBRID deployed 2026-08-08 at dir-precision 35.5% vs 34% chance - +1.5pp, best of 112 eras whose per-era values wandered 30%..35.5%. At the call counts these runs produce that is p_family 0.92..0.9999. Every OTHER best-of-N decision here already carries this correction, and every one REJECTS on this data: the barrier-geometry winner (null of the maximum over 6, p=0.3902), the indicator tuner (Sidak, p=1.0000), the MI lag profile (null of the maximum over 21 lags). The one decision that ships a model to a live account had none. BestCheckpointSurvivesSelection() re-tests the checkpoint that is about to deploy: z = (precision - chance)/SE, SE = sqrt(p0(1-p0)/n) p_single = P(Z >= z) p_family = 1 - (1-p_single)^N against DEPLOY_FAMILY_WISE_ALPHA. It uses the checkpoint's OWN snapshotted precision/chance/call-count, not the latest era's, because the model that ships is the one that has to clear the bar. N counts CANDIDATE eras (coverage measurable, at least one directional call) - an era that called nothing directional could never have become the best, so counting it would make the gate stricter than the search that actually happened. Conservative on purpose: consecutive eras share OOS bars and differ by one gradient step, so they are nowhere near N independent draws and the true family-wise error is below this bound. This gate decides what trades real money and the house posture is reject-unless-demonstrated. Effect at 2900 directional calls / N=112: required edge goes 1.76pp -> 2.92pp. A real edge clears it; +1.5pp does not. Applied to BOTH automatic paths - the plateau ladder's stage-3 deploy and the m_trainingComplete assignment - which must stay identical or the flag persisted into the .nnw disagrees with the decision to stop, and a reload runs inference on a model the ladder refused. NOT applied to the two operator paths (era-cap deploy, panel Deploy button). Those stay the operator's call; ReportSelectionGateVerdict() logs the verdict beside them so an authorised deploy can never later be misread as a validated one. NormalUpperTail() is A&S 26.2.17 (|err| < 7.5e-8), self-contained rather than pulling in Math\Stat. Verified against reference values to 6dp: Q(1.645)=0.049985, Q(1.96)=0.024998, Q(3.0)=0.001350. Its locals are ntB1..ntB5 because AI\Network.mqh line 79 does "#define b1 AdamBeta1". Compiles clean: 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-08 18:01:04 -04:00
if(se <= 0.0)
return false;
zObs = (m_bestDirPrecPct - m_bestChancePrecPct) / se;
refactor(dry): one binomial arithmetic for every "is this edge real" test The formula p(1-p)/n was transcribed nine times across six files - the two deploy gates, the two edge floors, the collapse recall floor, the barrier rung ladder, the inference bin SE, the pooled inverse-variance weights and both detectability reports. System\BinomialStats.mqh now holds it once, as free functions with no class dependency, so the god-class declaration does not grow to host pure math. BinomialVar(p, n) p(1-p)/n BinomialSEPct(p, n) 100*sqrt(p(1-p)/n) BinomialCallsForEdge(p, edge, sigmas) the same, solved for n NormalUpperTailQ(z) Q(z), via Math\Stat\Normal.mqh SidakFamilyP(z, N) 1-(1-Q(z))^N Value-preserving by construction: rates go in as probabilities so no call site gained a *100/100 round-trip, and BinomialSEPct is written through BinomialVar so the multiply order is the one it replaced. Every degenerate guard each site carried (p<=0, p>=1, n<=0) now lives in one place and returns the 0 those sites already treated as "no bar to clear". CExpertSignalAIBase::NormalUpperTail is gone; NormalUpperTailQ replaces it. What consolidating SURFACED, and is deliberately NOT changed here: the two Sidak selection gates compute their SE on the RAW call count, while every other SE in the project deflates by EffectiveSampleSize() for triple- barrier label overlap. That makes them the most permissive test in the codebase, by ~sqrt(mean label lifespan). Correcting it tightens a live deploy bar, which is a policy decision, not a refactor - flagged in the code at both sites. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-19 19:50:24 -04:00
pFamily = SidakFamilyP(zObs, nTried);
feat: gate deployment on the null of the MAXIMUM, not the per-era null EDGE_MIN_SIGMAS is a PER-ERA test and the deployed model is the MAXIMUM over every era a run ranks. A 2-sigma one-sided test passes on noise with probability 0.0228 per era, so over N eras the chance at least one clears it is 1-(1-0.0228)^N: 34% by era 18, 80% by era 70, 93% by era 112. The gate was near-certain to open on a long run whatever the data held. It did. HYBRID deployed 2026-08-08 at dir-precision 35.5% vs 34% chance - +1.5pp, best of 112 eras whose per-era values wandered 30%..35.5%. At the call counts these runs produce that is p_family 0.92..0.9999. Every OTHER best-of-N decision here already carries this correction, and every one REJECTS on this data: the barrier-geometry winner (null of the maximum over 6, p=0.3902), the indicator tuner (Sidak, p=1.0000), the MI lag profile (null of the maximum over 21 lags). The one decision that ships a model to a live account had none. BestCheckpointSurvivesSelection() re-tests the checkpoint that is about to deploy: z = (precision - chance)/SE, SE = sqrt(p0(1-p0)/n) p_single = P(Z >= z) p_family = 1 - (1-p_single)^N against DEPLOY_FAMILY_WISE_ALPHA. It uses the checkpoint's OWN snapshotted precision/chance/call-count, not the latest era's, because the model that ships is the one that has to clear the bar. N counts CANDIDATE eras (coverage measurable, at least one directional call) - an era that called nothing directional could never have become the best, so counting it would make the gate stricter than the search that actually happened. Conservative on purpose: consecutive eras share OOS bars and differ by one gradient step, so they are nowhere near N independent draws and the true family-wise error is below this bound. This gate decides what trades real money and the house posture is reject-unless-demonstrated. Effect at 2900 directional calls / N=112: required edge goes 1.76pp -> 2.92pp. A real edge clears it; +1.5pp does not. Applied to BOTH automatic paths - the plateau ladder's stage-3 deploy and the m_trainingComplete assignment - which must stay identical or the flag persisted into the .nnw disagrees with the decision to stop, and a reload runs inference on a model the ladder refused. NOT applied to the two operator paths (era-cap deploy, panel Deploy button). Those stay the operator's call; ReportSelectionGateVerdict() logs the verdict beside them so an authorised deploy can never later be misread as a validated one. NormalUpperTail() is A&S 26.2.17 (|err| < 7.5e-8), self-contained rather than pulling in Math\Stat. Verified against reference values to 6dp: Q(1.645)=0.049985, Q(1.96)=0.024998, Q(3.0)=0.001350. Its locals are ntB1..ntB5 because AI\Network.mqh line 79 does "#define b1 AdamBeta1". Compiles clean: 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-08 18:01:04 -04:00
return (pFamily <= DEPLOY_FAMILY_WISE_ALPHA);
}
//+------------------------------------------------------------------+
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
//| ENSEMBLE GATE - the same test as above, asked of the VOTE. |
//| See the ENSEMBLE DEPLOY GATE block in ExpertSignalAIBase.mqh for |
//| why the vote rather than the member is the thing being gated. |
//+------------------------------------------------------------------+
bool CExpertSignalAIBase::EnsembleSurvivesSelection(double &zObs, double &pFamily, int &nTried)
{
zObs = 0.0;
pFamily = 1.0;
nTried = MathMax(g_ensCandidateEras, 1);
if(g_ensBestCalls <= 0 || g_ensBestPrecPct < 0.0 || g_ensBestChancePct <= 0.0 || g_ensBestChancePct >= 100.0)
return false;
refactor(dry): one binomial arithmetic for every "is this edge real" test The formula p(1-p)/n was transcribed nine times across six files - the two deploy gates, the two edge floors, the collapse recall floor, the barrier rung ladder, the inference bin SE, the pooled inverse-variance weights and both detectability reports. System\BinomialStats.mqh now holds it once, as free functions with no class dependency, so the god-class declaration does not grow to host pure math. BinomialVar(p, n) p(1-p)/n BinomialSEPct(p, n) 100*sqrt(p(1-p)/n) BinomialCallsForEdge(p, edge, sigmas) the same, solved for n NormalUpperTailQ(z) Q(z), via Math\Stat\Normal.mqh SidakFamilyP(z, N) 1-(1-Q(z))^N Value-preserving by construction: rates go in as probabilities so no call site gained a *100/100 round-trip, and BinomialSEPct is written through BinomialVar so the multiply order is the one it replaced. Every degenerate guard each site carried (p<=0, p>=1, n<=0) now lives in one place and returns the 0 those sites already treated as "no bar to clear". CExpertSignalAIBase::NormalUpperTail is gone; NormalUpperTailQ replaces it. What consolidating SURFACED, and is deliberately NOT changed here: the two Sidak selection gates compute their SE on the RAW call count, while every other SE in the project deflates by EffectiveSampleSize() for triple- barrier label overlap. That makes them the most permissive test in the codebase, by ~sqrt(mean label lifespan). Correcting it tightens a live deploy bar, which is a policy decision, not a refactor - flagged in the code at both sites. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-19 19:50:24 -04:00
//--- Raw calls here too, matching the member gate above so neither is the easier one to clear.
double se = BinomialSEPct(g_ensBestChancePct / 100.0, (double)g_ensBestCalls);
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
if(se <= 0.0)
return false;
zObs = (g_ensBestPrecPct - g_ensBestChancePct) / se;
refactor(dry): one binomial arithmetic for every "is this edge real" test The formula p(1-p)/n was transcribed nine times across six files - the two deploy gates, the two edge floors, the collapse recall floor, the barrier rung ladder, the inference bin SE, the pooled inverse-variance weights and both detectability reports. System\BinomialStats.mqh now holds it once, as free functions with no class dependency, so the god-class declaration does not grow to host pure math. BinomialVar(p, n) p(1-p)/n BinomialSEPct(p, n) 100*sqrt(p(1-p)/n) BinomialCallsForEdge(p, edge, sigmas) the same, solved for n NormalUpperTailQ(z) Q(z), via Math\Stat\Normal.mqh SidakFamilyP(z, N) 1-(1-Q(z))^N Value-preserving by construction: rates go in as probabilities so no call site gained a *100/100 round-trip, and BinomialSEPct is written through BinomialVar so the multiply order is the one it replaced. Every degenerate guard each site carried (p<=0, p>=1, n<=0) now lives in one place and returns the 0 those sites already treated as "no bar to clear". CExpertSignalAIBase::NormalUpperTail is gone; NormalUpperTailQ replaces it. What consolidating SURFACED, and is deliberately NOT changed here: the two Sidak selection gates compute their SE on the RAW call count, while every other SE in the project deflates by EffectiveSampleSize() for triple- barrier label overlap. That makes them the most permissive test in the codebase, by ~sqrt(mean label lifespan). Correcting it tightens a live deploy bar, which is a policy decision, not a refactor - flagged in the code at both sites. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-19 19:50:24 -04:00
pFamily = SidakFamilyP(zObs, nTried);
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
return (pFamily <= DEPLOY_FAMILY_WISE_ALPHA);
}
//+------------------------------------------------------------------+
refactor(comments): box headers to stdlib length The //| box blocks were excluded from 0b06f8e and 5efdb48 and were what remained: 160 of them ran to 10+ lines, the longest to 88. Compressed to their leading topic sentences - 5 lines for a function header, 8 for a file header - keeping the box format and the standard MQL5 name/author lines verbatim. Verified at the BYTE level this time, across every in-scope file: the list of non-comment lines is byte-identical to HEAD and braces balance. The first check compared a locale-decoded 'git show' against a UTF-8 read and flagged 25 files that had not changed at all - every BOM and every non-ASCII line mismatched. 47,696 -> 40,665 lines in scope; comment share 38% -> 26%. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:30:14 -04:00
//| JOINT CHECKPOINT: snapshot EVERY member's weights, at this one |
//| era, and commit each member's own era statistics as the stats |
//| its best checkpoint is described by. |
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
//+------------------------------------------------------------------+
void CExpertSignalAIBase::EnsembleCommitJointCheckpoint(const long votedEra)
{
int captured = 0, members = 0;
for(int i = 0; i < ArraySize(g_warriorEnsemble); i++)
{
CExpertSignalAIBase *mm = g_warriorEnsemble[i];
if(CheckPointer(mm) == POINTER_INVALID || mm.m_ensembleIndex < 0)
continue;
if(mm.m_trainingComplete || mm.m_trainingStopRequested || mm.m_trainingPaused || !mm.m_isInitialized)
continue;
members++;
//--- The member's OWN figures at the winning era. They describe this member's contribution to a
//--- checkpoint the ENSEMBLE selected, which is why they are committed from the stash rather
//--- than from a per-member ranking: no member "won" this era, the vote did.
mm.m_bestOosForecast = mm.m_eraStatBlended;
mm.m_bestBalancedOos = mm.m_eraStatScore;
mm.m_bestPassedRecall = mm.m_eraStatTradeable;
mm.m_bestBothSidesLive = mm.m_eraStatTwoSided;
mm.m_bestDirPrecPct = mm.m_eraStatPrecPct;
mm.m_bestChancePrecPct = mm.m_eraStatChancePct;
mm.m_bestDirCalls = mm.m_eraStatCalls;
mm.m_bestDirConfThreshold = mm.m_eraStatThreshold;
//--- In-memory snapshot, same primitive the solo path uses. A member whose capture fails keeps
//--- m_haveOosCheckpoint false and is reported - it would otherwise deploy whatever weights it
//--- happens to hold at the end of the run, silently breaking the "deploy what was measured"
//--- guarantee this whole mechanism exists for.
if(CheckPointer(mm.Net) != POINTER_INVALID && mm.Net.CaptureWeights())
{
mm.m_haveOosCheckpoint = true;
mm.m_checkpointEra = votedEra; // the deploy gate cross-checks this against the winning era
captured++;
}
else
Print(mm.ID + ": WARNING - joint ensemble checkpoint capture FAILED at era " +
IntegerToString((int)votedEra) + ". This member cannot contribute the weights the vote"
" was measured with; the ensemble will not deploy a checkpoint it cannot reproduce.");
//--- a new joint best retires the shared ladder for everyone
mm.m_erasSinceBestBalanced = 0;
mm.m_plateauStage = 0;
mm.m_restartBoostErasLeft = 0;
mm.m_consecutiveRegressions = 0;
}
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- PARTIAL CAPTURE IS NOT A CHECKPOINT. Rolling it back lets the run carry on and simply find
//--- its best again.
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
if(captured < members)
{
g_ensBestScore = -1.0;
g_ensBestTradeable = false;
g_ensBestTwoSided = false;
g_ensBestCalls = 0;
g_ensBestEra = -1;
Print("AI ensemble: joint checkpoint INCOMPLETE at era " + IntegerToString((int)votedEra) +
" (" + IntegerToString(captured) + " of " + IntegerToString(members) + " members captured)"
" - discarding this era as the best; the search continues from no joint checkpoint.");
}
}
//+------------------------------------------------------------------+
refactor(comments): box headers to stdlib length The //| box blocks were excluded from 0b06f8e and 5efdb48 and were what remained: 160 of them ran to 10+ lines, the longest to 88. Compressed to their leading topic sentences - 5 lines for a function header, 8 for a file header - keeping the box format and the standard MQL5 name/author lines verbatim. Verified at the BYTE level this time, across every in-scope file: the list of non-comment lines is byte-identical to HEAD and braces balance. The first check compared a locale-decoded 'git show' against a UTF-8 read and flagged 25 files that had not changed at all - every BOM and every non-ASCII line mismatched. 47,696 -> 40,665 lines in scope; comment share 38% -> 26%. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:30:14 -04:00
//| Once per era, on the LAST still-training member to finish its |
//| pass-3 scan: score the combined vote, rank the era, checkpoint, |
//| advance the shared plateau ladder, and decide deployment. |
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
//+------------------------------------------------------------------+
void CExpertSignalAIBase::EnsembleEraVerdict(const int needMask, const long votedEra, double &etaLocal)
{
fix(gate): the ensemble gate certified a vote the EA never casts g_ensembleVoteThreshold's comment claims the combined-vote scorer "fires on the same criterion the live trade does". It did not. Two independent mismatches, both silent: CURRENCY. Each member contributed its raw signed confidence x100 - a 33..100 number straight off the softmax head. Live contributes m_weight x the tier's pattern weight, and BOTH of those are rewritten from the signal DB by UpdateSignalsWeights(). A head output and a DB-ranked win-rate weight share an axis and nothing relates them, so the same bar was one number to the gate and a different one to the order path. Same shape as the 2026-08-09 geometry incident: certified on one game, paid on another. DENOMINATOR. The gate divided by the member count, so an abstaining member pulled the average toward zero. CExpertSignalCustom::Direction() skips a zero contribution in BOTH the sum and the count (`if(direction == 0) continue;` before `number++`) - live is a mean over VOTERS. The gate was therefore scoring a strictly more agreement-heavy set of bars than the EA trades. The contribution hook's own comment asserted the opposite ("abstentions dilute the average exactly as they do in the live vote"), while the AI_CHOICE enum 20 lines away correctly documented union semantics. LiveVoteContribution() is now the single definition of "what this member votes", called from the gate; the live path reaches the same arithmetic through LongCondition/ShortCondition. g_ensVoteVoterMask records who actually voted, separately from who evaluated the bar, because those are the divisor and the shared-population test respectively. ConfidenceTier() is split into ConfidenceTierFor(signal) plus a thin live-bar wrapper - the OOS scan holds the scanned bar's decision in a local, and dPrevSignal is a different bar. NOT changed, deliberately: the gate still does not model live NMS declustering, and the per-member solo gate still scores every directional call rather than threshold-clearing ones. Both are selection-metric changes and this codebase has twice been bitten by switching one blind. Also corrects a stale paragraph in m_pattern_0's declaration block quoting 80/87/93/100 as the tier defaults. The constructor is 25/50/75/100 and has been since the confidence floor and alternation gate were removed; the block carried both tables at once, and the dead one was quoted back as fact. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 15:23:33 -04:00
int members = EnsembleBitCount(needMask);
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
//--- One trainer left (the others deployed, paused or stopped) is not an ensemble read: the
//--- "vote" would be that member's own signal and the gate would silently become the solo gate
//--- under an ensemble label. Members keep training; nothing is ranked or deployed from here.
if(members < 2)
return;
//--- SHARED BARS ONLY. A bar one member skipped (feature-window failure) has an average over a
//--- different membership, which is a different quantity - averaging it in would make the score
//--- depend on which member happened to fail where.
int shared = 0, fired = 0, wins = 0, firedLong = 0, firedShort = 0;
feat(ensemble): per-NN inputs replace the preset selector - the meta head becomes the vote's gate User design (2026-08-19): 'remove the enum menu that selects neural networks... individual inputs for every NN just like classic signals... the META NN should be integrated into the voting decision pipeline when enabled... as a bonus meta labelling is applied to enabled NNs.' - AI_CHOICE is GONE (tombstoned per the stale-.set doctrine). Use_MLP/Use_CONV/Use_LSTM/ Use_CONVLSTM are ordinary bools like the classic votes; the ensemble arithmetic adapts to any subset because the consensus divisor is the enabled capable weight. Two or more enabled = ensemble (|ENS1 token + joint gate, exactly the old AI_HYBRID fingerprints, so existing weight files keep loading); one = the old solo preset; none = classic-only. - Use_MetaLabeling un-couples META from the direction NNs (the old selector made them mutually exclusive). S3 ships: CSignalMETA::LiveMetaGate scores each vote-cleared entry (shared window at bar 1 + proposal descriptor: side, net vote, live geometry, spread/ATR; pattern one-hot ZEROED - ranking, not calibrated probability, documented in the body) and vetoes below the cost-adjusted break-even. Entries only; fail-open everywhere, loudly. - COEXISTENCE HAZARDS closed: VoteCapableWeight()=0 and ProspectiveVote()=false for the meta target - solo-only until today, a trained META would otherwise sit in the consensus divisor as a permanent abstainer and shrink every vote by its module weight. - CERTIFIED == TRADED: the ensemble era verdict replays the identical veto through the same g_warriorMetaGate pointer over its OOS fired bars (bar re-resolved from the row's own time; fail-open counted as fires and reported: 'metaGate: N approved, M vetoed, K unscored'). The overlay deliberately does NOT replay it (veto-filter-in-replay class, calendar-cliff precedent) - documented at the sweep site. Solo charts' own gate does not model the veto - the standing solo-gate caveat, documented at the input. - DB continuity: the pattern/journal DB fingerprint's first slot was (int)AIType; DbLegacyAiSlot() maps every legacy-expressible config to its OLD value (new 2-3 member subsets get 100+bitmask, outside the legacy range) so no existing database re-keys. filterID becomes the enabled roster via one EnabledNNSummary(). - HUD: the meta line shows the gate (armed/(trn), last P vs BE, ok/veto tally); the armed/disarmed announcement fires on state change via one latch (MetaGateArmedNow), not only when an entry happens to be proposed. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 13:01:02 -04:00
int metaOk = 0, metaVetoed = 0, metaOpen = 0;
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
int dirLabelBars = 0, alwaysLongWins = 0, alwaysShortWins = 0;
for(int r = 0; r < g_ensVoteRows; r++)
{
if((g_ensVoteMask[r] & needMask) != needMask)
continue;
shared++;
if(g_ensVoteDirLabel[r])
dirLabelBars++;
//--- zero-skill reference, measured over EVERY shared bar (see chancePrecPct's derivation in
//--- the era-end block): what always-long and always-short would have collected here
if(g_ensVoteWinLong[r])
alwaysLongWins++;
if(g_ensVoteWinShort[r])
alwaysShortWins++;
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- THE LIVE AGGREGATION, reproduced exactly (CExpertSignalCustom::Direction(), pass 2 plus
//--- the `result /= number` normalization): sum the members' signed votes, divide by how many
//--- of them ACTUALLY VOTED, and compare the magnitude against Signal_ThresholdOpen on the
//--- same 0..100 scale the tier weights already live on.
fix(gate): the ensemble gate certified a vote the EA never casts g_ensembleVoteThreshold's comment claims the combined-vote scorer "fires on the same criterion the live trade does". It did not. Two independent mismatches, both silent: CURRENCY. Each member contributed its raw signed confidence x100 - a 33..100 number straight off the softmax head. Live contributes m_weight x the tier's pattern weight, and BOTH of those are rewritten from the signal DB by UpdateSignalsWeights(). A head output and a DB-ranked win-rate weight share an axis and nothing relates them, so the same bar was one number to the gate and a different one to the order path. Same shape as the 2026-08-09 geometry incident: certified on one game, paid on another. DENOMINATOR. The gate divided by the member count, so an abstaining member pulled the average toward zero. CExpertSignalCustom::Direction() skips a zero contribution in BOTH the sum and the count (`if(direction == 0) continue;` before `number++`) - live is a mean over VOTERS. The gate was therefore scoring a strictly more agreement-heavy set of bars than the EA trades. The contribution hook's own comment asserted the opposite ("abstentions dilute the average exactly as they do in the live vote"), while the AI_CHOICE enum 20 lines away correctly documented union semantics. LiveVoteContribution() is now the single definition of "what this member votes", called from the gate; the live path reaches the same arithmetic through LongCondition/ShortCondition. g_ensVoteVoterMask records who actually voted, separately from who evaluated the bar, because those are the divisor and the shared-population test respectively. ConfidenceTier() is split into ConfidenceTierFor(signal) plus a thin live-bar wrapper - the OOS scan holds the scanned bar's decision in a local, and dPrevSignal is a different bar. NOT changed, deliberately: the gate still does not model live NMS declustering, and the per-member solo gate still scores every directional call rather than threshold-clearing ones. Both are selection-metric changes and this codebase has twice been bitten by switching one blind. Also corrects a stale paragraph in m_pattern_0's declaration block quoting 80/87/93/100 as the tier defaults. The constructor is 25/50/75/100 and has been since the confidence floor and alternation gate were removed; the block carried both tables at once, and the dead one was quoted back as fact. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 15:23:33 -04:00
int voters = EnsembleBitCount(g_ensVoteVoterMask[r] & needMask);
feat(vote): thresholds become confidence percentages, on ONE scale everywhere User request: "the entry/exit thresholds are manual numbers, I would like them to be confidence percentages, so the current 20 would be only 20% confidence in a profitable trade." WHY 20 WAS EVER SENSIBLE. Under UseDatabaseRanking both factors of a filter's contribution are win rates: the pattern weight is that pattern's measured win rate (UpdateSignalsWeights -> ApplyPatternWeight) and m_weight is the filter's average win rate over its patterns, /100. Dividing the sum by the VOTER COUNT therefore produced a mean of PRODUCTS of two win rates - a genuinely 60%-accurate filter firing a 60% pattern scored 0.60 x 60 = 36. The number was never on a probability scale, so its magnitude meant nothing on its own. Dividing by Sum(m_weight) instead makes it a weighted MEAN of win rates, which is a win rate: result = Sum(w_i*p_i)/Sum(w_i). Every voter at 60% now reads 60; MACD's double-divergence pattern (weight 100) voting alone reads 100. m_weight stops being a discount on the probability and becomes how much a filter's opinion COUNTS - which is what a module weight should always have been. Default Min_Vote_Open 20 -> 50: not a tightening, the same bar re-expressed. ONE SCALE, EVERYWHERE - the part that made this bigger than a rescale. Three other places compared against a 0..1 softmax confidence and would each have become a fresh currency mismatch the moment the input changed meaning: * the AI early-exit route (LiveSignedConfidence vs m_ai_exit_threshold) now reads m_lastAiVote - the AI filters' own weighted mean, undiluted by the classic side, which is the only reason that route exists - against the same m_threshold_close the averaged vote uses. m_ai_exit_threshold is retired rather than left dangling. * m_oosDecisionSeries now carries the vote, not the confidence, so the exit SIMULATION stops modelling a close rule the EA does not run. * ExitPolicy() clamped anything > 1.0 to zero. Passing the unscaled input through that would have silently switched vote exits off in the simulation while live went on running them - found before it shipped; the bound now tracks the scale. LiveSignedConfidence() is deliberately untouched and still 0..1: MM sizing, SL/TP scaling and the intelligent trailing want a model confidence, not a win rate. CALIBRATION CAVEAT, stated in the code where the claim is made: this is only a real probability to the extent the pattern weights are. A pattern with fewer than MIN_TRADES_FOR_WIN_RATE journaled trades keeps its DEFAULT weight - a designed prior (25/50/75/100 for the AI tiers), not a measurement. Until the signal DB fills, "60" means "the designed conviction of the patterns that fired". Closing that gap is the next commit. Also corrects VOTE_CLOSE_PRESETS' comment, which documented the two scales this removes. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 15:52:08 -04:00
if(voters <= 0 || g_ensVoteWeightSum[r] <= 0.0)
fix(gate): the ensemble gate certified a vote the EA never casts g_ensembleVoteThreshold's comment claims the combined-vote scorer "fires on the same criterion the live trade does". It did not. Two independent mismatches, both silent: CURRENCY. Each member contributed its raw signed confidence x100 - a 33..100 number straight off the softmax head. Live contributes m_weight x the tier's pattern weight, and BOTH of those are rewritten from the signal DB by UpdateSignalsWeights(). A head output and a DB-ranked win-rate weight share an axis and nothing relates them, so the same bar was one number to the gate and a different one to the order path. Same shape as the 2026-08-09 geometry incident: certified on one game, paid on another. DENOMINATOR. The gate divided by the member count, so an abstaining member pulled the average toward zero. CExpertSignalCustom::Direction() skips a zero contribution in BOTH the sum and the count (`if(direction == 0) continue;` before `number++`) - live is a mean over VOTERS. The gate was therefore scoring a strictly more agreement-heavy set of bars than the EA trades. The contribution hook's own comment asserted the opposite ("abstentions dilute the average exactly as they do in the live vote"), while the AI_CHOICE enum 20 lines away correctly documented union semantics. LiveVoteContribution() is now the single definition of "what this member votes", called from the gate; the live path reaches the same arithmetic through LongCondition/ShortCondition. g_ensVoteVoterMask records who actually voted, separately from who evaluated the bar, because those are the divisor and the shared-population test respectively. ConfidenceTier() is split into ConfidenceTierFor(signal) plus a thin live-bar wrapper - the OOS scan holds the scanned bar's decision in a local, and dPrevSignal is a different bar. NOT changed, deliberately: the gate still does not model live NMS declustering, and the per-member solo gate still scores every directional call rather than threshold-clearing ones. Both are selection-metric changes and this codebase has twice been bitten by switching one blind. Also corrects a stale paragraph in m_pattern_0's declaration block quoting 80/87/93/100 as the tier defaults. The constructor is 25/50/75/100 and has been since the confidence floor and alternation gate were removed; the block carried both tables at once, and the dead one was quoted back as fact. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 15:23:33 -04:00
continue; // every member abstained: no vote, no trade, not a fired bar
feat(vote): thresholds become confidence percentages, on ONE scale everywhere User request: "the entry/exit thresholds are manual numbers, I would like them to be confidence percentages, so the current 20 would be only 20% confidence in a profitable trade." WHY 20 WAS EVER SENSIBLE. Under UseDatabaseRanking both factors of a filter's contribution are win rates: the pattern weight is that pattern's measured win rate (UpdateSignalsWeights -> ApplyPatternWeight) and m_weight is the filter's average win rate over its patterns, /100. Dividing the sum by the VOTER COUNT therefore produced a mean of PRODUCTS of two win rates - a genuinely 60%-accurate filter firing a 60% pattern scored 0.60 x 60 = 36. The number was never on a probability scale, so its magnitude meant nothing on its own. Dividing by Sum(m_weight) instead makes it a weighted MEAN of win rates, which is a win rate: result = Sum(w_i*p_i)/Sum(w_i). Every voter at 60% now reads 60; MACD's double-divergence pattern (weight 100) voting alone reads 100. m_weight stops being a discount on the probability and becomes how much a filter's opinion COUNTS - which is what a module weight should always have been. Default Min_Vote_Open 20 -> 50: not a tightening, the same bar re-expressed. ONE SCALE, EVERYWHERE - the part that made this bigger than a rescale. Three other places compared against a 0..1 softmax confidence and would each have become a fresh currency mismatch the moment the input changed meaning: * the AI early-exit route (LiveSignedConfidence vs m_ai_exit_threshold) now reads m_lastAiVote - the AI filters' own weighted mean, undiluted by the classic side, which is the only reason that route exists - against the same m_threshold_close the averaged vote uses. m_ai_exit_threshold is retired rather than left dangling. * m_oosDecisionSeries now carries the vote, not the confidence, so the exit SIMULATION stops modelling a close rule the EA does not run. * ExitPolicy() clamped anything > 1.0 to zero. Passing the unscaled input through that would have silently switched vote exits off in the simulation while live went on running them - found before it shipped; the bound now tracks the scale. LiveSignedConfidence() is deliberately untouched and still 0..1: MM sizing, SL/TP scaling and the intelligent trailing want a model confidence, not a win rate. CALIBRATION CAVEAT, stated in the code where the claim is made: this is only a real probability to the extent the pattern weights are. A pattern with fewer than MIN_TRADES_FOR_WIN_RATE journaled trades keeps its DEFAULT weight - a designed prior (25/50/75/100 for the AI tiers), not a measurement. Until the signal DB fills, "60" means "the designed conviction of the patterns that fired". Closing that gap is the next commit. Also corrects VOTE_CLOSE_PRESETS' comment, which documented the two scales this removes. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 15:52:08 -04:00
double net = g_ensVoteSum[r] / g_ensVoteWeightSum[r];
fix(gate): the ensemble gate certified a vote the EA never casts g_ensembleVoteThreshold's comment claims the combined-vote scorer "fires on the same criterion the live trade does". It did not. Two independent mismatches, both silent: CURRENCY. Each member contributed its raw signed confidence x100 - a 33..100 number straight off the softmax head. Live contributes m_weight x the tier's pattern weight, and BOTH of those are rewritten from the signal DB by UpdateSignalsWeights(). A head output and a DB-ranked win-rate weight share an axis and nothing relates them, so the same bar was one number to the gate and a different one to the order path. Same shape as the 2026-08-09 geometry incident: certified on one game, paid on another. DENOMINATOR. The gate divided by the member count, so an abstaining member pulled the average toward zero. CExpertSignalCustom::Direction() skips a zero contribution in BOTH the sum and the count (`if(direction == 0) continue;` before `number++`) - live is a mean over VOTERS. The gate was therefore scoring a strictly more agreement-heavy set of bars than the EA trades. The contribution hook's own comment asserted the opposite ("abstentions dilute the average exactly as they do in the live vote"), while the AI_CHOICE enum 20 lines away correctly documented union semantics. LiveVoteContribution() is now the single definition of "what this member votes", called from the gate; the live path reaches the same arithmetic through LongCondition/ShortCondition. g_ensVoteVoterMask records who actually voted, separately from who evaluated the bar, because those are the divisor and the shared-population test respectively. ConfidenceTier() is split into ConfidenceTierFor(signal) plus a thin live-bar wrapper - the OOS scan holds the scanned bar's decision in a local, and dPrevSignal is a different bar. NOT changed, deliberately: the gate still does not model live NMS declustering, and the per-member solo gate still scores every directional call rather than threshold-clearing ones. Both are selection-metric changes and this codebase has twice been bitten by switching one blind. Also corrects a stale paragraph in m_pattern_0's declaration block quoting 80/87/93/100 as the tier defaults. The constructor is 25/50/75/100 and has been since the confidence floor and alternation gate were removed; the block carried both tables at once, and the dead one was quoted back as fact. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 15:23:33 -04:00
if(MathAbs(net) < g_ensembleVoteThreshold)
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
continue;
feat(consistency): the five review flaws fixed - training wears the live constraints, the gate wears the policy 1. Labels and the exit simulator go through the broker's stop-distance check: risk/reward widen to SYMBOL_TRADE_STOPS_LEVEL exactly as TCAdjustStops does at order time - the M5/tight-ATR case where live trades ran wider geometry than training measured. Current stops level stands in for history (like the spread); measured quantity, so it does not key the fingerprint. 2. The Intelligent drift verdict moved into RefreshDriftVerdict(), which RESCANS the label cache and now runs at every era end beside RankTiersFromOos - era-cadence instead of waiting for rare full rebuilds. Prints only on change. 3. Session filter is any-broker: sessions defined on their financial centres' civil clocks (London 08-16 Europe/London, NY 08-17 America/New_York, Tokyo 09-18 Asia/Tokyo), converted to UTC by each centre's own computed DST rule (EU last-Sun-Mar/Oct, US 2nd-Sun-Mar/1st-Sun-Nov), then to broker time by the MEASURED server-vs-GMT offset (half-hour brokers included). Windows may wrap midnight in broker time - the interval test handles it. Replaces the EET-hardcoded anchors, which were correct on exactly one broker and got Tokyo wrong by an hour each European summer. 4. The current-session-table-for-history caveat resolved by analysis: the bars bound the error - a too-late assumed close meets no bars (zero error), a too-early one truncates conservatively (<=1h, never optimistic, cannot manufacture edge). Documented at the site. 5. The ensemble deploy gate mirrors the direction policy: blocked-side fires are not fired bars (certified == traded), the zero-skill reference uses only ACHIEVABLE baselines (always-short is not a strategy a long-only book can run), and one-sidedness BY POLICY is not degeneracy - the two-sided requirement applies only when both sides are allowed. Sell predictions keep their other jobs (exit triggers, consensus dilution) untouched. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 12:14:01 -04:00
//--- THE DIRECTION POLICY IS PART OF WHAT GETS CERTIFIED (2026-08-19). Under LONG_ONLY/
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- SHORT_ONLY or an Intelligent drift verdict, live never places the blocked side's trades
//--- - scoring them here would certify a vote the EA does not cast, the exact
//--- certified!=traded defect this gate was rebuilt to end (2c443ba).
feat(consistency): the five review flaws fixed - training wears the live constraints, the gate wears the policy 1. Labels and the exit simulator go through the broker's stop-distance check: risk/reward widen to SYMBOL_TRADE_STOPS_LEVEL exactly as TCAdjustStops does at order time - the M5/tight-ATR case where live trades ran wider geometry than training measured. Current stops level stands in for history (like the spread); measured quantity, so it does not key the fingerprint. 2. The Intelligent drift verdict moved into RefreshDriftVerdict(), which RESCANS the label cache and now runs at every era end beside RankTiersFromOos - era-cadence instead of waiting for rare full rebuilds. Prints only on change. 3. Session filter is any-broker: sessions defined on their financial centres' civil clocks (London 08-16 Europe/London, NY 08-17 America/New_York, Tokyo 09-18 Asia/Tokyo), converted to UTC by each centre's own computed DST rule (EU last-Sun-Mar/Oct, US 2nd-Sun-Mar/1st-Sun-Nov), then to broker time by the MEASURED server-vs-GMT offset (half-hour brokers included). Windows may wrap midnight in broker time - the interval test handles it. Replaces the EET-hardcoded anchors, which were correct on exactly one broker and got Tokyo wrong by an hour each European summer. 4. The current-session-table-for-history caveat resolved by analysis: the bars bound the error - a too-late assumed close meets no bars (zero error), a too-early one truncates conservatively (<=1h, never optimistic, cannot manufacture edge). Documented at the site. 5. The ensemble deploy gate mirrors the direction policy: blocked-side fires are not fired bars (certified == traded), the zero-skill reference uses only ACHIEVABLE baselines (always-short is not a strategy a long-only book can run), and one-sidedness BY POLICY is not degeneracy - the two-sided requirement applies only when both sides are allowed. Sell predictions keep their other jobs (exit triggers, consensus dilution) untouched. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 12:14:01 -04:00
if(!WarriorDirectionAllows(net > 0.0))
continue;
feat(ensemble): per-NN inputs replace the preset selector - the meta head becomes the vote's gate User design (2026-08-19): 'remove the enum menu that selects neural networks... individual inputs for every NN just like classic signals... the META NN should be integrated into the voting decision pipeline when enabled... as a bonus meta labelling is applied to enabled NNs.' - AI_CHOICE is GONE (tombstoned per the stale-.set doctrine). Use_MLP/Use_CONV/Use_LSTM/ Use_CONVLSTM are ordinary bools like the classic votes; the ensemble arithmetic adapts to any subset because the consensus divisor is the enabled capable weight. Two or more enabled = ensemble (|ENS1 token + joint gate, exactly the old AI_HYBRID fingerprints, so existing weight files keep loading); one = the old solo preset; none = classic-only. - Use_MetaLabeling un-couples META from the direction NNs (the old selector made them mutually exclusive). S3 ships: CSignalMETA::LiveMetaGate scores each vote-cleared entry (shared window at bar 1 + proposal descriptor: side, net vote, live geometry, spread/ATR; pattern one-hot ZEROED - ranking, not calibrated probability, documented in the body) and vetoes below the cost-adjusted break-even. Entries only; fail-open everywhere, loudly. - COEXISTENCE HAZARDS closed: VoteCapableWeight()=0 and ProspectiveVote()=false for the meta target - solo-only until today, a trained META would otherwise sit in the consensus divisor as a permanent abstainer and shrink every vote by its module weight. - CERTIFIED == TRADED: the ensemble era verdict replays the identical veto through the same g_warriorMetaGate pointer over its OOS fired bars (bar re-resolved from the row's own time; fail-open counted as fires and reported: 'metaGate: N approved, M vetoed, K unscored'). The overlay deliberately does NOT replay it (veto-filter-in-replay class, calendar-cliff precedent) - documented at the sweep site. Solo charts' own gate does not model the veto - the standing solo-gate caveat, documented at the input. - DB continuity: the pattern/journal DB fingerprint's first slot was (int)AIType; DbLegacyAiSlot() maps every legacy-expressible config to its OLD value (new 2-3 member subsets get 100+bitmask, outside the legacy range) so no existing database re-keys. filterID becomes the enabled roster via one EnabledNNSummary(). - HUD: the meta line shows the gate (armed/(trn), last P vs BE, ok/veto tally); the armed/disarmed announcement fires on state change via one latch (MetaGateArmedNow), not only when an entry happens to be proposed. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 13:01:02 -04:00
//--- THE META GATE IS PART OF WHAT GETS CERTIFIED (2026-08-19), same doctrine as the
refactor(meta): the veto is a gate, not a virtual every signal carries Since S3 (f64e0f8) the meta head casts no vote - it scores an entry the consensus already cleared and vetoes the ones under the cost-adjusted break-even. The code still said otherwise. LiveMetaGate() was a virtual on CExpertSignalCustom, so MA, RSI, MACD, Ichimoku, the four direction nets, the session and news filters and the risk guard each carried a meta-gate method they had no business having; one class implemented it and a dozen inherited it. The trading pipeline held the gate as a CExpertSignalCustom* - a signal pointer, with a signal's two hundred other methods reachable from the entry path. Expert\Trading\MetaGate.mqh now owns the abstraction: CMetaGate one pure virtual, Evaluate(), and the two static readings of a verdict (Blocks / Scored) META_GATE_* names for the four codes the three call sites used to spell as bare 0/1/2 and test three different ways (`< 0` here, `== 2` there, `else` for the rest). Codes unchanged; only ONE of them blocks, and that asymmetry is now stated where it lives. SMetaGateTelemetry the five m_metaGate* members that were on the AI signal base - inherited by every direction model, meaningful for none of them. One lifetime, one writer, one object; the arm latch and the two counters are a set that clears together. g_warriorMetaGate is a CMetaGate*. MQL5's single inheritance means the head cannot also BE one (it already extends the AI base for the net, the era loop, the feature windows, the label caches and persistence), so it owns a bound CMetaGateAdapter and hands that out - the same shape CTrainingDataView uses for the same reason. LiveMetaGate() is gone from the signal base. Behaviour unchanged: same codes, same thresholds, same fail-open doctrine, same live-only telemetry rule. The adapter fails open when unbound, on that same doctrine. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 15:33:47 -04:00
//--- direction policy above: live, every vote-cleared entry passes the meta gate before it can
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- trade, so the verdict replays the identical veto through the identical pointer or it
//--- certifies fires the EA declines.
refactor(meta): the signal tree owns its gate - no global g_warriorMetaGate was a file-scope mutable pointer, and it did not need to be. The root CExpertSignalCustom - the one CExpert actually calls CheckOpenLong/Short on - now holds the gate as a member, and children reach it through a parent back-pointer AddFilter sets on adoption. That was the last piece of the meta veto that behaved like ambient state: - CheckOpenPosition reads MetaGate() instead of a global. - EnsembleEraVerdict's replay reads the same MetaGate(). It sits deep in the training code inside an AI filter and had no route up the tree; a global WAS that route. m_parentSignal is now, and a back-pointer is safe for the same reason the gate adapter's owner pointer is - m_filters and m_gates free their children, so a parent always outlives them. - The stale-pointer hazard is gone by construction. The global had to be hand-cleared at every re-init because an input change re-enters OnInit in the same program instance and frees the old head; the root signal is new'd fresh each time, so nothing survives one. That reset line is deleted, not moved. Note what did NOT need doing: the tree already owned the meta head itself. AddFilter routes non-voters into m_gates, so it has been a gate child of the root since the S3 wiring - it was only the VETO that lived outside. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 15:58:16 -04:00
CMetaGate *metaGate = MetaGate();
if(CheckPointer(metaGate) != POINTER_INVALID)
feat(ensemble): per-NN inputs replace the preset selector - the meta head becomes the vote's gate User design (2026-08-19): 'remove the enum menu that selects neural networks... individual inputs for every NN just like classic signals... the META NN should be integrated into the voting decision pipeline when enabled... as a bonus meta labelling is applied to enabled NNs.' - AI_CHOICE is GONE (tombstoned per the stale-.set doctrine). Use_MLP/Use_CONV/Use_LSTM/ Use_CONVLSTM are ordinary bools like the classic votes; the ensemble arithmetic adapts to any subset because the consensus divisor is the enabled capable weight. Two or more enabled = ensemble (|ENS1 token + joint gate, exactly the old AI_HYBRID fingerprints, so existing weight files keep loading); one = the old solo preset; none = classic-only. - Use_MetaLabeling un-couples META from the direction NNs (the old selector made them mutually exclusive). S3 ships: CSignalMETA::LiveMetaGate scores each vote-cleared entry (shared window at bar 1 + proposal descriptor: side, net vote, live geometry, spread/ATR; pattern one-hot ZEROED - ranking, not calibrated probability, documented in the body) and vetoes below the cost-adjusted break-even. Entries only; fail-open everywhere, loudly. - COEXISTENCE HAZARDS closed: VoteCapableWeight()=0 and ProspectiveVote()=false for the meta target - solo-only until today, a trained META would otherwise sit in the consensus divisor as a permanent abstainer and shrink every vote by its module weight. - CERTIFIED == TRADED: the ensemble era verdict replays the identical veto through the same g_warriorMetaGate pointer over its OOS fired bars (bar re-resolved from the row's own time; fail-open counted as fires and reported: 'metaGate: N approved, M vetoed, K unscored'). The overlay deliberately does NOT replay it (veto-filter-in-replay class, calendar-cliff precedent) - documented at the sweep site. Solo charts' own gate does not model the veto - the standing solo-gate caveat, documented at the input. - DB continuity: the pattern/journal DB fingerprint's first slot was (int)AIType; DbLegacyAiSlot() maps every legacy-expressible config to its OLD value (new 2-3 member subsets get 100+bitmask, outside the legacy range) so no existing database re-keys. filterID becomes the enabled roster via one EnabledNNSummary(). - HUD: the meta line shows the gate (armed/(trn), last P vs BE, ok/veto tally); the armed/disarmed announcement fires on state change via one latch (MetaGateArmedNow), not only when an entry happens to be proposed. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 13:01:02 -04:00
{
double mgP = -1.0, mgBe = -1.0;
int mgBar = iBarShift(m_symbol.Name(), (ENUM_TIMEFRAMES)m_period, g_ensVoteTime[r], true);
refactor(meta): the veto is a gate, not a virtual every signal carries Since S3 (f64e0f8) the meta head casts no vote - it scores an entry the consensus already cleared and vetoes the ones under the cost-adjusted break-even. The code still said otherwise. LiveMetaGate() was a virtual on CExpertSignalCustom, so MA, RSI, MACD, Ichimoku, the four direction nets, the session and news filters and the risk guard each carried a meta-gate method they had no business having; one class implemented it and a dozen inherited it. The trading pipeline held the gate as a CExpertSignalCustom* - a signal pointer, with a signal's two hundred other methods reachable from the entry path. Expert\Trading\MetaGate.mqh now owns the abstraction: CMetaGate one pure virtual, Evaluate(), and the two static readings of a verdict (Blocks / Scored) META_GATE_* names for the four codes the three call sites used to spell as bare 0/1/2 and test three different ways (`< 0` here, `== 2` there, `else` for the rest). Codes unchanged; only ONE of them blocks, and that asymmetry is now stated where it lives. SMetaGateTelemetry the five m_metaGate* members that were on the AI signal base - inherited by every direction model, meaningful for none of them. One lifetime, one writer, one object; the arm latch and the two counters are a set that clears together. g_warriorMetaGate is a CMetaGate*. MQL5's single inheritance means the head cannot also BE one (it already extends the AI base for the net, the era loop, the feature windows, the label caches and persistence), so it owns a bound CMetaGateAdapter and hands that out - the same shape CTrainingDataView uses for the same reason. LiveMetaGate() is gone from the signal base. Behaviour unchanged: same codes, same thresholds, same fail-open doctrine, same live-only telemetry rule. The adapter fails open when unbound, on that same doctrine. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 15:33:47 -04:00
//--- mgBar > 1, not > 0: barIdx 1 is the gate's "live entry" telemetry key, so a replay
//--- that resolves to the newest closed bar is left unscored rather than allowed to
feat(ensemble): per-NN inputs replace the preset selector - the meta head becomes the vote's gate User design (2026-08-19): 'remove the enum menu that selects neural networks... individual inputs for every NN just like classic signals... the META NN should be integrated into the voting decision pipeline when enabled... as a bonus meta labelling is applied to enabled NNs.' - AI_CHOICE is GONE (tombstoned per the stale-.set doctrine). Use_MLP/Use_CONV/Use_LSTM/ Use_CONVLSTM are ordinary bools like the classic votes; the ensemble arithmetic adapts to any subset because the consensus divisor is the enabled capable weight. Two or more enabled = ensemble (|ENS1 token + joint gate, exactly the old AI_HYBRID fingerprints, so existing weight files keep loading); one = the old solo preset; none = classic-only. - Use_MetaLabeling un-couples META from the direction NNs (the old selector made them mutually exclusive). S3 ships: CSignalMETA::LiveMetaGate scores each vote-cleared entry (shared window at bar 1 + proposal descriptor: side, net vote, live geometry, spread/ATR; pattern one-hot ZEROED - ranking, not calibrated probability, documented in the body) and vetoes below the cost-adjusted break-even. Entries only; fail-open everywhere, loudly. - COEXISTENCE HAZARDS closed: VoteCapableWeight()=0 and ProspectiveVote()=false for the meta target - solo-only until today, a trained META would otherwise sit in the consensus divisor as a permanent abstainer and shrink every vote by its module weight. - CERTIFIED == TRADED: the ensemble era verdict replays the identical veto through the same g_warriorMetaGate pointer over its OOS fired bars (bar re-resolved from the row's own time; fail-open counted as fires and reported: 'metaGate: N approved, M vetoed, K unscored'). The overlay deliberately does NOT replay it (veto-filter-in-replay class, calendar-cliff precedent) - documented at the sweep site. Solo charts' own gate does not model the veto - the standing solo-gate caveat, documented at the input. - DB continuity: the pattern/journal DB fingerprint's first slot was (int)AIType; DbLegacyAiSlot() maps every legacy-expressible config to its OLD value (new 2-3 member subsets get 100+bitmask, outside the legacy range) so no existing database re-keys. filterID becomes the enabled roster via one EnabledNNSummary(). - HUD: the meta line shows the gate (armed/(trn), last P vs BE, ok/veto tally); the armed/disarmed announcement fires on state change via one latch (MetaGateArmedNow), not only when an entry happens to be proposed. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 13:01:02 -04:00
//--- masquerade as a live approval/veto in the HUD counters.
refactor(meta): the signal tree owns its gate - no global g_warriorMetaGate was a file-scope mutable pointer, and it did not need to be. The root CExpertSignalCustom - the one CExpert actually calls CheckOpenLong/Short on - now holds the gate as a member, and children reach it through a parent back-pointer AddFilter sets on adoption. That was the last piece of the meta veto that behaved like ambient state: - CheckOpenPosition reads MetaGate() instead of a global. - EnsembleEraVerdict's replay reads the same MetaGate(). It sits deep in the training code inside an AI filter and had no route up the tree; a global WAS that route. m_parentSignal is now, and a back-pointer is safe for the same reason the gate adapter's owner pointer is - m_filters and m_gates free their children, so a parent always outlives them. - The stale-pointer hazard is gone by construction. The global had to be hand-cleared at every re-init because an input change re-enters OnInit in the same program instance and frees the old head; the root signal is new'd fresh each time, so nothing survives one. That reset line is deleted, not moved. Note what did NOT need doing: the tree already owned the meta head itself. AddFilter routes non-voters into m_gates, so it has been a gate child of the root since the S3 wiring - it was only the VETO that lived outside. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 15:58:16 -04:00
int mgV = (mgBar > 1) ? metaGate.Evaluate(net > 0.0, net, mgP, mgBe, mgBar)
refactor(meta): the veto is a gate, not a virtual every signal carries Since S3 (f64e0f8) the meta head casts no vote - it scores an entry the consensus already cleared and vetoes the ones under the cost-adjusted break-even. The code still said otherwise. LiveMetaGate() was a virtual on CExpertSignalCustom, so MA, RSI, MACD, Ichimoku, the four direction nets, the session and news filters and the risk guard each carried a meta-gate method they had no business having; one class implemented it and a dozen inherited it. The trading pipeline held the gate as a CExpertSignalCustom* - a signal pointer, with a signal's two hundred other methods reachable from the entry path. Expert\Trading\MetaGate.mqh now owns the abstraction: CMetaGate one pure virtual, Evaluate(), and the two static readings of a verdict (Blocks / Scored) META_GATE_* names for the four codes the three call sites used to spell as bare 0/1/2 and test three different ways (`< 0` here, `== 2` there, `else` for the rest). Codes unchanged; only ONE of them blocks, and that asymmetry is now stated where it lives. SMetaGateTelemetry the five m_metaGate* members that were on the AI signal base - inherited by every direction model, meaningful for none of them. One lifetime, one writer, one object; the arm latch and the two counters are a set that clears together. g_warriorMetaGate is a CMetaGate*. MQL5's single inheritance means the head cannot also BE one (it already extends the AI base for the net, the era loop, the feature windows, the label caches and persistence), so it owns a bound CMetaGateAdapter and hands that out - the same shape CTrainingDataView uses for the same reason. LiveMetaGate() is gone from the signal base. Behaviour unchanged: same codes, same thresholds, same fail-open doctrine, same live-only telemetry rule. The adapter fails open when unbound, on that same doctrine. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 15:33:47 -04:00
: META_GATE_FAIL_OPEN;
if(CMetaGate::Blocks(mgV))
feat(ensemble): per-NN inputs replace the preset selector - the meta head becomes the vote's gate User design (2026-08-19): 'remove the enum menu that selects neural networks... individual inputs for every NN just like classic signals... the META NN should be integrated into the voting decision pipeline when enabled... as a bonus meta labelling is applied to enabled NNs.' - AI_CHOICE is GONE (tombstoned per the stale-.set doctrine). Use_MLP/Use_CONV/Use_LSTM/ Use_CONVLSTM are ordinary bools like the classic votes; the ensemble arithmetic adapts to any subset because the consensus divisor is the enabled capable weight. Two or more enabled = ensemble (|ENS1 token + joint gate, exactly the old AI_HYBRID fingerprints, so existing weight files keep loading); one = the old solo preset; none = classic-only. - Use_MetaLabeling un-couples META from the direction NNs (the old selector made them mutually exclusive). S3 ships: CSignalMETA::LiveMetaGate scores each vote-cleared entry (shared window at bar 1 + proposal descriptor: side, net vote, live geometry, spread/ATR; pattern one-hot ZEROED - ranking, not calibrated probability, documented in the body) and vetoes below the cost-adjusted break-even. Entries only; fail-open everywhere, loudly. - COEXISTENCE HAZARDS closed: VoteCapableWeight()=0 and ProspectiveVote()=false for the meta target - solo-only until today, a trained META would otherwise sit in the consensus divisor as a permanent abstainer and shrink every vote by its module weight. - CERTIFIED == TRADED: the ensemble era verdict replays the identical veto through the same g_warriorMetaGate pointer over its OOS fired bars (bar re-resolved from the row's own time; fail-open counted as fires and reported: 'metaGate: N approved, M vetoed, K unscored'). The overlay deliberately does NOT replay it (veto-filter-in-replay class, calendar-cliff precedent) - documented at the sweep site. Solo charts' own gate does not model the veto - the standing solo-gate caveat, documented at the input. - DB continuity: the pattern/journal DB fingerprint's first slot was (int)AIType; DbLegacyAiSlot() maps every legacy-expressible config to its OLD value (new 2-3 member subsets get 100+bitmask, outside the legacy range) so no existing database re-keys. filterID becomes the enabled roster via one EnabledNNSummary(). - HUD: the meta line shows the gate (armed/(trn), last P vs BE, ok/veto tally); the armed/disarmed announcement fires on state change via one latch (MetaGateArmedNow), not only when an entry happens to be proposed. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 13:01:02 -04:00
{
metaVetoed++;
continue;
}
refactor(meta): the veto is a gate, not a virtual every signal carries Since S3 (f64e0f8) the meta head casts no vote - it scores an entry the consensus already cleared and vetoes the ones under the cost-adjusted break-even. The code still said otherwise. LiveMetaGate() was a virtual on CExpertSignalCustom, so MA, RSI, MACD, Ichimoku, the four direction nets, the session and news filters and the risk guard each carried a meta-gate method they had no business having; one class implemented it and a dozen inherited it. The trading pipeline held the gate as a CExpertSignalCustom* - a signal pointer, with a signal's two hundred other methods reachable from the entry path. Expert\Trading\MetaGate.mqh now owns the abstraction: CMetaGate one pure virtual, Evaluate(), and the two static readings of a verdict (Blocks / Scored) META_GATE_* names for the four codes the three call sites used to spell as bare 0/1/2 and test three different ways (`< 0` here, `== 2` there, `else` for the rest). Codes unchanged; only ONE of them blocks, and that asymmetry is now stated where it lives. SMetaGateTelemetry the five m_metaGate* members that were on the AI signal base - inherited by every direction model, meaningful for none of them. One lifetime, one writer, one object; the arm latch and the two counters are a set that clears together. g_warriorMetaGate is a CMetaGate*. MQL5's single inheritance means the head cannot also BE one (it already extends the AI base for the net, the era loop, the feature windows, the label caches and persistence), so it owns a bound CMetaGateAdapter and hands that out - the same shape CTrainingDataView uses for the same reason. LiveMetaGate() is gone from the signal base. Behaviour unchanged: same codes, same thresholds, same fail-open doctrine, same live-only telemetry rule. The adapter fails open when unbound, on that same doctrine. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 15:33:47 -04:00
if(mgV == META_GATE_APPROVED)
feat(ensemble): per-NN inputs replace the preset selector - the meta head becomes the vote's gate User design (2026-08-19): 'remove the enum menu that selects neural networks... individual inputs for every NN just like classic signals... the META NN should be integrated into the voting decision pipeline when enabled... as a bonus meta labelling is applied to enabled NNs.' - AI_CHOICE is GONE (tombstoned per the stale-.set doctrine). Use_MLP/Use_CONV/Use_LSTM/ Use_CONVLSTM are ordinary bools like the classic votes; the ensemble arithmetic adapts to any subset because the consensus divisor is the enabled capable weight. Two or more enabled = ensemble (|ENS1 token + joint gate, exactly the old AI_HYBRID fingerprints, so existing weight files keep loading); one = the old solo preset; none = classic-only. - Use_MetaLabeling un-couples META from the direction NNs (the old selector made them mutually exclusive). S3 ships: CSignalMETA::LiveMetaGate scores each vote-cleared entry (shared window at bar 1 + proposal descriptor: side, net vote, live geometry, spread/ATR; pattern one-hot ZEROED - ranking, not calibrated probability, documented in the body) and vetoes below the cost-adjusted break-even. Entries only; fail-open everywhere, loudly. - COEXISTENCE HAZARDS closed: VoteCapableWeight()=0 and ProspectiveVote()=false for the meta target - solo-only until today, a trained META would otherwise sit in the consensus divisor as a permanent abstainer and shrink every vote by its module weight. - CERTIFIED == TRADED: the ensemble era verdict replays the identical veto through the same g_warriorMetaGate pointer over its OOS fired bars (bar re-resolved from the row's own time; fail-open counted as fires and reported: 'metaGate: N approved, M vetoed, K unscored'). The overlay deliberately does NOT replay it (veto-filter-in-replay class, calendar-cliff precedent) - documented at the sweep site. Solo charts' own gate does not model the veto - the standing solo-gate caveat, documented at the input. - DB continuity: the pattern/journal DB fingerprint's first slot was (int)AIType; DbLegacyAiSlot() maps every legacy-expressible config to its OLD value (new 2-3 member subsets get 100+bitmask, outside the legacy range) so no existing database re-keys. filterID becomes the enabled roster via one EnabledNNSummary(). - HUD: the meta line shows the gate (armed/(trn), last P vs BE, ok/veto tally); the armed/disarmed announcement fires on state change via one latch (MetaGateArmedNow), not only when an entry happens to be proposed. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 13:01:02 -04:00
metaOk++;
else
metaOpen++;
}
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
fired++;
if(net > 0.0)
{
firedLong++;
if(g_ensVoteWinLong[r])
wins++;
}
else
{
firedShort++;
if(g_ensVoteWinShort[r])
wins++;
}
}
double slBe = 0.0, tpBe = 0.0;
BarrierMultiples(slBe, tpBe);
int bePct = (slBe > 0.0 && tpBe > 0.0) ? (int)MathRound(100.0 * slBe / (slBe + tpBe)) : -1;
bool measurable = (shared > 0 && dirLabelBars > 0);
double votePrecPct = (fired > 0) ? 100.0 * wins / fired : -1.0;
feat(consistency): the five review flaws fixed - training wears the live constraints, the gate wears the policy 1. Labels and the exit simulator go through the broker's stop-distance check: risk/reward widen to SYMBOL_TRADE_STOPS_LEVEL exactly as TCAdjustStops does at order time - the M5/tight-ATR case where live trades ran wider geometry than training measured. Current stops level stands in for history (like the spread); measured quantity, so it does not key the fingerprint. 2. The Intelligent drift verdict moved into RefreshDriftVerdict(), which RESCANS the label cache and now runs at every era end beside RankTiersFromOos - era-cadence instead of waiting for rare full rebuilds. Prints only on change. 3. Session filter is any-broker: sessions defined on their financial centres' civil clocks (London 08-16 Europe/London, NY 08-17 America/New_York, Tokyo 09-18 Asia/Tokyo), converted to UTC by each centre's own computed DST rule (EU last-Sun-Mar/Oct, US 2nd-Sun-Mar/1st-Sun-Nov), then to broker time by the MEASURED server-vs-GMT offset (half-hour brokers included). Windows may wrap midnight in broker time - the interval test handles it. Replaces the EET-hardcoded anchors, which were correct on exactly one broker and got Tokyo wrong by an hour each European summer. 4. The current-session-table-for-history caveat resolved by analysis: the bars bound the error - a too-late assumed close meets no bars (zero error), a too-early one truncates conservatively (<=1h, never optimistic, cannot manufacture edge). Documented at the site. 5. The ensemble deploy gate mirrors the direction policy: blocked-side fires are not fired bars (certified == traded), the zero-skill reference uses only ACHIEVABLE baselines (always-short is not a strategy a long-only book can run), and one-sidedness BY POLICY is not degeneracy - the two-sided requirement applies only when both sides are allowed. Sell predictions keep their other jobs (exit triggers, consensus dilution) untouched. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 12:14:01 -04:00
//--- The zero-skill reference must be ACHIEVABLE under the direction policy: with shorts
//--- blocked, always-short is not a strategy anyone could run, and ranking the vote against it
refactor(gate): the member gate and the ensemble gate were one rule written twice SDeployVerdict::EvaluateRates() is now the deploy arithmetic - coverage floor, chance + EDGE_MIN_SIGMAS x SE, tradeability, and the coverage- discounted ranking score - and both gates call it. The duplicate was self-documenting. The ensemble copy carried three comments asking a reader to keep it in step with the member copy by hand: "same intent as the member gate's coverage floor + bothSidesLive", "the two gates have to apply the identical correction or the ensemble becomes the easier one to clear", "same lexicographic ordering as isBetterEra". They had already fallen out of step once - 2c443ba found the ensemble certifying a vote the EA never casts, in the wrong currency and against the wrong denominator. THE TWO REAL DIFFERENCES ARE NOW ARGUMENTS, not branches: chancePct - the ensemble filters its zero-skill reference by the direction policy, because with shorts blocked "always short" is not a book anyone could run. twoSided - a member reads per-side RECALL against a floor; the vote reads whether it actually fired both ways. Everything else was identical and is now literally identical. effN stays an argument so the label-overlap deflation lives where it is measured - and so the remaining inconsistency stays visible rather than buried: the two FAMILY-WISE selection gates still take their SE from RAW n. Recorded in the header, deliberately not changed; tightening them is a policy call, not a refactor. The decision now reads no chart, holds no net, prints nothing and opens no file, so it can be exercised against a made-up tally. BEHAVIOUR UNCHANGED: every expression keeps its formula, its guard and its -1 sentinel; the ensemble's chance-reference and two-sidedness rules are passed through untouched. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:19:44 -04:00
//--- would score a long-only book against a baseline the policy forbids. This is one of the two
//--- places the vote genuinely differs from a member - see DeployGate.mqh.
feat(consistency): the five review flaws fixed - training wears the live constraints, the gate wears the policy 1. Labels and the exit simulator go through the broker's stop-distance check: risk/reward widen to SYMBOL_TRADE_STOPS_LEVEL exactly as TCAdjustStops does at order time - the M5/tight-ATR case where live trades ran wider geometry than training measured. Current stops level stands in for history (like the spread); measured quantity, so it does not key the fingerprint. 2. The Intelligent drift verdict moved into RefreshDriftVerdict(), which RESCANS the label cache and now runs at every era end beside RankTiersFromOos - era-cadence instead of waiting for rare full rebuilds. Prints only on change. 3. Session filter is any-broker: sessions defined on their financial centres' civil clocks (London 08-16 Europe/London, NY 08-17 America/New_York, Tokyo 09-18 Asia/Tokyo), converted to UTC by each centre's own computed DST rule (EU last-Sun-Mar/Oct, US 2nd-Sun-Mar/1st-Sun-Nov), then to broker time by the MEASURED server-vs-GMT offset (half-hour brokers included). Windows may wrap midnight in broker time - the interval test handles it. Replaces the EET-hardcoded anchors, which were correct on exactly one broker and got Tokyo wrong by an hour each European summer. 4. The current-session-table-for-history caveat resolved by analysis: the bars bound the error - a too-late assumed close meets no bars (zero error), a too-early one truncates conservatively (<=1h, never optimistic, cannot manufacture edge). Documented at the site. 5. The ensemble deploy gate mirrors the direction policy: blocked-side fires are not fired bars (certified == traded), the zero-skill reference uses only ACHIEVABLE baselines (always-short is not a strategy a long-only book can run), and one-sidedness BY POLICY is not degeneracy - the two-sided requirement applies only when both sides are allowed. Sell predictions keep their other jobs (exit triggers, consensus dilution) untouched. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 12:14:01 -04:00
double chancePct = -1.0;
if(measurable)
{
double chanceL = 100.0 * alwaysLongWins / shared;
double chanceS = 100.0 * alwaysShortWins / shared;
bool allowL = WarriorDirectionAllows(true);
bool allowS = WarriorDirectionAllows(false);
chancePct = (allowL && allowS) ? MathMax(chanceL, chanceS)
: (allowL ? chanceL : (allowS ? chanceS : MathMax(chanceL, chanceS)));
}
refactor(gate): the member gate and the ensemble gate were one rule written twice SDeployVerdict::EvaluateRates() is now the deploy arithmetic - coverage floor, chance + EDGE_MIN_SIGMAS x SE, tradeability, and the coverage- discounted ranking score - and both gates call it. The duplicate was self-documenting. The ensemble copy carried three comments asking a reader to keep it in step with the member copy by hand: "same intent as the member gate's coverage floor + bothSidesLive", "the two gates have to apply the identical correction or the ensemble becomes the easier one to clear", "same lexicographic ordering as isBetterEra". They had already fallen out of step once - 2c443ba found the ensemble certifying a vote the EA never casts, in the wrong currency and against the wrong denominator. THE TWO REAL DIFFERENCES ARE NOW ARGUMENTS, not branches: chancePct - the ensemble filters its zero-skill reference by the direction policy, because with shorts blocked "always short" is not a book anyone could run. twoSided - a member reads per-side RECALL against a floor; the vote reads whether it actually fired both ways. Everything else was identical and is now literally identical. effN stays an argument so the label-overlap deflation lives where it is measured - and so the remaining inconsistency stays visible rather than buried: the two FAMILY-WISE selection gates still take their SE from RAW n. Recorded in the header, deliberately not changed; tightening them is a policy call, not a refactor. The decision now reads no chart, holds no net, prints nothing and opens no file, so it can be exercised against a made-up tally. BEHAVIOUR UNCHANGED: every expression keeps its formula, its guard and its -1 sentinel; the ensemble's chance-reference and two-sidedness rules are passed through untouched. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:19:44 -04:00
//--- The other genuine difference: the vote's anti-degenerate test reads whether it actually
//--- FIRED both ways, where a member reads its per-side recalls.
feat(consistency): the five review flaws fixed - training wears the live constraints, the gate wears the policy 1. Labels and the exit simulator go through the broker's stop-distance check: risk/reward widen to SYMBOL_TRADE_STOPS_LEVEL exactly as TCAdjustStops does at order time - the M5/tight-ATR case where live trades ran wider geometry than training measured. Current stops level stands in for history (like the spread); measured quantity, so it does not key the fingerprint. 2. The Intelligent drift verdict moved into RefreshDriftVerdict(), which RESCANS the label cache and now runs at every era end beside RankTiersFromOos - era-cadence instead of waiting for rare full rebuilds. Prints only on change. 3. Session filter is any-broker: sessions defined on their financial centres' civil clocks (London 08-16 Europe/London, NY 08-17 America/New_York, Tokyo 09-18 Asia/Tokyo), converted to UTC by each centre's own computed DST rule (EU last-Sun-Mar/Oct, US 2nd-Sun-Mar/1st-Sun-Nov), then to broker time by the MEASURED server-vs-GMT offset (half-hour brokers included). Windows may wrap midnight in broker time - the interval test handles it. Replaces the EET-hardcoded anchors, which were correct on exactly one broker and got Tokyo wrong by an hour each European summer. 4. The current-session-table-for-history caveat resolved by analysis: the bars bound the error - a too-late assumed close meets no bars (zero error), a too-early one truncates conservatively (<=1h, never optimistic, cannot manufacture edge). Documented at the site. 5. The ensemble deploy gate mirrors the direction policy: blocked-side fires are not fired bars (certified == traded), the zero-skill reference uses only ACHIEVABLE baselines (always-short is not a strategy a long-only book can run), and one-sidedness BY POLICY is not degeneracy - the two-sided requirement applies only when both sides are allowed. Sell predictions keep their other jobs (exit triggers, consensus dilution) untouched. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 12:14:01 -04:00
bool bothAllowed = (WarriorDirectionAllows(true) && WarriorDirectionAllows(false));
bool twoSided = bothAllowed ? (firedLong > 0 && firedShort > 0) : (fired > 0);
refactor(gate): the member gate and the ensemble gate were one rule written twice SDeployVerdict::EvaluateRates() is now the deploy arithmetic - coverage floor, chance + EDGE_MIN_SIGMAS x SE, tradeability, and the coverage- discounted ranking score - and both gates call it. The duplicate was self-documenting. The ensemble copy carried three comments asking a reader to keep it in step with the member copy by hand: "same intent as the member gate's coverage floor + bothSidesLive", "the two gates have to apply the identical correction or the ensemble becomes the easier one to clear", "same lexicographic ordering as isBetterEra". They had already fallen out of step once - 2c443ba found the ensemble certifying a vote the EA never casts, in the wrong currency and against the wrong denominator. THE TWO REAL DIFFERENCES ARE NOW ARGUMENTS, not branches: chancePct - the ensemble filters its zero-skill reference by the direction policy, because with shorts blocked "always short" is not a book anyone could run. twoSided - a member reads per-side RECALL against a floor; the vote reads whether it actually fired both ways. Everything else was identical and is now literally identical. effN stays an argument so the label-overlap deflation lives where it is measured - and so the remaining inconsistency stays visible rather than buried: the two FAMILY-WISE selection gates still take their SE from RAW n. Recorded in the header, deliberately not changed; tightening them is a policy call, not a refactor. The decision now reads no chart, holds no net, prints nothing and opens no file, so it can be exercised against a made-up tally. BEHAVIOUR UNCHANGED: every expression keeps its formula, its guard and its -1 sentinel; the ensemble's chance-reference and two-sidedness rules are passed through untouched. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:19:44 -04:00
//--- THE SAME ARITHMETIC THE MEMBER GATE RUNS, on the vote's population. EFFECTIVE sample and
//--- not the raw fire count: the vote's outcomes are overlapping triple-barrier labels exactly
//--- as a member's are, and the two gates applying different corrections is precisely how the
//--- ensemble becomes the easier one to clear.
fix(gate): a field renamed on the definition side left one reader behind SDeployVerdict's bothSidesLive became twoSided when the member and ensemble gates were unified, and the member call site kept reading gate.bothSidesLive. SECOND TIME THIS EXACT SHAPE HAS BILLED THIS SESSION - the first was `s == 0` surviving the deletion of the loop that declared `s` (1d7ebbd). Renaming a declaration does not find its readers, and the compiler only finds them when no other binding happens to fit. So this is now checked rather than reviewed: every `instance.field` read against the six value objects is resolved against what the struct actually declares. Six structs, zero unresolved reads. Also renames the ensemble local `vote` to `voteGate`. SVoteAccumulator is already called `vote` in the base class, and two different `vote`s one inheritance step apart is a reader trap even where the scopes do not clash. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:40:29 -04:00
SDeployVerdict voteGate;
voteGate.EvaluateRates(fired, shared, dirLabelBars, votePrecPct, chancePct,
EffectiveSampleSize((double)fired), twoSided);
double coveragePct = voteGate.coveragePct;
double minCoverPct = voteGate.minCoveragePct;
double edgeFloorPct = voteGate.edgeFloorPct;
bool tradeableOK = voteGate.tradeable;
double score = voteGate.selectionScore;
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
//--- N for the family-wise correction: every era that COULD have won, mirroring the member gate's
//--- exclusion of eras with nothing to trade.
fix(gate): a field renamed on the definition side left one reader behind SDeployVerdict's bothSidesLive became twoSided when the member and ensemble gates were unified, and the member call site kept reading gate.bothSidesLive. SECOND TIME THIS EXACT SHAPE HAS BILLED THIS SESSION - the first was `s == 0` surviving the deletion of the loop that declared `s` (1d7ebbd). Renaming a declaration does not find its readers, and the compiler only finds them when no other binding happens to fit. So this is now checked rather than reviewed: every `instance.field` read against the six value objects is resolved against what the struct actually declares. Six structs, zero unresolved reads. Also renames the ensemble local `vote` to `voteGate`. SVoteAccumulator is already called `vote` in the base class, and two different `vote`s one inheritance step apart is a reader trap even where the scopes do not clash. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:40:29 -04:00
bool degenerate = voteGate.degenerate;
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
if(measurable && !degenerate)
g_ensCandidateEras++;
//--- Same lexicographic ordering as isBetterEra: deployable outranks two-sided outranks score.
bool isBetter = (tradeableOK && !g_ensBestTradeable) ||
(tradeableOK == g_ensBestTradeable && twoSided && !g_ensBestTwoSided) ||
(tradeableOK == g_ensBestTradeable && twoSided == g_ensBestTwoSided &&
!degenerate && score > g_ensBestScore);
if(isBetter)
{
g_ensBestScore = score;
g_ensBestTradeable = tradeableOK;
g_ensBestTwoSided = twoSided;
g_ensBestPrecPct = votePrecPct;
g_ensBestChancePct = chancePct;
g_ensBestCalls = fired;
g_ensBestEra = votedEra;
g_ensErasSinceBest = 0;
g_ensPlateauStage = 0;
EnsembleCommitJointCheckpoint(votedEra);
}
else
g_ensErasSinceBest++;
//--- SHARED PLATEAU LADDER. One counter, one stage, applied to every member at the same era, so
//--- the four nets escalate and finish together instead of drifting into different stages of
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- different searches.
fix(plateau): the IS-error early stop was inert for every ensemble member 15 hours of training, and the stop that exists to END a run announced itself 1,299 consecutive times without ending anything: SP500 ConvLSTM IN-SAMPLE ERROR PLATEAU - not improved in 1297 / 1298 / 1299 eras (best 0.2689, now 0.3269) ... era 1396, 1397, 1398 SP500 LSTM 536 eras SP500 CONV 442 eras SP500 PAI 150 eras XAUUSD HYB 478 eras XAUUSD LSTM 296 eras XAUUSD CONV 366 eras CAUSE: it wrote its decision into m_plateauStage, and EnsembleEraVerdict mirrors the shared ladder onto every member - `mm.m_plateauStage = g_ensPlateauStage` - on EVERY era, purely so each member's status line shows the collective stage. A display mirror was silently overwriting a decision, so the stop re-armed and re-fired the next era, forever. This is the worst possible direction for this particular bug. Every one of those 1,299 eras was scored out of sample and joined the family the deploy gate corrects over (Sidak, g_ensCandidateEras). The stop's entire purpose is to make that family SMALLER; instead the run spent fifteen hours raising its own bar. - m_isErrorPlateaued: a one-way per-member latch, cleared only by a fresh run. Nothing in the ladder may reset it. The stop condition and the two solo deploy conditions read the latch, not the mirrored stage. - The orchestrator combines: EnsembleEraVerdict requires UNANIMITY across participating members (same participation test the era barrier uses, so an excluded or finished member cannot veto). One member still learning can still move the combined vote, and the vote is what the gate certifies. - Fed in as `dueStage = PLATEAU_STAGE_DEPLOY`, NOT written to g_ensPlateauStage. The block that actually ends the run sits under `dueStage > g_ensPlateauStage`, so assigning the stage directly makes that test false and the deploy never happens - the same inert-write shape as the bug being fixed. Caught before committing; raising dueStage carries it through the ladder's own path (warm restarts skipped, family-wise vote test, measurement screen, joint checkpoint) unchanged. - g_ensIsPlateauAnnounced: announce once per run, not once per era. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 13:09:26 -04:00
int plateauedMembers = 0, learningMembers = 0;
for(int pi = 0; pi < ArraySize(g_warriorEnsemble); pi++)
{
CExpertSignalAIBase *pm = g_warriorEnsemble[pi];
if(CheckPointer(pm) == POINTER_INVALID || pm.m_ensembleIndex < 0)
continue;
//--- Same participation test the barrier uses: a member that has finished or been stopped is not
//--- something the rest should wait on, and must not veto the collective stop either.
if(pm.m_trainingComplete || pm.m_trainingStopRequested || !pm.m_isInitialized || pm.m_barrierExcluded)
continue;
if(pm.m_isErrorPlateaued)
plateauedMembers++;
else
learningMembers++;
}
bool allIsPlateaued = (plateauedMembers > 0 && learningMembers == 0);
if(allIsPlateaued && !g_ensIsPlateauAnnounced)
{
g_ensIsPlateauAnnounced = true;
PrintFormat("AI ensemble: EVERY member's IN-SAMPLE error has plateaued (%d participating members)."
" No member is still learning from the data it can see, so more eras cannot find a"
" better vote - they would only enlarge the family the deploy gate corrects over."
" Ending the search on the joint checkpoint at the next era that does not improve it."
" This stop never read an out-of-sample number, which is what makes the smaller family"
" legitimate rather than a peek.", plateauedMembers);
}
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
string ladderNote = "";
if(!isBetter)
{
int dueStage = g_ensErasSinceBest / TrainPlateauPatienceEras();
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- FED IN AS A DUE STAGE rather than written straight to g_ensPlateauStage, and the
//--- difference is the whole fix: the block that actually ends the run sits under `dueStage >
//--- g_ensPlateauStage`, so assigning the stage directly makes that test FALSE and the deploy
//--- never happens.
fix(gate): the plateau shortcut re-ran the deploy test every era, raising its own bar User report: 'eras since best' in the ensemble line is always 0 (era 147, best at era 90, '0 eras ago'). That is a control-flow bug wearing a display symptom. Once every member's in-sample error had plateaued, the shortcut forced the ladder to its DEPLOY stage on EVERY era. The failed-gate branch resets the stage to 0 so the ladder can climb again - so the shortcut raised it, the branch cleared it, forever. Three consequences, only the first of which was visible: - g_ensErasSinceBest was reset every era, pinning the counter at 0. - The stage-1/2 boosted warm restarts were never reached, so the one mechanism that can un-plateau a stuck member never ran. The models sat at a WORSE error than their best (0.2408 -> 0.3015 on PAI) with no escape. - Every repetition ran EnsembleSurvivesSelection against an unchanged best and incremented the candidate-era count the family-wise correction divides by. The run spent its time RAISING ITS OWN SIDAK BAR - the same waste as the 2026-08-18 inert IS-error stop, one layer up, and the reason a gate that needed >47.8% saw its bar climb era after era. Fix: the shortcut fires ONCE PER BEST-ERA (g_ensGateTestedEra, stamped before the outcome branches because it is the re-running that inflates the family, pass or fail). A refused gate now falls back to the normal counter-driven ladder - warm restart, anneal, then a fresh deploy test - which is the escape the shortcut was skipping. Also, per user: the signal marks were too small to see. Span doubled (2.6 bar widths, so the overhang either side of the candle is ~0.8 bars) and both layers thickened - 1px dotted was invisible on a candle chart at any realistic zoom. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 15:40:52 -04:00
if(allIsPlateaued && g_ensGateTestedEra != g_ensBestEra)
fix(plateau): the IS-error early stop was inert for every ensemble member 15 hours of training, and the stop that exists to END a run announced itself 1,299 consecutive times without ending anything: SP500 ConvLSTM IN-SAMPLE ERROR PLATEAU - not improved in 1297 / 1298 / 1299 eras (best 0.2689, now 0.3269) ... era 1396, 1397, 1398 SP500 LSTM 536 eras SP500 CONV 442 eras SP500 PAI 150 eras XAUUSD HYB 478 eras XAUUSD LSTM 296 eras XAUUSD CONV 366 eras CAUSE: it wrote its decision into m_plateauStage, and EnsembleEraVerdict mirrors the shared ladder onto every member - `mm.m_plateauStage = g_ensPlateauStage` - on EVERY era, purely so each member's status line shows the collective stage. A display mirror was silently overwriting a decision, so the stop re-armed and re-fired the next era, forever. This is the worst possible direction for this particular bug. Every one of those 1,299 eras was scored out of sample and joined the family the deploy gate corrects over (Sidak, g_ensCandidateEras). The stop's entire purpose is to make that family SMALLER; instead the run spent fifteen hours raising its own bar. - m_isErrorPlateaued: a one-way per-member latch, cleared only by a fresh run. Nothing in the ladder may reset it. The stop condition and the two solo deploy conditions read the latch, not the mirrored stage. - The orchestrator combines: EnsembleEraVerdict requires UNANIMITY across participating members (same participation test the era barrier uses, so an excluded or finished member cannot veto). One member still learning can still move the combined vote, and the vote is what the gate certifies. - Fed in as `dueStage = PLATEAU_STAGE_DEPLOY`, NOT written to g_ensPlateauStage. The block that actually ends the run sits under `dueStage > g_ensPlateauStage`, so assigning the stage directly makes that test false and the deploy never happens - the same inert-write shape as the bug being fixed. Caught before committing; raising dueStage carries it through the ladder's own path (warm restarts skipped, family-wise vote test, measurement screen, joint checkpoint) unchanged. - g_ensIsPlateauAnnounced: announce once per run, not once per era. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 13:09:26 -04:00
dueStage = PLATEAU_STAGE_DEPLOY;
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
if(dueStage > g_ensPlateauStage)
{
g_ensPlateauStage = dueStage;
if(g_ensPlateauStage == PLATEAU_STAGE_RESTART || g_ensPlateauStage == PLATEAU_STAGE_ANNEAL)
{
for(int i = 0; i < ArraySize(g_warriorEnsemble); i++)
{
CExpertSignalAIBase *mm = g_warriorEnsemble[i];
if(CheckPointer(mm) == POINTER_INVALID || mm.m_ensembleIndex < 0)
continue;
if(mm.m_trainingComplete || mm.m_trainingStopRequested || !mm.m_isInitialized)
continue;
mm.m_modelEta = mm.m_etaCeiling * PLATEAU_RESTART_BOOST;
mm.m_restartBoostErasLeft = TrainPlateauPatienceEras();
mm.m_plateauStage = g_ensPlateauStage;
if(CheckPointer(mm.Net) != POINTER_INVALID)
mm.Net.ResetOptimizerState();
fix(build): g_eta - the learning rate global no longer shadows a stdlib local MetaEditor: "declaration of 'eta' hides global variable" (Math.mqh:792 vs Network.mqh:80). The standard library's Math\Stat\Math.mqh declares a local `double eta` in its incomplete-gamma branch, and our bare global of the same name is in scope there. Same fault as the b1/b2/lr/momentum macros retired in ea2552e: a single-token global name living in a header that library code gets compiled beside. The library cannot move, so ours does - 112 references across 13 files, whole-word only. Named g_eta rather than g_learningRate to stay inside the vocabulary already around it (ETA_DECAY_FACTOR, ETA_MIN, m_etaCeiling, etaBefore), all of which are untouched and none of which shadow anything. One log line said "continuing to explore without decaying eta", where the word was prose rather than a symbol reference; that reads "the learning rate" now instead of naming a variable at the trader. Scanned for the next occurrence rather than waiting for it: the only other bare lowercase globals in the tree are eaName and tableschema, both distinctive enough not to collide with a library local. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-20 07:00:09 -04:00
//--- THIS member is the one still inside Train(), holding g_eta in a local that would
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
//--- overwrite m_modelEta on the way out - so its restart has to reach the local too.
if(mm == GetPointer(this))
etaLocal = mm.m_modelEta;
}
ladderNote = StringFormat(" | PLATEAU stage %d: %d eras with no better vote - boosted warm"
" restart on all %d models (learning rate x%.1f, optimizer momentum"
" reset). The joint checkpoint is safe.",
g_ensPlateauStage, g_ensErasSinceBest, members, PLATEAU_RESTART_BOOST);
}
else
if(g_ensPlateauStage >= PLATEAU_STAGE_DEPLOY)
{
//--- EXHAUSTED. Both escapes tried, nothing better found: this is the best vote this
//--- ensemble reaches. Now the gate that matters - has the best-of-N vote survived
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- having been chosen?
fix(gate): the plateau shortcut re-ran the deploy test every era, raising its own bar User report: 'eras since best' in the ensemble line is always 0 (era 147, best at era 90, '0 eras ago'). That is a control-flow bug wearing a display symptom. Once every member's in-sample error had plateaued, the shortcut forced the ladder to its DEPLOY stage on EVERY era. The failed-gate branch resets the stage to 0 so the ladder can climb again - so the shortcut raised it, the branch cleared it, forever. Three consequences, only the first of which was visible: - g_ensErasSinceBest was reset every era, pinning the counter at 0. - The stage-1/2 boosted warm restarts were never reached, so the one mechanism that can un-plateau a stuck member never ran. The models sat at a WORSE error than their best (0.2408 -> 0.3015 on PAI) with no escape. - Every repetition ran EnsembleSurvivesSelection against an unchanged best and incremented the candidate-era count the family-wise correction divides by. The run spent its time RAISING ITS OWN SIDAK BAR - the same waste as the 2026-08-18 inert IS-error stop, one layer up, and the reason a gate that needed >47.8% saw its bar climb era after era. Fix: the shortcut fires ONCE PER BEST-ERA (g_ensGateTestedEra, stamped before the outcome branches because it is the re-running that inflates the family, pass or fail). A refused gate now falls back to the normal counter-driven ladder - warm restart, anneal, then a fresh deploy test - which is the escape the shortcut was skipping. Also, per user: the signal marks were too small to see. Span doubled (2.6 bar widths, so the overhang either side of the candle is ~0.8 bars) and both layers thickened - 1px dotted was invisible on a candle chart at any realistic zoom. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 15:40:52 -04:00
g_ensGateTestedEra = g_ensBestEra;
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
double zBest = 0.0, pFam = 1.0;
int nTried = 0;
bool survives = EnsembleSurvivesSelection(zBest, pFam, nTried);
bool haveJoint = true;
for(int i = 0; i < ArraySize(g_warriorEnsemble); i++)
{
CExpertSignalAIBase *mm = g_warriorEnsemble[i];
if(CheckPointer(mm) == POINTER_INVALID || mm.m_ensembleIndex < 0)
continue;
if(mm.m_trainingComplete || mm.m_trainingStopRequested || mm.m_trainingPaused || !mm.m_isInitialized)
continue;
//--- Era-stamped, not just present: a snapshot from an EARLIER era would make the
//--- deployed quartet one that was never measured together (see m_checkpointEra).
if(!mm.m_haveOosCheckpoint || mm.m_checkpointEra != g_ensBestEra)
haveJoint = false;
}
string testNote = StringFormat(" best-of-%d test on the VOTE: edge %.1fpp (%.1f%% vs chance"
" %.1f%%) on %d fired bars = %.2f sigma, family-wise p=%.4f"
" (need <=%.2f)",
nTried, g_ensBestPrecPct - g_ensBestChancePct, g_ensBestPrecPct,
g_ensBestChancePct, g_ensBestCalls, zBest, pFam,
DEPLOY_FAMILY_WISE_ALPHA);
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- THE MEASUREMENT SCREEN, applied to the ensemble exactly as to a solo model.
//--- Four models finding nothing between them is not four chances at an edge; it is
//--- four fits to the same absent information.
fix(consistency): one geometry authority, one exit authority, and the MI screen finally gets a veto Consistency pass before a fresh deployment. Three places where two systems were choosing the same thing and one of them silently lost. 1. THE GEOMETRY SCAN'S DECISION WAS INERT - measured, not suspected. USDJPY, 2026-08-17: 14:24:12.844 adopting barrier geometry 2:8 ... Relabelling and training on it. 14:24:12.979 triple-barrier labels - stop 1.61*ATR, target 3.21*ATR ... this is what trains It adopted 2:8 and trained on 1.61:3.21. ReportBarrierGeometryScan wrote only m_sl_mode/m_tp_mode, and BarrierMultiples ranks the DERIVED pair ABOVE those ints - so on any model carrying a derived pair (every model with a .cfg, including a fresh one whose weights are gone but whose sidecar survived) the adoption changed nothing. Worse, had it changed something it would have been undone immediately: the adoption sets m_labelCachePrebuilt = false, and that prebuild re-runs DeriveBarrierGeometry at era 0, which overwrites m_derivedSl/TpMult from the excursion quantiles. ONE AUTHORITY: the derived pair, because it is what the labels read, what the deploy gate certifies, what g_Derived*AtrMult places on the live order, and what the .cfg pins across restarts. The scan now writes THAT (floored by MIN_SL_ATR_MULTIPLIER, the same floor DeriveBarrierGeometry applies so the live stop can never be wider than the labelled one), republishes to the bridge immediately rather than at the next era end, and forces the sidecar to be rewritten. m_geometryAdopted latches it so the derive pass the adoption itself triggers cannot overwrite it. The scan outranks the derive for an evidential reason, not an architectural one: its winner cleared a permutation test against the null of the MAXIMUM over every eligible pairing, and it scores the incumbent derived pair as a peer in that same field. The derive is a descriptive quantile read with no significance test attached. BEHAVIOURAL CHANGE, and the reason to flag it before a fresh test: barrier geometry will now actually move when the scan says so. Until today it never did. 2. ONE EXIT AUTHORITY, tied to whose certificate the trade was placed under. CheckClosePosition had two routes. The AI early-exit reads the AI vote undiluted and is exactly what the new exit replay reproduces. The blended route thresholds m_direction, the average over EVERY filter including classic ones whose live votes pass 3 never computes - so it can close a position the certificate never modelled, and no replay can ever check it. When g_DerivedSlAtrMult > 0 the AI's measured geometry is on the order, which means the deploy gate's certificate is the reason the trade exists. In that state the AI now governs the exit and the blended route is suppressed. Classic-only configurations are untouched: there the blended route is the only exit opinion and stays exactly as it was. Nothing moves at the shipped defaults either way (Min_Vote_Close = Disabled). 3. EDGEFINDER, SECOND HALF: THE MEASUREMENT NOW STEERS. The MI suite has always printed its verdicts and then trained the direction target regardless of what they said. That gap IS the difference between this and the EdgeFinder discipline: measure what the market offers, THEN aim. m_dirEvidence is set when EITHER the feature/label mutual information OR the normalised excursion asymmetry clears its block-permuted null - an OR, because the two look for the same thing by different routes and requiring both would reject on the weaker of two independent measurements. Normalised asymmetry specifically, never the raw one, which is the volatility confound. Deploy - solo AND ensemble - now requires it. A run without it still trains, and keeps its checkpoint: the research value is real and the measurement can be wrong. It simply may not go live. Reported separately from the statistical gate because the remedy is different: a failed selection test says train differently, this says look somewhere else. Excursion SIZE keeps clearing where direction does not, and that is a risk-control head rather than an entry signal. For the ensemble the check is per-chart by construction - the MI suite runs once and shares its outcome across members - which is the honest treatment: four models finding nothing between them is not four chances at an edge, it is four fits to the same absent information. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-17 16:43:20 -04:00
if(g_ensBestTradeable && haveJoint && survives && !m_dirEvidence)
Print("AI ensemble: DEPLOY REFUSED BY THE MEASUREMENT SCREEN - the combined vote cleared"
" its statistical gate, but neither the feature/label mutual information nor the"
" normalised excursion asymmetry cleared a permutation null on this chart's"
" feature set. The vote is a best-of-N maximum over a search that had no measured"
" directional information to find; clearing the gate on top of that is the"
" family-wise trap this project has hit four times. Checkpoints kept, training"
" untouched - this refuses to go LIVE, nothing else.");
if(g_ensBestTradeable && haveJoint && survives && m_dirEvidence)
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
{
g_ensDeployApproved = true;
Print("AI ensemble: PLATEAU stage " + IntegerToString(PLATEAU_STAGE_DEPLOY) +
" - no better vote for " + IntegerToString(g_ensErasSinceBest) + " eras across " +
IntegerToString(PLATEAU_STAGE_DEPLOY - 1) + " warm restarts." + testNote +
" - CLEARS. Deploying the JOINT checkpoint from era " +
IntegerToString((int)g_ensBestEra) + ": every model reverts to the weights it held"
" at the era whose combined vote scored best, so the ensemble that trades is"
" exactly the one that was measured.");
ladderNote = " | ENSEMBLE DEPLOY APPROVED";
}
else
{
//--- Restart the ladder and keep training, exactly as the solo gate does on a
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- failed selection test. The era cap stays the backstop. THROTTLED
//--- (2026-08-19): the refusal repeated ~450x/day with an unchanged reason.
feat(logs): throttle the settled per-era diagnostics - measured 22MB/9.5h of confirmed-working systems Measured from the journal (2026-08-19): the era deep-dive line (~2KB) plus the excursion verdict, tier re-rank, calibration move, barrier hold and selection-regressed note each printed EVERY era for EVERY member - ~940 eras/member/day - long after the systems they watch were confirmed working. Yesterday's file was 1.3GB (70% of it the news-filter calendar spam the sweep fix already removed). VerboseMode returns as an INPUT (demoted 2026-08-01 for the marketplace; that track is dead since the 2026-08-16 pivot) and gains a second job: false throttles each settled per-era print to eras 0-3 plus every TRAIN_LOG_EVERY_ERAS-th (25 ~= one deep-dive per ~15min per member); true restores the per-era firehose, flippable live. Never throttled: anything that marks a CHANGE - new bests, restores + eta decays, plateau stage transitions, deploy approvals, warnings, errors, the label-cache/adoption one-shots, and the combined-vote gate line (the active system's primary telemetry, still every era). Semantic fixes over blanket gating: - barrier hold now ARMS silently and prints only when the hold outlasts the 2-min report interval - a brief hold every era is the design, the long hold is the watchdog case the line exists for; - the ensemble deploy REFUSAL prints immediately when its reason changes (that is a finding), on cadence when unchanged; - the filtered-view census prints when its RESULT moves (drawn count, or strongest vote by >=2pp) and at least every 10th sweep. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 09:36:15 -04:00
int refusalKey = (!g_ensBestTradeable ? 1 : (!haveJoint ? 2 : 3));
if(refusalKey != m_lastEnsRefusalKey || TrainLogDue())
Print("AI ensemble: PLATEAU stage " + IntegerToString(PLATEAU_STAGE_DEPLOY) + " - " +
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
(!g_ensBestTradeable
? "no era's combined vote ever cleared the deployability floor (fires on at least a"
" quarter as many bars as actually swing, both directions alive, at a win rate"
" above the always-one-way reference by 2 sigma), so there is nothing safe to deploy."
: (!haveJoint
? "the joint checkpoint is incomplete - at least one model has no snapshot of the"
" winning era, so the measured ensemble cannot be reproduced."
: "the best combined vote clears the per-era floor but DOES NOT clear the null of"
" the MAXIMUM over the eras it was chosen from." + testNote +
" A best-of-N this large happens routinely when every era is a noise draw.")) +
" Restarting the ladder and continuing to train; the era cap remains the backstop.");
feat(logs): throttle the settled per-era diagnostics - measured 22MB/9.5h of confirmed-working systems Measured from the journal (2026-08-19): the era deep-dive line (~2KB) plus the excursion verdict, tier re-rank, calibration move, barrier hold and selection-regressed note each printed EVERY era for EVERY member - ~940 eras/member/day - long after the systems they watch were confirmed working. Yesterday's file was 1.3GB (70% of it the news-filter calendar spam the sweep fix already removed). VerboseMode returns as an INPUT (demoted 2026-08-01 for the marketplace; that track is dead since the 2026-08-16 pivot) and gains a second job: false throttles each settled per-era print to eras 0-3 plus every TRAIN_LOG_EVERY_ERAS-th (25 ~= one deep-dive per ~15min per member); true restores the per-era firehose, flippable live. Never throttled: anything that marks a CHANGE - new bests, restores + eta decays, plateau stage transitions, deploy approvals, warnings, errors, the label-cache/adoption one-shots, and the combined-vote gate line (the active system's primary telemetry, still every era). Semantic fixes over blanket gating: - barrier hold now ARMS silently and prints only when the hold outlasts the 2-min report interval - a brief hold every era is the design, the long hold is the watchdog case the line exists for; - the ensemble deploy REFUSAL prints immediately when its reason changes (that is a finding), on cadence when unchanged; - the filtered-view census prints when its RESULT moves (drawn count, or strongest vote by >=2pp) and at least every 10th sweep. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 09:36:15 -04:00
m_lastEnsRefusalKey = refusalKey;
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
g_ensErasSinceBest = 0;
g_ensPlateauStage = 0;
for(int i = 0; i < ArraySize(g_warriorEnsemble); i++)
{
CExpertSignalAIBase *mm = g_warriorEnsemble[i];
if(CheckPointer(mm) != POINTER_INVALID && mm.m_ensembleIndex >= 0)
mm.m_plateauStage = 0;
}
ladderNote = " | ladder restarted (gate not cleared)";
}
}
}
}
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- Mirror the shared ladder onto every member.
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
for(int i = 0; i < ArraySize(g_warriorEnsemble); i++)
{
CExpertSignalAIBase *mm = g_warriorEnsemble[i];
if(CheckPointer(mm) == POINTER_INVALID || mm.m_ensembleIndex < 0)
continue;
mm.m_erasSinceBestBalanced = g_ensErasSinceBest;
mm.m_plateauStage = g_ensPlateauStage;
}
feat: implement one-shot pattern-database backfill and enhance accuracy tracking for ensemble models
2026-08-16 21:08:41 -04:00
//--- LIFETIME ACCUMULATION - same cadence as a solo model's m_cumOosTotal (see its increment sites):
//--- every scored era adds the bars the vote fired on and how many paid, monotonically, never reset
//--- per era. `wins`/`fired` above are this era's OOS rows only; the panel reads the running total.
g_ensCumOosTotal += fired;
g_ensCumOosCorrect += wins;
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- PANEL + JOURNAL.
feat: implement one-shot pattern-database backfill and enhance accuracy tracking for ensemble models
2026-08-16 21:08:41 -04:00
string ensAccLine;
if(g_ensCumOosTotal > 0)
{
int winPctLifetime = (int)MathRound(g_ensCumOosCorrect * 100.0 / g_ensCumOosTotal);
//--- THIS ERA alongside the lifetime figure - same reason and same fix as the solo panel's
//--- ComputeCompoundedAccuracyLine (see its "THIS ERA" comment): the lifetime average is diluted
//--- by every fired bar from every prior era, so a real swing this era barely moves it. `wins`/
//--- `fired` above are this era's combined-vote rows only.
string thisEra = (fired > 0) ? StringFormat(", this era %d%%", (int)MathRound(votePrecPct)) : "";
ensAccLine = StringFormat("Buy/Sell calls correct: %d%% (unseen data%s%s)", winPctLifetime,
(bePct >= 0 ? StringFormat(", need %d%%", bePct) : ""), thisEra);
}
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
else
feat: implement one-shot pattern-database backfill and enhance accuracy tracking for ensemble models
2026-08-16 21:08:41 -04:00
ensAccLine = (g_ensCandidateEras > 0) ? "Buy/Sell calls correct: no directional calls yet"
: "Buy/Sell calls correct: measuring...";
g_ensembleVoteLine = StringFormat("%s (era %d, %d models%s)", ensAccLine, (int)votedEra, members,
(g_ensDeployApproved ? ", DEPLOYING" : (tradeableOK ? ", deployable" : "")));
feat(ensemble): per-NN inputs replace the preset selector - the meta head becomes the vote's gate User design (2026-08-19): 'remove the enum menu that selects neural networks... individual inputs for every NN just like classic signals... the META NN should be integrated into the voting decision pipeline when enabled... as a bonus meta labelling is applied to enabled NNs.' - AI_CHOICE is GONE (tombstoned per the stale-.set doctrine). Use_MLP/Use_CONV/Use_LSTM/ Use_CONVLSTM are ordinary bools like the classic votes; the ensemble arithmetic adapts to any subset because the consensus divisor is the enabled capable weight. Two or more enabled = ensemble (|ENS1 token + joint gate, exactly the old AI_HYBRID fingerprints, so existing weight files keep loading); one = the old solo preset; none = classic-only. - Use_MetaLabeling un-couples META from the direction NNs (the old selector made them mutually exclusive). S3 ships: CSignalMETA::LiveMetaGate scores each vote-cleared entry (shared window at bar 1 + proposal descriptor: side, net vote, live geometry, spread/ATR; pattern one-hot ZEROED - ranking, not calibrated probability, documented in the body) and vetoes below the cost-adjusted break-even. Entries only; fail-open everywhere, loudly. - COEXISTENCE HAZARDS closed: VoteCapableWeight()=0 and ProspectiveVote()=false for the meta target - solo-only until today, a trained META would otherwise sit in the consensus divisor as a permanent abstainer and shrink every vote by its module weight. - CERTIFIED == TRADED: the ensemble era verdict replays the identical veto through the same g_warriorMetaGate pointer over its OOS fired bars (bar re-resolved from the row's own time; fail-open counted as fires and reported: 'metaGate: N approved, M vetoed, K unscored'). The overlay deliberately does NOT replay it (veto-filter-in-replay class, calendar-cliff precedent) - documented at the sweep site. Solo charts' own gate does not model the veto - the standing solo-gate caveat, documented at the input. - DB continuity: the pattern/journal DB fingerprint's first slot was (int)AIType; DbLegacyAiSlot() maps every legacy-expressible config to its OLD value (new 2-3 member subsets get 100+bitmask, outside the legacy range) so no existing database re-keys. filterID becomes the enabled roster via one EnabledNNSummary(). - HUD: the meta line shows the gate (armed/(trn), last P vs BE, ok/veto tally); the armed/disarmed announcement fires on state change via one latch (MetaGateArmedNow), not only when an entry happens to be proposed. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 13:01:02 -04:00
//--- Present only when a meta head is attached and at least one fired bar reached it - the
//--- unscored count is the honesty term (bars the gate could not score are certified as fires
//--- because live they would trade ungated).
refactor(meta): the signal tree owns its gate - no global g_warriorMetaGate was a file-scope mutable pointer, and it did not need to be. The root CExpertSignalCustom - the one CExpert actually calls CheckOpenLong/Short on - now holds the gate as a member, and children reach it through a parent back-pointer AddFilter sets on adoption. That was the last piece of the meta veto that behaved like ambient state: - CheckOpenPosition reads MetaGate() instead of a global. - EnsembleEraVerdict's replay reads the same MetaGate(). It sits deep in the training code inside an AI filter and had no route up the tree; a global WAS that route. m_parentSignal is now, and a back-pointer is safe for the same reason the gate adapter's owner pointer is - m_filters and m_gates free their children, so a parent always outlives them. - The stale-pointer hazard is gone by construction. The global had to be hand-cleared at every re-init because an input change re-enters OnInit in the same program instance and frees the old head; the root signal is new'd fresh each time, so nothing survives one. That reset line is deleted, not moved. Note what did NOT need doing: the tree already owned the meta head itself. AddFilter routes non-voters into m_gates, so it has been a gate child of the root since the S3 wiring - it was only the VETO that lived outside. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 15:58:16 -04:00
string metaNote = (CheckPointer(MetaGate()) != POINTER_INVALID && (metaOk + metaVetoed + metaOpen) > 0)
feat(ensemble): per-NN inputs replace the preset selector - the meta head becomes the vote's gate User design (2026-08-19): 'remove the enum menu that selects neural networks... individual inputs for every NN just like classic signals... the META NN should be integrated into the voting decision pipeline when enabled... as a bonus meta labelling is applied to enabled NNs.' - AI_CHOICE is GONE (tombstoned per the stale-.set doctrine). Use_MLP/Use_CONV/Use_LSTM/ Use_CONVLSTM are ordinary bools like the classic votes; the ensemble arithmetic adapts to any subset because the consensus divisor is the enabled capable weight. Two or more enabled = ensemble (|ENS1 token + joint gate, exactly the old AI_HYBRID fingerprints, so existing weight files keep loading); one = the old solo preset; none = classic-only. - Use_MetaLabeling un-couples META from the direction NNs (the old selector made them mutually exclusive). S3 ships: CSignalMETA::LiveMetaGate scores each vote-cleared entry (shared window at bar 1 + proposal descriptor: side, net vote, live geometry, spread/ATR; pattern one-hot ZEROED - ranking, not calibrated probability, documented in the body) and vetoes below the cost-adjusted break-even. Entries only; fail-open everywhere, loudly. - COEXISTENCE HAZARDS closed: VoteCapableWeight()=0 and ProspectiveVote()=false for the meta target - solo-only until today, a trained META would otherwise sit in the consensus divisor as a permanent abstainer and shrink every vote by its module weight. - CERTIFIED == TRADED: the ensemble era verdict replays the identical veto through the same g_warriorMetaGate pointer over its OOS fired bars (bar re-resolved from the row's own time; fail-open counted as fires and reported: 'metaGate: N approved, M vetoed, K unscored'). The overlay deliberately does NOT replay it (veto-filter-in-replay class, calendar-cliff precedent) - documented at the sweep site. Solo charts' own gate does not model the veto - the standing solo-gate caveat, documented at the input. - DB continuity: the pattern/journal DB fingerprint's first slot was (int)AIType; DbLegacyAiSlot() maps every legacy-expressible config to its OLD value (new 2-3 member subsets get 100+bitmask, outside the legacy range) so no existing database re-keys. filterID becomes the enabled roster via one EnabledNNSummary(). - HUD: the meta line shows the gate (armed/(trn), last P vs BE, ok/veto tally); the armed/disarmed announcement fires on state change via one latch (MetaGateArmedNow), not only when an entry happens to be proposed. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 13:01:02 -04:00
? StringFormat(" | metaGate: %d approved, %d vetoed, %d unscored(open)",
metaOk, metaVetoed, metaOpen)
: "";
fix(vote): "0 fired" on USDJPY meant the threshold is above the highest vote the ensemble can cast USDJPY has taken no trades in 66 eras and its highest vote ever seen is 13 against a 25% threshold. Not a bug and not undertrained models - arithmetic. Direction() divides the summed contributions by the CAPABLE weight, so a unanimous vote returns the capability-weighted mean of the tier weights, which is roughly the pooled holdout win rate. USDJPY's members pool at 15.6-19.4% (its label base rate is 14.0% against SP500's 25.4%, because its derived geometry resolves far fewer bars directionally: Buy 10.3% Sell 11.2% Neutral 78.6%). So the ensemble's CEILING is ~19 and the threshold is 25. Coverage can never leave 0, and no amount of training moves it, because the ceiling IS the win rate. The report now computes that ceiling - every member voting at its best tier - and says so when the threshold sits above it, instead of printing "0 fired at vote>=25%" which reads as "the models are unsure". Same class as the excursion head's disjoint gate (ee4d459) and the reason ReportDetectability exists: a configuration that cannot reach its own bar has to say that, not report a number that looks like evidence. Also: VerboseMode and Run_Alglib_Baselines back to false. The per-era cadence was for reading the horizon break-even and the excursion sigmas; both are settled, and TrainLogDue still prints them every 25 eras. The baselines cost a 45 s single-threaded freeze at every attach and their forest row turned out to be one deterministic observation that does not survive overlap deflation. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 08:16:11 -04:00
//--- THE HIGHEST VOTE THIS ENSEMBLE CAN PRODUCE: every member voting, each at its best tier. The
//--- divisor in Direction() is the CAPABLE weight, so unanimity returns the capability-weighted mean
//--- of the tier weights - which is roughly the pooled holdout win rate. A threshold above that can
//--- NEVER fire, and "0 fired" then reads as "the models are unsure" when it means "unreachable in
//--- this configuration". Measured on USDJPY 2026-08-22: pooled win rates 15.6-19.4% against a
//--- 25% threshold, highest vote ever seen 13. Same class as the excursion head's disjoint gate.
double capSum = 0.0, bestSum = 0.0;
fix(vote): unranked members voted with the stock 25/50/75/100 ladder Two defects behind "arrows drawn while members are still mid-era". 1. THE DRAW. The filtered overlay armed on the FIRST member to finish pass 3 and leaned on a 60 s rate limit to "collapse the burst", assuming members finish seconds apart. They do not - on USDJPY one member was at sample 10496 of pass 2 while another was at 2304, minutes apart. A member with no era-end snapshot returns false from SnapshotVoteAt, and the sweep's `if(!hasData) continue;` skips it BEFORE `den += ModuleWeight()`, so the one finished model's tier weight became the entire vote and was drawn as a consensus arrow. An abstention is a member that looked at the bar and said nothing; a missing snapshot is a member that has not looked. The first must dilute the vote, the second must suppress the draw. The arm is now a readiness MASK - one bit per m_ensembleIndex, set at that member's pass-3 completion, cleared when a sweep arms - and a sweep waits for every enrolled member. Bounded at 10 minutes so a member that stops cannot freeze the chart, and the partial draw PRINTS which members were missing: the be39674 lesson is that a hold must never silence the thing that reports it. 2. THE VOTE ITSELF, which is the worse half and is not display-only. Tier weights are not persisted in the .nnw - they exist only as the output of a completed pass 3 - so before a member's first RankTiersFromOos() it holds the constructor's stock 25/50/75/100. Since 4858507 the vote currency is a WIN RATE, so an unranked tier-3 call enters the capability-weighted mean claiming a 100% win rate beside ranked members contributing ~25. Not a strong opinion: the wrong unit. One unranked member drags the ensemble over any threshold, on every fresh deploy and every resume. USDJPY has a measured ceiling of ~19 and was firing anyway. LiveVoteContribution() now abstains until self-ranked, which drops the member from the sum AND the divisor. One function, so live and the gate move together (2c443ba). Era 0 will therefore report 0 coverage until each member completes one era. The ensemble line says so explicitly rather than leaving it to look like the USDJPY unreachable-threshold case - the two are identical in the coverage number and completely different problems. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 08:55:04 -04:00
int rankedMembers = 0, enrolledMembers = 0;
fix(vote): "0 fired" on USDJPY meant the threshold is above the highest vote the ensemble can cast USDJPY has taken no trades in 66 eras and its highest vote ever seen is 13 against a 25% threshold. Not a bug and not undertrained models - arithmetic. Direction() divides the summed contributions by the CAPABLE weight, so a unanimous vote returns the capability-weighted mean of the tier weights, which is roughly the pooled holdout win rate. USDJPY's members pool at 15.6-19.4% (its label base rate is 14.0% against SP500's 25.4%, because its derived geometry resolves far fewer bars directionally: Buy 10.3% Sell 11.2% Neutral 78.6%). So the ensemble's CEILING is ~19 and the threshold is 25. Coverage can never leave 0, and no amount of training moves it, because the ceiling IS the win rate. The report now computes that ceiling - every member voting at its best tier - and says so when the threshold sits above it, instead of printing "0 fired at vote>=25%" which reads as "the models are unsure". Same class as the excursion head's disjoint gate (ee4d459) and the reason ReportDetectability exists: a configuration that cannot reach its own bar has to say that, not report a number that looks like evidence. Also: VerboseMode and Run_Alglib_Baselines back to false. The per-era cadence was for reading the horizon break-even and the excursion sigmas; both are settled, and TrainLogDue still prints them every 25 eras. The baselines cost a 45 s single-threaded freeze at every attach and their forest row turned out to be one deterministic observation that does not survive overlap deflation. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 08:16:11 -04:00
for(int ci = 0; ci < ArraySize(g_warriorEnsemble); ci++)
{
CExpertSignalAIBase *cm = g_warriorEnsemble[ci];
if(CheckPointer(cm) == POINTER_INVALID || cm.m_ensembleIndex < 0)
continue;
fix(vote): unranked members voted with the stock 25/50/75/100 ladder Two defects behind "arrows drawn while members are still mid-era". 1. THE DRAW. The filtered overlay armed on the FIRST member to finish pass 3 and leaned on a 60 s rate limit to "collapse the burst", assuming members finish seconds apart. They do not - on USDJPY one member was at sample 10496 of pass 2 while another was at 2304, minutes apart. A member with no era-end snapshot returns false from SnapshotVoteAt, and the sweep's `if(!hasData) continue;` skips it BEFORE `den += ModuleWeight()`, so the one finished model's tier weight became the entire vote and was drawn as a consensus arrow. An abstention is a member that looked at the bar and said nothing; a missing snapshot is a member that has not looked. The first must dilute the vote, the second must suppress the draw. The arm is now a readiness MASK - one bit per m_ensembleIndex, set at that member's pass-3 completion, cleared when a sweep arms - and a sweep waits for every enrolled member. Bounded at 10 minutes so a member that stops cannot freeze the chart, and the partial draw PRINTS which members were missing: the be39674 lesson is that a hold must never silence the thing that reports it. 2. THE VOTE ITSELF, which is the worse half and is not display-only. Tier weights are not persisted in the .nnw - they exist only as the output of a completed pass 3 - so before a member's first RankTiersFromOos() it holds the constructor's stock 25/50/75/100. Since 4858507 the vote currency is a WIN RATE, so an unranked tier-3 call enters the capability-weighted mean claiming a 100% win rate beside ranked members contributing ~25. Not a strong opinion: the wrong unit. One unranked member drags the ensemble over any threshold, on every fresh deploy and every resume. USDJPY has a measured ceiling of ~19 and was firing anyway. LiveVoteContribution() now abstains until self-ranked, which drops the member from the sum AND the divisor. One function, so live and the gate move together (2c443ba). Era 0 will therefore report 0 coverage until each member completes one era. The ensemble line says so explicitly rather than leaving it to look like the USDJPY unreachable-threshold case - the two are identical in the coverage number and completely different problems. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 08:55:04 -04:00
enrolledMembers++;
//--- Unranked members abstain (see LiveVoteContribution), so they are not part of the ceiling
//--- either - counting their stock 100 would put the ceiling above anything reachable.
if(!cm.SelfRanked())
continue;
rankedMembers++;
fix(vote): "0 fired" on USDJPY meant the threshold is above the highest vote the ensemble can cast USDJPY has taken no trades in 66 eras and its highest vote ever seen is 13 against a 25% threshold. Not a bug and not undertrained models - arithmetic. Direction() divides the summed contributions by the CAPABLE weight, so a unanimous vote returns the capability-weighted mean of the tier weights, which is roughly the pooled holdout win rate. USDJPY's members pool at 15.6-19.4% (its label base rate is 14.0% against SP500's 25.4%, because its derived geometry resolves far fewer bars directionally: Buy 10.3% Sell 11.2% Neutral 78.6%). So the ensemble's CEILING is ~19 and the threshold is 25. Coverage can never leave 0, and no amount of training moves it, because the ceiling IS the win rate. The report now computes that ceiling - every member voting at its best tier - and says so when the threshold sits above it, instead of printing "0 fired at vote>=25%" which reads as "the models are unsure". Same class as the excursion head's disjoint gate (ee4d459) and the reason ReportDetectability exists: a configuration that cannot reach its own bar has to say that, not report a number that looks like evidence. Also: VerboseMode and Run_Alglib_Baselines back to false. The per-era cadence was for reading the horizon break-even and the excursion sigmas; both are settled, and TrainLogDue still prints them every 25 eras. The baselines cost a 45 s single-threaded freeze at every attach and their forest row turned out to be one deterministic observation that does not survive overlap deflation. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 08:16:11 -04:00
double capW = cm.VoteCapableWeight();
if(!MathIsValidNumber(capW) || capW <= 0.0)
continue;
int best = 0;
for(int t = 0; t < 4; t++)
best = (int)MathMax(best, cm.PatternWeightForTier(t));
capSum += capW;
bestSum += capW * best;
}
double voteCeiling = (capSum > 0.0) ? bestSum / capSum : 0.0;
fix(vote): unranked members voted with the stock 25/50/75/100 ladder Two defects behind "arrows drawn while members are still mid-era". 1. THE DRAW. The filtered overlay armed on the FIRST member to finish pass 3 and leaned on a 60 s rate limit to "collapse the burst", assuming members finish seconds apart. They do not - on USDJPY one member was at sample 10496 of pass 2 while another was at 2304, minutes apart. A member with no era-end snapshot returns false from SnapshotVoteAt, and the sweep's `if(!hasData) continue;` skips it BEFORE `den += ModuleWeight()`, so the one finished model's tier weight became the entire vote and was drawn as a consensus arrow. An abstention is a member that looked at the bar and said nothing; a missing snapshot is a member that has not looked. The first must dilute the vote, the second must suppress the draw. The arm is now a readiness MASK - one bit per m_ensembleIndex, set at that member's pass-3 completion, cleared when a sweep arms - and a sweep waits for every enrolled member. Bounded at 10 minutes so a member that stops cannot freeze the chart, and the partial draw PRINTS which members were missing: the be39674 lesson is that a hold must never silence the thing that reports it. 2. THE VOTE ITSELF, which is the worse half and is not display-only. Tier weights are not persisted in the .nnw - they exist only as the output of a completed pass 3 - so before a member's first RankTiersFromOos() it holds the constructor's stock 25/50/75/100. Since 4858507 the vote currency is a WIN RATE, so an unranked tier-3 call enters the capability-weighted mean claiming a 100% win rate beside ranked members contributing ~25. Not a strong opinion: the wrong unit. One unranked member drags the ensemble over any threshold, on every fresh deploy and every resume. USDJPY has a measured ceiling of ~19 and was firing anyway. LiveVoteContribution() now abstains until self-ranked, which drops the member from the sum AND the divisor. One function, so live and the gate move together (2c443ba). Era 0 will therefore report 0 coverage until each member completes one era. The ensemble line says so explicitly rather than leaving it to look like the USDJPY unreachable-threshold case - the two are identical in the coverage number and completely different problems. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 08:55:04 -04:00
//--- "0 fired because nobody has ranked yet" and "0 fired because the threshold is unreachable"
//--- look identical in the coverage number and are completely different problems.
string rankNote = (rankedMembers < enrolledMembers)
? StringFormat(" | %d of %d members have NOT ranked their tiers yet and are"
" abstaining: tier weights only exist as the output of a"
" completed pass 3 and are not persisted in the .nnw, so every"
" fresh deploy and every resume starts here. Self-corrects after"
" one era per member.",
enrolledMembers - rankedMembers, enrolledMembers)
: "";
fix(vote): "0 fired" on USDJPY meant the threshold is above the highest vote the ensemble can cast USDJPY has taken no trades in 66 eras and its highest vote ever seen is 13 against a 25% threshold. Not a bug and not undertrained models - arithmetic. Direction() divides the summed contributions by the CAPABLE weight, so a unanimous vote returns the capability-weighted mean of the tier weights, which is roughly the pooled holdout win rate. USDJPY's members pool at 15.6-19.4% (its label base rate is 14.0% against SP500's 25.4%, because its derived geometry resolves far fewer bars directionally: Buy 10.3% Sell 11.2% Neutral 78.6%). So the ensemble's CEILING is ~19 and the threshold is 25. Coverage can never leave 0, and no amount of training moves it, because the ceiling IS the win rate. The report now computes that ceiling - every member voting at its best tier - and says so when the threshold sits above it, instead of printing "0 fired at vote>=25%" which reads as "the models are unsure". Same class as the excursion head's disjoint gate (ee4d459) and the reason ReportDetectability exists: a configuration that cannot reach its own bar has to say that, not report a number that looks like evidence. Also: VerboseMode and Run_Alglib_Baselines back to false. The per-era cadence was for reading the horizon break-even and the excursion sigmas; both are settled, and TrainLogDue still prints them every 25 eras. The baselines cost a 45 s single-threaded freeze at every attach and their forest row turned out to be one deterministic observation that does not survive overlap deflation. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 08:16:11 -04:00
string ceilingNote = (voteCeiling > 0.0 && voteCeiling < g_ensembleVoteThreshold)
? StringFormat(" | THRESHOLD UNREACHABLE: the highest vote this ensemble can"
" cast is %.1f%% (every member voting at its best tier) against"
" a %.0f%% threshold. Coverage cannot rise above 0 until the"
" threshold sits below that ceiling, which IS the pooled win"
" rate - no amount of training moves it.",
voteCeiling, g_ensembleVoteThreshold)
: "";
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
Print(StringFormat("AI ensemble: combined-vote era %d - %d models, %d shared OOS bars, %d fired at"
" vote>=%.0f%% (%.1f%% coverage, floor %.1f%%), win %s vs chance %.1f%% (needs"
fix(gate): the ensemble gate certified a vote the EA never casts g_ensembleVoteThreshold's comment claims the combined-vote scorer "fires on the same criterion the live trade does". It did not. Two independent mismatches, both silent: CURRENCY. Each member contributed its raw signed confidence x100 - a 33..100 number straight off the softmax head. Live contributes m_weight x the tier's pattern weight, and BOTH of those are rewritten from the signal DB by UpdateSignalsWeights(). A head output and a DB-ranked win-rate weight share an axis and nothing relates them, so the same bar was one number to the gate and a different one to the order path. Same shape as the 2026-08-09 geometry incident: certified on one game, paid on another. DENOMINATOR. The gate divided by the member count, so an abstaining member pulled the average toward zero. CExpertSignalCustom::Direction() skips a zero contribution in BOTH the sum and the count (`if(direction == 0) continue;` before `number++`) - live is a mean over VOTERS. The gate was therefore scoring a strictly more agreement-heavy set of bars than the EA trades. The contribution hook's own comment asserted the opposite ("abstentions dilute the average exactly as they do in the live vote"), while the AI_CHOICE enum 20 lines away correctly documented union semantics. LiveVoteContribution() is now the single definition of "what this member votes", called from the gate; the live path reaches the same arithmetic through LongCondition/ShortCondition. g_ensVoteVoterMask records who actually voted, separately from who evaluated the bar, because those are the divisor and the shared-population test respectively. ConfidenceTier() is split into ConfidenceTierFor(signal) plus a thin live-bar wrapper - the OOS scan holds the scanned bar's decision in a local, and dPrevSignal is a different bar. NOT changed, deliberately: the gate still does not model live NMS declustering, and the per-member solo gate still scores every directional call rather than threshold-clearing ones. Both are selection-metric changes and this codebase has twice been bitten by switching one blind. Also corrects a stale paragraph in m_pattern_0's declaration block quoting 80/87/93/100 as the tier defaults. The constructor is 25/50/75/100 and has been since the confidence floor and alternation gate were removed; the block carried both tables at once, and the dead one was quoted back as fact. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 15:23:33 -04:00
" >%.1f%% at %d sigma)%s -> score %.1f%s%s. The vote that actually trades: each"
" member's DB-ranked tier weight x module weight, averaged over the members that"
" VOTED (abstentions excluded, as live), graded on target-before-stop.",
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
(int)votedEra, members, shared, fired, g_ensembleVoteThreshold,
coveragePct, minCoverPct,
(fired > 0 ? StringFormat("%.1f%%", votePrecPct) : "n/a"), chancePct, edgeFloorPct,
(int)EDGE_MIN_SIGMAS, (tradeableOK ? " DEPLOYABLE" : ""), score,
(isBetter ? StringFormat(" <-- NEW BEST, joint checkpoint captured (era %d)", (int)votedEra)
: StringFormat(" (best %.1f at era %d, %d eras ago)", g_ensBestScore,
(int)g_ensBestEra, g_ensErasSinceBest)),
fix(vote): unranked members voted with the stock 25/50/75/100 ladder Two defects behind "arrows drawn while members are still mid-era". 1. THE DRAW. The filtered overlay armed on the FIRST member to finish pass 3 and leaned on a 60 s rate limit to "collapse the burst", assuming members finish seconds apart. They do not - on USDJPY one member was at sample 10496 of pass 2 while another was at 2304, minutes apart. A member with no era-end snapshot returns false from SnapshotVoteAt, and the sweep's `if(!hasData) continue;` skips it BEFORE `den += ModuleWeight()`, so the one finished model's tier weight became the entire vote and was drawn as a consensus arrow. An abstention is a member that looked at the bar and said nothing; a missing snapshot is a member that has not looked. The first must dilute the vote, the second must suppress the draw. The arm is now a readiness MASK - one bit per m_ensembleIndex, set at that member's pass-3 completion, cleared when a sweep arms - and a sweep waits for every enrolled member. Bounded at 10 minutes so a member that stops cannot freeze the chart, and the partial draw PRINTS which members were missing: the be39674 lesson is that a hold must never silence the thing that reports it. 2. THE VOTE ITSELF, which is the worse half and is not display-only. Tier weights are not persisted in the .nnw - they exist only as the output of a completed pass 3 - so before a member's first RankTiersFromOos() it holds the constructor's stock 25/50/75/100. Since 4858507 the vote currency is a WIN RATE, so an unranked tier-3 call enters the capability-weighted mean claiming a 100% win rate beside ranked members contributing ~25. Not a strong opinion: the wrong unit. One unranked member drags the ensemble over any threshold, on every fresh deploy and every resume. USDJPY has a measured ceiling of ~19 and was firing anyway. LiveVoteContribution() now abstains until self-ranked, which drops the member from the sum AND the divisor. One function, so live and the gate move together (2c443ba). Era 0 will therefore report 0 coverage until each member completes one era. The ensemble line says so explicitly rather than leaving it to look like the USDJPY unreachable-threshold case - the two are identical in the coverage number and completely different problems. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 08:55:04 -04:00
ladderNote + metaNote + rankNote + ceilingNote));
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
}
//+------------------------------------------------------------------+
//| Per-member era-end hook: mark this member done for the era and, |
//| when it is the last one, run the verdict above. |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::EnsembleOosPassComplete(const long votedEra, double &etaLocal)
{
if(!m_ensembleMember || m_ensembleIndex < 0)
return;
//--- The rows were stamped during pass 3, BEFORE this member incremented its era counter, so the
//--- buffer's era is the era that just finished. A mismatch means this member contributed nothing
//--- to the current buffer (no OOS bars scored this era) - it cannot be counted as having read the
//--- vote, or the verdict would be taken on a subset that silently excludes it.
if(g_ensVoteEra != votedEra)
return;
g_ensVoteDoneMask |= (1 << m_ensembleIndex);
int need = 0;
for(int i = 0; i < ArraySize(g_warriorEnsemble); i++)
{
CExpertSignalAIBase *mm = g_warriorEnsemble[i];
if(CheckPointer(mm) == POINTER_INVALID || mm.m_ensembleIndex < 0)
continue;
if(mm.m_trainingComplete || mm.m_trainingStopRequested || mm.m_trainingPaused || !mm.m_isInitialized)
continue;
need |= (1 << mm.m_ensembleIndex);
}
if(need == 0 || (g_ensVoteDoneMask & need) != need)
return;
//--- Idempotence: one verdict per era, whatever order the members arrive in.
if(g_ensLastVerdictEra == votedEra)
return;
g_ensLastVerdictEra = votedEra;
EnsembleEraVerdict(need, votedEra, etaLocal);
}
//+------------------------------------------------------------------+
feat: gate deployment on the null of the MAXIMUM, not the per-era null EDGE_MIN_SIGMAS is a PER-ERA test and the deployed model is the MAXIMUM over every era a run ranks. A 2-sigma one-sided test passes on noise with probability 0.0228 per era, so over N eras the chance at least one clears it is 1-(1-0.0228)^N: 34% by era 18, 80% by era 70, 93% by era 112. The gate was near-certain to open on a long run whatever the data held. It did. HYBRID deployed 2026-08-08 at dir-precision 35.5% vs 34% chance - +1.5pp, best of 112 eras whose per-era values wandered 30%..35.5%. At the call counts these runs produce that is p_family 0.92..0.9999. Every OTHER best-of-N decision here already carries this correction, and every one REJECTS on this data: the barrier-geometry winner (null of the maximum over 6, p=0.3902), the indicator tuner (Sidak, p=1.0000), the MI lag profile (null of the maximum over 21 lags). The one decision that ships a model to a live account had none. BestCheckpointSurvivesSelection() re-tests the checkpoint that is about to deploy: z = (precision - chance)/SE, SE = sqrt(p0(1-p0)/n) p_single = P(Z >= z) p_family = 1 - (1-p_single)^N against DEPLOY_FAMILY_WISE_ALPHA. It uses the checkpoint's OWN snapshotted precision/chance/call-count, not the latest era's, because the model that ships is the one that has to clear the bar. N counts CANDIDATE eras (coverage measurable, at least one directional call) - an era that called nothing directional could never have become the best, so counting it would make the gate stricter than the search that actually happened. Conservative on purpose: consecutive eras share OOS bars and differ by one gradient step, so they are nowhere near N independent draws and the true family-wise error is below this bound. This gate decides what trades real money and the house posture is reject-unless-demonstrated. Effect at 2900 directional calls / N=112: required edge goes 1.76pp -> 2.92pp. A real edge clears it; +1.5pp does not. Applied to BOTH automatic paths - the plateau ladder's stage-3 deploy and the m_trainingComplete assignment - which must stay identical or the flag persisted into the .nnw disagrees with the decision to stop, and a reload runs inference on a model the ladder refused. NOT applied to the two operator paths (era-cap deploy, panel Deploy button). Those stay the operator's call; ReportSelectionGateVerdict() logs the verdict beside them so an authorised deploy can never later be misread as a validated one. NormalUpperTail() is A&S 26.2.17 (|err| < 7.5e-8), self-contained rather than pulling in Math\Stat. Verified against reference values to 6dp: Q(1.645)=0.049985, Q(1.96)=0.024998, Q(3.0)=0.001350. Its locals are ntB1..ntB5 because AI\Network.mqh line 79 does "#define b1 AdamBeta1". Compiles clean: 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-08 18:01:04 -04:00
//| Log the selection-gate verdict for a deploy the gate does NOT |
//| block - the era-cap path and the panel's Deploy button, both of |
//| which are explicit operator decisions and stay that way. The point |
//| is that "I chose to ship this" and "this cleared the bar" should |
//| never be confusable in the log afterwards. |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::ReportSelectionGateVerdict(string context)
{
double z = 0.0, pFam = 1.0;
int nTried = 0;
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
//--- ENSEMBLE: report the gate that actually governs this model. Quoting the member's own
//--- best-of-N here would answer a question nobody asked - the member never deploys alone, and a
//--- member-level "CLEARS" next to a vote that did not is precisely the confusion this function
//--- exists to prevent.
if(m_ensembleMember)
{
bool okEns = EnsembleSurvivesSelection(z, pFam, nTried);
if(g_ensBestCalls <= 0)
{
Print(ID + ": " + context + " - the ENSEMBLE selection gate cannot be evaluated (no era's"
" combined vote has been ranked yet). Treat this ensemble as unvalidated.");
return;
}
Print(ID + ": " + context + " - ENSEMBLE best-of-" + IntegerToString(nTried) + " test on the"
" combined VOTE: edge " + DoubleToString(g_ensBestPrecPct - g_ensBestChancePct, 1) + "pp (" +
DoubleToString(g_ensBestPrecPct, 1) + "% vs chance " + DoubleToString(g_ensBestChancePct, 1) +
"%) on " + IntegerToString(g_ensBestCalls) + " fired bars = " + DoubleToString(z, 2) +
" sigma, family-wise p=" + DoubleToString(pFam, 4) + " (need <=" +
DoubleToString(DEPLOY_FAMILY_WISE_ALPHA, 2) + ") - " +
(okEns ? "CLEARS."
: "DOES NOT CLEAR. A maximum this size arises routinely when every era is a noise"
" draw, so this ensemble is being deployed on operator authority, NOT on measured"
" evidence of an edge."));
return;
}
feat: gate deployment on the null of the MAXIMUM, not the per-era null EDGE_MIN_SIGMAS is a PER-ERA test and the deployed model is the MAXIMUM over every era a run ranks. A 2-sigma one-sided test passes on noise with probability 0.0228 per era, so over N eras the chance at least one clears it is 1-(1-0.0228)^N: 34% by era 18, 80% by era 70, 93% by era 112. The gate was near-certain to open on a long run whatever the data held. It did. HYBRID deployed 2026-08-08 at dir-precision 35.5% vs 34% chance - +1.5pp, best of 112 eras whose per-era values wandered 30%..35.5%. At the call counts these runs produce that is p_family 0.92..0.9999. Every OTHER best-of-N decision here already carries this correction, and every one REJECTS on this data: the barrier-geometry winner (null of the maximum over 6, p=0.3902), the indicator tuner (Sidak, p=1.0000), the MI lag profile (null of the maximum over 21 lags). The one decision that ships a model to a live account had none. BestCheckpointSurvivesSelection() re-tests the checkpoint that is about to deploy: z = (precision - chance)/SE, SE = sqrt(p0(1-p0)/n) p_single = P(Z >= z) p_family = 1 - (1-p_single)^N against DEPLOY_FAMILY_WISE_ALPHA. It uses the checkpoint's OWN snapshotted precision/chance/call-count, not the latest era's, because the model that ships is the one that has to clear the bar. N counts CANDIDATE eras (coverage measurable, at least one directional call) - an era that called nothing directional could never have become the best, so counting it would make the gate stricter than the search that actually happened. Conservative on purpose: consecutive eras share OOS bars and differ by one gradient step, so they are nowhere near N independent draws and the true family-wise error is below this bound. This gate decides what trades real money and the house posture is reject-unless-demonstrated. Effect at 2900 directional calls / N=112: required edge goes 1.76pp -> 2.92pp. A real edge clears it; +1.5pp does not. Applied to BOTH automatic paths - the plateau ladder's stage-3 deploy and the m_trainingComplete assignment - which must stay identical or the flag persisted into the .nnw disagrees with the decision to stop, and a reload runs inference on a model the ladder refused. NOT applied to the two operator paths (era-cap deploy, panel Deploy button). Those stay the operator's call; ReportSelectionGateVerdict() logs the verdict beside them so an authorised deploy can never later be misread as a validated one. NormalUpperTail() is A&S 26.2.17 (|err| < 7.5e-8), self-contained rather than pulling in Math\Stat. Verified against reference values to 6dp: Q(1.645)=0.049985, Q(1.96)=0.024998, Q(3.0)=0.001350. Its locals are ntB1..ntB5 because AI\Network.mqh line 79 does "#define b1 AdamBeta1". Compiles clean: 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-08 18:01:04 -04:00
bool ok = BestCheckpointSurvivesSelection(z, pFam, nTried);
if(m_bestDirCalls <= 0)
{
Print(ID + ": " + context + " - selection gate cannot be evaluated (no ranked checkpoint with"
" directional calls). Treat this model as unvalidated.");
return;
}
Print(ID + ": " + context + " - best-of-" + IntegerToString(nTried) + " selection test: edge " +
DoubleToString(m_bestDirPrecPct - m_bestChancePrecPct, 1) + "pp (" +
DoubleToString(m_bestDirPrecPct, 1) + "% vs chance " + DoubleToString(m_bestChancePrecPct, 1) +
"%) on " + IntegerToString(m_bestDirCalls) + " directional calls = " + DoubleToString(z, 2) +
" sigma, family-wise p=" + DoubleToString(pFam, 4) + " (need <=" +
DoubleToString(DEPLOY_FAMILY_WISE_ALPHA, 2) + ") - " +
(ok ? "CLEARS."
: "DOES NOT CLEAR. A maximum this size arises routinely when every era is a noise draw, so"
" this model is being deployed on operator authority, NOT on measured evidence of an edge."));
}
//+------------------------------------------------------------------+
refactor(comments): box headers to stdlib length The //| box blocks were excluded from 0b06f8e and 5efdb48 and were what remained: 160 of them ran to 10+ lines, the longest to 88. Compressed to their leading topic sentences - 5 lines for a function header, 8 for a file header - keeping the box format and the standard MQL5 name/author lines verbatim. Verified at the BYTE level this time, across every in-scope file: the list of non-comment lines is byte-identical to HEAD and braces balance. The first check compared a locale-decoded 'git show' against a UTF-8 read and flagged 25 files that had not changed at all - every BOM and every non-ASCII line mismatched. 47,696 -> 40,665 lines in scope; comment share 38% -> 26%. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:30:14 -04:00
//| Training and Signal Methods Where the TRAINING window starts: |
//| ALL available history, floored by MinTrainYear. |
fix: prebuild and era sized different windows; diag: Train() names its branch TWO things, one incident. 1) THE BUG I SHIPPED IN 0c85c54. m_tuneStartTrainBar is declared, initialised to 0, and NEVER ASSIGNED - the assignment existed before the God-class split and the split dropped it, leaving a dead member. Harmless while nothing read it; a real defect the moment 0c85c54 made StartLabelCachePrebuild() reset dtStudied from it. Train() then computed the window as max(StartTrainBar, floor) while the prebuild computed max(0, floor), where StartTrainBar is the non-zero datetime OnChartEventHandler passes through from the "New Bar" event. The two therefore disagreed about `bars`, so EnsureBarCachesCapacity() saw a changed size at era start, wiped the caches, and re-armed a full 38k-bar prebuild - instead of training. Restored the assignment so both sides evaluate the identical expression. 2) THE REASON IT TOOK ALL NIGHT TO FIND. Train() is a state machine with six early-return branches above the era loop and every one of them is silent. Four charts burned a core each for 15 minutes with an empty journal: the pass heartbeats (694b756) proved the era loop was never reached, no prebuild completion line appeared either, and nothing external can see inside a single MQL5 thread - per-thread CPU says "busy", file writes say nothing, and the VPS has no debugger. That is an undiagnosable state, and it is the thing to fix, not just the bug of the day. ReportTrainStall() now names the branch Train() is taking whenever no era has completed for 3 minutes, at most once a minute per signal, with the state that decides the branch: run/prebuild/simOos/resume flags, era, dtStudied, and - for the cache-invalidation branch specifically - BOTH bar counts, since two sizings disagreeing is exactly what re-arms the prebuild forever. Silent on a healthy run: an era completing resets the clock. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 07:32:08 -04:00
//+------------------------------------------------------------------+
void CExpertSignalAIBase::ReportTrainStall(const string branch)
{
const uint STALL_AFTER_MS = 180000; // 3 min: ~2x the slowest healthy era seen on this config
const uint STALL_REPORT_INTERVAL = 60000;
uint nowTick = GetTickCount();
//--- First call ever: adopt now as the baseline rather than reporting instantly against tick 0.
if(m_lastEraCompleteTick == 0)
{
m_lastEraCompleteTick = nowTick;
return;
}
uint since = nowTick - m_lastEraCompleteTick;
if(since < STALL_AFTER_MS)
return;
if(m_lastStallReportTick != 0 && nowTick - m_lastStallReportTick < STALL_REPORT_INTERVAL)
return;
m_lastStallReportTick = nowTick;
PrintFormat("%s: TRAIN STALL - no era has completed for %.0fs and Train() is taking the '%s' branch"
" | era %d | runActive=%s prebuildActive=%s cachePrebuilt=%s simOos=%s eraResume=%s"
" paused=%s stopReq=%s | labelCacheBars=%d anchor=%s dtStudied=%s",
ID, since / 1000.0, branch, (int)m_eraCount,
m_trainRunActive ? "Y" : "N", m_labelPrebuildActive ? "Y" : "N",
m_labelCachePrebuilt ? "Y" : "N", m_simOosRunActive ? "Y" : "N",
m_eraResumePending ? "Y" : "N", m_trainingPaused ? "Y" : "N",
m_trainingStopRequested ? "Y" : "N",
m_labelCacheBars, TimeToString(m_labelCacheAnchorTime), TimeToString(dtStudied));
}
//+------------------------------------------------------------------+
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
//| Speaks ONLY when an era is genuinely slow: nothing for the first |
//| 60 seconds of an era, at most 6 lines after that, one per 4096 |
//| processed items. Reports where the time actually went, split into |
//| the two candidate costs and the remainder, because "the era is |
//| slow" without the split is exactly the undiagnosable state the |
//| 2026-08-10 restart produced (see the member declarations). |
//+------------------------------------------------------------------+
fix: the panel showed "100%" for the whole of pass 1 The simple panel derived its percentage from pass 2's counters: (m_isTrainCursor+1) / max(m_isTrainQueueCount,1). During pass 1 those are 0 and 0, so the expression is (0+1)/max(0,1) = 100%. An era spends its first pass scanning ~38k bars - minutes of work - and the panel reported that phase as finished the entire time. Observed by the user as "started learning at 100% of their era and are stuck there", and it actively misled the diagnosis: the one number on screen said the opposite of what was happening. The UI cannot fix this on its own - it can see pass 2's counters but has no way to know which pass owns them. So each pass now PUBLISHES its own progress and a short phase name through TrainHeartbeat (which every pass already calls per item), and the panel just displays them: "learning (era 45, scan 34%)". Published before the heartbeat's 4096-item journal gate, so the panel updates continuously while the journal stays quiet. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 07:22:29 -04:00
void CExpertSignalAIBase::TrainHeartbeat(const string tag, int done, int total, const string shortLabel)
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
{
fix: the panel showed "100%" for the whole of pass 1 The simple panel derived its percentage from pass 2's counters: (m_isTrainCursor+1) / max(m_isTrainQueueCount,1). During pass 1 those are 0 and 0, so the expression is (0+1)/max(0,1) = 100%. An era spends its first pass scanning ~38k bars - minutes of work - and the panel reported that phase as finished the entire time. Observed by the user as "started learning at 100% of their era and are stuck there", and it actively misled the diagnosis: the one number on screen said the opposite of what was happening. The UI cannot fix this on its own - it can see pass 2's counters but has no way to know which pass owns them. So each pass now PUBLISHES its own progress and a short phase name through TrainHeartbeat (which every pass already calls per item), and the panel just displays them: "learning (era 45, scan 34%)". Published before the heartbeat's 4096-item journal gate, so the panel updates continuously while the journal stays quiet. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 07:22:29 -04:00
//--- Panel progress is published on EVERY call, before the 4096-item gate below: the gate exists to
//--- keep the JOURNAL quiet, and applying it to the panel too would leave the display frozen between
//--- boundaries. Two assignments, no formatting - cheap enough for a per-item path.
m_passLabel = shortLabel;
m_passProgressPct = (total > 0) ? (int)MathMin(100.0, 100.0 * done / total) : 0;
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- TIME-gated, not item-gated. A diagnostic whose trigger can be outrun by the condition it
//--- watches for is worse than none - it produces confident wrong conclusions. The 255-item mask
//--- only keeps GetTickCount() off the hot path.
diag: the heartbeat could be outrun by the condition it watched for It fired only on 4096-item boundaries once an era had already run 60s. Those boundaries are all crossed in the first few chunks of pass 1, so an era that became slow AFTER them printed nothing at all - which is precisely what happened: 20 minutes, four pegged cores, zero heartbeats. I read that silence as "the era loop is never reached" and went looking for a wedge above it. The silence may simply have meant "past the last boundary". A diagnostic whose trigger can be outrun by the condition it watches for is worse than no diagnostic, because it produces confident wrong conclusions. Now time-gated: checked every 256 items (the mask only keeps GetTickCount off the hot path), prints when the era has run >60s and >30s since the last line, up to 12 per era. Progress/phase for the panel is still published on every call, before any gate. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 07:44:03 -04:00
if((done & 255) != 0)
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
return;
diag: the heartbeat could be outrun by the condition it watched for It fired only on 4096-item boundaries once an era had already run 60s. Those boundaries are all crossed in the first few chunks of pass 1, so an era that became slow AFTER them printed nothing at all - which is precisely what happened: 20 minutes, four pegged cores, zero heartbeats. I read that silence as "the era loop is never reached" and went looking for a wedge above it. The silence may simply have meant "past the last boundary". A diagnostic whose trigger can be outrun by the condition it watches for is worse than no diagnostic, because it produces confident wrong conclusions. Now time-gated: checked every 256 items (the mask only keeps GetTickCount off the hot path), prints when the era has run >60s and >30s since the last line, up to 12 per era. Progress/phase for the panel is still published on every call, before any gate. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 07:44:03 -04:00
uint nowTick = GetTickCount();
uint elapsedMs = nowTick - m_eraStartTick;
if(elapsedMs < 60000 || m_passHeartbeatPrints >= 12)
return;
if(m_lastHeartbeatTick != 0 && nowTick - m_lastHeartbeatTick < 30000)
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
return;
diag: the heartbeat could be outrun by the condition it watched for It fired only on 4096-item boundaries once an era had already run 60s. Those boundaries are all crossed in the first few chunks of pass 1, so an era that became slow AFTER them printed nothing at all - which is precisely what happened: 20 minutes, four pegged cores, zero heartbeats. I read that silence as "the era loop is never reached" and went looking for a wedge above it. The silence may simply have meant "past the last boundary". A diagnostic whose trigger can be outrun by the condition it watches for is worse than no diagnostic, because it produces confident wrong conclusions. Now time-gated: checked every 256 items (the mask only keeps GetTickCount off the hot path), prints when the era has run >60s and >30s since the last line, up to 12 per era. Progress/phase for the panel is still published on every call, before any gate. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 07:44:03 -04:00
m_lastHeartbeatTick = nowTick;
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
m_passHeartbeatPrints++;
double featS = (double)m_passFeatUs / 1000000.0;
double netS = (double)m_passNetUs / 1000000.0;
PrintFormat("%s: SLOW ERA heartbeat - %s %d of %d after %.0fs | feature windows %.1fs | net fwd/back %.1fs | everything else %.1fs",
ID, tag, done, total, elapsedMs / 1000.0, featS, netS,
MathMax(elapsedMs / 1000.0 - featS - netS, 0.0));
}
//+------------------------------------------------------------------+
fix: a restart no longer loses the measured geometry or the training window Terminal restart, 22:25: all four resumed models sat on empty windows with enum 2:6 barriers. Three interlocking causes, all visible in one log excerpt: 1) THE PRE-SCAN WINDOW WAS SIZED BY THE SAVED WATERMARK. A resumed model's dtStudied sits at its last studied bar, so Bars(dtStudied, now) ~ 0 and the resumed-model MI pre-scan built a zero-bar "complete" label cache - logged as "Buy: 0 | Sell: 0 | Neutral: 0". Train()'s own era start RESETS dtStudied to the training-window rule before computing its window; the pre-scan did not. The rule is now factored into TrainWindowStart() and both use it. The scan also refuses to arm before SERIES_SYNCHRONIZED (it ran in the same second as OnInit), and deployed models keep their watermark - for them it gates inference recency, not a training window. 2) THE HORIZON LATCHED ON AN INDICATOR WARM-UP. ComputeBarrierHorizonBars ran against a ZigZag with 0 calculated legs, fell back, and EnsureBarrierHorizon latched fallback(32) x slMult x tpMult = 384 for the process lifetime. A leg-starved horizon is now PROVISIONAL: re-resolved on the next rebuild, the label cache wiped if it moved (labels from two horizons answer different questions), and the geometry deriver refuses to run from it - a pair derived over a warm-up window would get PINNED. 3) THE DERIVED GEOMETRY WAS NEVER PERSISTED. The .cfg is written at model creation and at weights-reset - both BEFORE era 0 derives - so the measured pair lived only in memory: every restart read back zeros, adopted nothing, fell back to the enum barriers, and the era-0-only gate meant a resumed model could NEVER re-derive. A full day of training on 3.33/1.62 resumed as 2:6. Now: the settled pair is pinned to the .cfg the moment derivation completes (one-shot, atomic write), and the derive gate accepts any model with no pinned pair, not just era 0 - mid-run stability is carried by m_geometryDerived itself, which never allows a second derivation. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 22:40:43 -04:00
datetime CExpertSignalAIBase::TrainWindowStart(datetime startTrainBar)
{
datetime firstAvailableBar = (datetime)SeriesInfoInteger(m_symbol.Name(), PERIOD_CURRENT, SERIES_FIRSTDATE);
MqlDateTime floor_time;
TimeCurrent(floor_time);
floor_time.year = m_minTrainYear;
floor_time.mon = 1;
floor_time.day = 1;
floor_time.hour = 0;
floor_time.min = 0;
floor_time.sec = 0;
datetime st_time = StructToTime(floor_time);
if(firstAvailableBar > st_time)
st_time = firstAvailableBar;
return MathMax(startTrainBar, st_time);
}
//+------------------------------------------------------------------+
refactor(dry): one writer for the era-resume context, one for an alt-data row Two literal duplications the scan found, both of the kind where a divergence is silent: - Training.mqh stashed the era-loop resume context at FOUR yield points, seven identical assignments each (pass 1 differing only in i-1). A field missed at one of them resumes the next chunk against a different era than the one that yielded, and nothing reports it until the numbers drift. Now StashEraResume(). - AltDataFetch grew its five parallel arrays inline in three places. They are one record split across five buffers, so a resize missed on any one reads out of range on the NEXT append, not at the site of the mistake. Now AltSeriesAppend(), which returns the new index and zero-fills; callers set only the columns their source has. Braces balance across every in-scope file. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:36:36 -04:00
//| Save the era-loop context a yielding chunk resumes against. |
//| |
//| Each pass keeps its OWN cursor (m_isTrainCursor, m_calibIndex, |
//| m_oosScoreIndex); these five are what every pass shares. One |
//| writer, because a field missed at one of the four yield points |
//| resumes the next chunk against a different era than the one that |
//| yielded, and nothing reports that until the numbers drift. |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::StashEraResume(const int bars, const int totalIter, const int oosCutoff,
const bool add_loop, const int barIndex)
{
m_resumeBars = bars;
m_resumeTotalIter = totalIter;
m_resumeOosCutoff = oosCutoff;
m_resumeAddLoop = add_loop;
m_resumeBarIndex = barIndex;
m_eraResumePending = true;
//--- This model's own learning-rate trajectory, out of the shared global before yielding.
m_modelEta = g_eta;
}
//+------------------------------------------------------------------+
refactor(training): the era log is not part of the era loop Train() was 2,572 lines in one function. The largest single block in it was ~200 lines of string building for the console line, reachable only because twenty-one loose ints were declared at the top of the function and read nine hundred lines later. Those declarations were the reason the block could not move. Introduce SEraTelemetry - one parameter object holding exactly those twenty-one numbers, self-initialising to -1 ("not measured this era", which is what era 0 and any stopped era report, and is not the same as a measured zero). ReportEraProgress() takes it and renders it, guarding on its own shouldLog so the call site is one unconditional line rather than a 200-line branch. Nothing is decided or measured in the moved code - it reads state and prints. Verified by stripping comments and whitespace from both revisions and diffing the remaining statements: the only differences are the ten declarations collapsing into one object, the throttle test moving inside the callee, and the new signature plus its call. Every other statement is byte-identical. Train() 2,572 -> 2,370 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:25:07 -04:00
//| THE ERA LINE. Everything below is string building over already- |
//| measured state - it decides nothing and changes nothing, which |
//| is exactly why it does not belong inside the era loop. |
//| |
//| Self-guarding on tel.shouldLog: the throttle is decided where |
//| the tick count is known and carried here, so the caller is one |
//| unconditional call rather than a 200-line branch. |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::ReportEraProgress(const SEraTelemetry &tel)
{
if(!tel.shouldLog)
return;
string recallInfo = (tel.buyRecall < 0 && tel.sellRecall < 0 && tel.neutralRecall < 0) ? "" :
(" | OOS recall Buy:" + (tel.buyRecall < 0 ? "n/a" : IntegerToString(tel.buyRecall) + "%") +
" Sell:" + (tel.sellRecall < 0 ? "n/a" : IntegerToString(tel.sellRecall) + "%") +
" Neutral:" + (tel.neutralRecall < 0 ? "n/a" : IntegerToString(tel.neutralRecall) + "%") +
//--- The floor is DERIVED per class now, so it has to be printed rather than assumed -
//--- a reader comparing these recalls against a remembered "40" would be reading the
//--- wrong bar.
StringFormat(" (collapse floor >=%.1f%% each - DERIVED from each class's effective sample,"
" and it sits BELOW the 33.3%% zero-skill recall on purpose: it refuses a"
" COLLAPSED model, it does not certify a good one)", m_lastRecallFloorPct));
//--- Balanced accuracy = the checkpoint-selection metric (see m_bestBalancedOos). Shown so
//--- the number the deployed model is actually chosen on is visible next to the recalls it
//--- averages.
string balancedInfo = (tel.balancedAcc < 0) ? "" : (" | OOS balanced acc " + IntegerToString(tel.balancedAcc) + "% (diagnostic)");
//--- "win-rate", not "dir-precision": since 2026-08-09 this counts calls whose TRADE
//--- reached target before stop, and the chance figure beside it is what always-
//--- long/always-short collected on the same bars.
string selectionInfo = (tel.dirPrec < 0) ? " | SELECT: no directional calls survived the threshold" :
(" | SELECT win-rate " + IntegerToString(tel.dirPrec) + "% on " +
IntegerToString(tel.coverage) + "% of bars (post-threshold)" +
(tel.chancePrec >= 0
? " (chance=break-even " + IntegerToString(tel.chancePrec) + "%, edge " +
(tel.dirPrec - tel.chancePrec >= 0 ? "+" : "") +
IntegerToString(tel.dirPrec - tel.chancePrec) + "pp)"
: ""));
//--- The operating point that produced the coverage figure just above it, so the two are read
//--- together: coverage falling is only good news if it is this that caused it.
selectionInfo += " @margin>=" + DoubleToString(m_dirConfThreshold, 2);
//--- TRADED precision: the same calls after declustering, which since 2026-08-09 is
//--- exactly the set that becomes positions (live NMS gates the trade, not just the
//--- arrow).
if(m_signalClusterWindow > 0 && m_oosNmsFired > 0)
{
int nmsPrec = (int)MathRound(100.0 * m_oosNmsHits / m_oosNmsFired);
selectionInfo += " | TRADED (declustered) " + IntegerToString(nmsPrec) + "% on " +
IntegerToString(m_oosNmsFired) + " calls" +
(tel.chancePrec >= 0
? " (edge " + (nmsPrec - tel.chancePrec >= 0 ? "+" : "") +
IntegerToString(nmsPrec - tel.chancePrec) + "pp)"
: "");
}
// See tel.buyPred's declaration comment for why this is worth logging alongside recall -
// it's what tells apart a suppressed/dead output (predicted rate stuck at 0%) from a
// miscalibrated boundary (predicted rate healthy, precision poor), which look identical from
// recall alone.
string predictedInfo = (tel.buyPred < 0 && tel.sellPred < 0) ? "" :
(" | OOS calls Buy:" + (tel.buyPred < 0 ? "n/a" : IntegerToString(tel.buyPred) + "%") +
" (win rate " + (tel.buyPrec < 0 ? "n/a" : IntegerToString(tel.buyPrec) + "%") + ")" +
" Sell:" + (tel.sellPred < 0 ? "n/a" : IntegerToString(tel.sellPred) + "%") +
" (win rate " + (tel.sellPrec < 0 ? "n/a" : IntegerToString(tel.sellPrec) + "%") + ")");
//--- CALIBRATION - "does the model call each class as often as the class actually occurs".
//--- Ratios, because 1.0x is the answer and the distance from it is the error.
string calibInfo = (tel.buyTrue < 0 || tel.buyFired < 0) ? "" :
StringFormat(" | CALIBRATION traded vs true rate Buy %d%% vs %d%% (%s) Sell %d%% vs %d%% (%s)"
" Neutral %d%% vs %d%% (%s) | pre-threshold argmax Buy %d%% Sell %d%% Neutral %d%%",
tel.buyFired, tel.buyTrue, CalibrationRatio(tel.buyFired, tel.buyTrue),
tel.sellFired, tel.sellTrue, CalibrationRatio(tel.sellFired, tel.sellTrue),
tel.neutralFired, tel.neutralTrue,
CalibrationRatio(tel.neutralFired, tel.neutralTrue),
tel.buyPred, tel.sellPred, tel.neutralPred);
//--- Live-fired precision: the number that actually predicts forward-trading performance - only
//--- the directional calls that cleared the confidence floor under the live/prior-corrected rule
//--- (see AdjustedSignalFromSoftmax). Count in parentheses = how many bars the model would have
//--- traded this era. "0" fires = the calibration is (this era) suppressing all directional trades.
string liveInfo = (m_lastBuyFired <= 0 && m_lastSellFired <= 0) ? " | live fires 0 this era" :
(" | live win rate Buy:" + (tel.buyFiredPrec < 0 ? "n/a" : IntegerToString(tel.buyFiredPrec) + "%") +
" (" + IntegerToString(m_lastBuyFired) + ")" +
" Sell:" + (tel.sellFiredPrec < 0 ? "n/a" : IntegerToString(tel.sellFiredPrec) + "%") +
" (" + IntegerToString(m_lastSellFired) + ")");
//--- Precision BY CONFIDENCE TIER, and cumulatively from each tier upward - the two
//--- numbers a decision about Signal_ThresholdOpen actually needs.
string tierInfo = "";
int tierFiredTotal = 0;
for(int ti = 0; ti < 4; ti++)
tierFiredTotal += m_oosTierFired[ti];
if(tierFiredTotal > 0)
{
tierInfo = " | tier prec";
for(int ti = 0; ti < 4; ti++)
{
int cumFired = 0, cumHits = 0;
for(int tj = ti; tj < 4; tj++)
{
cumFired += m_oosTierFired[tj];
cumHits += m_oosTierHits[tj];
}
tierInfo += " T" + IntegerToString(ti) + ":" +
(m_oosTierFired[ti] > 0
? IntegerToString((int)MathRound(100.0 * m_oosTierHits[ti] / m_oosTierFired[ti])) + "%"
: "n/a") +
"(" + IntegerToString(m_oosTierFired[ti]) + ")" +
(cumFired > 0
? "[>=" + IntegerToString((int)MathRound(100.0 * cumHits / cumFired)) + "%/" +
IntegerToString(cumFired) + "]"
: "");
}
}
//--- Per-layer weight movement. Pairs with rawOutInfo below: a collapsed constant-
//--- classifier state has two very different causes, and only this tells them apart. See
//--- CNet::LayerLearningReport.
string layerInfo = (CheckPointer(Net) == POINTER_INVALID) ? "" :
(" | dW/W" + Net.LayerLearningReport());
// Raw-output saturation diagnostic - see m_oosOutMin's declaration comment. Spread ~0 with
// all six min/max values pinned together = the collapsed constant-classifier state.
string rawOutInfo = (m_oosOutCount <= 0) ? "" :
StringFormat(" | OOS raw out B:%.3f..%.3f S:%.3f..%.3f N:%.3f..%.3f spread avg %.4f",
m_oosOutMin[0], m_oosOutMax[0], m_oosOutMin[1], m_oosOutMax[1],
m_oosOutMin[2], m_oosOutMax[2], m_oosOutSpreadSum / m_oosOutCount);
//--- Splits a reported "Neutral" into the two events that share that label. CHOSE = the
//--- net ranks Neutral highest (a class-prior problem); TIED = the top two are exactly
//--- equal and the tie-break reported Neutral (a saturation problem).
double beFrictionless = 50.0;
{
double slBe = 0.0, tpBe = 0.0;
BarrierMultiples(slBe, tpBe);
if(slBe + tpBe > 0.0)
beFrictionless = 100.0 * slBe / (slBe + tpBe);
}
//--- DENOMINATOR IS THE PER-ERA BAR COUNT, not m_oosSamples (fixed 2026-08-17).
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
int zsBars = m_oos.Bars();
refactor(training): the era log is not part of the era loop Train() was 2,572 lines in one function. The largest single block in it was ~200 lines of string building for the console line, reachable only because twenty-one loose ints were declared at the top of the function and read nine hundred lines later. Those declarations were the reason the block could not move. Introduce SEraTelemetry - one parameter object holding exactly those twenty-one numbers, self-initialising to -1 ("not measured this era", which is what era 0 and any stopped era report, and is not the same as a measured zero). ReportEraProgress() takes it and renders it, guarding on its own shouldLog so the call site is one unconditional line rather than a 200-line branch. Nothing is decided or measured in the moved code - it reads state and prints. Verified by stripping comments and whitespace from both revisions and diffing the remaining statements: the only differences are the ten declarations collapsing into one object, the throttle test moving inside the callee, and the new signature plus its call. Every other statement is byte-identical. Train() 2,572 -> 2,370 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:25:07 -04:00
string zeroSkillInfo = (zsBars <= 0) ? "" :
StringFormat(" | zero-skill on these bars: always-long %.1f%%, always-short %.1f%%,"
" coin-flip %.1f%% (the gate ranks on the LARGER of the first two; the gap"
" between them IS the directional drift, and a model that only reproduces it"
" has found the drift, not an edge) | break-even %.1f%% frictionless, %.1f%%"
" AFTER SPREAD (%.3f*ATR)",
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
100.0 * (double)m_oos.winLongTotal / zsBars,
100.0 * (double)m_oos.winShortTotal / zsBars,
50.0 * ((double)m_oos.winLongTotal + (double)m_oos.winShortTotal) / zsBars,
refactor(training): the era log is not part of the era loop Train() was 2,572 lines in one function. The largest single block in it was ~200 lines of string building for the console line, reachable only because twenty-one loose ints were declared at the top of the function and read nine hundred lines later. Those declarations were the reason the block could not move. Introduce SEraTelemetry - one parameter object holding exactly those twenty-one numbers, self-initialising to -1 ("not measured this era", which is what era 0 and any stopped era report, and is not the same as a measured zero). ReportEraProgress() takes it and renders it, guarding on its own shouldLog so the call site is one unconditional line rather than a 200-line branch. Nothing is decided or measured in the moved code - it reads state and prints. Verified by stripping comments and whitespace from both revisions and diffing the remaining statements: the only differences are the ten declarations collapsing into one object, the throttle test moving inside the callee, and the new signature plus its call. Every other statement is byte-identical. Train() 2,572 -> 2,370 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:25:07 -04:00
beFrictionless, CostAdjustedBreakEvenPct(), m_spreadAtr);
//--- THE DEPLOY BAR, stated. Reading "edge -1pp" era after era tells you the model is
//--- short; it does not tell you whether it is short by a hair or by an amount no strategy
//--- could ever cover.
string gateInfo = (m_lastEdgeFloorPct < 0.0 || m_lastEffN <= 0.0) ? "" :
StringFormat(" | DEPLOY BAR %.1f%% (chance + %.0f x SE %.1fpp on %.0f INDEPENDENT calls -"
" %d raw calls deflated by the %.1f-bar mean label lifespan)%s",
m_lastEdgeFloorPct, EDGE_MIN_SIGMAS, m_lastPrecSE, m_lastEffN,
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.DirCalls(), MeanLabelLifespan(),
refactor(training): the era log is not part of the era loop Train() was 2,572 lines in one function. The largest single block in it was ~200 lines of string building for the console line, reachable only because twenty-one loose ints were declared at the top of the function and read nine hundred lines later. Those declarations were the reason the block could not move. Introduce SEraTelemetry - one parameter object holding exactly those twenty-one numbers, self-initialising to -1 ("not measured this era", which is what era 0 and any stopped era report, and is not the same as a measured zero). ReportEraProgress() takes it and renders it, guarding on its own shouldLog so the call site is one unconditional line rather than a 200-line branch. Nothing is decided or measured in the moved code - it reads state and prints. Verified by stripping comments and whitespace from both revisions and diffing the remaining statements: the only differences are the ten declarations collapsing into one object, the throttle test moving inside the callee, and the new signature plus its call. Every other statement is byte-identical. Train() 2,572 -> 2,370 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:25:07 -04:00
//--- A bar above 100% is not "hard", it is unreachable, and no amount of
//--- training addresses it - only a bigger independent sample does.
(m_lastEdgeFloorPct >= 100.0
? " <-- UNREACHABLE: no win rate can clear this. The OOS window does not hold"
" enough independent observations to certify ANY edge; widen the sample"
" (more instruments / lower timeframe) or narrow the barrier."
: ""));
string neutralWhy = (m_oosOutCount <= 0) ? "" :
StringFormat(" | Neutral CHOSE %.1f%% / TIED %.1f%% (of which B=S %d) | rail %.1f%%",
100.0 * (double)m_oosNeutralStrict / m_oosOutCount,
100.0 * (double)m_oosNeutralTie / m_oosOutCount,
(int)m_oosTieBuySell,
100.0 * (double)m_oosRailBars / m_oosOutCount);
//--- No "(target X%)" any more - there is no absolute accuracy target. What replaces it as the
//--- progress indicator is the plateau counter: how many eras since the last new best, and how
//--- close that is to ending the run (see the PLATEAU_* ladder).
string plateauInfo = (m_bestBalancedOos < 0) ? "" :
(" | best bal " + DoubleToString(m_bestBalancedOos, 1) + "%, " + IntegerToString(m_erasSinceBestBalanced) +
" eras since (stage " + IntegerToString(m_plateauStage) + "/" + IntegerToString(PLATEAU_STAGE_DEPLOY) + ")");
//--- Lifetime IS/OOS directional accuracy. The GAP between the two is still the over-
//--- fitting read, so it survives here, once per era, behind the compile-time
//--- DebuggingMode constant.
string lifetimeInfo = (!DebuggingMode || (m_cumIsTotal <= 0 && m_cumOosTotal <= 0)) ? "" :
(" | lifetime dir acc IS " + (m_cumIsTotal > 0 ? IntegerToString((int)MathRound(m_cumIsCorrect * 100.0 / m_cumIsTotal)) + "%" : "n/a") +
" OOS " + (m_cumOosTotal > 0 ? IntegerToString((int)MathRound(m_cumOosCorrect * 100.0 / m_cumOosTotal)) + "%" : "n/a") +
" over " + IntegerToString(m_cumIsTotal + m_cumOosTotal) + " calls");
//--- Wall-clock split for the era that just finished, but only when it was SLOW - a
//--- healthy era stays exactly one line. An era finished: the stall clock restarts from
//--- here (see m_lastEraCompleteTick).
m_lastEraCompleteTick = GetTickCount();
string eraTimeInfo = "";
{
double eraS = (GetTickCount() - m_eraStartTick) / 1000.0;
if(eraS > 120.0)
//--- The excursion head gets its OWN column. "other" is now genuinely everything
//--- else.
eraTimeInfo = StringFormat(" | ERA TOOK %.0fs (feature windows %.0fs, net fwd/back %.0fs,"
" excursion head %.0fs, other %.0fs)",
eraS, m_passFeatUs / 1000000.0, m_passNetUs / 1000000.0,
m_excUs / 1000000.0,
MathMax(eraS - m_passFeatUs / 1000000.0 - m_passNetUs / 1000000.0
- m_excUs / 1000000.0, 0.0));
}
//--- THROTTLED (2026-08-19): this is the ~2KB deep-dive block, and it printed every era
//--- for every member - ~3.7MB per member per day, the single largest line in a measured
//--- 22MB/9.5h journal. VerboseMode = every era again.
if(TrainLogDue())
Print(ID + ": training in progress - era " + IntegerToString(m_eraCount) + ", OOS accuracy " + DoubleToString(dOosForecast, 1) + "%, IS error " + DoubleToString(dError, 2) + recallInfo + balancedInfo + selectionInfo + predictedInfo + calibInfo + liveInfo + tierInfo + plateauInfo + lifetimeInfo + zeroSkillInfo + gateInfo + m_lastPoolReport + rawOutInfo + neutralWhy + layerInfo + eraTimeInfo);
// Forced (unthrottled) panel refresh, right here alongside the console line above, using this
// era's own just-finalized m_eraCount/dOosForecast - see UpdateTrainingStatusLabel's
// declaration comment for why this can't just rely on the next throttled bar-scan call to
// catch up (it would, but a full era later than the console already reported it).
refactor(chart): ChartUI is a real collaborator, not a raw-include partial (S2) Expert/AIBase/ChartUI.mqh was 869 lines of method bodies of CExpertSignalAIBase, #included after the class declaration - free to touch any of its ~500 members. First of the eleven AIBase/*.mqh partials to come out (fewest inbound edges - see the SOLID campaign session order), using the same view+adapter shape already proven for CTrainingDataView. CChartView (Expert/Chart/IChartView.mqh) is the abstract read/behaviour surface a chart-rendering collaborator needs - identity, bar/model access, the prediction cache, and the training/vote/meta scalars the panel and HUD line summarise. CAIBaseChartView is the adapter the signal owns and binds to itself (MQL5 gives a class exactly one base, so CExpertSignalAIBase cannot implement the view directly). CChartUI is the real collaborator: it owns the arrow-restore queue, the rescan queue/tally, the last-arrows-saved count and the purge-mismatch latch as its own fields (verified via grep to be touched nowhere else in Expert/), and reaches everything else - including StartChartSignalRescan, moved in from its old inline home in the header since it drives the exact same rescan state machine AdvanceChartSignalRescan drains - through the view. m_arrowSignalCache and m_signalClusterWindow stay on the signal: Training.mqh writes the cache directly every era and the training-data view already reads it, so moving it would mean rewriting Training.mqh's write sites too - out of scope here. CChartUI reaches it through four bounds-checked accessors instead of a raw member poke. All 10 public methods keep their exact signatures and become one-line forwards on the signal, so no other file's call sites change except Training.mqh's one era-end status refresh, which now reads RefreshStatusLabel() rather than reaching into CChartUI's now-private last-displayed-neuron cache directly. Verified structurally, not compiled (never compile - the operator does, in MetaEditor): brace balance checked on every touched/new file against HEAD, and the view/adapter/impl method lists cross-diffed to confirm all 59 accessors match 1:1 across the interface, the adapter declaration and the adapter body. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-23 20:03:52 -04:00
RefreshStatusLabel();
refactor(training): the era log is not part of the era loop Train() was 2,572 lines in one function. The largest single block in it was ~200 lines of string building for the console line, reachable only because twenty-one loose ints were declared at the top of the function and read nine hundred lines later. Those declarations were the reason the block could not move. Introduce SEraTelemetry - one parameter object holding exactly those twenty-one numbers, self-initialising to -1 ("not measured this era", which is what era 0 and any stopped era report, and is not the same as a measured zero). ReportEraProgress() takes it and renders it, guarding on its own shouldLog so the call site is one unconditional line rather than a 200-line branch. Nothing is decided or measured in the moved code - it reads state and prints. Verified by stripping comments and whitespace from both revisions and diffing the remaining statements: the only differences are the ten declarations collapsing into one object, the throttle test moving inside the callee, and the new signature plus its call. Every other statement is byte-identical. Train() 2,572 -> 2,370 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:25:07 -04:00
}
//+------------------------------------------------------------------+
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
//| PASS 1: the scan/queue sweep that walks the era backwards from |
//| era.i, building the sample queue and training on it. |
//| |
//| era.i is a MEMBER of the era state rather than a loop local |
//| because this loop yields on the wall-clock budget and resumes at |
//| the same bar on the next call. |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::RunPass1(STrainEra &era)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
for(; era.i >= 0 && !era.stop; era.i--)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
//--- Build THIS bar's own feature window and feed it forward BEFORE checking/training against
//--- its label - see r's declaration comment below for why the window must end AT bar i, and
//--- why this must run before the label-check block rather than after: the label check needs
//--- this bar's own freshly-computed prediction, not the previous iteration's (see windowOk).
TempData.Clear();
//--- Window ends AT (includes) bar i itself, extending m_historyBars bars into the past -
//--- i.e.
int r = era.i;
bool windowOk = false;
double displayNeuron0 = 0, displayNeuron1 = 0, displayNeuron2 = 0;
if(r <= era.bars)
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
{
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
ulong hbT = GetMicrosecondCount();
windowOk = BuildFeatureWindow(r);
m_passFeatUs += GetMicrosecondCount() - hbT;
if(windowOk)
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
{
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
era.addLoop = true;
m_passWindowOk++;
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
}
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
else
m_passWindowFail++;
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
}
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
TrainHeartbeat("pass 1 (scan/queue), bar", era.bars - MathMax(m_historyBars, 0) - era.i, era.totalIter, "scan");
//--- Determine label/queue-eligibility BEFORE running any feedForward this bar - see
//--- wouldQueue's use below for why. Mirrors the label-check condition this block used to
//--- gate on (moved earlier, unchanged).
bool haveLabel = false, buy = false, sell = false, wouldQueue = false;
//--- "some LATER pass in this same era will feed this exact bar forward anyway", which is a
//--- strictly wider set than wouldQueue - see its use at the feedForward below. Declared out
//--- here because the three membership tests that decide it are scoped to the label block.
bool laterPassForwards = false;
if(windowOk && era.i < (int)(era.bars - MathMax(m_historyBars, 0) - 1) && era.i > 1 && m_Time.GetData(era.i) > dtStudied
&& (m_outputNeuronsCount == 1 || m_outputNeuronsCount == 3 || IsMetaTarget()))
fix(resume): model reload stalled training - three hardenings on the resume path A resumed META model hot-looped pass 1 (0->100% scan oscillation, silent for 3 minutes until the stall reporter fired) because EVERY window failed at the first AD/Wyckoff feature: the init-time param adoption called ReInitADIndicators unconditionally, destroying five freshly-calculating indicator instances to recreate them with BYTE-IDENTICAL params (verified by parsing the .nnw header - the MI tuner had kept the configured settings), at process start, on a box with 1 GB free of 31. The replacements sat cold for 6+ minutes while full-history resweeps starved the indicator threads harder. - AdoptIndicatorParams: installs a loaded param set into the tuner and rebuilds handles ONLY when the set actually differs from what the live indicators run. Both call sites (resume init + panel reload) use it. - Resumed models get the same 3 warm-up passes as fresh ones. The skip was the shared root cause of the cold-ATR (ba13eef), cold-AD (2026-08-11) and this incident - custom indicators recompute from scratch every process start regardless of what the .nnw proves. - Cold-sweep backoff: a pass-1 sweep in which every window failed on a TRANSIENT cause arms a 5s era-start pause instead of an immediate full-history resweep, so the retry loop stops consuming the CPU/memory the warming indicators need. The stall reporter names the backoff branch. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 10:23:11 -04:00
{
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
//--- The fractal/swing-confirmation/trend-context label at now-relative index i only
//--- depends on price/ATR history, never on model state, so it's identical every era
//--- until a new bar closes and shifts the index frame (see the cache invalidation
//--- check above) - cache it rather than recomputing from scratch every single era.
if(m_labelCacheHasValue[era.i])
{
buy = m_labelCacheBuy[era.i];
sell = m_labelCacheSell[era.i];
}
else
{
ComputeLabelForBar(era.i, era.bars, buy, sell);
m_labelCacheBuy[era.i] = buy;
m_labelCacheSell[era.i] = sell;
//--- Kept in step with the label caches by hand here, because this fallback does not
//--- go through AdvanceBarrierLabelState.
if(era.i < ArraySize(m_winLongCache))
{
m_winLongCache[era.i] = false;
m_winShortCache[era.i] = false;
}
m_labelCacheHasValue[era.i] = true;
}
haveLabel = true;
bool isOOS = (era.i < era.oosCutoff);
//--- Embargo: a bar's triple-barrier label is decided by the m_barrierHorizonBars bars
//--- that follow it (see TripleBarrierLabel()). Lopez de Prado ch.
int calibLo = CalibLoIndex(era.oosCutoff); // = oosCutoff + one purge width
int calibHi = CalibHiIndex(era.totalIter, era.oosCutoff); // == calibLo when the band is empty
bool isEmbargoed = (!isOOS && era.i < calibLo);
//--- The calibration slice and its far-side purge are held out of backprop for the same
//--- reason the OOS window is, and the layout is documented once at CalibLoIndex().
bool isCalib = (era.i >= calibLo && era.i < calibHi);
bool isCalibPurge = (calibHi > calibLo && era.i >= calibHi && era.i < calibHi + CalibPurgeBars());
wouldQueue = (!isOOS && !isEmbargoed && !isCalib && !isCalibPurge);
//--- Meta target: only bars HOSTING a candidate carry training rows, and passes 2/2.5/3
//--- forward those per-candidate themselves (the descriptor differs per candidate, so a
//--- bar-level scan forward could not be reused anyway).
wouldQueue = wouldQueue && (!IsMetaTarget() || MetaCandFirst(era.i) >= 0);
//--- Pass 2 re-forwards every queued bar, pass 2.5 re-forwards the whole calibration
//--- band, and pass 3 re-forwards the whole OOS window - each over EXACTLY this bar set
//--- (all three derive their bounds from the same helpers and apply the identical
//--- eligibility test this block gates on).
laterPassForwards = (wouldQueue || isOOS || isCalib);
fix(resume): model reload stalled training - three hardenings on the resume path A resumed META model hot-looped pass 1 (0->100% scan oscillation, silent for 3 minutes until the stall reporter fired) because EVERY window failed at the first AD/Wyckoff feature: the init-time param adoption called ReInitADIndicators unconditionally, destroying five freshly-calculating indicator instances to recreate them with BYTE-IDENTICAL params (verified by parsing the .nnw header - the MI tuner had kept the configured settings), at process start, on a box with 1 GB free of 31. The replacements sat cold for 6+ minutes while full-history resweeps starved the indicator threads harder. - AdoptIndicatorParams: installs a loaded param set into the tuner and rebuilds handles ONLY when the set actually differs from what the live indicators run. Both call sites (resume init + panel reload) use it. - Resumed models get the same 3 warm-up passes as fresh ones. The skip was the shared root cause of the cold-ATR (ba13eef), cold-AD (2026-08-11) and this incident - custom indicators recompute from scratch every process start regardless of what the .nnw proves. - Cold-sweep backoff: a pass-1 sweep in which every window failed on a TRANSIENT cause arms a 5s era-start pause instead of an immediate full-history resweep, so the retry loop stops consuming the CPU/memory the warming indicators need. The stall reporter names the backoff branch. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 10:23:11 -04:00
}
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
//--- Only run this bar's feedForward (and the display/count/chart-draw work that depends
//--- on it) when NO later pass is about to redo it anyway.
ulong hbFwd = GetMicrosecondCount();
//--- !IsMetaTarget(): the scan-time forward exists only for the direction display/tally on
//--- bars no later pass revisits; a meta forward without a candidate descriptor would be
//--- width-mismatched against the meta input layer as well as meaningless.
bool scanForwardOk = (windowOk && !laterPassForwards && !IsMetaTarget() && Net.feedForward(TempData));
m_passNetUs += GetMicrosecondCount() - hbFwd;
if(scanForwardOk)
feat(depth): prime -> settle -> sweep, and name which handle is short "Max bars in chart" is set to Unlimited, so the static-terminal-limit reading in 1dda479 was wrong. Two other candidate causes are falsified too: the price series is fully downloaded and flat (USDJPY 50,162 -> 50,163 over 80 minutes, i.e. one new H4 bar), and the handles have been stable since 13:07 with zero windows for the 17 minutes after, so it is not download-in-progress and not handle churn. The MA period tops out at 200 (ADIndicatorTuner MA_PERIOD_PRESETS) against ~50k bars, so it is not indicator cost either. What IS verified stays verified: CopyBuffer past the calculated depth fails outright rather than short-reading, so the buffer holds nothing and every index reads EMPTY_VALUE; m_MA is the only CiCustom whose block REJECTS on that (m_ADZigZag neutral-fills, RSI/MACD/Ichimoku/ATR are built-ins); the wall is therefore feature 25 of every bar, exactly as the "24 of 832" stall lines said. And it is depth-correlated: 16k-bar charts train, 34k/50k get zero windows forever. So the WHY is still open, and this fix does not depend on it. Per the user's protocol: the request itself is the primer, so prime at full depth, then poll TunableBarsCalculated() every 3s and hold the sweep until it stops changing (3 steady probes), then use whatever it settled at. Bounded at 10 min, and a give-up is logged as a give-up so an abandoned depth is never mistaken for a settled one. This supersedes 1dda479's clamp on the two training paths, which snapshotted a value that may still have been climbing; the clamp remains for the paths that cannot wait (inference/online/rescan/export, see 7e63a8b). The load-bearing part is what does NOT happen while waiting: no sweep. A 50k-bar feature scan starves the indicator threads the request just woke, which is how the failure sustained itself for 40 minutes at a time - discard era, re-sweep, discard, which is the 0->100% oscillation on the panel. Also adds IndicatorDepthReport(): per-handle BarsCalculated() on the priming, cap and stall lines. The logs proved WHICH FEATURE died but never WHICH HANDLE was short, so the cause had to be inferred - and was guessed wrong twice. The next occurrence reads it off. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-17 13:44:27 -04:00
{
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
Net.getResults(TempData);
if(m_outputNeuronsCount == 1)
dPrevSignal = TempData[0];
else
if(m_outputNeuronsCount == 3)
dPrevSignal = ApplyClassificationSoftmax();
//--- Snapshot the just-computed neuron output(s) for the status label display below, before
//--- the label-check block clears/refills TempData with the target label (Step A always
//--- runs after this point now) - reading TempData directly for display after that would
//--- show the TRUE LABEL of the bar just trained on, not the network's own prediction.
if(TempData.Total() > 0)
displayNeuron0 = TempData[0];
if(TempData.Total() > 1)
displayNeuron1 = TempData[1];
if(TempData.Total() > 2)
displayNeuron2 = TempData[2];
switch(DoubleToSignal(dPrevSignal))
{
case Buy:
m_countBuySignals++;
break;
case Sell:
m_countSellSignals++;
break;
default:
m_countNeutralSignals++;
break;
}
m_lastBarTime = m_Time.GetData(era.i);
if(era.i > 0)
{
// NMS on: record only - the era-end sweep is the SOLE renderer, so no raw (un-
// declustered) arrow is ever drawn mid-era. NMS off: draw inline as before.
if(m_signalClusterWindow > 0)
{
if(era.i < ArraySize(m_arrowSignalCache))
m_arrowSignalCache[era.i] = dPrevSignal;
}
else
if(DoubleToSignal(dPrevSignal) == Neutral)
DeleteObject(m_lastBarTime);
else
DrawObject(m_lastBarTime, dPrevSignal, m_Close.GetData(era.i));
}
UpdateTrainingStatusLabel(
StringFormat("Bar %d of %d -> %.2f%% (scan)", era.bars - era.i + 1, era.bars, (double)(era.bars - era.i + 1.0) / era.bars * 100),
displayNeuron0, displayNeuron1, displayNeuron2, dPrevSignal);
feat(depth): prime -> settle -> sweep, and name which handle is short "Max bars in chart" is set to Unlimited, so the static-terminal-limit reading in 1dda479 was wrong. Two other candidate causes are falsified too: the price series is fully downloaded and flat (USDJPY 50,162 -> 50,163 over 80 minutes, i.e. one new H4 bar), and the handles have been stable since 13:07 with zero windows for the 17 minutes after, so it is not download-in-progress and not handle churn. The MA period tops out at 200 (ADIndicatorTuner MA_PERIOD_PRESETS) against ~50k bars, so it is not indicator cost either. What IS verified stays verified: CopyBuffer past the calculated depth fails outright rather than short-reading, so the buffer holds nothing and every index reads EMPTY_VALUE; m_MA is the only CiCustom whose block REJECTS on that (m_ADZigZag neutral-fills, RSI/MACD/Ichimoku/ATR are built-ins); the wall is therefore feature 25 of every bar, exactly as the "24 of 832" stall lines said. And it is depth-correlated: 16k-bar charts train, 34k/50k get zero windows forever. So the WHY is still open, and this fix does not depend on it. Per the user's protocol: the request itself is the primer, so prime at full depth, then poll TunableBarsCalculated() every 3s and hold the sweep until it stops changing (3 steady probes), then use whatever it settled at. Bounded at 10 min, and a give-up is logged as a give-up so an abandoned depth is never mistaken for a settled one. This supersedes 1dda479's clamp on the two training paths, which snapshotted a value that may still have been climbing; the clamp remains for the paths that cannot wait (inference/online/rescan/export, see 7e63a8b). The load-bearing part is what does NOT happen while waiting: no sweep. A 50k-bar feature scan starves the indicator threads the request just woke, which is how the failure sustained itself for 40 minutes at a time - discard era, re-sweep, discard, which is the 0->100% oscillation on the panel. Also adds IndicatorDepthReport(): per-handle BarsCalculated() on the priming, cap and stall lines. The logs proved WHICH FEATURE died but never WHICH HANDLE was short, so the cause had to be inferred - and was guessed wrong twice. The next occurrence reads it off. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-17 13:44:27 -04:00
}
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
else
//--- Bars a later pass will re-forward skip the feedForward above, and they are now
//--- very nearly ALL of pass 1 - the queued IS bars (~58%, processed FIRST because the
//--- loop walks oldest-to-newest), plus the calibration band and the OOS slice.
UpdateTrainingStatusLabel(
StringFormat("Bar %d of %d -> %.2f%% (scan)", era.bars - era.i + 1, era.bars, (double)(era.bars - era.i + 1.0) / era.bars * 100),
displayNeuron0, displayNeuron1, displayNeuron2, dPrevSignal);
//--- META TARGET: one training row per candidate journaled at this bar (bars without a
//--- candidate carry no rows - wouldQueue already required one). See the pass 3 meta
//--- branch.
if(haveLabel && IsMetaTarget())
feat(depth): prime -> settle -> sweep, and name which handle is short "Max bars in chart" is set to Unlimited, so the static-terminal-limit reading in 1dda479 was wrong. Two other candidate causes are falsified too: the price series is fully downloaded and flat (USDJPY 50,162 -> 50,163 over 80 minutes, i.e. one new H4 bar), and the handles have been stable since 13:07 with zero windows for the 17 minutes after, so it is not download-in-progress and not handle churn. The MA period tops out at 200 (ADIndicatorTuner MA_PERIOD_PRESETS) against ~50k bars, so it is not indicator cost either. What IS verified stays verified: CopyBuffer past the calculated depth fails outright rather than short-reading, so the buffer holds nothing and every index reads EMPTY_VALUE; m_MA is the only CiCustom whose block REJECTS on that (m_ADZigZag neutral-fills, RSI/MACD/Ichimoku/ATR are built-ins); the wall is therefore feature 25 of every bar, exactly as the "24 of 832" stall lines said. And it is depth-correlated: 16k-bar charts train, 34k/50k get zero windows forever. So the WHY is still open, and this fix does not depend on it. Per the user's protocol: the request itself is the primer, so prime at full depth, then poll TunableBarsCalculated() every 3s and hold the sweep until it stops changing (3 steady probes), then use whatever it settled at. Bounded at 10 min, and a give-up is logged as a give-up so an abandoned depth is never mistaken for a settled one. This supersedes 1dda479's clamp on the two training paths, which snapshotted a value that may still have been climbing; the clamp remains for the paths that cannot wait (inference/online/rescan/export, see 7e63a8b). The load-bearing part is what does NOT happen while waiting: no sweep. A 50k-bar feature scan starves the indicator threads the request just woke, which is how the failure sustained itself for 40 minutes at a time - discard era, re-sweep, discard, which is the 0->100% oscillation on the panel. Also adds IndicatorDepthReport(): per-handle BarsCalculated() on the priming, cap and stall lines. The logs proved WHICH FEATURE died but never WHICH HANDLE was short, so the cause had to be inferred - and was guessed wrong twice. The next occurrence reads it off. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-17 13:44:27 -04:00
{
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
for(int cd = MetaCandFirst(era.i); cd >= 0; cd = MetaCandNext(cd))
{
if(MetaCandidateWon(cd, era.i))
m_trueBuyCount++;
else
m_trueSellCount++;
if(!wouldQueue)
continue;
if(m_isTrainQueueCount + 1 > ArraySize(m_isTrainQueue))
{
int newQueueSize = m_isTrainQueueCount + 1;
ArrayResize(m_isTrainQueue, newQueueSize, 16384);
ArrayResize(m_isTrainQueueCand, newQueueSize, 16384);
}
m_isTrainQueue[m_isTrainQueueCount] = era.i;
m_isTrainQueueCand[m_isTrainQueueCount] = cd;
m_isTrainQueueCount++;
}
feat(depth): prime -> settle -> sweep, and name which handle is short "Max bars in chart" is set to Unlimited, so the static-terminal-limit reading in 1dda479 was wrong. Two other candidate causes are falsified too: the price series is fully downloaded and flat (USDJPY 50,162 -> 50,163 over 80 minutes, i.e. one new H4 bar), and the handles have been stable since 13:07 with zero windows for the 17 minutes after, so it is not download-in-progress and not handle churn. The MA period tops out at 200 (ADIndicatorTuner MA_PERIOD_PRESETS) against ~50k bars, so it is not indicator cost either. What IS verified stays verified: CopyBuffer past the calculated depth fails outright rather than short-reading, so the buffer holds nothing and every index reads EMPTY_VALUE; m_MA is the only CiCustom whose block REJECTS on that (m_ADZigZag neutral-fills, RSI/MACD/Ichimoku/ATR are built-ins); the wall is therefore feature 25 of every bar, exactly as the "24 of 832" stall lines said. And it is depth-correlated: 16k-bar charts train, 34k/50k get zero windows forever. So the WHY is still open, and this fix does not depend on it. Per the user's protocol: the request itself is the primer, so prime at full depth, then poll TunableBarsCalculated() every 3s and hold the sweep until it stops changing (3 steady probes), then use whatever it settled at. Bounded at 10 min, and a give-up is logged as a give-up so an abandoned depth is never mistaken for a settled one. This supersedes 1dda479's clamp on the two training paths, which snapshotted a value that may still have been climbing; the clamp remains for the paths that cannot wait (inference/online/rescan/export, see 7e63a8b). The load-bearing part is what does NOT happen while waiting: no sweep. A 50k-bar feature scan starves the indicator threads the request just woke, which is how the failure sustained itself for 40 minutes at a time - discard era, re-sweep, discard, which is the 0->100% oscillation on the panel. Also adds IndicatorDepthReport(): per-handle BarsCalculated() on the priming, cap and stall lines. The logs proved WHICH FEATURE died but never WHICH HANDLE was short, so the cause had to be inferred - and was guessed wrong twice. The next occurrence reads it off. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-17 13:44:27 -04:00
}
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
else
if(haveLabel)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
// True label as an ENUM_SIGNAL, derived directly from the buy/sell bools - not read
// back from TempData, which no longer holds a target at this point at all (see above).
ENUM_SIGNAL trueSignal = buy ? Buy : (sell ? Sell : Neutral);
// Track the true class distribution this era (used below to weight IS oversampling,
// and surfaced in the status label text alongside the predicted-class counts)
switch(trueSignal)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
case Buy:
m_trueBuyCount++;
break;
case Sell:
m_trueSellCount++;
break;
default:
m_trueNeutralCount++;
break;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
// OOS scoring used to happen right here, against whatever weights this bar's earlier
// feedForward (this pass) happened to be using - which for era 0 is the network's
// still-untrained cold-start state (100% Neutral - see the output-layer bias seed's
// declaration comment), and for every later era is last era's END-of-training state,
// never THIS era's. That silently gave every era's OOS score a full one-era lag behind
// its own training, and made era 0's OOS score meaningless by construction. OOS scoring
// now happens in its own pass (see m_isPass3Active's declaration comment), AFTER pass 2
// has actually trained on this era's IS data, against a fresh feedForward on each OOS
// bar rather than this scan's now-stale one.
if(wouldQueue)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
//--- Queue this bar for pass 2's shuffled backProp instead of training on it here,
//--- immediately, in strict chronological order - see m_isTrainQueue's declaration
//--- comment for the full rationale.
//--- MINORITY REPLAY IS GONE (2026-07-31): every bar is queued exactly ONCE and the
//--- class imbalance is corrected analytically in the gradient by the logit-adjusted
//--- loss (Menon et al. 2021).
if(m_isTrainQueueCount + 1 > ArraySize(m_isTrainQueue))
fix: the deploy gate was benchmarking a win rate against a label frequency The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test. That invariant needs reward >= risk, and the measured geometry no longer satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but both-won bars were stripped out of Buy and Sell so the label base rate read 37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma against 37.5% and loses money on every single trade. Live since 217b9bc. Root cause is that label agreement stopped being the same question as trade profitability. Buy implies winLong, but the converse fails on every both-won bar, and the label can only name one of two directions that both pay. So stop asking the model whether it matched a label and start asking whether its trade paid: - cache winLong/winShort per bar beside the label, under the same validity flag; published from the barrier walk before the collapse to 3 classes - dirPrecPct now counts wins on the side actually called - chancePrecPct is max(P(winLong), P(winShort)), MEASURED - the textbook m/(m+k) would credit SP500's drift to the model - the NMS "what would I have made" pair, the live-fired precision, and the IS/OOS cumulative win rates all move to the same test. IS and OOS are read side by side as the overfitting signal, so measuring one in wins and the other in agreement would put a fixed gap between them that has nothing to do with generalization - the confidence threshold is FITTED on wins too, so the operating point maximises what the gate grades - per-class label-agreement precision is still computed and logged; it is the right diagnostic for class separation, just not for a deploy decision - era line renamed dir-precision -> win-rate, chance -> chance=break-even Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 16:00:51 -04:00
{
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
int newQueueSize = m_isTrainQueueCount + 1;
ArrayResize(m_isTrainQueue, newQueueSize, 16384);
ArrayResize(m_isTrainQueueCand, newQueueSize, 16384);
fix: the deploy gate was benchmarking a win rate against a label frequency The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test. That invariant needs reward >= risk, and the measured geometry no longer satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but both-won bars were stripped out of Buy and Sell so the label base rate read 37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma against 37.5% and loses money on every single trade. Live since 217b9bc. Root cause is that label agreement stopped being the same question as trade profitability. Buy implies winLong, but the converse fails on every both-won bar, and the label can only name one of two directions that both pay. So stop asking the model whether it matched a label and start asking whether its trade paid: - cache winLong/winShort per bar beside the label, under the same validity flag; published from the barrier walk before the collapse to 3 classes - dirPrecPct now counts wins on the side actually called - chancePrecPct is max(P(winLong), P(winShort)), MEASURED - the textbook m/(m+k) would credit SP500's drift to the model - the NMS "what would I have made" pair, the live-fired precision, and the IS/OOS cumulative win rates all move to the same test. IS and OOS are read side by side as the overfitting signal, so measuring one in wins and the other in agreement would put a fixed gap between them that has nothing to do with generalization - the confidence threshold is FITTED on wins too, so the operating point maximises what the gate grades - per-class label-agreement precision is still computed and logged; it is the right diagnostic for class separation, just not for a deploy decision - era line renamed dir-precision -> win-rate, chance -> chance=break-even Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 16:00:51 -04:00
}
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
m_isTrainQueue[m_isTrainQueueCount] = era.i;
m_isTrainQueueCand[m_isTrainQueueCount] = -1;
m_isTrainQueueCount++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
}
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
era.stop = IsStopped() || m_trainingStopRequested;
fix(training): the wall-clock budget was left behind in Train() Compile error, four sites: TRAIN_TIME_BUDGET_MS was a const local to Train(), and the four passes that yield on it are now defined above Train(). I checked every pass for the eight locals STrainEra replaced and missed the ninth, because it was a const rather than a variable. It is per-call state like everything else in STrainEra, so it moves there as budgetMs. All four sites asked the same question the same way GetTickCount() - era.chunkStartTick >= TRAIN_TIME_BUDGET_MS so the struct answers it once as BudgetSpent(). Swept for the same class of mistake rather than waiting for another compile: Train() now has exactly two top-level locals left (STABILITY_WINDOW, STABILITY_TOLERANCE) and neither appears in any extracted body. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:40:15 -04:00
if(!era.stop && era.i > 0 && era.BudgetSpent())
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
//--- yield: save exactly enough to resume this same era, mid-bar-loop, on the next call -
//--- see m_trainRunActive's declaration comment for why this must happen instead of
//--- letting one era (or the whole run) process synchronously to completion
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
StashEraResume(era.bars, era.totalIter, era.oosCutoff, era.addLoop, era.i - 1);
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
return;
}
}
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
}
//+------------------------------------------------------------------+
//| PASS 2: the second sweep over the in-sample span. |
//| |
//| Ordering matters here in a way it does not in pass 1 - see |
//| dOosForecast's declaration comment for why the recursion makes |
//| this pass's direction load-bearing. |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::RunPass2(STrainEra &era)
{
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
if(!era.stop && era.addLoop && !m_isPass2Done)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
if(!m_isPass2Active)
{
m_isPass2Active = true;
m_isTrainCursor = 0;
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- MINI-BATCH ON, for pass 2 only (2026-08-09 audit, F4). Switched back off where pass 2
//--- completes.
feat: mini-batch gradient accumulation (F4), front-end-aware capacity budget (F6), split Wyckoff categoricals (N1) Completes the 2026-08-09 training audit. FORCES A RETRAIN of every Wyckoff-enabled config (N1 re-keys the fingerprint), and BOTH DLLs must be redeployed alongside the .ex5 - they carry new exports. F4 - mini-batch accumulation, TRAIN_BATCH_SIZE=32. Training was pure online SGD (one weight update per bar), which is the mechanical source of the era-to-era whipsaw every downstream guard was built to cope with. The O(n^2) outer product is native - AccumulateWeightGrad / AccumulateWeightGradConv / AccumulateBufferInto in Network.cl, WarriorCPU and WarriorDML - while the optimizer step is host-side MQL5 shared by all tiers (ApplyAccumToBlock), so there is one Adam/SGD implementation instead of four that can drift. - the LSTM needs no outer-product kernel (WeightsGradient already holds the sample's full dW) but could NOT simply be left un-zeroed between samples: CPU_LSTMSeqBackward/DML_LSTMSeqBackward memset it on entry. Hence a separate accumulator plus an elementwise add. - batch-norm gamma/beta accumulate in host arrays, not new BatchOptions slots - BN_OPT_STRIDE is baked into every persisted .nnw. - scoped to pass 2; online learning keeps immediate updates. Every save / checkpoint / scoring boundary flushes, scaling by the real sample count. - degrades to per-sample updates (one log line) on a tier that cannot accumulate, so old devices and DLL-free builds are unaffected. - verified offline: DirectML/batch_accum_check.cpp drives the real exports against an independent reference; at B=1 the accumulator matches the shipped unbatched kernel's own gradient to 1.1e-16. Math only - the in-situ check remains the per-layer dW/W report on a real era. F6 - ComputeFirstLayerWidth budgeted against the RAW input width even where a conv/LSTM front end had already reduced it, so an LSTM's dense stack was charged for 1,280 inputs when it receives 64. Confirmed from the deployed .cfg files: CONV, LSTM and HYBRID were all pinned at the 16-unit floor. Now budgeted against the front-end output and capped at it (never fan out), with the derivation reordered so both stages settle first. N1 - EventCode/EventPhase/StructuralPhase are signed categoricals packing direction and Wyckoff stage into one scalar across a sign discontinuity. Split into direction + [0,1] magnitude, the same convention the base OHLC block uses. Information-preserving; 13 readings now occupy 16 inputs. Compiled clean (0 errors, 0 warnings); both DLLs rebuilt. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 11:48:03 -04:00
Net.SetBatchSize(TRAIN_BATCH_SIZE);
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- 2026-07-28: a "replay-only optimizer override" was removed from here. It arrived with
//--- the DFA change set and was never part of any validated run. The optimizer the user
//--- selects is now the optimizer that runs.
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
for(int sIdx = m_isTrainQueueCount - 1; sIdx > 0; sIdx--)
{
fix: training-stability audit fixes F1/F2/F3/F5 - unbiased shuffle, real plateau escapes, fresh optimizer state on restore, pure OOS metric Four of the six findings from research/training_pipeline_audit_2026-08-09.md (F4 mini-batching and F6 feature re-encode deliberately deferred - see the report's implementation-status section for why): - F1: pass-2 Fisher-Yates (and AutoTune's MI block shuffle) used MathRand()%, which is 15-bit - provably non-uniform on every full-history era over 32,768 queued samples. New 30-bit ShuffleRandomIndex(). - F2: plateau warm restarts were a no-op whenever eta already sat at its ceiling (the normal state of a non-regressing plateau) - the ladder was just a 24-era countdown. Restarts now overshoot to 5x the ceiling (PLATEAU_RESTART_BOOST) and anneal geometrically back over the patience window, SGDR-style; ETA_MIN widened 1e-4 -> 1e-5 so the decay schedule has real range. - F3: checkpoint restores put weights back but kept the rejected trajectory's Adam moments, so the optimizer immediately pushed back toward the rolled-back state (the restore->regress->restore oscillation). CNet::ResetOptimizerState() zeroes moments/momentum/step counters (weights, BN statistics, gamma/beta untouched) on every mid-run restore, every boosted restart, and the deploy-time restore that online learning continues from. - F5: batch-norm running statistics now freeze for the pass-3 OOS scoring walk, so the selection metric the checkpoint ranking and deploy gate read is a pure function of the checkpoint instead of partly measuring BN drift. Defensive unfreeze in FinalizeTrainRun covers stop-mid-pass; live/online adaptation and the OOS continual-learning simulation stay adaptive by design. Compiled clean (0 errors, 0 warnings) via the staged-tree recipe. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 10:54:09 -04:00
//--- ShuffleRandomIndex, NOT MathRand()%: the queue routinely exceeds MathRand()'s 15-bit
//--- range on a full-history window, which silently biased this shuffle - see the helper.
int sJ = ShuffleRandomIndex(sIdx + 1);
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
int sTmp = m_isTrainQueue[sIdx];
m_isTrainQueue[sIdx] = m_isTrainQueue[sJ];
m_isTrainQueue[sJ] = sTmp;
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
//--- the candidate id is the meta label's identity - it must stay attached to its slot
int sCandTmp = m_isTrainQueueCand[sIdx];
m_isTrainQueueCand[sIdx] = m_isTrainQueueCand[sJ];
m_isTrainQueueCand[sJ] = sCandTmp;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
}
for(; m_isTrainCursor < m_isTrainQueueCount; m_isTrainCursor++)
{
int qi = m_isTrainQueue[m_isTrainCursor];
fix: the panel showed "100%" for the whole of pass 1 The simple panel derived its percentage from pass 2's counters: (m_isTrainCursor+1) / max(m_isTrainQueueCount,1). During pass 1 those are 0 and 0, so the expression is (0+1)/max(0,1) = 100%. An era spends its first pass scanning ~38k bars - minutes of work - and the panel reported that phase as finished the entire time. Observed by the user as "started learning at 100% of their era and are stuck there", and it actively misled the diagnosis: the one number on screen said the opposite of what was happening. The UI cannot fix this on its own - it can see pass 2's counters but has no way to know which pass owns them. So each pass now PUBLISHES its own progress and a short phase name through TrainHeartbeat (which every pass already calls per item), and the panel just displays them: "learning (era 45, scan 34%)". Published before the heartbeat's 4096-item journal gate, so the panel updates continuously while the journal stays quiet. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 07:22:29 -04:00
TrainHeartbeat("pass 2 (shuffled backprop), sample", m_isTrainCursor + 1, m_isTrainQueueCount, "training");
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
ulong hbT = GetMicrosecondCount();
fix: the sequence models were reading the window backwards BuildFeatureWindow() replaces eight hand-rolled copies of the same loop and feeds the window OLDEST BAR FIRST. Every copy fed it newest-first, because MQL5 timeseries indices run backwards and `r + b` with b ascending walks into the past. Harmless for PAI and CONV - a dense layer learns a weight per position either way, a conv learns time-mirrored kernels. Not harmless for the recurrent stacks: - LSTM_SeqStepForward reads `inputs + t*Iw`, so step t is block t. - It writes output[] only when t == steps-1: the visible output IS the last hidden state. - c_t = f*c_{t-1} + i*g decays toward the start of the sequence. lstm_seq_flowcheck.cpp measured block 0's influence on the output at 1.2e-2 of block T-1's, at the shipped forget bias of 1.0. So the bar being PREDICTED sat at the far end of the decay and the output was handed to the OLDEST bar in the window - the exact inverse of what the window is for. ~80x backwards on LSTM and HYBRID, on all three tiers (OpenCL kernel, CPU DLL, pure-MQL5 inference), which is why it never surfaced as a backend discrepancy. This does not create edge - the MI diagnostics read at the noise floor (p=0.4975) with a working positive control. It makes the one hypothesis those diagnostics explicitly do NOT cover testable: they are marginal and per-bar, and state they "cannot rule out one that only exists in combination or across time". The sequence model is the instrument for across-time structure and it has been crippled, so that hypothesis has never been honestly tested. Fingerprint gets an unconditional |WIN:2 - the vector keeps its shape and its features, so a stale .nnw would load cleanly and run a model fitted to one ordering against the other, silently. Re-keying every config is the point, not collateral damage. FORCES A FULL RETRAIN. Also: the now-relative bar caches are re-keyed on the two live paths. EnsureBarCachesCapacity() was only ever called from training paths, but once m_trainingComplete is set ScheduleTrainingIfNeeded() routes every bar to RefreshConvergedSignal() and Train() is never re-entered - so nothing cleared the feature cache again for the life of the process. A chart that trained to convergence kept replaying the rows computed for the last training era's bar grid: the live signal froze at its convergence-time value, and OnlineLearnStep() backpropped those stale features against freshly resolved labels. Backtests were never affected (an inference-only process never allocates the arrays, so every read recomputes). Compiles clean: 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-07 18:28:44 -04:00
bool qWindowOk = BuildFeatureWindow(qi);
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
//--- Meta target: the input is window + per-candidate setup descriptor; the net's input layer
//--- is sized for both (NetInputWidth), so the append must happen before EVERY forward.
if(qWindowOk && IsMetaTarget())
AppendCandidateFeatures(m_isTrainQueueCand[m_isTrainCursor]);
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
m_passFeatUs += GetMicrosecondCount() - hbT;
fix: improve error messages and suppress false sharing-violation logs - BufferDouble: replace hardcoded "DirectML/CPU-DLL" with dynamic backend name and add buffer index/element count to all error prints for easier debugging. - NetPersistence: distinguish missing file from transient lock by probing FileIsExist before logging, eliminating false "sharing violation" warnings when no saved model exists on first run.
2026-08-02 01:09:18 -04:00
//--- A failed forward pass must NOT be followed by backProp() further down this block: the
//--- output layer would still hold the PREVIOUS sample's activations, so the update would be
//--- this bar's label against another bar's prediction - training on pure noise while every
//--- accuracy counter kept reporting normally.
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
hbT = GetMicrosecondCount();
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
bool qForwardOk = (qWindowOk && TempData.Total() >= NetInputWidth() &&
fix: improve error messages and suppress false sharing-violation logs - BufferDouble: replace hardcoded "DirectML/CPU-DLL" with dynamic backend name and add buffer index/element count to all error prints for easier debugging. - NetPersistence: distinguish missing file from transient lock by probing FileIsExist before logging, eliminating false "sharing violation" warnings when no saved model exists on first run.
2026-08-02 01:09:18 -04:00
Net.feedForward(TempData));
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
m_passNetUs += GetMicrosecondCount() - hbT;
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
if(qWindowOk && !qForwardOk && !era.forwardFailureReported)
fix: improve error messages and suppress false sharing-violation logs - BufferDouble: replace hardcoded "DirectML/CPU-DLL" with dynamic backend name and add buffer index/element count to all error prints for easier debugging. - NetPersistence: distinguish missing file from transient lock by probing FileIsExist before logging, eliminating false "sharing violation" warnings when no saved model exists on first run.
2026-08-02 01:09:18 -04:00
{
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
era.forwardFailureReported = true;
fix: improve error messages and suppress false sharing-violation logs - BufferDouble: replace hardcoded "DirectML/CPU-DLL" with dynamic backend name and add buffer index/element count to all error prints for easier debugging. - NetPersistence: distinguish missing file from transient lock by probing FileIsExist before logging, eliminating false "sharing violation" warnings when no saved model exists on first run.
2026-08-02 01:09:18 -04:00
Print(__FUNCTION__ + ": CNet::feedForward FAILED at era " + IntegerToString((int)m_eraCount) +
" - this era's remaining samples are being skipped, not trained. A layer is refusing to"
" accept its own output (check the preceding BufferWrite/BufferRead lines for which"
" buffer, and see NormalizeHost in AI\\NeuronBatchNorm.mqh for the batch-norm case).");
}
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
//--- META TARGET pass 2: binary win/loss backprop per candidate. No excursion step (that head
//--- belongs to the direction models), no arrows, no 3-class softmax - just the running IS
//--- stats under the win->Buy / loss->Sell mapping documented at pass 1's meta branch.
if(qForwardOk && IsMetaTarget())
{
int qc = m_isTrainQueueCand[m_isTrainCursor];
Net.getResults(TempData);
double qPwin = MetaWinProbability();
bool qWon = MetaCandidateWon(qc, qi);
//--- the argmax of a 2-class softmax IS pWin >= 0.5 - the unthresholded "call"
bool qCall = (qPwin >= 0.5);
bool qHit = (qCall == qWon);
if(qHit)
dForecast += (100 - dForecast) / Net.recentAverageSmoothingFactor;
else
dForecast -= dForecast / Net.recentAverageSmoothingFactor;
dUndefine -= dUndefine / Net.recentAverageSmoothingFactor;
if(qCall)
m_countBuySignals++;
else
m_countSellSignals++;
//--- persistent IS precision over the candidates the model would trade, in WINS - the
//--- meta analogue of the direction path's m_cumIsTotal contract (compared against the OOS
//--- side as the overfitting signal, so both must count the same quantity).
if(qCall)
{
m_cumIsTotal++;
if(qWon)
m_cumIsCorrect++;
}
UpdateTrainingStatusLabel(
StringFormat("Training candidate %d of %d -> %.2f%% (shuffled)", m_isTrainCursor + 1,
m_isTrainQueueCount,
(double)(m_isTrainCursor + 1.0) / MathMax(m_isTrainQueueCount, 1) * 100),
(TempData.Total() > 0) ? TempData[0] : 0.0,
(TempData.Total() > 1) ? TempData[1] : 0.0, 0.0, qPwin);
TempData.Clear();
//--- slot 0 = P(win), slot 1 = P(loss); same label smoothing as the 3-class head
TempData.Add(qWon ? LABEL_SMOOTH_HIGH : LABEL_SMOOTH_LOW);
TempData.Add(qWon ? LABEL_SMOOTH_LOW : LABEL_SMOOTH_HIGH);
ulong hbBpM = GetMicrosecondCount();
Net.backProp(TempData, 1.0);
m_passNetUs += GetMicrosecondCount() - hbBpM;
}
else
if(qForwardOk)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
feat: excursion-size head (Stage 1, measurement only) Direction is closed - normalised asymmetry fails on three instruments with a working positive control, and the classifier's own best-of-999 era-cap test agrees (+0.9pp = 1.48 sigma, family-wise p=1.0000). SIZE is a different question and RANGE clears at ~4x its null. Checked the denomination before building on that, since the source memo warns to: m_excUpCache holds (maxHigh - fill)/ATR, so "RANGE is predictable" is a claim about travel RELATIVE to current ATR, not a restatement of "ATR is autocorrelated". It is exactly the part a fixed multiple (stop 3.31*ATR, target 1.64*ATR) discards. A second small CNet, 760 -> 24 -> 32 sigmoid outputs = P(price reaches ladder rung k) upward and downward. Survival parameterisation rather than regressing the multiple, because it needs nothing new from CNet: sigmoid outputs and the per-neuron delta the `total != 3` branch already applies (a quantile head would need a linear activation and a pinball gradient in Network.mqh, Network.cl and the DirectML path, on a class four topologies share). Targets are free - m_ladderUpAt already records first-touch age per rung with 0 meaning never reached. Separate net, not extra outputs on the classifier: more outputs would change m_outputNeuronsCount, the .nnw shape and the fingerprint, and push the count off 3 - the exact condition backProp uses to select the joint softmax gradient the 3-class head depends on. The classifier is bit-for-bit unaffected and this is removable without trace. STAGE 1 PLACES NO ORDERS. It reports a Brier skill score against the constant per-rung base rate - the baseline a fixed ATR multiple already assumes - with both predictors fitted IS and evaluated OOS, so neither gets a look at the test set. Positive skill justifies Stage 2 (drive SL/TP and sizing off ExcursionQuantile, which is defined and deliberately uncalled). Zero or negative means ATR already carries everything and Stage 2 must not be built. Trains only on primary occurrences: the replay queue oversamples for CLASS balance, and a direction-balanced sample is a biased SIZE sample. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-11 07:40:01 -04:00
//--- EXCURSION HEAD, trained here and ONLY here in pass 2. Must run BEFORE getResults(),
//--- which overwrites TempData in place with the classifier's output activations - the
refactor(training): delete the minority-replay machinery that stopped running in July Two arrays parallel to m_isTrainQueue existed only to serve replay: a per-occurrence sample weight, and a "count this bar once" flag that kept the reported IS accuracy on the natural class distribution while backProp trained on the oversampled one. Replay was removed on 2026-07-31 - every bar has been queued exactly once since - and the scaffolding was left standing, provably constant: m_isTrainQueueWeightScale[] - written 1.0 at both queue sites, swapped through the Fisher-Yates shuffle to stay in lockstep with nothing, read into a variable passed to backProp, whose own default is 1.0. m_isTrainQueuePrimary[] - written true at both sites, swapped the same way, and read as two guards that could not be false. Also a `for(int rep = 0; rep < repCount; rep++)` around a hardcoded repCount = 1, and both arrays preallocated at totalIter * 4 - about 1.5MB per model of always-constant data, on a six-core box that trains four of them at once. Behaviour is unchanged by construction: every removed read had one possible value. m_maxClassSampleWeight goes with them - declared, initialised to 1.5 in the constructor, read nowhere, and documented as "currently unread by that path... kept in case a smaller, additive loss-level nudge is ever reintroduced". That is the definition of YAGNI, and its 17-line comment described the class-balance correction as data-level oversampling, which has not been true since July. Comment pass on ExpertSignalAIBase.mqh, -164 lines this session with every constant and measured number kept. One correction worth naming: the header carried 15 lines arguing for HARD 0/1 one-hot targets and explaining why smoothing was no longer needed - directly above LABEL_SMOOTH_HIGH 0.9 / LABEL_SMOOTH_LOW 0.05, which every training path actually uses. It described the opposite of what ships. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-20 09:30:51 -04:00
//--- feature window is gone after the next line.
ExcursionTrainStep(qi);
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
Net.getResults(TempData);
// Must go through ApplyClassificationSoftmax() (3-output case) before reading the
// per-class values below - Net.getResults() returns each output neuron's own independent
// SIGMOID activation (each already in [0,1] but NOT summing to 1 across the three), not a
// true class-conditional probability distribution; ApplyClassificationSoftmax() is what
// turns that into one (and is also what pass 1/3's displayNeuron0/1/2 already go through).
double qPrevSignal = (m_outputNeuronsCount == 3) ? ApplyClassificationSoftmax() : TempData[0];
double pt0 = (TempData.Total() > 0) ? TempData[0] : 0.0;
double pt1 = (TempData.Total() > 1) ? TempData[1] : 0.0;
double pt2 = (TempData.Total() > 2) ? TempData[2] : 0.0;
bool qBuy = m_labelCacheHasValue[qi] ? m_labelCacheBuy[qi] : false;
bool qSell = m_labelCacheHasValue[qi] ? m_labelCacheSell[qi] : false;
ENUM_SIGNAL qTrueSignal = qBuy ? Buy : (qSell ? Sell : Neutral);
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
//--- Per-direction outcomes for this bar - see m_oos.buyPredictedWins. Needed on the IS side
fix: the deploy gate was benchmarking a win rate against a label frequency The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test. That invariant needs reward >= risk, and the measured geometry no longer satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but both-won bars were stripped out of Buy and Sell so the label base rate read 37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma against 37.5% and loses money on every single trade. Live since 217b9bc. Root cause is that label agreement stopped being the same question as trade profitability. Buy implies winLong, but the converse fails on every both-won bar, and the label can only name one of two directions that both pay. So stop asking the model whether it matched a label and start asking whether its trade paid: - cache winLong/winShort per bar beside the label, under the same validity flag; published from the barrier walk before the collapse to 3 classes - dirPrecPct now counts wins on the side actually called - chancePrecPct is max(P(winLong), P(winShort)), MEASURED - the textbook m/(m+k) would credit SP500's drift to the model - the NMS "what would I have made" pair, the live-fired precision, and the IS/OOS cumulative win rates all move to the same test. IS and OOS are read side by side as the overfitting signal, so measuring one in wins and the other in agreement would put a fixed gap between them that has nothing to do with generalization - the confidence threshold is FITTED on wins too, so the operating point maximises what the gate grades - per-class label-agreement precision is still computed and logged; it is the right diagnostic for class separation, just not for a deploy decision - era line renamed dir-precision -> win-rate, chance -> chance=break-even Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 16:00:51 -04:00
//--- too: the operating point is FITTED here and GRADED by the OOS gate, so if the two
//--- optimise different quantities the threshold is tuned for the wrong objective.
bool qWinLong = (m_labelCacheHasValue[qi] && qi < ArraySize(m_winLongCache))
? m_winLongCache[qi] : false;
bool qWinShort = (m_labelCacheHasValue[qi] && qi < ArraySize(m_winShortCache))
? m_winShortCache[qi] : false;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
UpdateTrainingStatusLabel(
StringFormat("Training bar %d of %d -> %.2f%% (shuffled)", m_isTrainCursor + 1, m_isTrainQueueCount, (double)(m_isTrainCursor + 1.0) / MathMax(m_isTrainQueueCount, 1) * 100),
pt0, pt1, pt2, qPrevSignal);
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- Predicted-signal tally, chart marker, and IS-accuracy stat that pass 1 used to
//--- compute from its own (now-removed) redundant feedForward on this same bar - see
//--- pass 1's wouldQueue comment.
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
switch(DoubleToSignal(qPrevSignal))
{
case Buy:
m_countBuySignals++;
break;
case Sell:
m_countSellSignals++;
break;
default:
m_countNeutralSignals++;
break;
}
datetime qBarTime = m_Time.GetData(qi);
// NMS on: record only (the era-end sweep renders); off: draw inline. See pass 1's note.
if(m_signalClusterWindow > 0)
{
if(qi < ArraySize(m_arrowSignalCache))
m_arrowSignalCache[qi] = qPrevSignal;
}
else
if(DoubleToSignal(qPrevSignal) == Neutral)
DeleteObject(qBarTime);
else
feat(chart): signal marks become price LEVELS at the trigger, not arrows beside the candle User request: 'move from arrows on lows and highs to small horizontal lines at the actual prices the entry/exit would trigger, just a bit larger than the candles. dark green for buy, dark red for sell.' Every mark is now an OBJ_TREND segment with both anchors at one price and both rays off, spanning 1.3 bar widths, drawn at the bar's CLOSE - the price a market order actually fires at, and the exact entry TripleBarrierLabel assumes. It used to sit on the candle's LOW for a Buy and its HIGH for a Sell: prices the trade never touches, picked so an arrow glyph would clear the candle. The tooltip now carries that price too. COLOUR NOW MEANS DIRECTION AND ONLY DIRECTION on every layer (dark green / dark red). Layer moves to width+style - the traded vote is solid and thick and drawn in front, a single model's raw opinion is thin, dotted and behind the candles - which keeps the distinction the old palette existed to draw (a model's opinion must never read as a trade) while freeing colour to say one thing consistently. Consequences handled, all of them the same 'a typed scan went blind' failure: - SaveChartSignals filtered OBJPROP_TYPE == OBJ_ARROW and read OBJPROP_ARROWCODE. It now filters OBJ_TREND and recovers direction from the colour. The sidecar keeps the old 217/218 numbers as its buy/sell token deliberately, so existing .arrows files still load. - AdvanceChartSignalRestore now rebuilds through the SAME creation point the live path uses, so a restored mark and a fresh one are identical objects. - The rescan-scoped delete enumerated ObjectsTotal(OBJ_ARROW) - retyped, or it silently deletes nothing. - ApplySignalsVisibility enumerated OBJ_ARROW with NO prefix filter. Under the new type that would have hidden and shown THE USER'S OWN trend lines on every Hide/Show click; it is now prefix-scoped. The old type was uncommon enough on a real chart to mask the missing check - trend lines are the most hand-drawn object there is. - DrawObject's high/low parameters are gone (6 call sites pass m_Close instead), so no caller can hand it a price it no longer draws at. - Fixed a pre-existing stale comment that still described the purge sweep as OBJ_ARROW-only three lines above the note explaining it had been widened to every type. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 14:11:49 -04:00
DrawObject(qBarTime, qPrevSignal, m_Close.GetData(qi));
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
bool qClassified = (DoubleToSignal(qPrevSignal) == Buy || DoubleToSignal(qPrevSignal) == Sell || DoubleToSignal(qPrevSignal) == Neutral);
if(qClassified)
{
bool isHit = (DoubleToSignal(qPrevSignal) == qTrueSignal);
if(isHit)
dForecast += (100 - dForecast) / Net.recentAverageSmoothingFactor;
else
dForecast -= dForecast / Net.recentAverageSmoothingFactor;
dUndefine -= dUndefine / Net.recentAverageSmoothingFactor;
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- Compounded, persistent DIRECTIONAL win-rate: count only bars the model actually
//--- called Buy or Sell (a Neutral "no trade" call is neither a win nor a loss), so
//--- this tracks the accuracy of its directional signals rather than the Neutral-
//--- inflated all-class rate.
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
ENUM_SIGNAL qPred = DoubleToSignal(qPrevSignal);
fix: the deploy gate was benchmarking a win rate against a label frequency The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test. That invariant needs reward >= risk, and the measured geometry no longer satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but both-won bars were stripped out of Buy and Sell so the label base rate read 37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma against 37.5% and loses money on every single trade. Live since 217b9bc. Root cause is that label agreement stopped being the same question as trade profitability. Buy implies winLong, but the converse fails on every both-won bar, and the label can only name one of two directions that both pay. So stop asking the model whether it matched a label and start asking whether its trade paid: - cache winLong/winShort per bar beside the label, under the same validity flag; published from the barrier walk before the collapse to 3 classes - dirPrecPct now counts wins on the side actually called - chancePrecPct is max(P(winLong), P(winShort)), MEASURED - the textbook m/(m+k) would credit SP500's drift to the model - the NMS "what would I have made" pair, the live-fired precision, and the IS/OOS cumulative win rates all move to the same test. IS and OOS are read side by side as the overfitting signal, so measuring one in wins and the other in agreement would put a fixed gap between them that has nothing to do with generalization - the confidence threshold is FITTED on wins too, so the operating point maximises what the gate grades - per-class label-agreement precision is still computed and logged; it is the right diagnostic for class separation, just not for a deploy decision - era line renamed dir-precision -> win-rate, chance -> chance=break-even Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 16:00:51 -04:00
//--- Did the implied trade pay? Same distinction as the OOS side - see
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
//--- m_oos.buyPredictedWins - and it has to be made identically on both, because the
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- IS and OOS win rates are read side by side as the overfitting signal.
fix: the deploy gate was benchmarking a win rate against a label frequency The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test. That invariant needs reward >= risk, and the measured geometry no longer satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but both-won bars were stripped out of Buy and Sell so the label base rate read 37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma against 37.5% and loses money on every single trade. Live since 217b9bc. Root cause is that label agreement stopped being the same question as trade profitability. Buy implies winLong, but the converse fails on every both-won bar, and the label can only name one of two directions that both pay. So stop asking the model whether it matched a label and start asking whether its trade paid: - cache winLong/winShort per bar beside the label, under the same validity flag; published from the barrier walk before the collapse to 3 classes - dirPrecPct now counts wins on the side actually called - chancePrecPct is max(P(winLong), P(winShort)), MEASURED - the textbook m/(m+k) would credit SP500's drift to the model - the NMS "what would I have made" pair, the live-fired precision, and the IS/OOS cumulative win rates all move to the same test. IS and OOS are read side by side as the overfitting signal, so measuring one in wins and the other in agreement would put a fixed gap between them that has nothing to do with generalization - the confidence threshold is FITTED on wins too, so the operating point maximises what the gate grades - per-class label-agreement precision is still computed and logged; it is the right diagnostic for class separation, just not for a deploy decision - era line renamed dir-precision -> win-rate, chance -> chance=break-even Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 16:00:51 -04:00
bool qTradeWon = (qPred == Buy) ? qWinLong : ((qPred == Sell) ? qWinShort : false);
refactor(training): delete the minority-replay machinery that stopped running in July Two arrays parallel to m_isTrainQueue existed only to serve replay: a per-occurrence sample weight, and a "count this bar once" flag that kept the reported IS accuracy on the natural class distribution while backProp trained on the oversampled one. Replay was removed on 2026-07-31 - every bar has been queued exactly once since - and the scaffolding was left standing, provably constant: m_isTrainQueueWeightScale[] - written 1.0 at both queue sites, swapped through the Fisher-Yates shuffle to stay in lockstep with nothing, read into a variable passed to backProp, whose own default is 1.0. m_isTrainQueuePrimary[] - written true at both sites, swapped the same way, and read as two guards that could not be false. Also a `for(int rep = 0; rep < repCount; rep++)` around a hardcoded repCount = 1, and both arrays preallocated at totalIter * 4 - about 1.5MB per model of always-constant data, on a six-core box that trains four of them at once. Behaviour is unchanged by construction: every removed read had one possible value. m_maxClassSampleWeight goes with them - declared, initialised to 1.5 in the constructor, read nowhere, and documented as "currently unread by that path... kept in case a smaller, additive loss-level nudge is ever reintroduced". That is the definition of YAGNI, and its 17-line comment described the class-balance correction as data-level oversampling, which has not been true since July. Comment pass on ExpertSignalAIBase.mqh, -164 lines this session with every constant and measured number kept. One correction worth naming: the header carried 15 lines arguing for HARD 0/1 one-hot targets and explaining why smoothing was no longer needed - directly above LABEL_SMOOTH_HIGH 0.9 / LABEL_SMOOTH_LOW 0.05, which every training path actually uses. It described the opposite of what ships. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-20 09:30:51 -04:00
if(qPred == Buy || qPred == Sell)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
m_cumIsTotal++;
fix: the deploy gate was benchmarking a win rate against a label frequency The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test. That invariant needs reward >= risk, and the measured geometry no longer satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but both-won bars were stripped out of Buy and Sell so the label base rate read 37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma against 37.5% and loses money on every single trade. Live since 217b9bc. Root cause is that label agreement stopped being the same question as trade profitability. Buy implies winLong, but the converse fails on every both-won bar, and the label can only name one of two directions that both pay. So stop asking the model whether it matched a label and start asking whether its trade paid: - cache winLong/winShort per bar beside the label, under the same validity flag; published from the barrier walk before the collapse to 3 classes - dirPrecPct now counts wins on the side actually called - chancePrecPct is max(P(winLong), P(winShort)), MEASURED - the textbook m/(m+k) would credit SP500's drift to the model - the NMS "what would I have made" pair, the live-fired precision, and the IS/OOS cumulative win rates all move to the same test. IS and OOS are read side by side as the overfitting signal, so measuring one in wins and the other in agreement would put a fixed gap between them that has nothing to do with generalization - the confidence threshold is FITTED on wins too, so the operating point maximises what the gate grades - per-class label-agreement precision is still computed and logged; it is the right diagnostic for class separation, just not for a deploy decision - era line renamed dir-precision -> win-rate, chance -> chance=break-even Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 16:00:51 -04:00
if(qTradeWon)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
m_cumIsCorrect++;
}
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- THE OPERATING-POINT FIT NO LONGER HARVESTS HERE. It moved to the held-out
//--- calibration walk below; DIR_CONF_CALIB_PCT_OF_IS carries the measured IS-vs-OOS
//--- divergence that forced the move.
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
else
if(qBuy && qSell)
dUndefine += (100 - dUndefine) / Net.recentAverageSmoothingFactor;
TempData.Clear();
if(m_outputNeuronsCount == 1)
TempData.Add(qBuy && !qSell ? 1 : !qBuy && qSell ? -1 : 0);
else
if(m_outputNeuronsCount == 3)
{
TempData.Add(qBuy ? LABEL_SMOOTH_HIGH : LABEL_SMOOTH_LOW);
TempData.Add(qSell ? LABEL_SMOOTH_HIGH : LABEL_SMOOTH_LOW);
TempData.Add((!qBuy && !qSell) ? LABEL_SMOOTH_HIGH : LABEL_SMOOTH_LOW);
}
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- FOCAL-LOSS MODULATION REMOVED 2026-07-31. It multiplied this weight by
//--- (1-pt)^gamma, a second correction on the same axis as the logit adjustment - the
//--- stacking failure Buda et al.
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
ulong hbBp = GetMicrosecondCount();
refactor(training): delete the minority-replay machinery that stopped running in July Two arrays parallel to m_isTrainQueue existed only to serve replay: a per-occurrence sample weight, and a "count this bar once" flag that kept the reported IS accuracy on the natural class distribution while backProp trained on the oversampled one. Replay was removed on 2026-07-31 - every bar has been queued exactly once since - and the scaffolding was left standing, provably constant: m_isTrainQueueWeightScale[] - written 1.0 at both queue sites, swapped through the Fisher-Yates shuffle to stay in lockstep with nothing, read into a variable passed to backProp, whose own default is 1.0. m_isTrainQueuePrimary[] - written true at both sites, swapped the same way, and read as two guards that could not be false. Also a `for(int rep = 0; rep < repCount; rep++)` around a hardcoded repCount = 1, and both arrays preallocated at totalIter * 4 - about 1.5MB per model of always-constant data, on a six-core box that trains four of them at once. Behaviour is unchanged by construction: every removed read had one possible value. m_maxClassSampleWeight goes with them - declared, initialised to 1.5 in the constructor, read nowhere, and documented as "currently unread by that path... kept in case a smaller, additive loss-level nudge is ever reintroduced". That is the definition of YAGNI, and its 17-line comment described the class-balance correction as data-level oversampling, which has not been true since July. Comment pass on ExpertSignalAIBase.mqh, -164 lines this session with every constant and measured number kept. One correction worth naming: the header carried 15 lines arguing for HARD 0/1 one-hot targets and explaining why smoothing was no longer needed - directly above LABEL_SMOOTH_HIGH 0.9 / LABEL_SMOOTH_LOW 0.05, which every training path actually uses. It described the opposite of what ships. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-20 09:30:51 -04:00
//--- No per-sample weight: the imbalance correction is analytic (logit-adjusted loss), so
//--- backProp's own sampleWeight default of 1.0 is the shipped behaviour.
Net.backProp(TempData);
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
m_passNetUs += GetMicrosecondCount() - hbBp;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- YIELD ON TIME **OR** ON A STOP REQUEST. The time budget bounds THROUGHPUT; it does
//--- not bound LATENCY to an unload. Pass 1 has checked IsStopped() all along; passes 2,
//--- 2.5 and 3 never did, and they are the ones that grow with history.
fix(training): the wall-clock budget was left behind in Train() Compile error, four sites: TRAIN_TIME_BUDGET_MS was a const local to Train(), and the four passes that yield on it are now defined above Train(). I checked every pass for the eight locals STrainEra replaced and missed the ninth, because it was a const rather than a variable. It is per-call state like everything else in STrainEra, so it moves there as budgetMs. All four sites asked the same question the same way GetTickCount() - era.chunkStartTick >= TRAIN_TIME_BUDGET_MS so the struct answers it once as BudgetSpent(). Swept for the same class of mistake rather than waiting for another compile: Train() now has exactly two top-level locals left (STABILITY_WINDOW, STABILITY_TOLERANCE) and neither appears in any extracted body. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:40:15 -04:00
if(m_isTrainCursor + 1 < m_isTrainQueueCount && (IsStopped() || era.BudgetSpent()))
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
//--- yield: save enough to resume PASS 2 mid-queue on the next call - m_isPass2Active
//--- and m_isTrainCursor (both members) carry the actual resume position; bars/oosCutoff/
//--- add_loop are stashed the same way pass 1 already does, since era-end logic just
//--- below still needs them once pass 2 finishes.
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
StashEraResume(era.bars, era.totalIter, era.oosCutoff, era.addLoop, era.i);
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
return;
}
}
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- Apply whatever the final (usually short) batch of this era accumulated, and return the
//--- net to per-sample updates. FlushBatch scales by the REAL sample count, so a short
//--- trailing batch still takes a correctly-sized step.
feat: mini-batch gradient accumulation (F4), front-end-aware capacity budget (F6), split Wyckoff categoricals (N1) Completes the 2026-08-09 training audit. FORCES A RETRAIN of every Wyckoff-enabled config (N1 re-keys the fingerprint), and BOTH DLLs must be redeployed alongside the .ex5 - they carry new exports. F4 - mini-batch accumulation, TRAIN_BATCH_SIZE=32. Training was pure online SGD (one weight update per bar), which is the mechanical source of the era-to-era whipsaw every downstream guard was built to cope with. The O(n^2) outer product is native - AccumulateWeightGrad / AccumulateWeightGradConv / AccumulateBufferInto in Network.cl, WarriorCPU and WarriorDML - while the optimizer step is host-side MQL5 shared by all tiers (ApplyAccumToBlock), so there is one Adam/SGD implementation instead of four that can drift. - the LSTM needs no outer-product kernel (WeightsGradient already holds the sample's full dW) but could NOT simply be left un-zeroed between samples: CPU_LSTMSeqBackward/DML_LSTMSeqBackward memset it on entry. Hence a separate accumulator plus an elementwise add. - batch-norm gamma/beta accumulate in host arrays, not new BatchOptions slots - BN_OPT_STRIDE is baked into every persisted .nnw. - scoped to pass 2; online learning keeps immediate updates. Every save / checkpoint / scoring boundary flushes, scaling by the real sample count. - degrades to per-sample updates (one log line) on a tier that cannot accumulate, so old devices and DLL-free builds are unaffected. - verified offline: DirectML/batch_accum_check.cpp drives the real exports against an independent reference; at B=1 the accumulator matches the shipped unbatched kernel's own gradient to 1.1e-16. Math only - the in-situ check remains the per-layer dW/W report on a real era. F6 - ComputeFirstLayerWidth budgeted against the RAW input width even where a conv/LSTM front end had already reduced it, so an LSTM's dense stack was charged for 1,280 inputs when it receives 64. Confirmed from the deployed .cfg files: CONV, LSTM and HYBRID were all pinned at the 16-unit floor. Now budgeted against the front-end output and capped at it (never fan out), with the derivation reordered so both stages settle first. N1 - EventCode/EventPhase/StructuralPhase are signed categoricals packing direction and Wyckoff stage into one scalar across a sign discontinuity. Split into direction + [0,1] magnitude, the same convention the base OHLC block uses. Information-preserving; 13 readings now occupy 16 inputs. Compiled clean (0 errors, 0 warnings); both DLLs rebuilt. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 11:48:03 -04:00
Net.FlushBatch();
Net.SetBatchSize(1);
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
m_isPass2Active = false;
m_isPass2Done = true;
}
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
}
//+------------------------------------------------------------------+
//| CALIBRATION PASS: fit the directional confidence threshold on a |
//| PURGED held-out slice. |
//| |
//| Separate from pass 2 because it must not see bars the weights |
//| were fitted on - a threshold fitted on memorised bars is the |
//| single easiest way to manufacture an edge that does not exist. |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::RunCalibrationPass(STrainEra &era)
{
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
if(!era.stop && era.addLoop && !m_isCalibDone)
fix: the operating point was fitted on bars the net had memorized FitDirConfThreshold harvested its margin histogram from pass 2's own backprop samples. Pairing every fit against the same era's OOS result shows what that measured: PAI era 1 IS 25% cov @ 66.1% (-0.8pp) -> OOS 64% (-3pp) gap +2.1pp PAI era 76 IS 90% cov @ 79.6% (+12.7pp) -> OOS 65% (-2pp) gap +14.6pp LSTM era 9 IS 77% cov @ 81.6% (+14.6pp) -> OOS 63% (-4pp) gap +18.6pp The gap grows monotonically while OOS stays flat, so within a handful of eras the curve stops describing behaviour on unseen bars. That is fatal here specifically, because the objective branches on the SIGN of (p - break-even): the memorized curve reads +12pp at 95% coverage, so coverage x (p - p0) correctly maximises coverage and returns ~0.02 - fire on every bar. The "p < p0 -> get more selective" branch, which is the actual regime and the entire point of 983a6a3, could never fire because IS never showed p < p0. Carve a calibration slice out of the IS span - DIR_CONF_CALIB_PCT_OF_IS, purged from backprop by one label horizon on BOTH sides (the far-side purge is not optional: without it the newest training bars carry labels partly decided by price action inside the slice, putting the memorization straight back into the curve). Score it in a new chunked pass 2.5, after pass 2 has trained and before pass 3 grades - the only position where the histogram is simultaneously not-trained-on, not-graded, and current with the weights it will be applied to. Costs 15% of the training data. Worth it beyond honesty: the deploy gate needs dirPrecPct > chance + EDGE_MIN_SIGMAS*SE, and a threshold pinned near zero dilutes any edge concentrated in the confident bars across every bar the model calls, driving dirPrecPct toward chance by construction. A threshold that can be selective is the only mechanism by which a small, concentrated edge could ever clear that gate. Also: a sparse histogram now KEEPS the previous threshold instead of resetting to 0.0. A failed measurement must not decay to the most exposed setting in the range. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-10 15:58:18 -04:00
{
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
int calibLo = CalibLoIndex(era.oosCutoff);
int calibHi = CalibHiIndex(era.totalIter, era.oosCutoff);
fix: the operating point was fitted on bars the net had memorized FitDirConfThreshold harvested its margin histogram from pass 2's own backprop samples. Pairing every fit against the same era's OOS result shows what that measured: PAI era 1 IS 25% cov @ 66.1% (-0.8pp) -> OOS 64% (-3pp) gap +2.1pp PAI era 76 IS 90% cov @ 79.6% (+12.7pp) -> OOS 65% (-2pp) gap +14.6pp LSTM era 9 IS 77% cov @ 81.6% (+14.6pp) -> OOS 63% (-4pp) gap +18.6pp The gap grows monotonically while OOS stays flat, so within a handful of eras the curve stops describing behaviour on unseen bars. That is fatal here specifically, because the objective branches on the SIGN of (p - break-even): the memorized curve reads +12pp at 95% coverage, so coverage x (p - p0) correctly maximises coverage and returns ~0.02 - fire on every bar. The "p < p0 -> get more selective" branch, which is the actual regime and the entire point of 983a6a3, could never fire because IS never showed p < p0. Carve a calibration slice out of the IS span - DIR_CONF_CALIB_PCT_OF_IS, purged from backprop by one label horizon on BOTH sides (the far-side purge is not optional: without it the newest training bars carry labels partly decided by price action inside the slice, putting the memorization straight back into the curve). Score it in a new chunked pass 2.5, after pass 2 has trained and before pass 3 grades - the only position where the histogram is simultaneously not-trained-on, not-graded, and current with the weights it will be applied to. Costs 15% of the training data. Worth it beyond honesty: the deploy gate needs dirPrecPct > chance + EDGE_MIN_SIGMAS*SE, and a threshold pinned near zero dilutes any edge concentrated in the confident bars across every bar the model calls, driving dirPrecPct toward chance by construction. A threshold that can be selective is the only mechanism by which a small, concentrated edge could ever clear that gate. Also: a sparse histogram now KEEPS the previous threshold instead of resetting to 0.0. A failed measurement must not decay to the most exposed setting in the range. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-10 15:58:18 -04:00
if(!m_isCalibActive)
{
m_isCalibActive = true;
Net.SetBatchNormFrozen(true);
ResetDirConfHistogram();
//--- Same upper clamp pass 3 applies: a bar needs m_historyBars of older bars behind it to
//--- build a window at all, so the band is trimmed to what is actually scoreable.
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
m_calibStartIndex = (int)MathMin(calibHi - 1, era.bars - MathMax(m_historyBars, 0) - 2);
fix: the operating point was fitted on bars the net had memorized FitDirConfThreshold harvested its margin histogram from pass 2's own backprop samples. Pairing every fit against the same era's OOS result shows what that measured: PAI era 1 IS 25% cov @ 66.1% (-0.8pp) -> OOS 64% (-3pp) gap +2.1pp PAI era 76 IS 90% cov @ 79.6% (+12.7pp) -> OOS 65% (-2pp) gap +14.6pp LSTM era 9 IS 77% cov @ 81.6% (+14.6pp) -> OOS 63% (-4pp) gap +18.6pp The gap grows monotonically while OOS stays flat, so within a handful of eras the curve stops describing behaviour on unseen bars. That is fatal here specifically, because the objective branches on the SIGN of (p - break-even): the memorized curve reads +12pp at 95% coverage, so coverage x (p - p0) correctly maximises coverage and returns ~0.02 - fire on every bar. The "p < p0 -> get more selective" branch, which is the actual regime and the entire point of 983a6a3, could never fire because IS never showed p < p0. Carve a calibration slice out of the IS span - DIR_CONF_CALIB_PCT_OF_IS, purged from backprop by one label horizon on BOTH sides (the far-side purge is not optional: without it the newest training bars carry labels partly decided by price action inside the slice, putting the memorization straight back into the curve). Score it in a new chunked pass 2.5, after pass 2 has trained and before pass 3 grades - the only position where the histogram is simultaneously not-trained-on, not-graded, and current with the weights it will be applied to. Costs 15% of the training data. Worth it beyond honesty: the deploy gate needs dirPrecPct > chance + EDGE_MIN_SIGMAS*SE, and a threshold pinned near zero dilutes any edge concentrated in the confident bars across every bar the model calls, driving dirPrecPct toward chance by construction. A threshold that can be selective is the only mechanism by which a small, concentrated edge could ever clear that gate. Also: a sparse histogram now KEEPS the previous threshold instead of resetting to 0.0. A failed measurement must not decay to the most exposed setting in the range. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-10 15:58:18 -04:00
m_calibIndex = m_calibStartIndex;
}
for(; m_calibIndex >= calibLo; m_calibIndex--)
{
int ci = m_calibIndex;
//--- Same eligibility test pass 1 gates labelling on (its line reads
//--- `i < bars-historyBars-1 && i > 1 && Time[i] > dtStudied`), so this walk can only score bars
//--- pass 1 actually produced a label for. Pass 3 applies the identical test on its own window.
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
if(!(ci < (int)(era.bars - MathMax(m_historyBars, 0) - 1) && ci > 1 && m_Time.GetData(ci) > dtStudied))
fix: the operating point was fitted on bars the net had memorized FitDirConfThreshold harvested its margin histogram from pass 2's own backprop samples. Pairing every fit against the same era's OOS result shows what that measured: PAI era 1 IS 25% cov @ 66.1% (-0.8pp) -> OOS 64% (-3pp) gap +2.1pp PAI era 76 IS 90% cov @ 79.6% (+12.7pp) -> OOS 65% (-2pp) gap +14.6pp LSTM era 9 IS 77% cov @ 81.6% (+14.6pp) -> OOS 63% (-4pp) gap +18.6pp The gap grows monotonically while OOS stays flat, so within a handful of eras the curve stops describing behaviour on unseen bars. That is fatal here specifically, because the objective branches on the SIGN of (p - break-even): the memorized curve reads +12pp at 95% coverage, so coverage x (p - p0) correctly maximises coverage and returns ~0.02 - fire on every bar. The "p < p0 -> get more selective" branch, which is the actual regime and the entire point of 983a6a3, could never fire because IS never showed p < p0. Carve a calibration slice out of the IS span - DIR_CONF_CALIB_PCT_OF_IS, purged from backprop by one label horizon on BOTH sides (the far-side purge is not optional: without it the newest training bars carry labels partly decided by price action inside the slice, putting the memorization straight back into the curve). Score it in a new chunked pass 2.5, after pass 2 has trained and before pass 3 grades - the only position where the histogram is simultaneously not-trained-on, not-graded, and current with the weights it will be applied to. Costs 15% of the training data. Worth it beyond honesty: the deploy gate needs dirPrecPct > chance + EDGE_MIN_SIGMAS*SE, and a threshold pinned near zero dilutes any edge concentrated in the confident bars across every bar the model calls, driving dirPrecPct toward chance by construction. A threshold that can be selective is the only mechanism by which a small, concentrated edge could ever clear that gate. Also: a sparse histogram now KEEPS the previous threshold instead of resetting to 0.0. A failed measurement must not decay to the most exposed setting in the range. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-10 15:58:18 -04:00
continue;
TrainHeartbeat("pass 2.5 (calibration), bar", m_calibStartIndex - m_calibIndex + 1,
m_calibStartIndex - calibLo + 1, "calibrating");
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- META TARGET: harvest one histogram sample per CANDIDATE in the band - margin is
//--- P(win), outcome is the candidate's own triple-barrier win.
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
if(IsMetaTarget())
{
for(int cd = MetaCandFirst(ci); cd >= 0; cd = MetaCandNext(cd))
{
ulong hbM = GetMicrosecondCount();
bool mWindowOk = BuildFeatureWindow(ci);
if(mWindowOk)
AppendCandidateFeatures(cd);
m_passFeatUs += GetMicrosecondCount() - hbM;
hbM = GetMicrosecondCount();
bool mForwardOk = (mWindowOk && TempData.Total() >= NetInputWidth() &&
Net.feedForward(TempData));
m_passNetUs += GetMicrosecondCount() - hbM;
if(!mForwardOk)
break;
Net.getResults(TempData);
AccumulateDirConfSample(MetaWinProbability(), MetaCandidateWon(cd, ci), true);
}
}
else
{
fix: the operating point was fitted on bars the net had memorized FitDirConfThreshold harvested its margin histogram from pass 2's own backprop samples. Pairing every fit against the same era's OOS result shows what that measured: PAI era 1 IS 25% cov @ 66.1% (-0.8pp) -> OOS 64% (-3pp) gap +2.1pp PAI era 76 IS 90% cov @ 79.6% (+12.7pp) -> OOS 65% (-2pp) gap +14.6pp LSTM era 9 IS 77% cov @ 81.6% (+14.6pp) -> OOS 63% (-4pp) gap +18.6pp The gap grows monotonically while OOS stays flat, so within a handful of eras the curve stops describing behaviour on unseen bars. That is fatal here specifically, because the objective branches on the SIGN of (p - break-even): the memorized curve reads +12pp at 95% coverage, so coverage x (p - p0) correctly maximises coverage and returns ~0.02 - fire on every bar. The "p < p0 -> get more selective" branch, which is the actual regime and the entire point of 983a6a3, could never fire because IS never showed p < p0. Carve a calibration slice out of the IS span - DIR_CONF_CALIB_PCT_OF_IS, purged from backprop by one label horizon on BOTH sides (the far-side purge is not optional: without it the newest training bars carry labels partly decided by price action inside the slice, putting the memorization straight back into the curve). Score it in a new chunked pass 2.5, after pass 2 has trained and before pass 3 grades - the only position where the histogram is simultaneously not-trained-on, not-graded, and current with the weights it will be applied to. Costs 15% of the training data. Worth it beyond honesty: the deploy gate needs dirPrecPct > chance + EDGE_MIN_SIGMAS*SE, and a threshold pinned near zero dilutes any edge concentrated in the confident bars across every bar the model calls, driving dirPrecPct toward chance by construction. A threshold that can be selective is the only mechanism by which a small, concentrated edge could ever clear that gate. Also: a sparse histogram now KEEPS the previous threshold instead of resetting to 0.0. A failed measurement must not decay to the most exposed setting in the range. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-10 15:58:18 -04:00
ulong hbC = GetMicrosecondCount();
bool cWindowOk = BuildFeatureWindow(ci);
m_passFeatUs += GetMicrosecondCount() - hbC;
hbC = GetMicrosecondCount();
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
bool cForwardOk = (cWindowOk && TempData.Total() >= NetInputWidth() &&
fix: the operating point was fitted on bars the net had memorized FitDirConfThreshold harvested its margin histogram from pass 2's own backprop samples. Pairing every fit against the same era's OOS result shows what that measured: PAI era 1 IS 25% cov @ 66.1% (-0.8pp) -> OOS 64% (-3pp) gap +2.1pp PAI era 76 IS 90% cov @ 79.6% (+12.7pp) -> OOS 65% (-2pp) gap +14.6pp LSTM era 9 IS 77% cov @ 81.6% (+14.6pp) -> OOS 63% (-4pp) gap +18.6pp The gap grows monotonically while OOS stays flat, so within a handful of eras the curve stops describing behaviour on unseen bars. That is fatal here specifically, because the objective branches on the SIGN of (p - break-even): the memorized curve reads +12pp at 95% coverage, so coverage x (p - p0) correctly maximises coverage and returns ~0.02 - fire on every bar. The "p < p0 -> get more selective" branch, which is the actual regime and the entire point of 983a6a3, could never fire because IS never showed p < p0. Carve a calibration slice out of the IS span - DIR_CONF_CALIB_PCT_OF_IS, purged from backprop by one label horizon on BOTH sides (the far-side purge is not optional: without it the newest training bars carry labels partly decided by price action inside the slice, putting the memorization straight back into the curve). Score it in a new chunked pass 2.5, after pass 2 has trained and before pass 3 grades - the only position where the histogram is simultaneously not-trained-on, not-graded, and current with the weights it will be applied to. Costs 15% of the training data. Worth it beyond honesty: the deploy gate needs dirPrecPct > chance + EDGE_MIN_SIGMAS*SE, and a threshold pinned near zero dilutes any edge concentrated in the confident bars across every bar the model calls, driving dirPrecPct toward chance by construction. A threshold that can be selective is the only mechanism by which a small, concentrated edge could ever clear that gate. Also: a sparse histogram now KEEPS the previous threshold instead of resetting to 0.0. A failed measurement must not decay to the most exposed setting in the range. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-10 15:58:18 -04:00
Net.feedForward(TempData));
m_passNetUs += GetMicrosecondCount() - hbC;
if(cForwardOk)
{
Net.getResults(TempData);
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- RAW argmax softmax, NOT AdjustedSignalFromSoftmax(): feeding the fit its own
//--- already- thresholded decisions would make the threshold a fixed point of itself,
//--- able only to ratchet upward.
fix: the operating point was fitted on bars the net had memorized FitDirConfThreshold harvested its margin histogram from pass 2's own backprop samples. Pairing every fit against the same era's OOS result shows what that measured: PAI era 1 IS 25% cov @ 66.1% (-0.8pp) -> OOS 64% (-3pp) gap +2.1pp PAI era 76 IS 90% cov @ 79.6% (+12.7pp) -> OOS 65% (-2pp) gap +14.6pp LSTM era 9 IS 77% cov @ 81.6% (+14.6pp) -> OOS 63% (-4pp) gap +18.6pp The gap grows monotonically while OOS stays flat, so within a handful of eras the curve stops describing behaviour on unseen bars. That is fatal here specifically, because the objective branches on the SIGN of (p - break-even): the memorized curve reads +12pp at 95% coverage, so coverage x (p - p0) correctly maximises coverage and returns ~0.02 - fire on every bar. The "p < p0 -> get more selective" branch, which is the actual regime and the entire point of 983a6a3, could never fire because IS never showed p < p0. Carve a calibration slice out of the IS span - DIR_CONF_CALIB_PCT_OF_IS, purged from backprop by one label horizon on BOTH sides (the far-side purge is not optional: without it the newest training bars carry labels partly decided by price action inside the slice, putting the memorization straight back into the curve). Score it in a new chunked pass 2.5, after pass 2 has trained and before pass 3 grades - the only position where the histogram is simultaneously not-trained-on, not-graded, and current with the weights it will be applied to. Costs 15% of the training data. Worth it beyond honesty: the deploy gate needs dirPrecPct > chance + EDGE_MIN_SIGMAS*SE, and a threshold pinned near zero dilutes any edge concentrated in the confident bars across every bar the model calls, driving dirPrecPct toward chance by construction. A threshold that can be selective is the only mechanism by which a small, concentrated edge could ever clear that gate. Also: a sparse histogram now KEEPS the previous threshold instead of resetting to 0.0. A failed measurement must not decay to the most exposed setting in the range. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-10 15:58:18 -04:00
double cSignal = (m_outputNeuronsCount == 3) ? ApplyClassificationSoftmax() : TempData[0];
ENUM_SIGNAL cPred = DoubleToSignal(cSignal);
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- Scored in WINS - did the trade this call implies actually pay - not in agreement
//--- with the collapsed 3-class label.
fix: the operating point was fitted on bars the net had memorized FitDirConfThreshold harvested its margin histogram from pass 2's own backprop samples. Pairing every fit against the same era's OOS result shows what that measured: PAI era 1 IS 25% cov @ 66.1% (-0.8pp) -> OOS 64% (-3pp) gap +2.1pp PAI era 76 IS 90% cov @ 79.6% (+12.7pp) -> OOS 65% (-2pp) gap +14.6pp LSTM era 9 IS 77% cov @ 81.6% (+14.6pp) -> OOS 63% (-4pp) gap +18.6pp The gap grows monotonically while OOS stays flat, so within a handful of eras the curve stops describing behaviour on unseen bars. That is fatal here specifically, because the objective branches on the SIGN of (p - break-even): the memorized curve reads +12pp at 95% coverage, so coverage x (p - p0) correctly maximises coverage and returns ~0.02 - fire on every bar. The "p < p0 -> get more selective" branch, which is the actual regime and the entire point of 983a6a3, could never fire because IS never showed p < p0. Carve a calibration slice out of the IS span - DIR_CONF_CALIB_PCT_OF_IS, purged from backprop by one label horizon on BOTH sides (the far-side purge is not optional: without it the newest training bars carry labels partly decided by price action inside the slice, putting the memorization straight back into the curve). Score it in a new chunked pass 2.5, after pass 2 has trained and before pass 3 grades - the only position where the histogram is simultaneously not-trained-on, not-graded, and current with the weights it will be applied to. Costs 15% of the training data. Worth it beyond honesty: the deploy gate needs dirPrecPct > chance + EDGE_MIN_SIGMAS*SE, and a threshold pinned near zero dilutes any edge concentrated in the confident bars across every bar the model calls, driving dirPrecPct toward chance by construction. A threshold that can be selective is the only mechanism by which a small, concentrated edge could ever clear that gate. Also: a sparse histogram now KEEPS the previous threshold instead of resetting to 0.0. A failed measurement must not decay to the most exposed setting in the range. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-10 15:58:18 -04:00
bool cWinLong = (m_labelCacheHasValue[ci] && ci < ArraySize(m_winLongCache))
? m_winLongCache[ci] : false;
bool cWinShort = (m_labelCacheHasValue[ci] && ci < ArraySize(m_winShortCache))
? m_winShortCache[ci] : false;
bool cTradeWon = (cPred == Buy) ? cWinLong : ((cPred == Sell) ? cWinShort : false);
//--- isPrimaryBar is unconditionally true: this walk visits each bar once in chronological
//--- order, so there is no oversampled replay to correct for here.
AccumulateDirConfSample(DirectionalMargin(), cTradeWon, true);
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- Predicted-class tally and chart marker for the calibration band, which pass 1 used
//--- to compute from its own (now-removed) redundant feedForward on this same bar.
perf: pass 1 forward-passed ~40% of bars that a later pass redid anyway Pass 1 already skipped its feedForward on QUEUED bars, because pass 2 redoes them. The same argument covers two more bands it was still forwarding: OOS window (30% of bars) - pass 3 re-forwards every one of them calibration band (~10% of bars) - pass 2.5 re-forwards every one of them All three passes derive their bounds from the same helpers and apply the identical eligibility test, so the bar sets are equal by construction, not by coincidence. Only the two purge bands and the ineligible edge bars are visited in pass 1 and nowhere else - those keep their forward pass. The scan's copy was never the one that survived. Its arrow-cache write was overwritten by pass 3's (with the thresholded, post-training decision), its status-label paint was transient, and its predicted-class tally measured last era's weights. Those tallies move to pass 2.5 and pass 3, on the raw argmax exactly as pass 1 and pass 2 count it, so the population behind the panel's "Predicted -> Buy/Sell/Neutral" line is unchanged and stays comparable with the "Actual" line beside it, which pass 1 still accumulates over every labelled bar. Verified unaffected by the cut: dPrevSignal and m_lastBarTime are both written last by bars 0/1, which are label-ineligible and therefore still forwarded, so FinalizeTrainRun's `dtStudied = m_lastBarTime` and Lifecycle's newBarPending sentinel read the same values as before. Correctness, not just speed: batch norm is UNFROZEN during pass 1 (passes 2.5 and 3 freeze it deliberately), so every scan-time forward on a held-out bar was advancing the BN running mean/variance from data the model is graded on. Those running statistics are inference-time model state. It is the mild, unsupervised kind of leakage - feature statistics, not labels - but it fed the weights pass 3 then scored, and it is now gone. Cost: ~40% of all bars lose one forward pass per era, ~16% of net time once pass 2's backward pass is weighted in. Per-dispatch, so it lands on every backend. Both variants compile 0 errors / 0 warnings. Build tag scan-nofwd-v5. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-11 16:50:14 -04:00
switch(cPred)
{
case Buy:
m_countBuySignals++;
break;
case Sell:
m_countSellSignals++;
break;
default:
m_countNeutralSignals++;
break;
}
datetime cBarTime = m_Time.GetData(ci);
if(ci > 0)
{
// NMS on: record only (the era-end sweep renders); off: draw inline. See pass 1's note.
if(m_signalClusterWindow > 0)
{
if(ci < ArraySize(m_arrowSignalCache))
m_arrowSignalCache[ci] = cSignal;
}
else
if(cPred == Neutral)
DeleteObject(cBarTime);
else
feat(chart): signal marks become price LEVELS at the trigger, not arrows beside the candle User request: 'move from arrows on lows and highs to small horizontal lines at the actual prices the entry/exit would trigger, just a bit larger than the candles. dark green for buy, dark red for sell.' Every mark is now an OBJ_TREND segment with both anchors at one price and both rays off, spanning 1.3 bar widths, drawn at the bar's CLOSE - the price a market order actually fires at, and the exact entry TripleBarrierLabel assumes. It used to sit on the candle's LOW for a Buy and its HIGH for a Sell: prices the trade never touches, picked so an arrow glyph would clear the candle. The tooltip now carries that price too. COLOUR NOW MEANS DIRECTION AND ONLY DIRECTION on every layer (dark green / dark red). Layer moves to width+style - the traded vote is solid and thick and drawn in front, a single model's raw opinion is thin, dotted and behind the candles - which keeps the distinction the old palette existed to draw (a model's opinion must never read as a trade) while freeing colour to say one thing consistently. Consequences handled, all of them the same 'a typed scan went blind' failure: - SaveChartSignals filtered OBJPROP_TYPE == OBJ_ARROW and read OBJPROP_ARROWCODE. It now filters OBJ_TREND and recovers direction from the colour. The sidecar keeps the old 217/218 numbers as its buy/sell token deliberately, so existing .arrows files still load. - AdvanceChartSignalRestore now rebuilds through the SAME creation point the live path uses, so a restored mark and a fresh one are identical objects. - The rescan-scoped delete enumerated ObjectsTotal(OBJ_ARROW) - retyped, or it silently deletes nothing. - ApplySignalsVisibility enumerated OBJ_ARROW with NO prefix filter. Under the new type that would have hidden and shown THE USER'S OWN trend lines on every Hide/Show click; it is now prefix-scoped. The old type was uncommon enough on a real chart to mask the missing check - trend lines are the most hand-drawn object there is. - DrawObject's high/low parameters are gone (6 call sites pass m_Close instead), so no caller can hand it a price it no longer draws at. - Fixed a pre-existing stale comment that still described the purge sweep as OBJ_ARROW-only three lines above the note explaining it had been widened to every type. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-19 14:11:49 -04:00
DrawObject(cBarTime, cSignal, m_Close.GetData(ci));
perf: pass 1 forward-passed ~40% of bars that a later pass redid anyway Pass 1 already skipped its feedForward on QUEUED bars, because pass 2 redoes them. The same argument covers two more bands it was still forwarding: OOS window (30% of bars) - pass 3 re-forwards every one of them calibration band (~10% of bars) - pass 2.5 re-forwards every one of them All three passes derive their bounds from the same helpers and apply the identical eligibility test, so the bar sets are equal by construction, not by coincidence. Only the two purge bands and the ineligible edge bars are visited in pass 1 and nowhere else - those keep their forward pass. The scan's copy was never the one that survived. Its arrow-cache write was overwritten by pass 3's (with the thresholded, post-training decision), its status-label paint was transient, and its predicted-class tally measured last era's weights. Those tallies move to pass 2.5 and pass 3, on the raw argmax exactly as pass 1 and pass 2 count it, so the population behind the panel's "Predicted -> Buy/Sell/Neutral" line is unchanged and stays comparable with the "Actual" line beside it, which pass 1 still accumulates over every labelled bar. Verified unaffected by the cut: dPrevSignal and m_lastBarTime are both written last by bars 0/1, which are label-ineligible and therefore still forwarded, so FinalizeTrainRun's `dtStudied = m_lastBarTime` and Lifecycle's newBarPending sentinel read the same values as before. Correctness, not just speed: batch norm is UNFROZEN during pass 1 (passes 2.5 and 3 freeze it deliberately), so every scan-time forward on a held-out bar was advancing the BN running mean/variance from data the model is graded on. Those running statistics are inference-time model state. It is the mild, unsupervised kind of leakage - feature statistics, not labels - but it fed the weights pass 3 then scored, and it is now gone. Cost: ~40% of all bars lose one forward pass per era, ~16% of net time once pass 2's backward pass is weighted in. Per-dispatch, so it lands on every backend. Both variants compile 0 errors / 0 warnings. Build tag scan-nofwd-v5. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-11 16:50:14 -04:00
}
fix: the operating point was fitted on bars the net had memorized FitDirConfThreshold harvested its margin histogram from pass 2's own backprop samples. Pairing every fit against the same era's OOS result shows what that measured: PAI era 1 IS 25% cov @ 66.1% (-0.8pp) -> OOS 64% (-3pp) gap +2.1pp PAI era 76 IS 90% cov @ 79.6% (+12.7pp) -> OOS 65% (-2pp) gap +14.6pp LSTM era 9 IS 77% cov @ 81.6% (+14.6pp) -> OOS 63% (-4pp) gap +18.6pp The gap grows monotonically while OOS stays flat, so within a handful of eras the curve stops describing behaviour on unseen bars. That is fatal here specifically, because the objective branches on the SIGN of (p - break-even): the memorized curve reads +12pp at 95% coverage, so coverage x (p - p0) correctly maximises coverage and returns ~0.02 - fire on every bar. The "p < p0 -> get more selective" branch, which is the actual regime and the entire point of 983a6a3, could never fire because IS never showed p < p0. Carve a calibration slice out of the IS span - DIR_CONF_CALIB_PCT_OF_IS, purged from backprop by one label horizon on BOTH sides (the far-side purge is not optional: without it the newest training bars carry labels partly decided by price action inside the slice, putting the memorization straight back into the curve). Score it in a new chunked pass 2.5, after pass 2 has trained and before pass 3 grades - the only position where the histogram is simultaneously not-trained-on, not-graded, and current with the weights it will be applied to. Costs 15% of the training data. Worth it beyond honesty: the deploy gate needs dirPrecPct > chance + EDGE_MIN_SIGMAS*SE, and a threshold pinned near zero dilutes any edge concentrated in the confident bars across every bar the model calls, driving dirPrecPct toward chance by construction. A threshold that can be selective is the only mechanism by which a small, concentrated edge could ever clear that gate. Also: a sparse histogram now KEEPS the previous threshold instead of resetting to 0.0. A failed measurement must not decay to the most exposed setting in the range. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-10 15:58:18 -04:00
}
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
} // end direction (non-meta) calibration body
fix(deinit): vote arrows survived the cheap sweep, and 5 long loops ignored the stop Leftover chart objects on long-history charts. Two causes, one of them introduced by 07aa017. THE ONE I ADDED. The filtered view's overlay draws up to SIGNAL_RESCAN_LOOKBACK_BARS vote arrows. OnDeinit's EARLY VISIBLE-UI SWEEP runs with skipArrows=true, which skips any prefix equal to SIG_ARROW_PREFIX - and "WarSig_VOTE_..." starts with "WarSig_", so every one of them was skipped by the one sweep that is cheap enough to always complete. They then sat in the object list while the two expensive scans that follow walked it: a per-member SaveChartSignals O(total) scan, then the by-name rescan. On a chart with years of history that is thousands of extra objects walked twice, inside a teardown budget measured from the stop REQUEST rather than from OnDeinit's first line. skipArrows exists because the per-model arrows' sidecar is rebuilt by SCANNING them off the chart, so they cannot be deleted before that write. Vote arrows have no sidecar - they are a reconstruction, rebuilt on the next attach - so nothing is preserving them and they now get their own prefix slot, deleted by one native call in the first few milliseconds. THE FIVE LOOPS. A time budget bounds THROUGHPUT, not latency to an unload, and OnDeinit cannot begin until whatever is in flight returns. These all scaled with history and none of them checked: * Training passes 2, 2.5 and 3 yielded only on TRAIN_TIME_BUDGET_MS. Pass 1 has checked IsStopped() all along; the other three never have, and they are the ones that grow with the bar count. Free to fix - the resume state is written either way, so a stopped chunk simply is not re-entered. * PruneDirectionalClusters: the one UNCHUNKED sweep left, once per era over every bar, with its own header noting that raising the training budget cannot help its cost. Now bails outright. * AdvanceChartSignalRestore / AdvanceChartSignalRescan: chunked, but the rescan runs a full feedForward per bar over up to 5000 bars and the restore can hold MAX_RESTORED_ARROWS entries. Checked on the same 64-object stride as the clock read, since the check is not free either. * AdvanceFilteredOverlay (mine, 07aa017) replays Direction() on every classic filter per bar and had no check at all. Now per bar. ChartUI.mqh had ZERO shutdown checks across six loops before this. Nothing was added to the purge path itself: that is the work that must complete, and an IsStopped() check inside it would abort unconditionally - IsStopped() is already true by the time OnDeinit runs. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 17:13:50 -04:00
//--- Time OR stop - see pass 2's matching comment.
fix(training): the wall-clock budget was left behind in Train() Compile error, four sites: TRAIN_TIME_BUDGET_MS was a const local to Train(), and the four passes that yield on it are now defined above Train(). I checked every pass for the eight locals STrainEra replaced and missed the ninth, because it was a const rather than a variable. It is per-call state like everything else in STrainEra, so it moves there as budgetMs. All four sites asked the same question the same way GetTickCount() - era.chunkStartTick >= TRAIN_TIME_BUDGET_MS so the struct answers it once as BudgetSpent(). Swept for the same class of mistake rather than waiting for another compile: Train() now has exactly two top-level locals left (STABILITY_WINDOW, STABILITY_TOLERANCE) and neither appears in any extracted body. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:40:15 -04:00
if(m_calibIndex - 1 >= calibLo && (IsStopped() || era.BudgetSpent()))
fix: the operating point was fitted on bars the net had memorized FitDirConfThreshold harvested its margin histogram from pass 2's own backprop samples. Pairing every fit against the same era's OOS result shows what that measured: PAI era 1 IS 25% cov @ 66.1% (-0.8pp) -> OOS 64% (-3pp) gap +2.1pp PAI era 76 IS 90% cov @ 79.6% (+12.7pp) -> OOS 65% (-2pp) gap +14.6pp LSTM era 9 IS 77% cov @ 81.6% (+14.6pp) -> OOS 63% (-4pp) gap +18.6pp The gap grows monotonically while OOS stays flat, so within a handful of eras the curve stops describing behaviour on unseen bars. That is fatal here specifically, because the objective branches on the SIGN of (p - break-even): the memorized curve reads +12pp at 95% coverage, so coverage x (p - p0) correctly maximises coverage and returns ~0.02 - fire on every bar. The "p < p0 -> get more selective" branch, which is the actual regime and the entire point of 983a6a3, could never fire because IS never showed p < p0. Carve a calibration slice out of the IS span - DIR_CONF_CALIB_PCT_OF_IS, purged from backprop by one label horizon on BOTH sides (the far-side purge is not optional: without it the newest training bars carry labels partly decided by price action inside the slice, putting the memorization straight back into the curve). Score it in a new chunked pass 2.5, after pass 2 has trained and before pass 3 grades - the only position where the histogram is simultaneously not-trained-on, not-graded, and current with the weights it will be applied to. Costs 15% of the training data. Worth it beyond honesty: the deploy gate needs dirPrecPct > chance + EDGE_MIN_SIGMAS*SE, and a threshold pinned near zero dilutes any edge concentrated in the confident bars across every bar the model calls, driving dirPrecPct toward chance by construction. A threshold that can be selective is the only mechanism by which a small, concentrated edge could ever clear that gate. Also: a sparse histogram now KEEPS the previous threshold instead of resetting to 0.0. A failed measurement must not decay to the most exposed setting in the range. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-10 15:58:18 -04:00
{
//--- yield: m_isCalibActive + m_calibIndex carry the resume position, same as passes 1-3.
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
StashEraResume(era.bars, era.totalIter, era.oosCutoff, era.addLoop, era.i);
fix: the operating point was fitted on bars the net had memorized FitDirConfThreshold harvested its margin histogram from pass 2's own backprop samples. Pairing every fit against the same era's OOS result shows what that measured: PAI era 1 IS 25% cov @ 66.1% (-0.8pp) -> OOS 64% (-3pp) gap +2.1pp PAI era 76 IS 90% cov @ 79.6% (+12.7pp) -> OOS 65% (-2pp) gap +14.6pp LSTM era 9 IS 77% cov @ 81.6% (+14.6pp) -> OOS 63% (-4pp) gap +18.6pp The gap grows monotonically while OOS stays flat, so within a handful of eras the curve stops describing behaviour on unseen bars. That is fatal here specifically, because the objective branches on the SIGN of (p - break-even): the memorized curve reads +12pp at 95% coverage, so coverage x (p - p0) correctly maximises coverage and returns ~0.02 - fire on every bar. The "p < p0 -> get more selective" branch, which is the actual regime and the entire point of 983a6a3, could never fire because IS never showed p < p0. Carve a calibration slice out of the IS span - DIR_CONF_CALIB_PCT_OF_IS, purged from backprop by one label horizon on BOTH sides (the far-side purge is not optional: without it the newest training bars carry labels partly decided by price action inside the slice, putting the memorization straight back into the curve). Score it in a new chunked pass 2.5, after pass 2 has trained and before pass 3 grades - the only position where the histogram is simultaneously not-trained-on, not-graded, and current with the weights it will be applied to. Costs 15% of the training data. Worth it beyond honesty: the deploy gate needs dirPrecPct > chance + EDGE_MIN_SIGMAS*SE, and a threshold pinned near zero dilutes any edge concentrated in the confident bars across every bar the model calls, driving dirPrecPct toward chance by construction. A threshold that can be selective is the only mechanism by which a small, concentrated edge could ever clear that gate. Also: a sparse histogram now KEEPS the previous threshold instead of resetting to 0.0. A failed measurement must not decay to the most exposed setting in the range. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-10 15:58:18 -04:00
return;
}
}
Net.SetBatchNormFrozen(false);
//--- An empty band (era too short to carve one - see CalibBandBars) means there is no measurement
//--- this era, which is not the same as a measurement that says "trade everything". Leave the
//--- operating point exactly where the last successful fit put it rather than refitting on nothing.
if(calibHi > calibLo)
FitDirConfThreshold();
m_isCalibActive = false;
m_isCalibDone = true;
}
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
}
//+------------------------------------------------------------------+
//| PASS 3: SCORE THE OUT-OF-SAMPLE SPAN. |
//| |
//| Walks the OOS bars with batch-norm frozen (scoring must not move |
//| the running statistics - live adaptation is untouched), then runs |
//| the reports that read the walk it just finished: exit-policy |
//| simulation, candidate geometry, excursions, cluster pruning, tier |
//| re-ranking, drift and the Alglib baselines. |
//| |
//| It MEASURES. Nothing here decides anything - the recall gate, the |
//| plateau ladder, the deploy gate and the era checkpoint all read |
//| these numbers afterwards, back in Train(). |
//| |
//| Guarded on era.addLoop: a chunk that ran out of wall-clock budget |
//| mid-era has no complete era to score. |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::RunOosPass(STrainEra &era)
{
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
if(!era.stop && era.addLoop)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
if(!m_isPass3Active)
{
m_isPass3Active = true;
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- Freeze batch-norm running statistics for the whole scoring walk (2026-08-09 audit,
//--- F5). Same reasoning (and same mechanism) as ValidateCpuInference. Live/online
//--- adaptation is untouched - only scoring is frozen.
fix: training-stability audit fixes F1/F2/F3/F5 - unbiased shuffle, real plateau escapes, fresh optimizer state on restore, pure OOS metric Four of the six findings from research/training_pipeline_audit_2026-08-09.md (F4 mini-batching and F6 feature re-encode deliberately deferred - see the report's implementation-status section for why): - F1: pass-2 Fisher-Yates (and AutoTune's MI block shuffle) used MathRand()%, which is 15-bit - provably non-uniform on every full-history era over 32,768 queued samples. New 30-bit ShuffleRandomIndex(). - F2: plateau warm restarts were a no-op whenever eta already sat at its ceiling (the normal state of a non-regressing plateau) - the ladder was just a 24-era countdown. Restarts now overshoot to 5x the ceiling (PLATEAU_RESTART_BOOST) and anneal geometrically back over the patience window, SGDR-style; ETA_MIN widened 1e-4 -> 1e-5 so the decay schedule has real range. - F3: checkpoint restores put weights back but kept the rejected trajectory's Adam moments, so the optimizer immediately pushed back toward the rolled-back state (the restore->regress->restore oscillation). CNet::ResetOptimizerState() zeroes moments/momentum/step counters (weights, BN statistics, gamma/beta untouched) on every mid-run restore, every boosted restart, and the deploy-time restore that online learning continues from. - F5: batch-norm running statistics now freeze for the pass-3 OOS scoring walk, so the selection metric the checkpoint ranking and deploy gate read is a pure function of the checkpoint instead of partly measuring BN drift. Defensive unfreeze in FinalizeTrainRun covers stop-mid-pass; live/online adaptation and the OOS continual-learning simulation stay adaptive by design. Compiled clean (0 errors, 0 warnings) via the staged-tree recipe. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 10:54:09 -04:00
Net.SetBatchNormFrozen(true);
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
m_oosScoreStartIndex = (int)MathMin(era.oosCutoff - 1, era.bars - MathMax(m_historyBars, 0) - 2);
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
m_oosScoreIndex = m_oosScoreStartIndex;
for(int rn = 0; rn < 3; rn++)
{
m_oosOutMin[rn] = DBL_MAX;
m_oosOutMax[rn] = -DBL_MAX;
}
m_oosOutSpreadSum = 0.0;
m_oosOutCount = 0;
feat(diagnostics): split a reported "Neutral" into CHOSE vs TIED - they need opposite fixes ApplyClassificationSoftmax() requires a STRICT majority over both rivals and sends every tie, 2-way or 3-way, to Neutral. So "OOS recall Neutral:100%" is two completely different events sharing one label: CHOSE - the net genuinely ranks Neutral highest. A class-prior/label problem. TIED - the top two are EXACTLY equal, so the net expressed no preference and the tie-break reported Neutral. A SATURATION problem: the head is SIGMOID, and a saturated sigmoid returns exactly 0.0f or 1.0f in the DLL's float32, so two classes pinned to the same rail compare equal and the bar is silently discarded. Nothing in the logs could tell them apart, and the fixes point opposite ways. Eras 1-25 of the 2026-08-17 solo PAI run read "Neutral 100%" at spread avg 0.99 - fully saturated - and broke out at era 27 as the spread fell to 0.75. That is consistent with EITHER story. The user reports the Neutral phase on most runs, so it is worth four longs to stop guessing. Four per-era counters on the pass 3 OOS walk, reported as: | Neutral CHOSE 12.4% / TIED 38.1% (of which B=S 1204) | rail 61.2% m_oosNeutralStrict - Neutral strictly highest m_oosNeutralTie - no strict winner; the tie-break produced Neutral m_oosTieBuySell - the costly subset: Buy and Sell tied AT the top, i.e. a DIRECTIONAL reading thrown away by float equality m_oosRailBars - any raw output sitting on a sigmoid asymptote, the saturation that makes exact ties possible at all Read on the RAW logits, before ApplyClassificationSoftmax() overwrites TempData in place. Legitimate because softmax is strictly monotone: it cannot change the ordering and cannot break a tie either, so the raw reading and the decision always agree. Placed alongside the existing min/max/spread capture so all the output diagnostics describe the same values. Measurement only - no decision path reads these. NOT COMPILED - user compiles. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-17 00:06:54 -04:00
m_oosNeutralStrict = 0;
m_oosNeutralTie = 0;
m_oosTieBuySell = 0;
m_oosRailBars = 0;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
fix(gate): move the ranking slice to the OLD end - it walled off the recent chart NOT COMPILED - user compiles. User: "there is quite some trading going on, but absolutely nothing on the recent area of the chart, like there is a hard wall starting around november 2025." That wall is 7caf2f6's ranking slice, and it was placed at the wrong end. Chart arrows are only ever drawn on bars pass 3 GRADES, and the slice reserved the NEWEST 20% of the OOS window plus a label-horizon purge. At the live sizing - ~4,860 OOS bars, 128-bar horizon - that is ~1,100 H4 bars withheld from grading, about ten months back from today, exactly where the wall appears. The invisible cost was worse than the visible one: it handed the deploy gate the OLDEST 80% of the OOS window and withheld the most recent regime from the single decision that has to generalise forward. Both fixed by putting the reserve at the oldest end instead: [0, oosScoreHi) OOS - graded by pass 3 (NEWEST, arrows restored) [oosScoreHi, rankLo) purge - one label horizon [rankLo, oosCutoff) RANKING - backfill only, graded by nobody [oosCutoff, calibLo) purge [calibLo, calibHi) CALIBRATION ... IS Of the three consumers competing for those bars, recency is worth least to the ranking: it is an ORDERING of confidence tiers, far less regime-sensitive than an absolute win rate, while the gate's power and the operator's read of the chart both want the newest data. The slice keeps every property that made it worth carving - never graded, never selected on, never seen by the gate, purged on both sides - so the backfilled rows are still honestly out-of-sample. RankSliceHiIndex is replaced by RankSliceLoIndex + OosScoreHiIndex; pass 3 now excludes the slice at the TOP of its walk and descends to 2 as it always did. The backfill walks [RankSliceLoIndex, oosCutoff) via a new m_dbBackfillStopIndex, clamped at both ends so a degenerate slice yields an empty walk rather than one that wanders into graded bars. Verified no reference to the old helper survives. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-16 22:58:55 -04:00
for(; m_oosScoreIndex >= 2; m_oosScoreIndex--)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
int oi = m_oosScoreIndex;
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
if(!(oi < (int)(era.bars - MathMax(m_historyBars, 0) - 1) && m_Time.GetData(oi) > dtStudied))
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
continue;
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
TrainHeartbeat("pass 3 (OOS scoring), bar", m_oosScoreStartIndex - m_oosScoreIndex + 1,
fix: the panel showed "100%" for the whole of pass 1 The simple panel derived its percentage from pass 2's counters: (m_isTrainCursor+1) / max(m_isTrainQueueCount,1). During pass 1 those are 0 and 0, so the expression is (0+1)/max(0,1) = 100%. An era spends its first pass scanning ~38k bars - minutes of work - and the panel reported that phase as finished the entire time. Observed by the user as "started learning at 100% of their era and are stuck there", and it actively misled the diagnosis: the one number on screen said the opposite of what was happening. The UI cannot fix this on its own - it can see pass 2's counters but has no way to know which pass owns them. So each pass now PUBLISHES its own progress and a short phase name through TrainHeartbeat (which every pass already calls per item), and the panel just displays them: "learning (era 45, scan 34%)". Published before the heartbeat's 4096-item journal gate, so the panel updates continuously while the journal stays quiet. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 07:22:29 -04:00
m_oosScoreStartIndex + 1, "scoring");
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
//--- META TARGET OOS scoring, one row per candidate, feeding the SAME members the era-end
//--- selection/deploy block reads - under the win->Buy / loss->Sell mapping (pass 1 comment)
//--- every downstream figure keeps a correct meta meaning:
//--- dirPrecPct = wins among candidates the operating point trades (the win rate)
//--- chancePrec = base win rate of ALL candidates (always-call zero-skill reference,
//--- which under cost-charged win-counting IS the break-even coincidence
//--- the 2026-08-09 note below derives)
//--- coveragePct = fraction of candidates traded
//--- buy/sell recall = sensitivity/specificity, so bothSidesLive rejects the
//--- always-call and never-call collapses
//--- so checkpoint selection, the edge floor's standard error, the plateau ladder and the
//--- family-wise deploy gate all run UNCHANGED on the meta head.
if(IsMetaTarget())
{
for(int cd = MetaCandFirst(oi); cd >= 0; cd = MetaCandNext(cd))
{
ulong hbM = GetMicrosecondCount();
bool mWindowOk = BuildFeatureWindow(oi);
if(mWindowOk)
AppendCandidateFeatures(cd);
m_passFeatUs += GetMicrosecondCount() - hbM;
hbM = GetMicrosecondCount();
bool mForwardOk = (mWindowOk && TempData.Total() >= NetInputWidth() &&
Net.feedForward(TempData));
m_passNetUs += GetMicrosecondCount() - hbM;
if(!mForwardOk)
{
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
if(mWindowOk && !era.forwardFailureReported)
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
{
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
era.forwardFailureReported = true;
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
Print(__FUNCTION__ + ": CNet::feedForward FAILED during meta OOS scoring at era " +
IntegerToString((int)m_eraCount) + " - affected candidates are excluded.");
}
break;
}
Net.getResults(TempData);
double oPwin = MetaWinProbability();
bool oWon = MetaCandidateWon(cd, oi);
bool oCall = (oPwin >= 0.5); // the 2-class argmax
bool oHit = (oCall == oWon);
m_oosSamples++;
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.confidenceSum += oPwin;
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
if(dOosError < 0)
dOosError = 0;
//--- mapped confusion counts (recall gate + balanced-accuracy diagnostics)
if(oWon)
{
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.buyTotal++;
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
if(oHit)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.buyHits++;
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
//--- the always-call reference wins exactly when the candidate wins
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.winLongTotal++;
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
}
else
{
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.sellTotal++;
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
if(oHit)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.sellHits++;
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
}
//--- predicted-keyed tallies (panel Called/precision diagnostics)
if(oCall)
{
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.buyPredicted++;
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
if(oHit)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.buyPredictedHits++;
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
if(oWon)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.buyPredictedWins++;
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
m_countBuySignals++;
//--- persistent OOS precision over called candidates, in WINS (matches the IS side)
m_cumOosTotal++;
if(oWon)
m_cumOosCorrect++;
}
else
{
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.sellPredicted++;
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
if(oHit)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.sellPredictedHits++;
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
m_countSellSignals++;
}
//--- THE POPULATION THAT TRADES: candidates clearing the fitted operating point - what
//--- the deployability gate and selection score actually read (see the era-end block).
feat: per-family x per-side OOS breakdown in the META era report 350-era S2 verdict on SP500 H1: the meta head carries REAL ranking skill (+1.0-1.3pp mean over base, 101/350 eras clear their own 2-sigma bar, traded subset wins 66.1% at <30% coverage vs 64.5% base) but 0/350 eras produced a positive cov x (p - BE): the candidate stream sits 3pp under the derived geometry's 67.5% break-even and ~2.6pp of recovered skill cannot bridge it. Skill plateaued by mid-run (1.28pp -> 1.05pp), so more eras only buy multiplicity, and the deploy gate correctly shipped nothing. The aggregate can hide a deployable subset (one family/side clearing BE blended with junk), so the META era line now decomposes the SAME traded population into MA/RSI/MACD/Ichimoku x LONG/SHORT cells, each as traded/candidates base->traded win rate. 32 cells is a best-of-N search by construction - any candidate cell faces the family-wise rule before belief. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 09:03:40 -04:00
bool oFired = (oPwin >= m_dirConfThreshold);
if(oFired)
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
{
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.buyFired++;
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
if(oWon)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.buyFiredHits++;
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
}
feat: per-family x per-side OOS breakdown in the META era report 350-era S2 verdict on SP500 H1: the meta head carries REAL ranking skill (+1.0-1.3pp mean over base, 101/350 eras clear their own 2-sigma bar, traded subset wins 66.1% at <30% coverage vs 64.5% base) but 0/350 eras produced a positive cov x (p - BE): the candidate stream sits 3pp under the derived geometry's 67.5% break-even and ~2.6pp of recovered skill cannot bridge it. Skill plateaued by mid-run (1.28pp -> 1.05pp), so more eras only buy multiplicity, and the deploy gate correctly shipped nothing. The aggregate can hide a deployable subset (one family/side clearing BE blended with junk), so the META era line now decomposes the SAME traded population into MA/RSI/MACD/Ichimoku x LONG/SHORT cells, each as traded/candidates base->traded win rate. 32 cells is a best-of-N search by construction - any candidate cell faces the family-wise rule before belief. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 09:03:40 -04:00
//--- per-family / per-side decomposition of the same population (see the declaration)
refactor(meta): the era's candidates are an object, not eight base members Five parallel arrays, a count and a two-array intrusive chain sat on CExpertSignalAIBase - inherited by every direction model, filled and read by exactly one subclass. CMetaCandidateStore takes all eight. What that fixes beyond the clutter: - THE CHAIN WAS LINKED BY HAND. MetaPrepareEra wrote next[id] = head[bar] then head[bar] = id itself, after six ArrayResize calls it also wrote out itself. Add() does the linking, Reset() does the sizing, and a bar off the grid now cannot be stored at all rather than stored unreachable. - THE BOUNDS TEST HAD FOUR SITES AND THREE IMPLEMENTATIONS. MetaCandidateWon indexed side[] with no test at all and answered "short" for any id out of range - the same shape as the ladder's negative-index read (2c351a0). Side() is three-state here, IsLong() and SideIndex() are the safe ways to ask, and the per-side era tally in RunOosPass is now guarded exactly like the per-family one beside it, which always was. Like the ladder and the OOS tally, none of it needs a chart, a net or a broker: hand it bars and rows and every answer is a function of those. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 15:36:31 -04:00
int oFam = (int)m_metaCands.Family(cd);
int oSideIdx = m_metaCands.SideIndex(cd);
feat: per-family x per-side OOS breakdown in the META era report 350-era S2 verdict on SP500 H1: the meta head carries REAL ranking skill (+1.0-1.3pp mean over base, 101/350 eras clear their own 2-sigma bar, traded subset wins 66.1% at <30% coverage vs 64.5% base) but 0/350 eras produced a positive cov x (p - BE): the candidate stream sits 3pp under the derived geometry's 67.5% break-even and ~2.6pp of recovered skill cannot bridge it. Skill plateaued by mid-run (1.28pp -> 1.05pp), so more eras only buy multiplicity, and the deploy gate correctly shipped nothing. The aggregate can hide a deployable subset (one family/side clearing BE blended with junk), so the META era line now decomposes the SAME traded population into MA/RSI/MACD/Ichimoku x LONG/SHORT cells, each as traded/candidates base->traded win rate. 32 cells is a best-of-N search by construction - any candidate cell faces the family-wise rule before belief. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 09:03:40 -04:00
if(oFam >= 0 && oFam < 4)
{
m_metaFamCand[oFam]++;
if(oWon)
m_metaFamWins[oFam]++;
if(oFired)
{
m_metaFamFired[oFam]++;
if(oWon)
m_metaFamFiredWins[oFam]++;
}
}
refactor(meta): the era's candidates are an object, not eight base members Five parallel arrays, a count and a two-array intrusive chain sat on CExpertSignalAIBase - inherited by every direction model, filled and read by exactly one subclass. CMetaCandidateStore takes all eight. What that fixes beyond the clutter: - THE CHAIN WAS LINKED BY HAND. MetaPrepareEra wrote next[id] = head[bar] then head[bar] = id itself, after six ArrayResize calls it also wrote out itself. Add() does the linking, Reset() does the sizing, and a bar off the grid now cannot be stored at all rather than stored unreachable. - THE BOUNDS TEST HAD FOUR SITES AND THREE IMPLEMENTATIONS. MetaCandidateWon indexed side[] with no test at all and answered "short" for any id out of range - the same shape as the ladder's negative-index read (2c351a0). Side() is three-state here, IsLong() and SideIndex() are the safe ways to ask, and the per-side era tally in RunOosPass is now guarded exactly like the per-family one beside it, which always was. Like the ladder and the OOS tally, none of it needs a chart, a net or a broker: hand it bars and rows and every answer is a function of those. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 15:36:31 -04:00
//--- guarded like the family block above: SideIndex is -1 for an id that is not a
//--- candidate, and the old `side > 0 ? 0 : 1` had no third answer to guard.
if(oSideIdx >= 0 && oSideIdx < 2)
feat: per-family x per-side OOS breakdown in the META era report 350-era S2 verdict on SP500 H1: the meta head carries REAL ranking skill (+1.0-1.3pp mean over base, 101/350 eras clear their own 2-sigma bar, traded subset wins 66.1% at <30% coverage vs 64.5% base) but 0/350 eras produced a positive cov x (p - BE): the candidate stream sits 3pp under the derived geometry's 67.5% break-even and ~2.6pp of recovered skill cannot bridge it. Skill plateaued by mid-run (1.28pp -> 1.05pp), so more eras only buy multiplicity, and the deploy gate correctly shipped nothing. The aggregate can hide a deployable subset (one family/side clearing BE blended with junk), so the META era line now decomposes the SAME traded population into MA/RSI/MACD/Ichimoku x LONG/SHORT cells, each as traded/candidates base->traded win rate. 32 cells is a best-of-N search by construction - any candidate cell faces the family-wise rule before belief. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 09:03:40 -04:00
{
refactor(meta): the era's candidates are an object, not eight base members Five parallel arrays, a count and a two-array intrusive chain sat on CExpertSignalAIBase - inherited by every direction model, filled and read by exactly one subclass. CMetaCandidateStore takes all eight. What that fixes beyond the clutter: - THE CHAIN WAS LINKED BY HAND. MetaPrepareEra wrote next[id] = head[bar] then head[bar] = id itself, after six ArrayResize calls it also wrote out itself. Add() does the linking, Reset() does the sizing, and a bar off the grid now cannot be stored at all rather than stored unreachable. - THE BOUNDS TEST HAD FOUR SITES AND THREE IMPLEMENTATIONS. MetaCandidateWon indexed side[] with no test at all and answered "short" for any id out of range - the same shape as the ladder's negative-index read (2c351a0). Side() is three-state here, IsLong() and SideIndex() are the safe ways to ask, and the per-side era tally in RunOosPass is now guarded exactly like the per-family one beside it, which always was. Like the ladder and the OOS tally, none of it needs a chart, a net or a broker: hand it bars and rows and every answer is a function of those. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 15:36:31 -04:00
m_metaSideCand[oSideIdx]++;
feat: per-family x per-side OOS breakdown in the META era report 350-era S2 verdict on SP500 H1: the meta head carries REAL ranking skill (+1.0-1.3pp mean over base, 101/350 eras clear their own 2-sigma bar, traded subset wins 66.1% at <30% coverage vs 64.5% base) but 0/350 eras produced a positive cov x (p - BE): the candidate stream sits 3pp under the derived geometry's 67.5% break-even and ~2.6pp of recovered skill cannot bridge it. Skill plateaued by mid-run (1.28pp -> 1.05pp), so more eras only buy multiplicity, and the deploy gate correctly shipped nothing. The aggregate can hide a deployable subset (one family/side clearing BE blended with junk), so the META era line now decomposes the SAME traded population into MA/RSI/MACD/Ichimoku x LONG/SHORT cells, each as traded/candidates base->traded win rate. 32 cells is a best-of-N search by construction - any candidate cell faces the family-wise rule before belief. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 09:03:40 -04:00
if(oWon)
refactor(meta): the era's candidates are an object, not eight base members Five parallel arrays, a count and a two-array intrusive chain sat on CExpertSignalAIBase - inherited by every direction model, filled and read by exactly one subclass. CMetaCandidateStore takes all eight. What that fixes beyond the clutter: - THE CHAIN WAS LINKED BY HAND. MetaPrepareEra wrote next[id] = head[bar] then head[bar] = id itself, after six ArrayResize calls it also wrote out itself. Add() does the linking, Reset() does the sizing, and a bar off the grid now cannot be stored at all rather than stored unreachable. - THE BOUNDS TEST HAD FOUR SITES AND THREE IMPLEMENTATIONS. MetaCandidateWon indexed side[] with no test at all and answered "short" for any id out of range - the same shape as the ladder's negative-index read (2c351a0). Side() is three-state here, IsLong() and SideIndex() are the safe ways to ask, and the per-side era tally in RunOosPass is now guarded exactly like the per-family one beside it, which always was. Like the ladder and the OOS tally, none of it needs a chart, a net or a broker: hand it bars and rows and every answer is a function of those. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 15:36:31 -04:00
m_metaSideWins[oSideIdx]++;
if(oFired)
{
m_metaSideFired[oSideIdx]++;
if(oWon)
m_metaSideFiredWins[oSideIdx]++;
}
feat: per-family x per-side OOS breakdown in the META era report 350-era S2 verdict on SP500 H1: the meta head carries REAL ranking skill (+1.0-1.3pp mean over base, 101/350 eras clear their own 2-sigma bar, traded subset wins 66.1% at <30% coverage vs 64.5% base) but 0/350 eras produced a positive cov x (p - BE): the candidate stream sits 3pp under the derived geometry's 67.5% break-even and ~2.6pp of recovered skill cannot bridge it. Skill plateaued by mid-run (1.28pp -> 1.05pp), so more eras only buy multiplicity, and the deploy gate correctly shipped nothing. The aggregate can hide a deployable subset (one family/side clearing BE blended with junk), so the META era line now decomposes the SAME traded population into MA/RSI/MACD/Ichimoku x LONG/SHORT cells, each as traded/candidates base->traded win rate. 32 cells is a best-of-N search by construction - any candidate cell faces the family-wise rule before belief. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 09:03:40 -04:00
}
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
if(oHit)
{
dOosForecast += (100 - dOosForecast) / Net.recentAverageSmoothingFactor;
dOosError -= dOosError / Net.recentAverageSmoothingFactor;
}
else
{
dOosForecast -= dOosForecast / Net.recentAverageSmoothingFactor;
dOosError += (100 - dOosError) / Net.recentAverageSmoothingFactor;
}
UpdateTrainingStatusLabel(
StringFormat("Scoring OOS bar %d of %d -> %.2f%% (meta)",
m_oosScoreStartIndex - m_oosScoreIndex + 1, m_oosScoreStartIndex + 1,
(double)(m_oosScoreStartIndex - m_oosScoreIndex + 1.0) /
MathMax(m_oosScoreStartIndex + 1, 1) * 100),
(TempData.Total() > 0) ? TempData[0] : 0.0,
(TempData.Total() > 1) ? TempData[1] : 0.0, 0.0, oPwin);
}
}
else
{
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
ulong hbT = GetMicrosecondCount();
fix: the sequence models were reading the window backwards BuildFeatureWindow() replaces eight hand-rolled copies of the same loop and feeds the window OLDEST BAR FIRST. Every copy fed it newest-first, because MQL5 timeseries indices run backwards and `r + b` with b ascending walks into the past. Harmless for PAI and CONV - a dense layer learns a weight per position either way, a conv learns time-mirrored kernels. Not harmless for the recurrent stacks: - LSTM_SeqStepForward reads `inputs + t*Iw`, so step t is block t. - It writes output[] only when t == steps-1: the visible output IS the last hidden state. - c_t = f*c_{t-1} + i*g decays toward the start of the sequence. lstm_seq_flowcheck.cpp measured block 0's influence on the output at 1.2e-2 of block T-1's, at the shipped forget bias of 1.0. So the bar being PREDICTED sat at the far end of the decay and the output was handed to the OLDEST bar in the window - the exact inverse of what the window is for. ~80x backwards on LSTM and HYBRID, on all three tiers (OpenCL kernel, CPU DLL, pure-MQL5 inference), which is why it never surfaced as a backend discrepancy. This does not create edge - the MI diagnostics read at the noise floor (p=0.4975) with a working positive control. It makes the one hypothesis those diagnostics explicitly do NOT cover testable: they are marginal and per-bar, and state they "cannot rule out one that only exists in combination or across time". The sequence model is the instrument for across-time structure and it has been crippled, so that hypothesis has never been honestly tested. Fingerprint gets an unconditional |WIN:2 - the vector keeps its shape and its features, so a stale .nnw would load cleanly and run a model fitted to one ordering against the other, silently. Re-keying every config is the point, not collateral damage. FORCES A FULL RETRAIN. Also: the now-relative bar caches are re-keyed on the two live paths. EnsureBarCachesCapacity() was only ever called from training paths, but once m_trainingComplete is set ScheduleTrainingIfNeeded() routes every bar to RefreshConvergedSignal() and Train() is never re-entered - so nothing cleared the feature cache again for the life of the process. A chart that trained to convergence kept replaying the rows computed for the last training era's bar grid: the live signal froze at its convergence-time value, and OnlineLearnStep() backpropped those stale features against freshly resolved labels. Backtests were never affected (an inference-only process never allocates the arrays, so every read recomputes). Compiles clean: 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-07 18:28:44 -04:00
bool oWindowOk = BuildFeatureWindow(oi);
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
m_passFeatUs += GetMicrosecondCount() - hbT;
fix: improve error messages and suppress false sharing-violation logs - BufferDouble: replace hardcoded "DirectML/CPU-DLL" with dynamic backend name and add buffer index/element count to all error prints for easier debugging. - NetPersistence: distinguish missing file from transient lock by probing FileIsExist before logging, eliminating false "sharing violation" warnings when no saved model exists on first run.
2026-08-02 01:09:18 -04:00
//--- Same guard as pass 2, and it matters more here: OOS accuracy is what checkpoint selection
//--- and the plateau ladder's auto-deploy both rank on, so scoring a stale forward pass would
//--- not just be wrong, it would be wrong in the one number that decides which model ships.
//--- A skipped bar simply isn't counted; it never becomes a hit or a miss.
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
hbT = GetMicrosecondCount();
fix: improve error messages and suppress false sharing-violation logs - BufferDouble: replace hardcoded "DirectML/CPU-DLL" with dynamic backend name and add buffer index/element count to all error prints for easier debugging. - NetPersistence: distinguish missing file from transient lock by probing FileIsExist before logging, eliminating false "sharing violation" warnings when no saved model exists on first run.
2026-08-02 01:09:18 -04:00
bool oForwardOk = (oWindowOk && TempData.Total() >= (int)m_historyBars * m_neuronsCount &&
Net.feedForward(TempData));
diag: slow eras must explain themselves - heartbeat + era time split + pass-1 paint The 23:42 restart left all four charts grinding ~25x slower than the 18:01 baseline (era lines in 86 seconds there; 20+ minutes of nothing here), and NOTHING could say why from outside: pass 1 logs nothing, its status paint sat inside the !wouldQueue branch so the IS sweep - 80% of the pass, processed FIRST - painted nothing either, the VPS has no debugger for a thread stack, and the hourly new-bar cache invalidation cancels and restarts an unfinished era, so a slow era can stay invisible FOREVER. Externals gave: four chart threads at ~95% pure user-mode compute, DLL pool idle, no file writes. That narrows it to "MQL5-side per-item work in the era passes" and no further. So training now explains itself: - TrainHeartbeat: one line per 4096 processed items, only after an era has already run 60s, at most 6 lines per era - a healthy era stays exactly as quiet as before. Reports position and the cumulative split: feature-window builds vs net forward/backprop vs everything else. Hooked into all three passes. - The era summary line gains "| ERA TOOK Ns (feature windows X, net fwd/back Y, other Z)" whenever an era exceeded 120s. - Pass 1 paints its progress for QUEUED bars too, not just the OOS slice, so the panel shows "learning (era N)" instead of sitting on the idle writer's "Getting ready..." for the entire IS sweep. The label is throttled internally; painting per bar costs nothing. Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-10 00:10:45 -04:00
m_passNetUs += GetMicrosecondCount() - hbT;
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
if(oWindowOk && !oForwardOk && !era.forwardFailureReported)
fix: improve error messages and suppress false sharing-violation logs - BufferDouble: replace hardcoded "DirectML/CPU-DLL" with dynamic backend name and add buffer index/element count to all error prints for easier debugging. - NetPersistence: distinguish missing file from transient lock by probing FileIsExist before logging, eliminating false "sharing violation" warnings when no saved model exists on first run.
2026-08-02 01:09:18 -04:00
{
refactor(training): Train()'s working state is one object, not eight locals Train() is not a function that trains a model - it is one STEP of a resumable state machine, called again every tick until the era ends. Eight locals carried the state from one step to the next: bars, totalIter, oosCutoff, i, add_loop, stop, chunkStartTick and the forward-failure latch. Those eight are the sole reason none of the four passes could be lifted into a method. Each would have needed eight by-reference parameters, and a pass that takes eight parameters is not a pass - it is the same function under another name. Collapse them into STrainEra. Nothing else changes: no logic, no ordering, no early return. Verified the same way as the era log - strip comments and whitespace from both revisions, map era.X back to X, and diff the remaining statements. The only differences are the five declaration lines becoming one object and two assignments losing their type. Every other statement is byte-identical. One incidental fix: a for(int i...) loop over g_warriorEnsemble shadowed the era counter. It ran before the era locals were declared so it was never a live bug, but it becomes one the moment a pass moves out. It is now mi. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:28:11 -04:00
era.forwardFailureReported = true;
fix: improve error messages and suppress false sharing-violation logs - BufferDouble: replace hardcoded "DirectML/CPU-DLL" with dynamic backend name and add buffer index/element count to all error prints for easier debugging. - NetPersistence: distinguish missing file from transient lock by probing FileIsExist before logging, eliminating false "sharing violation" warnings when no saved model exists on first run.
2026-08-02 01:09:18 -04:00
Print(__FUNCTION__ + ": CNet::feedForward FAILED during OOS scoring at era " +
IntegerToString((int)m_eraCount) + " - affected bars are excluded from the OOS"
" accuracy rather than scored against a stale prediction.");
}
if(oForwardOk)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
feat: excursion-size head (Stage 1, measurement only) Direction is closed - normalised asymmetry fails on three instruments with a working positive control, and the classifier's own best-of-999 era-cap test agrees (+0.9pp = 1.48 sigma, family-wise p=1.0000). SIZE is a different question and RANGE clears at ~4x its null. Checked the denomination before building on that, since the source memo warns to: m_excUpCache holds (maxHigh - fill)/ATR, so "RANGE is predictable" is a claim about travel RELATIVE to current ATR, not a restatement of "ATR is autocorrelated". It is exactly the part a fixed multiple (stop 3.31*ATR, target 1.64*ATR) discards. A second small CNet, 760 -> 24 -> 32 sigmoid outputs = P(price reaches ladder rung k) upward and downward. Survival parameterisation rather than regressing the multiple, because it needs nothing new from CNet: sigmoid outputs and the per-neuron delta the `total != 3` branch already applies (a quantile head would need a linear activation and a pinball gradient in Network.mqh, Network.cl and the DirectML path, on a class four topologies share). Targets are free - m_ladderUpAt already records first-touch age per rung with 0 meaning never reached. Separate net, not extra outputs on the classifier: more outputs would change m_outputNeuronsCount, the .nnw shape and the fingerprint, and push the count off 3 - the exact condition backProp uses to select the joint softmax gradient the 3-class head depends on. The classifier is bit-for-bit unaffected and this is removable without trace. STAGE 1 PLACES NO ORDERS. It reports a Brier skill score against the constant per-rung base rate - the baseline a fixed ATR multiple already assumes - with both predictors fitted IS and evaluated OOS, so neither gets a look at the test set. Positive skill justifies Stage 2 (drive SL/TP and sizing off ExcursionQuantile, which is defined and deliberately uncalled). Zero or negative means ATR already carries everything and Stage 2 must not be built. Trains only on primary occurrences: the replay queue oversamples for CLASS balance, and a direction-balanced sample is a biased SIZE sample. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-11 07:40:01 -04:00
//--- EXCURSION HEAD scored on the SAME held-out bars the classifier is graded on, and for
//--- the same reason: it never trained on them. Before getResults() overwrites TempData.
ExcursionScoreStep(oi);
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
Net.getResults(TempData);
// Raw output stats MUST be captured here, before ApplyClassificationSoftmax() overwrites
// TempData[0..2] in place with the softmax probabilities - see m_oosOutMin's declaration
// comment for what these feed.
if(m_outputNeuronsCount == 3 && TempData.Total() >= 3)
{
double rawHi = -DBL_MAX, rawLo = DBL_MAX;
for(int rn = 0; rn < 3; rn++)
{
double rv = TempData.At(rn);
if(rv < m_oosOutMin[rn])
m_oosOutMin[rn] = rv;
if(rv > m_oosOutMax[rn])
m_oosOutMax[rn] = rv;
rawHi = MathMax(rawHi, rv);
rawLo = MathMin(rawLo, rv);
}
m_oosOutSpreadSum += rawHi - rawLo;
m_oosOutCount++;
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- WHY Neutral won, split into its two causes - see m_oosNeutralStrict's
//--- declaration.
feat(diagnostics): split a reported "Neutral" into CHOSE vs TIED - they need opposite fixes ApplyClassificationSoftmax() requires a STRICT majority over both rivals and sends every tie, 2-way or 3-way, to Neutral. So "OOS recall Neutral:100%" is two completely different events sharing one label: CHOSE - the net genuinely ranks Neutral highest. A class-prior/label problem. TIED - the top two are EXACTLY equal, so the net expressed no preference and the tie-break reported Neutral. A SATURATION problem: the head is SIGMOID, and a saturated sigmoid returns exactly 0.0f or 1.0f in the DLL's float32, so two classes pinned to the same rail compare equal and the bar is silently discarded. Nothing in the logs could tell them apart, and the fixes point opposite ways. Eras 1-25 of the 2026-08-17 solo PAI run read "Neutral 100%" at spread avg 0.99 - fully saturated - and broke out at era 27 as the spread fell to 0.75. That is consistent with EITHER story. The user reports the Neutral phase on most runs, so it is worth four longs to stop guessing. Four per-era counters on the pass 3 OOS walk, reported as: | Neutral CHOSE 12.4% / TIED 38.1% (of which B=S 1204) | rail 61.2% m_oosNeutralStrict - Neutral strictly highest m_oosNeutralTie - no strict winner; the tie-break produced Neutral m_oosTieBuySell - the costly subset: Buy and Sell tied AT the top, i.e. a DIRECTIONAL reading thrown away by float equality m_oosRailBars - any raw output sitting on a sigmoid asymptote, the saturation that makes exact ties possible at all Read on the RAW logits, before ApplyClassificationSoftmax() overwrites TempData in place. Legitimate because softmax is strictly monotone: it cannot change the ordering and cannot break a tie either, so the raw reading and the decision always agree. Placed alongside the existing min/max/spread capture so all the output diagnostics describe the same values. Measurement only - no decision path reads these. NOT COMPILED - user compiles. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-17 00:06:54 -04:00
double rB = TempData.At(0), rS = TempData.At(1), rN = TempData.At(2);
bool strictB = (rB > rS && rB > rN);
bool strictS = (rS > rB && rS > rN);
bool strictN = (rN > rB && rN > rS);
if(strictN)
m_oosNeutralStrict++;
else
if(!strictB && !strictS)
{
//--- No class holds a strict majority, so the top two are EXACTLY equal and
//--- ApplyClassificationSoftmax() returns Neutral by the tie rule, not by choice.
m_oosNeutralTie++;
//--- The expensive subset: Buy and Sell tied AT the top (either a 2-way tie above
//--- Neutral, or a 3-way). The net had a directional reading and float equality
//--- threw it away.
if(rB == rS && rB >= rN)
m_oosTieBuySell++;
}
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- Sigmoid rails. The head is SIGMOID (Topology.mqh), so 0 and 1 are its
//--- asymptotes; a raw value sitting ON one in float32 is the saturation that MAKES
//--- exact ties possible.
feat(diagnostics): split a reported "Neutral" into CHOSE vs TIED - they need opposite fixes ApplyClassificationSoftmax() requires a STRICT majority over both rivals and sends every tie, 2-way or 3-way, to Neutral. So "OOS recall Neutral:100%" is two completely different events sharing one label: CHOSE - the net genuinely ranks Neutral highest. A class-prior/label problem. TIED - the top two are EXACTLY equal, so the net expressed no preference and the tie-break reported Neutral. A SATURATION problem: the head is SIGMOID, and a saturated sigmoid returns exactly 0.0f or 1.0f in the DLL's float32, so two classes pinned to the same rail compare equal and the bar is silently discarded. Nothing in the logs could tell them apart, and the fixes point opposite ways. Eras 1-25 of the 2026-08-17 solo PAI run read "Neutral 100%" at spread avg 0.99 - fully saturated - and broke out at era 27 as the spread fell to 0.75. That is consistent with EITHER story. The user reports the Neutral phase on most runs, so it is worth four longs to stop guessing. Four per-era counters on the pass 3 OOS walk, reported as: | Neutral CHOSE 12.4% / TIED 38.1% (of which B=S 1204) | rail 61.2% m_oosNeutralStrict - Neutral strictly highest m_oosNeutralTie - no strict winner; the tie-break produced Neutral m_oosTieBuySell - the costly subset: Buy and Sell tied AT the top, i.e. a DIRECTIONAL reading thrown away by float equality m_oosRailBars - any raw output sitting on a sigmoid asymptote, the saturation that makes exact ties possible at all Read on the RAW logits, before ApplyClassificationSoftmax() overwrites TempData in place. Legitimate because softmax is strictly monotone: it cannot change the ordering and cannot break a tie either, so the raw reading and the decision always agree. Placed alongside the existing min/max/spread capture so all the output diagnostics describe the same values. Measurement only - no decision path reads these. NOT COMPILED - user compiles. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-17 00:06:54 -04:00
if(rawLo <= 1e-6 || rawHi >= 1.0 - 1e-6)
m_oosRailBars++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
double oPrevSignal = (m_outputNeuronsCount == 3) ? ApplyClassificationSoftmax() : TempData[0];
double oDeploySignal = oPrevSignal;
if(m_outputNeuronsCount == 3)
oDeploySignal = AdjustedSignalFromSoftmax();
double oNeuron0 = (TempData.Total() > 0) ? TempData[0] : 0.0;
double oNeuron1 = (TempData.Total() > 1) ? TempData[1] : 0.0;
double oNeuron2 = (TempData.Total() > 2) ? TempData[2] : 0.0;
bool oBuy = m_labelCacheHasValue[oi] ? m_labelCacheBuy[oi] : false;
bool oSell = m_labelCacheHasValue[oi] ? m_labelCacheSell[oi] : false;
ENUM_SIGNAL oTrueSignal = oBuy ? Buy : (oSell ? Sell : Neutral);
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
//--- Per-direction OUTCOMES, kept apart from the label - see m_oos.buyPredictedWins.
fix: the deploy gate was benchmarking a win rate against a label frequency The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test. That invariant needs reward >= risk, and the measured geometry no longer satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but both-won bars were stripped out of Buy and Sell so the label base rate read 37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma against 37.5% and loses money on every single trade. Live since 217b9bc. Root cause is that label agreement stopped being the same question as trade profitability. Buy implies winLong, but the converse fails on every both-won bar, and the label can only name one of two directions that both pay. So stop asking the model whether it matched a label and start asking whether its trade paid: - cache winLong/winShort per bar beside the label, under the same validity flag; published from the barrier walk before the collapse to 3 classes - dirPrecPct now counts wins on the side actually called - chancePrecPct is max(P(winLong), P(winShort)), MEASURED - the textbook m/(m+k) would credit SP500's drift to the model - the NMS "what would I have made" pair, the live-fired precision, and the IS/OOS cumulative win rates all move to the same test. IS and OOS are read side by side as the overfitting signal, so measuring one in wins and the other in agreement would put a fixed gap between them that has nothing to do with generalization - the confidence threshold is FITTED on wins too, so the operating point maximises what the gate grades - per-class label-agreement precision is still computed and logged; it is the right diagnostic for class separation, just not for a deploy decision - era line renamed dir-precision -> win-rate, chance -> chance=break-even Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 16:00:51 -04:00
bool oWinLong = (m_labelCacheHasValue[oi] && oi < ArraySize(m_winLongCache))
? m_winLongCache[oi] : false;
bool oWinShort = (m_labelCacheHasValue[oi] && oi < ArraySize(m_winShortCache))
? m_winShortCache[oi] : false;
feat(vote): thresholds become confidence percentages, on ONE scale everywhere User request: "the entry/exit thresholds are manual numbers, I would like them to be confidence percentages, so the current 20 would be only 20% confidence in a profitable trade." WHY 20 WAS EVER SENSIBLE. Under UseDatabaseRanking both factors of a filter's contribution are win rates: the pattern weight is that pattern's measured win rate (UpdateSignalsWeights -> ApplyPatternWeight) and m_weight is the filter's average win rate over its patterns, /100. Dividing the sum by the VOTER COUNT therefore produced a mean of PRODUCTS of two win rates - a genuinely 60%-accurate filter firing a 60% pattern scored 0.60 x 60 = 36. The number was never on a probability scale, so its magnitude meant nothing on its own. Dividing by Sum(m_weight) instead makes it a weighted MEAN of win rates, which is a win rate: result = Sum(w_i*p_i)/Sum(w_i). Every voter at 60% now reads 60; MACD's double-divergence pattern (weight 100) voting alone reads 100. m_weight stops being a discount on the probability and becomes how much a filter's opinion COUNTS - which is what a module weight should always have been. Default Min_Vote_Open 20 -> 50: not a tightening, the same bar re-expressed. ONE SCALE, EVERYWHERE - the part that made this bigger than a rescale. Three other places compared against a 0..1 softmax confidence and would each have become a fresh currency mismatch the moment the input changed meaning: * the AI early-exit route (LiveSignedConfidence vs m_ai_exit_threshold) now reads m_lastAiVote - the AI filters' own weighted mean, undiluted by the classic side, which is the only reason that route exists - against the same m_threshold_close the averaged vote uses. m_ai_exit_threshold is retired rather than left dangling. * m_oosDecisionSeries now carries the vote, not the confidence, so the exit SIMULATION stops modelling a close rule the EA does not run. * ExitPolicy() clamped anything > 1.0 to zero. Passing the unscaled input through that would have silently switched vote exits off in the simulation while live went on running them - found before it shipped; the bound now tracks the scale. LiveSignedConfidence() is deliberately untouched and still 0..1: MM sizing, SL/TP scaling and the intelligent trailing want a model confidence, not a win rate. CALIBRATION CAVEAT, stated in the code where the claim is made: this is only a real probability to the extent the pattern weights are. A pattern with fewer than MIN_TRADES_FOR_WIN_RATE journaled trades keeps its DEFAULT weight - a designed prior (25/50/75/100 for the AI tiers), not a measurement. Until the signal DB fills, "60" means "the designed conviction of the patterns that fired". Closing that gap is the next commit. Also corrects VOTE_CLOSE_PRESETS' comment, which documented the two scales this removes. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 15:52:08 -04:00
//--- ONE CURRENCY, and it is the live one. oEnsembleVote is the signed vote this member
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- would have cast on this bar - m_weight x its tier's pattern weight, the same
//--- number CExpertSignalCustom::Direction() sums and the same 0-100 win-rate scale
//--- Signal_ThresholdOpen/Signal_ThresholdClose are expressed in.
fix(gate): the ensemble gate certified a vote the EA never casts g_ensembleVoteThreshold's comment claims the combined-vote scorer "fires on the same criterion the live trade does". It did not. Two independent mismatches, both silent: CURRENCY. Each member contributed its raw signed confidence x100 - a 33..100 number straight off the softmax head. Live contributes m_weight x the tier's pattern weight, and BOTH of those are rewritten from the signal DB by UpdateSignalsWeights(). A head output and a DB-ranked win-rate weight share an axis and nothing relates them, so the same bar was one number to the gate and a different one to the order path. Same shape as the 2026-08-09 geometry incident: certified on one game, paid on another. DENOMINATOR. The gate divided by the member count, so an abstaining member pulled the average toward zero. CExpertSignalCustom::Direction() skips a zero contribution in BOTH the sum and the count (`if(direction == 0) continue;` before `number++`) - live is a mean over VOTERS. The gate was therefore scoring a strictly more agreement-heavy set of bars than the EA trades. The contribution hook's own comment asserted the opposite ("abstentions dilute the average exactly as they do in the live vote"), while the AI_CHOICE enum 20 lines away correctly documented union semantics. LiveVoteContribution() is now the single definition of "what this member votes", called from the gate; the live path reaches the same arithmetic through LongCondition/ShortCondition. g_ensVoteVoterMask records who actually voted, separately from who evaluated the bar, because those are the divisor and the shared-population test respectively. ConfidenceTier() is split into ConfidenceTierFor(signal) plus a thin live-bar wrapper - the OOS scan holds the scanned bar's decision in a local, and dPrevSignal is a different bar. NOT changed, deliberately: the gate still does not model live NMS declustering, and the per-member solo gate still scores every directional call rather than threshold-clearing ones. Both are selection-metric changes and this codebase has twice been bitten by switching one blind. Also corrects a stale paragraph in m_pattern_0's declaration block quoting 80/87/93/100 as the tier defaults. The constructor is 25/50/75/100 and has been since the confidence floor and alternation gate were removed; the block carried both tables at once, and the dead one was quoted back as fact. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 15:23:33 -04:00
double oEnsembleVote = LiveVoteContribution(oDeploySignal);
feat(vote): CONSENSUS arithmetic - agreement is now what the threshold dials Era-680 report, all three observations one equation: "peak 29, no arrows at threshold 30" / "at 20, arrows on EVERY bar" / "label at 12 while arrows everywhere". Under the voters-only divisor, any bar with at least one directional voter read the weighted mean of the firing tiers' weights - and once the tiers self-ranked to each model's pooled win rate (~28-31), that mean was NEAR-CONSTANT regardless of headcount. One member alone: ~29. Four unanimous: ~29. Min_Vote_Open was a step function around that constant - above it nothing ever fired, below it everything did - and the label's 12 was a 3v1 split netting through the same divisor. Not three display bugs: one arithmetic that could not express agreement. The divisor is now the CAPABLE weight - every filter that could vote, whether it did or not: * live (Direction): VoteCapableWeight() - classic pattern ladders always, veto filters never, AI members once past the same readiness test LongCondition gates on. A model still training must not dilute an ensemble it cannot join: four trainees + one deployed model is a solo chart wearing an ensemble label, and the solo vote reads full strength. * gate (EnsembleEraVerdict): g_ensVoteWeightSum accumulates for every member that EVALUATED the bar, Neutral included. * overlay sweep + prospective readout: weight counts whenever the member has data; a snapshotted Neutral dilutes. One arithmetic, four sites, same numbers everywhere. What the numbers become (four members, w~0.29, tiers~29): unanimous ~29 - the CEILING, which is the pooled win rate and is what the peak displays; 3-of-4 ~22; 2-of-4 ~14.5; 3v1 ~14.5. Min_Vote_Open 20 now means "roughly three-quarters of the ensemble's trust agrees, net". It MUST sit below the ceiling to ever fire - the census/peak states the ceiling. This is the ensemble the user specified in the original design discussion ("if the perceptron also votes, both together reach the threshold; if another NN votes the other side, the threshold is not reached") - union semantics was the pre-ensemble behaviour, kept until measurement showed its vote magnitude was a constant. Plus overlay DECLUSTERING, the other half of "arrows on every bar": the same three NMS rules as the per-member arrows (same-direction runs collapse to their first bar, cross-direction flicker keeps the stronger side), online over the sweep's strictly oldest->newest walk. Suppression is a verdict and deletes a standing arrow; the den==0 no-data skip still never does. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-19 06:58:03 -04:00
//--- The divisor term that goes with it - the member's weight WHENEVER it evaluated the
//--- bar, Neutral included, because consensus arithmetic (2026-08-19) has abstention
//--- dilute. Was zeroed on abstention under union semantics.
double oEnsembleWeight = ModuleWeight();
fix(ensemble): responsive panel + synchronized eras + combined-vote accuracy Four user-reported/requested items, one root cause chain: 1) DEAD CONTROL PANEL in AI_HYBRID mode. All members posted custom event id 1 and handled id 1001, and CExpertCustom broadcasts every chart event to every filter - so each posted event ran a train chunk in ALL N members (N*N chunks per round) and the chart thread never idled long enough to deliver clicks/drags. profiling.csv: 99.45% of time in OnChartEventHandler. Fix: per-instance study-event ids (STUDY_EVENT_ID_BASE + construction order, offset above the Controls library's ON_* codes - id 1 was also ON_DBL_CLICK, so panel double-clicks fired training chunks). ArmStudyEvent() is the single post site; lost-event watchdog replaces the accidental sibling-clears-my-flag rescue. 2) WARM-UP DUPLICATION. The auto-tune sweep is deterministic over identical features/labels, and it ends in the full MI diagnostic suite, which the MI-share gate never intercepted on the sweep path - four members ran four identical ~36s sweep+report blocks. First member publishes outcome (g_ensembleChartTuneDone/Installed/Settings); the rest apply it and skip both. 3) DEINIT STRANDED PANEL+ARROWS (user repro 18:52). Root cause from the log: the 4,500ms budget runs from MetaTrader's stop REQUEST - a heavy autosave in flight ate it, OnDeinit got ~430ms and died in the first member's arrow persist ("Abnormal termination" 432ms in). Fix: early visible-UI sweep (native prefix deletes for status/panel/dialog) right after ClearStatusLabel, and a fast path for still-training models - their arrows are re-rendered every era, so they get one bulk purge instead of scan+atomic-write in the death window. 4) ENSEMBLE FEATURES (user requests): era BARRIER - members advance era by era together; a member ahead of the slowest still-training member declines Train() calls and its chunk budget is donated (TRAIN_TIME_BUDGET_MS = 120/activeTrainers, UI headroom constant). COMBINED-VOTE OOS SCORE - each member's pass-3 scan contributes its adjusted per-bar decision (0.0 on abstain) to a shared row buffer; the last member to finish the era scores the averaged vote vs the mirrored Min_Vote_Open against the same target-before-stop outcomes members grade themselves on, publishing an "Ensemble vote" line on the aggregated panel. Member headlines now carry their lifetime win rate with break-even. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:06:04 -04:00
if(m_ensembleMember && m_labelCacheHasValue[oi])
feat(vote): thresholds become confidence percentages, on ONE scale everywhere User request: "the entry/exit thresholds are manual numbers, I would like them to be confidence percentages, so the current 20 would be only 20% confidence in a profitable trade." WHY 20 WAS EVER SENSIBLE. Under UseDatabaseRanking both factors of a filter's contribution are win rates: the pattern weight is that pattern's measured win rate (UpdateSignalsWeights -> ApplyPatternWeight) and m_weight is the filter's average win rate over its patterns, /100. Dividing the sum by the VOTER COUNT therefore produced a mean of PRODUCTS of two win rates - a genuinely 60%-accurate filter firing a 60% pattern scored 0.60 x 60 = 36. The number was never on a probability scale, so its magnitude meant nothing on its own. Dividing by Sum(m_weight) instead makes it a weighted MEAN of win rates, which is a win rate: result = Sum(w_i*p_i)/Sum(w_i). Every voter at 60% now reads 60; MACD's double-divergence pattern (weight 100) voting alone reads 100. m_weight stops being a discount on the probability and becomes how much a filter's opinion COUNTS - which is what a module weight should always have been. Default Min_Vote_Open 20 -> 50: not a tightening, the same bar re-expressed. ONE SCALE, EVERYWHERE - the part that made this bigger than a rescale. Three other places compared against a 0..1 softmax confidence and would each have become a fresh currency mismatch the moment the input changed meaning: * the AI early-exit route (LiveSignedConfidence vs m_ai_exit_threshold) now reads m_lastAiVote - the AI filters' own weighted mean, undiluted by the classic side, which is the only reason that route exists - against the same m_threshold_close the averaged vote uses. m_ai_exit_threshold is retired rather than left dangling. * m_oosDecisionSeries now carries the vote, not the confidence, so the exit SIMULATION stops modelling a close rule the EA does not run. * ExitPolicy() clamped anything > 1.0 to zero. Passing the unscaled input through that would have silently switched vote exits off in the simulation while live went on running them - found before it shipped; the bound now tracks the scale. LiveSignedConfidence() is deliberately untouched and still 0..1: MM sizing, SL/TP scaling and the intelligent trailing want a model confidence, not a win rate. CALIBRATION CAVEAT, stated in the code where the claim is made: this is only a real probability to the extent the pattern weights are. A pattern with fewer than MIN_TRADES_FOR_WIN_RATE journaled trades keeps its DEFAULT weight - a designed prior (25/50/75/100 for the AI tiers), not a measurement. Until the signal DB fills, "60" means "the designed conviction of the patterns that fired". Closing that gap is the next commit. Also corrects VOTE_CLOSE_PRESETS' comment, which documented the two scales this removes. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 15:52:08 -04:00
EnsembleOosContribute(oi, oEnsembleVote, oEnsembleWeight, oWinLong, oWinShort, (oBuy || oSell));
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- THE DECISION SERIES, for the exit simulation. Stored on the bar's own series index
//--- so SimulateTradeOutcome can walk it forward against price.
feat(gate): grade OOS calls on the exit policy actually in force, and move vote combining out of the members and into the orchestrator Option (a) from the exit-policy question: the certified number must be the traded number. Plus the modularity correction the user called for on 778b6c0. 1. VOTE COMBINING BELONGS TO THE ORCHESTRATOR, NOT TO A MEMBER. 778b6c0 fixed the last-writer-wins bug on g_LiveAISignedConfidence by having a member average its siblings through g_warriorEnsemble. That trades a scheduling bug for a coupling bug, and it is the wrong shape for this EA: every signal runs in its own instance, minds its own state, and VOTES to the orchestrator, which is the only thing allowed to combine opinions. Replaced with a publish/aggregate pair in Variables\ConfidenceBridge.mqh whose split is enforced by shape rather than by convention: - PublishAIVote(slot, conf) - a member writes ONLY its own slot, reads nobody's; - AggregateAIVotes() - called by CExpertSignalCustom::LiveSignedConfidence. CExpertSignalAIBase::EnsembleLiveSignedConfidence is gone. The orchestrator also republishes the aggregate into g_LiveAISignedConfidence, because the intelligent trailing reads that global directly and must act on the same number the exit route does rather than on a leftover from whichever member ticked last. A solo AI signal owns slot 0, so the non-ensemble path is unchanged. 2. THE GATE NOW REPLAYS THE REAL EXIT RULE. SimulateTradeOutcome() walks the same price series with the same fill/barrier/spread convention as ComputeLabelForBar - deliberately by copy, so a disagreement between the two can only be a policy effect and never a discrepancy between two pieces of our own arithmetic - and terminates at the FIRST of stop / target / vote reversal / horizon. Barriers are tested before the vote on the same bar: intrabar we cannot know which came first, and the barrier is what the broker executes automatically, so checking the vote first would credit the exit policy with escapes a real stop would have taken out of its hands. It runs AFTER pass 3, not inside it. A vote-flip exit for a trade entered at bar r is decided by the model's output at bars r-1, r-2, ... - NEWER bars - and pass 3 walks oldest-to-newest, so at the moment r is graded its own exit does not exist yet. Only once m_oosDecisionSeries is complete over the whole OOS window can the replay run. In ensemble mode that series carries the member's adjusted decision and the live exit reads the ensemble aggregate, which is the coupling the user identified: an LSTM entry really can be closed by the ensemble turning against it. 3. THE STATISTIC HAS TO CHANGE WITH THE POLICY, AND THAT IS THE REAL FINDING. A barrier exit pays a fixed R. A vote exit pays whatever the close happens to be. So the moment vote exits are enabled the payoff is CONTINUOUS, and "win rate vs break-even" stops being a meaningful test - there is no fixed break-even for a variable payoff. SimulateTradeOutcome therefore returns R rather than a bool, and the replay reports expectancy in R with its SE taken from the R distribution (overlap- deflated on the same EffectiveSampleSize doctrine as every other SE here), not from a binomial. This is the same class of error as win-based scoring in 2026-08-09: measuring a variable-payoff process with a fixed-payoff statistic. Naming it now, while vote exits are still off, is much cheaper than discovering it after they go on. 4. WHY THIS IS SAFE TO SHIP TODAY. Min_Vote_Close ships Disabled (101, unreachable on both scales it drives) and reaches the AI signal through the new ExitPolicy() setter as 1.01, which the setter turns into 0.0 = no vote exit. Under that policy every replayed trade resolves at a barrier and the simulation is arithmetically the same trade the deploy gate already certifies - they cannot drift. The report says so explicitly, and prints ONCE per run in that state; when vote exits are on it prints every era, because then the divergence is the thing to watch. Nothing about today's numbers moves. The gate switchover is wired but dormant by construction: it becomes exit-aware the moment the input is enabled, which is exactly what "the certified number is the traded number" has to mean. KNOWN LIMIT, stated rather than hidden: only the AI early-exit route is replayed. The rule-based averaged-vote close (m_threshold_close) depends on every other filter's live vote, which pass 3 does not reproduce, so a position the classic filters would have closed is held to its barrier here. The replay therefore holds LONGER than live and overstates barrier-reached outcomes. Faithful only while the AI is the dominant vote - which is the configuration this is being built for. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-17 16:25:57 -04:00
if(oi >= 0 && oi < ArraySize(m_oosDecisionSeries))
feat(vote): thresholds become confidence percentages, on ONE scale everywhere User request: "the entry/exit thresholds are manual numbers, I would like them to be confidence percentages, so the current 20 would be only 20% confidence in a profitable trade." WHY 20 WAS EVER SENSIBLE. Under UseDatabaseRanking both factors of a filter's contribution are win rates: the pattern weight is that pattern's measured win rate (UpdateSignalsWeights -> ApplyPatternWeight) and m_weight is the filter's average win rate over its patterns, /100. Dividing the sum by the VOTER COUNT therefore produced a mean of PRODUCTS of two win rates - a genuinely 60%-accurate filter firing a 60% pattern scored 0.60 x 60 = 36. The number was never on a probability scale, so its magnitude meant nothing on its own. Dividing by Sum(m_weight) instead makes it a weighted MEAN of win rates, which is a win rate: result = Sum(w_i*p_i)/Sum(w_i). Every voter at 60% now reads 60; MACD's double-divergence pattern (weight 100) voting alone reads 100. m_weight stops being a discount on the probability and becomes how much a filter's opinion COUNTS - which is what a module weight should always have been. Default Min_Vote_Open 20 -> 50: not a tightening, the same bar re-expressed. ONE SCALE, EVERYWHERE - the part that made this bigger than a rescale. Three other places compared against a 0..1 softmax confidence and would each have become a fresh currency mismatch the moment the input changed meaning: * the AI early-exit route (LiveSignedConfidence vs m_ai_exit_threshold) now reads m_lastAiVote - the AI filters' own weighted mean, undiluted by the classic side, which is the only reason that route exists - against the same m_threshold_close the averaged vote uses. m_ai_exit_threshold is retired rather than left dangling. * m_oosDecisionSeries now carries the vote, not the confidence, so the exit SIMULATION stops modelling a close rule the EA does not run. * ExitPolicy() clamped anything > 1.0 to zero. Passing the unscaled input through that would have silently switched vote exits off in the simulation while live went on running them - found before it shipped; the bound now tracks the scale. LiveSignedConfidence() is deliberately untouched and still 0..1: MM sizing, SL/TP scaling and the intelligent trailing want a model confidence, not a win rate. CALIBRATION CAVEAT, stated in the code where the claim is made: this is only a real probability to the extent the pattern weights are. A pattern with fewer than MIN_TRADES_FOR_WIN_RATE journaled trades keeps its DEFAULT weight - a designed prior (25/50/75/100 for the AI tiers), not a measurement. Until the signal DB fills, "60" means "the designed conviction of the patterns that fired". Closing that gap is the next commit. Also corrects VOTE_CLOSE_PRESETS' comment, which documented the two scales this removes. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 15:52:08 -04:00
m_oosDecisionSeries[oi] = oEnsembleVote;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
UpdateTrainingStatusLabel(
StringFormat("Scoring OOS bar %d of %d -> %.2f%% (post-training)", m_oosScoreStartIndex - m_oosScoreIndex + 1, m_oosScoreStartIndex + 1,
(double)(m_oosScoreStartIndex - m_oosScoreIndex + 1.0) / MathMax(m_oosScoreStartIndex + 1, 1) * 100),
oNeuron0, oNeuron1, oNeuron2, oDeploySignal);
// Held-out bar: score the model's freshly-trained-this-era forecast against the actual
// outcome without learning from it - keeps the OOS accuracy an honest overfitting signal.
bool oClassified = (DoubleToSignal(oPrevSignal) == Buy || DoubleToSignal(oPrevSignal) == Sell || DoubleToSignal(oPrevSignal) == Neutral);
if(oClassified)
{
m_oosSamples++;
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.confidenceSum += MathAbs(oPrevSignal);
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
if(dOosError < 0)
dOosError = 0;
bool hit = (DoubleToSignal(oPrevSignal) == oTrueSignal);
ENUM_SIGNAL oPred = DoubleToSignal(oPrevSignal);
fix: the deploy gate was benchmarking a win rate against a label frequency The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test. That invariant needs reward >= risk, and the measured geometry no longer satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but both-won bars were stripped out of Buy and Sell so the label base rate read 37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma against 37.5% and loses money on every single trade. Live since 217b9bc. Root cause is that label agreement stopped being the same question as trade profitability. Buy implies winLong, but the converse fails on every both-won bar, and the label can only name one of two directions that both pay. So stop asking the model whether it matched a label and start asking whether its trade paid: - cache winLong/winShort per bar beside the label, under the same validity flag; published from the barrier walk before the collapse to 3 classes - dirPrecPct now counts wins on the side actually called - chancePrecPct is max(P(winLong), P(winShort)), MEASURED - the textbook m/(m+k) would credit SP500's drift to the model - the NMS "what would I have made" pair, the live-fired precision, and the IS/OOS cumulative win rates all move to the same test. IS and OOS are read side by side as the overfitting signal, so measuring one in wins and the other in agreement would put a fixed gap between them that has nothing to do with generalization - the confidence threshold is FITTED on wins too, so the operating point maximises what the gate grades - per-class label-agreement precision is still computed and logged; it is the right diagnostic for class separation, just not for a deploy decision - era line renamed dir-precision -> win-rate, chance -> chance=break-even Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 16:00:51 -04:00
//--- Did the TRADE this call implies actually pay? Distinct from `hit`, which asks the
//--- narrower question of whether the call matched the single label the bar was collapsed
//--- to. On a both-won bar the label names one direction and this pays either way.
bool oTradeWon = (oPred == Buy) ? oWinLong : ((oPred == Sell) ? oWinShort : false);
//--- Zero-skill reference, measured over EVERY scored bar (not just the called ones):
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
//--- what always-long and always-short would have collected. See m_oos.winLongTotal.
fix: the deploy gate was benchmarking a win rate against a label frequency The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test. That invariant needs reward >= risk, and the measured geometry no longer satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but both-won bars were stripped out of Buy and Sell so the label base rate read 37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma against 37.5% and loses money on every single trade. Live since 217b9bc. Root cause is that label agreement stopped being the same question as trade profitability. Buy implies winLong, but the converse fails on every both-won bar, and the label can only name one of two directions that both pay. So stop asking the model whether it matched a label and start asking whether its trade paid: - cache winLong/winShort per bar beside the label, under the same validity flag; published from the barrier walk before the collapse to 3 classes - dirPrecPct now counts wins on the side actually called - chancePrecPct is max(P(winLong), P(winShort)), MEASURED - the textbook m/(m+k) would credit SP500's drift to the model - the NMS "what would I have made" pair, the live-fired precision, and the IS/OOS cumulative win rates all move to the same test. IS and OOS are read side by side as the overfitting signal, so measuring one in wins and the other in agreement would put a fixed gap between them that has nothing to do with generalization - the confidence threshold is FITTED on wins too, so the operating point maximises what the gate grades - per-class label-agreement precision is still computed and logged; it is the right diagnostic for class separation, just not for a deploy decision - era line renamed dir-precision -> win-rate, chance -> chance=break-even Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 16:00:51 -04:00
if(oWinLong)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.winLongTotal++;
fix: the deploy gate was benchmarking a win rate against a label frequency The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test. That invariant needs reward >= risk, and the measured geometry no longer satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but both-won bars were stripped out of Buy and Sell so the label base rate read 37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma against 37.5% and loses money on every single trade. Live since 217b9bc. Root cause is that label agreement stopped being the same question as trade profitability. Buy implies winLong, but the converse fails on every both-won bar, and the label can only name one of two directions that both pay. So stop asking the model whether it matched a label and start asking whether its trade paid: - cache winLong/winShort per bar beside the label, under the same validity flag; published from the barrier walk before the collapse to 3 classes - dirPrecPct now counts wins on the side actually called - chancePrecPct is max(P(winLong), P(winShort)), MEASURED - the textbook m/(m+k) would credit SP500's drift to the model - the NMS "what would I have made" pair, the live-fired precision, and the IS/OOS cumulative win rates all move to the same test. IS and OOS are read side by side as the overfitting signal, so measuring one in wins and the other in agreement would put a fixed gap between them that has nothing to do with generalization - the confidence threshold is FITTED on wins too, so the operating point maximises what the gate grades - per-class label-agreement precision is still computed and logged; it is the right diagnostic for class separation, just not for a deploy decision - era line renamed dir-precision -> win-rate, chance -> chance=break-even Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 16:00:51 -04:00
if(oWinShort)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.winShortTotal++;
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- Compounded, persistent DIRECTIONAL win-rate: count only bars the model actually
//--- called Buy or Sell (Neutral "no trade" calls aren't wins or losses).
perf(autotune): replace the genetic search with a filter score - hours to seconds MEASURED COST OF THE GA, which is what retired it. Per generation: rung 0: 8 cand x 3 seeds x 3 eras = 72 eras rung 1: 4 cand x 3 seeds x 8 eras = 96 rung 2: 2 cand x 3 seeds x 20 eras = 120 = 288 eras/generation x 4 generations = 1152 eras BEFORE the winner's real training began. Against the observed era times on SP500 H1: PAI 29.1 s/era -> 9.3 h (matches the observed 00:37 -> 09:22) CONV 41.3 s/era -> 13.2 h LSTM 150.4 s/era -> 48.1 h HYBRID 154.6 s/era -> 49.5 h Two days to tune is not a first-run experience, and it is the phase in which the panel goes quiet, which is what made it look like a hang. It also bought nothing. The space is 90 points (10 MA periods x 9 MA types), so 1152 evaluations revisited each point ~13 times; and rungs of 3 and 8 eras cannot separate two MA periods at all. The 2026-08-01 run proves it: every finalist scored 25.0-25.9% balanced accuracy - below the 33.3% one-class floor, i.e. indistinguishable noise - and the search then "deployed the winner" of that. THE ERROR WAS THE SCORING FUNCTION, not its constants. Using a full training run to choose a feature's period is a wrapper method paying wrapper prices for a decision that does not need one. The reference book does not do this: ch. 3.3 selects inputs by measuring each candidate indicator's CORRELATION with the target and dropping the ones with none, with no network involved. So: rank candidates by the MUTUAL INFORMATION between the resulting feature vector and the triple-barrier label. MI rather than correlation because the label is 3-class categorical and the features are not monotonically related to it. Equal-FREQUENCY binning (rank-based), because these features are ATR-normalised and heavy-tailed - fixed-width bins put nearly everything in one bucket and report ~0 information for a genuinely useful feature. Scoring is arithmetic over the feature cache, so it costs seconds and its cost is independent of topology: LSTM now tunes as fast as the MLP. Coordinate sweep, not product sweep - cost is the SUM of per-parameter candidate counts, so enabling every indicator stays affordable - with a second pass that breaks early once nothing moves. Sampling is IS-ONLY. Letting the OOS window influence which indicator settings ship would mean the holdout had been used for selection and had stopped being a holdout. HONEST LIMIT, recorded because it is the price: MI is marginal, so a parameter that only pays off in combination with another can be missed (Guyon & Elisseeff 2003, filter vs wrapper). Given the wrapper it replaces was ranking pure noise at 48 h a run, this is strictly better. Deleted with it: GaRungEras/GaExtract/GaStore/GaMutate/GaRandomCandidate/ GaBlockCrossover/GaSortAliveByScoreDesc/GaBreedNextGeneration, 14 m_ga* members, the GA_*/TUNE_POP_* constants, and ComputeTuneTrialBudget. AND m_evalMode/m_evalEraBudget, because nothing set them any more - 28 read sites all permanently inert. That is not a tidy-up: the `if (!m_evalMode)` guard on UpdateClassPriors is exactly what silently disabled the imbalance correction for entire runs two commits ago. Dead machinery that still reads like live machinery is this codebase's most expensive recurring bug, and leaving 28 more instances of it would have been indefensible. The panel's tuning-progress state goes too - tuning no longer takes long enough to need one. Both builds compile 0 errors / 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-01 10:29:31 -04:00
if(oPred == Buy || oPred == Sell)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
m_cumOosTotal++;
fix: the deploy gate was benchmarking a win rate against a label frequency The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test. That invariant needs reward >= risk, and the measured geometry no longer satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but both-won bars were stripped out of Buy and Sell so the label base rate read 37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma against 37.5% and loses money on every single trade. Live since 217b9bc. Root cause is that label agreement stopped being the same question as trade profitability. Buy implies winLong, but the converse fails on every both-won bar, and the label can only name one of two directions that both pay. So stop asking the model whether it matched a label and start asking whether its trade paid: - cache winLong/winShort per bar beside the label, under the same validity flag; published from the barrier walk before the collapse to 3 classes - dirPrecPct now counts wins on the side actually called - chancePrecPct is max(P(winLong), P(winShort)), MEASURED - the textbook m/(m+k) would credit SP500's drift to the model - the NMS "what would I have made" pair, the live-fired precision, and the IS/OOS cumulative win rates all move to the same test. IS and OOS are read side by side as the overfitting signal, so measuring one in wins and the other in agreement would put a fixed gap between them that has nothing to do with generalization - the confidence threshold is FITTED on wins too, so the operating point maximises what the gate grades - per-class label-agreement precision is still computed and logged; it is the right diagnostic for class separation, just not for a deploy decision - era line renamed dir-precision -> win-rate, chance -> chance=break-even Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 16:00:51 -04:00
if(oTradeWon)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
m_cumOosCorrect++;
}
// Per-class confusion counts, used for the Buy/Sell recall convergence gate below
switch(oTrueSignal)
{
case Buy:
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.buyTotal++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
if(hit)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.buyHits++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
break;
case Sell:
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.sellTotal++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
if(hit)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.sellHits++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
break;
default:
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.neutralTotal++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
if(hit)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.neutralHits++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
break;
}
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- DECLUSTERED count: of the calls that would actually become POSITIONS, how many
//--- were right. This pair is the one that answers "what would I have made".
fix: NMS gates the TRADE, not just the arrow - one arrow is now one trade NmsLiveAccept() appeared in exactly one place: wrapped around DrawObject(). It never touched dPrevSignal, and dPrevSignal is what LongCondition() / ShortCondition() / SignedAIConfidence() read. So a declustered bar lost its arrow and still opened a position. Measured on SP500 H1 2026-08-09: CONV called a direction on 64% of bars, so the ~500 bars visible on screen held ~320 decisions - and ~40 arrows were drawn. Roughly one arrow per eight positions the EA would take. And the survivors are not a random eighth. Rule 2 of the declustering keeps the HIGHER-CONFIDENCE side of a cluster, so the visible set is systematically the best member of each run. A chart showing the best of every eight decisions and hiding the rest reads far better than the model is - the same best-of-N selection error already corrected in the geometry scan, the indicator tuner, the lag profile and the deploy gate, this time on the display layer, where it is most likely to mislead the person deciding whether to trade. Fixed by neutralising dPrevSignal when NMS rejects, rather than adding a "may trade" flag consulted at each read site: that leaves exactly ONE definition of what the model decided this bar, so the arrow, the panel's "Current signal", the confidence feeding sizing/SL/TP/trailing, the refresh tally and the order itself cannot drift apart again. Also reports the consequence instead of hiding it. Every OOS counter on the era line still scores every directional call - a population ~8x larger than what now trades - so the line carries a second figure: | TRADED (declustered) NN% on N calls (edge +Npp) replaying the identical rule over pass 3 (which walks OOS bars oldest to newest, the same order the live sweep sees). Its cursors are separate members from the live ones so a training pass can never disturb the live chart's declustering. Deliberately NOT switched into selectionScore yet. Declustering cuts coverage from ~64% of bars to ~8%, well under MIN_COVERAGE_FRACTION_OF_BASE_RATE, which would make every checkpoint undeployable overnight - the minRR collision and the recall-floor catch-22 twice over. The floor gets re-derived from these measurements first. Compiles clean: 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-09 10:22:31 -04:00
if(m_signalClusterWindow > 0)
{
fix: the deploy gate graded the un-thresholded model coveragePct, dirPrecPct and the declustered TRADED tally were all computed from oPrevSignal - the RAW argmax - while the live order, the arrow and the panel all run on oDeploySignal, which is argmax AFTER the confidence threshold. The gate was certifying a strategy the EA does not trade. Invisible until now: the threshold sat at ~0.02, so the two populations were the same set. The held-out calibration slice (2189316) moved it to 0.14-0.40 and the gap opened immediately - PAI era 256 graded 100% coverage while its traded population was 21% (3,399 of ~16,200 OOS bars). Consequences that were being hidden: - coveragePct >= minCoveragePct was tested against the wrong population, so a model whose TRADED coverage falls under the 24.8% floor still read as clearing it - precSE = sqrt(p(1-p)/n) used n ~16,000 instead of n ~3,400, so the EDGE_MIN_SIGMAS bar was ~2.2x too lenient on the real evidence - the NMS replay declustered a different, larger stream than live, so threshold-rejected bars consumed cluster slots and set alternation state Gate quantities now read m_oosBuyFired/m_oosSellFired (the thresholded population, already tracked for the live-precision line) and the NMS replay runs on oDeploySignal. The threshold can only turn a direction into Neutral, never flip a side, so the fired set is a strict subset and every per-bar outcome is the one already computed. Recall and logBuyPrecPct deliberately stay on the raw argmax: they measure intrinsic class separation, and thresholding them would conflate "cannot separate the classes" with "declines to act on the separation it found". This is the 9a7c37f defect class, and the NMS block carried a comment warning about it while committing it three lines above. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-10 19:34:32 -04:00
//--- oDeploySignal, NOT oPrevSignal: live NMS runs downstream of the confidence
//--- threshold (RefreshLatestSignal feeds NmsLiveAccept the ADJUSTED decision), so
//--- replaying it on the raw argmax declusters a different, strictly larger stream
//--- than the EA ever sees - different survivors, not just more of them, because rule 1
//--- collapses runs and rule 3 alternates over whatever sequence it is given. Bars the
//--- threshold rejects must not consume a cluster slot or set the alternation state.
ENUM_SIGNAL nmsDir = DoubleToSignal(oDeploySignal);
fix: NMS gates the TRADE, not just the arrow - one arrow is now one trade NmsLiveAccept() appeared in exactly one place: wrapped around DrawObject(). It never touched dPrevSignal, and dPrevSignal is what LongCondition() / ShortCondition() / SignedAIConfidence() read. So a declustered bar lost its arrow and still opened a position. Measured on SP500 H1 2026-08-09: CONV called a direction on 64% of bars, so the ~500 bars visible on screen held ~320 decisions - and ~40 arrows were drawn. Roughly one arrow per eight positions the EA would take. And the survivors are not a random eighth. Rule 2 of the declustering keeps the HIGHER-CONFIDENCE side of a cluster, so the visible set is systematically the best member of each run. A chart showing the best of every eight decisions and hiding the rest reads far better than the model is - the same best-of-N selection error already corrected in the geometry scan, the indicator tuner, the lag profile and the deploy gate, this time on the display layer, where it is most likely to mislead the person deciding whether to trade. Fixed by neutralising dPrevSignal when NMS rejects, rather than adding a "may trade" flag consulted at each read site: that leaves exactly ONE definition of what the model decided this bar, so the arrow, the panel's "Current signal", the confidence feeding sizing/SL/TP/trailing, the refresh tally and the order itself cannot drift apart again. Also reports the consequence instead of hiding it. Every OOS counter on the era line still scores every directional call - a population ~8x larger than what now trades - so the line carries a second figure: | TRADED (declustered) NN% on N calls (edge +Npp) replaying the identical rule over pass 3 (which walks OOS bars oldest to newest, the same order the live sweep sees). Its cursors are separate members from the live ones so a training pass can never disturb the live chart's declustering. Deliberately NOT switched into selectionScore yet. Declustering cuts coverage from ~64% of bars to ~8%, well under MIN_COVERAGE_FRACTION_OF_BASE_RATE, which would make every checkpoint undeployable overnight - the minRR collision and the recall-floor catch-22 twice over. The floor gets re-derived from these measurements first. Compiles clean: 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-09 10:22:31 -04:00
if(nmsDir == Buy || nmsDir == Sell)
{
fix: the deploy gate graded the un-thresholded model coveragePct, dirPrecPct and the declustered TRADED tally were all computed from oPrevSignal - the RAW argmax - while the live order, the arrow and the panel all run on oDeploySignal, which is argmax AFTER the confidence threshold. The gate was certifying a strategy the EA does not trade. Invisible until now: the threshold sat at ~0.02, so the two populations were the same set. The held-out calibration slice (2189316) moved it to 0.14-0.40 and the gap opened immediately - PAI era 256 graded 100% coverage while its traded population was 21% (3,399 of ~16,200 OOS bars). Consequences that were being hidden: - coveragePct >= minCoveragePct was tested against the wrong population, so a model whose TRADED coverage falls under the 24.8% floor still read as clearing it - precSE = sqrt(p(1-p)/n) used n ~16,000 instead of n ~3,400, so the EDGE_MIN_SIGMAS bar was ~2.2x too lenient on the real evidence - the NMS replay declustered a different, larger stream than live, so threshold-rejected bars consumed cluster slots and set alternation state Gate quantities now read m_oosBuyFired/m_oosSellFired (the thresholded population, already tracked for the live-precision line) and the NMS replay runs on oDeploySignal. The threshold can only turn a direction into Neutral, never flip a side, so the fired set is a strict subset and every per-bar outcome is the one already computed. Recall and logBuyPrecPct deliberately stay on the raw argmax: they measure intrinsic class separation, and thresholding them would conflate "cannot separate the classes" with "declines to act on the separation it found". This is the 9a7c37f defect class, and the NMS block carried a comment warning about it while committing it three lines above. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-10 19:34:32 -04:00
//--- Confidence for rule 2's cross-direction resolution comes from the same adjusted
//--- decision, matching NmsLiveAccept's input exactly.
double nmsConf = MathAbs(oDeploySignal);
fix: NMS gates the TRADE, not just the arrow - one arrow is now one trade NmsLiveAccept() appeared in exactly one place: wrapped around DrawObject(). It never touched dPrevSignal, and dPrevSignal is what LongCondition() / ShortCondition() / SignedAIConfidence() read. So a declustered bar lost its arrow and still opened a position. Measured on SP500 H1 2026-08-09: CONV called a direction on 64% of bars, so the ~500 bars visible on screen held ~320 decisions - and ~40 arrows were drawn. Roughly one arrow per eight positions the EA would take. And the survivors are not a random eighth. Rule 2 of the declustering keeps the HIGHER-CONFIDENCE side of a cluster, so the visible set is systematically the best member of each run. A chart showing the best of every eight decisions and hiding the rest reads far better than the model is - the same best-of-N selection error already corrected in the geometry scan, the indicator tuner, the lag profile and the deploy gate, this time on the display layer, where it is most likely to mislead the person deciding whether to trade. Fixed by neutralising dPrevSignal when NMS rejects, rather than adding a "may trade" flag consulted at each read site: that leaves exactly ONE definition of what the model decided this bar, so the arrow, the panel's "Current signal", the confidence feeding sizing/SL/TP/trailing, the refresh tally and the order itself cannot drift apart again. Also reports the consequence instead of hiding it. Every OOS counter on the era line still scores every directional call - a population ~8x larger than what now trades - so the line carries a second figure: | TRADED (declustered) NN% on N calls (edge +Npp) replaying the identical rule over pass 3 (which walks OOS bars oldest to newest, the same order the live sweep sees). Its cursors are separate members from the live ones so a training pass can never disturb the live chart's declustering. Deliberately NOT switched into selectionScore yet. Declustering cuts coverage from ~64% of bars to ~8%, well under MIN_COVERAGE_FRACTION_OF_BASE_RATE, which would make every checkpoint undeployable overnight - the minRR collision and the recall-floor catch-22 twice over. The floor gets re-derived from these measurements first. Compiles clean: 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-09 10:22:31 -04:00
int lastSame = (nmsDir == Buy) ? m_oosNmsLastBuyIdx : m_oosNmsLastSellIdx;
//--- 1) same-direction contiguous collapse; last-seen advances either way so a whole
//--- run collapses to its first bar.
bool cont = (lastSame >= 0 && (lastSame - oi) <= m_signalClusterWindow);
if(nmsDir == Buy)
m_oosNmsLastBuyIdx = oi;
else
m_oosNmsLastSellIdx = oi;
bool keep = !cont;
//--- 2) cross-direction resolution against the last KEPT opposite signal: flicker at
//--- one turn zone resolves to the more confident side.
if(keep && m_oosNmsKeptIdx >= 0 && m_oosNmsKeptDir != nmsDir &&
m_oosNmsKeptDir != Neutral && (m_oosNmsKeptIdx - oi) <= m_signalClusterWindow)
keep = (nmsConf > m_oosNmsKeptConf);
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- 3) ALTERNATION, identical to NmsLiveAccept's rule 3.
feat: 10-bar decluster window + alternation on every signal consumer SignalClusterWindow 3 -> 10 for all topologies. On H1 a 3-bar window collapsed only the tightest runs and left visible clusters at every turn; 10 bars is closer to the spacing of genuinely distinct setups. ALTERNATION. Rule 1 only collapses a same-direction run INSIDE the window; past it a second Buy is emitted with no Sell between, giving Buy/Buy/Buy/Sell. With both directions tradeable that sequence is the model re-entering a move it is already in rather than finding a new one. The kept sequence must now alternate: the first signal passes, and after that a direction passes only if the last KEPT signal was the opposite one. Added to ALL THREE consumers, with identical logic, because they must agree: - NmsLiveAccept -> the live trade - pass 3's OOS replay -> the tally the deploy gate grades - PruneDirectionalClusters -> the drawn history A rule applied to only some of these certifies one strategy and trades another - the same defect class as the geometry the gate certified while OpenParams placed something else (9a7c37f) - and would draw the user arrows the EA would never have taken. Deliberately NOT applied to the LABEL. The barrier target has no "must flip" invariant: consecutive Buy labels are routinely correct, and an earlier alternation gate was removed with the triple-barrier relabel for exactly that reason. This filters what is ACTED ON, which is what "applies to training" can honestly mean here - pass 3's declustered tally is the training-side number that decides deployment. BothDirectionsTradeable() is the stated precondition (with one side disabled there is no opposite to wait for, so alternation would suppress everything after the first call). This build has no long-only/short-only input, so it is constant true - kept as a named predicate so a future direction restriction has one place to change rather than three call sites silently assuming both sides. Build tag -> nms-alternate-v4. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-10 14:26:12 -04:00
if(keep && BothDirectionsTradeable() && m_oosNmsKeptIdx >= 0 &&
m_oosNmsKeptDir == nmsDir)
keep = false;
fix: NMS gates the TRADE, not just the arrow - one arrow is now one trade NmsLiveAccept() appeared in exactly one place: wrapped around DrawObject(). It never touched dPrevSignal, and dPrevSignal is what LongCondition() / ShortCondition() / SignedAIConfidence() read. So a declustered bar lost its arrow and still opened a position. Measured on SP500 H1 2026-08-09: CONV called a direction on 64% of bars, so the ~500 bars visible on screen held ~320 decisions - and ~40 arrows were drawn. Roughly one arrow per eight positions the EA would take. And the survivors are not a random eighth. Rule 2 of the declustering keeps the HIGHER-CONFIDENCE side of a cluster, so the visible set is systematically the best member of each run. A chart showing the best of every eight decisions and hiding the rest reads far better than the model is - the same best-of-N selection error already corrected in the geometry scan, the indicator tuner, the lag profile and the deploy gate, this time on the display layer, where it is most likely to mislead the person deciding whether to trade. Fixed by neutralising dPrevSignal when NMS rejects, rather than adding a "may trade" flag consulted at each read site: that leaves exactly ONE definition of what the model decided this bar, so the arrow, the panel's "Current signal", the confidence feeding sizing/SL/TP/trailing, the refresh tally and the order itself cannot drift apart again. Also reports the consequence instead of hiding it. Every OOS counter on the era line still scores every directional call - a population ~8x larger than what now trades - so the line carries a second figure: | TRADED (declustered) NN% on N calls (edge +Npp) replaying the identical rule over pass 3 (which walks OOS bars oldest to newest, the same order the live sweep sees). Its cursors are separate members from the live ones so a training pass can never disturb the live chart's declustering. Deliberately NOT switched into selectionScore yet. Declustering cuts coverage from ~64% of bars to ~8%, well under MIN_COVERAGE_FRACTION_OF_BASE_RATE, which would make every checkpoint undeployable overnight - the minRR collision and the recall-floor catch-22 twice over. The floor gets re-derived from these measurements first. Compiles clean: 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-09 10:22:31 -04:00
if(keep)
{
m_oosNmsKeptIdx = oi;
m_oosNmsKeptDir = nmsDir;
m_oosNmsKeptConf = nmsConf;
m_oosNmsFired++;
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- oTradeWon, not `hit`: this pair exists specifically to answer "what
//--- would I have made", and that is a question about the trade, not about
//--- the label.
fix: the deploy gate was benchmarking a win rate against a label frequency The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test. That invariant needs reward >= risk, and the measured geometry no longer satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but both-won bars were stripped out of Buy and Sell so the label base rate read 37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma against 37.5% and loses money on every single trade. Live since 217b9bc. Root cause is that label agreement stopped being the same question as trade profitability. Buy implies winLong, but the converse fails on every both-won bar, and the label can only name one of two directions that both pay. So stop asking the model whether it matched a label and start asking whether its trade paid: - cache winLong/winShort per bar beside the label, under the same validity flag; published from the barrier walk before the collapse to 3 classes - dirPrecPct now counts wins on the side actually called - chancePrecPct is max(P(winLong), P(winShort)), MEASURED - the textbook m/(m+k) would credit SP500's drift to the model - the NMS "what would I have made" pair, the live-fired precision, and the IS/OOS cumulative win rates all move to the same test. IS and OOS are read side by side as the overfitting signal, so measuring one in wins and the other in agreement would put a fixed gap between them that has nothing to do with generalization - the confidence threshold is FITTED on wins too, so the operating point maximises what the gate grades - per-class label-agreement precision is still computed and logged; it is the right diagnostic for class separation, just not for a deploy decision - era line renamed dir-precision -> win-rate, chance -> chance=break-even Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 16:00:51 -04:00
if(oTradeWon)
fix: NMS gates the TRADE, not just the arrow - one arrow is now one trade NmsLiveAccept() appeared in exactly one place: wrapped around DrawObject(). It never touched dPrevSignal, and dPrevSignal is what LongCondition() / ShortCondition() / SignedAIConfidence() read. So a declustered bar lost its arrow and still opened a position. Measured on SP500 H1 2026-08-09: CONV called a direction on 64% of bars, so the ~500 bars visible on screen held ~320 decisions - and ~40 arrows were drawn. Roughly one arrow per eight positions the EA would take. And the survivors are not a random eighth. Rule 2 of the declustering keeps the HIGHER-CONFIDENCE side of a cluster, so the visible set is systematically the best member of each run. A chart showing the best of every eight decisions and hiding the rest reads far better than the model is - the same best-of-N selection error already corrected in the geometry scan, the indicator tuner, the lag profile and the deploy gate, this time on the display layer, where it is most likely to mislead the person deciding whether to trade. Fixed by neutralising dPrevSignal when NMS rejects, rather than adding a "may trade" flag consulted at each read site: that leaves exactly ONE definition of what the model decided this bar, so the arrow, the panel's "Current signal", the confidence feeding sizing/SL/TP/trailing, the refresh tally and the order itself cannot drift apart again. Also reports the consequence instead of hiding it. Every OOS counter on the era line still scores every directional call - a population ~8x larger than what now trades - so the line carries a second figure: | TRADED (declustered) NN% on N calls (edge +Npp) replaying the identical rule over pass 3 (which walks OOS bars oldest to newest, the same order the live sweep sees). Its cursors are separate members from the live ones so a training pass can never disturb the live chart's declustering. Deliberately NOT switched into selectionScore yet. Declustering cuts coverage from ~64% of bars to ~8%, well under MIN_COVERAGE_FRACTION_OF_BASE_RATE, which would make every checkpoint undeployable overnight - the minRR collision and the recall-floor catch-22 twice over. The floor gets re-derived from these measurements first. Compiles clean: 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-09 10:22:31 -04:00
m_oosNmsHits++;
}
}
}
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
// Same confusion counts keyed by what the model actually PREDICTED this bar, not the
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
// true label - see m_oos.buyPredicted's declaration comment for why recall alone can
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
// hide an over-firing class.
switch(DoubleToSignal(oPrevSignal))
{
case Buy:
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.buyPredicted++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
if(hit)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.buyPredictedHits++;
fix: the deploy gate was benchmarking a win rate against a label frequency The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test. That invariant needs reward >= risk, and the measured geometry no longer satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but both-won bars were stripped out of Buy and Sell so the label base rate read 37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma against 37.5% and loses money on every single trade. Live since 217b9bc. Root cause is that label agreement stopped being the same question as trade profitability. Buy implies winLong, but the converse fails on every both-won bar, and the label can only name one of two directions that both pay. So stop asking the model whether it matched a label and start asking whether its trade paid: - cache winLong/winShort per bar beside the label, under the same validity flag; published from the barrier walk before the collapse to 3 classes - dirPrecPct now counts wins on the side actually called - chancePrecPct is max(P(winLong), P(winShort)), MEASURED - the textbook m/(m+k) would credit SP500's drift to the model - the NMS "what would I have made" pair, the live-fired precision, and the IS/OOS cumulative win rates all move to the same test. IS and OOS are read side by side as the overfitting signal, so measuring one in wins and the other in agreement would put a fixed gap between them that has nothing to do with generalization - the confidence threshold is FITTED on wins too, so the operating point maximises what the gate grades - per-class label-agreement precision is still computed and logged; it is the right diagnostic for class separation, just not for a deploy decision - era line renamed dir-precision -> win-rate, chance -> chance=break-even Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 16:00:51 -04:00
if(oWinLong)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.buyPredictedWins++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
break;
case Sell:
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.sellPredicted++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
if(hit)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.sellPredictedHits++;
fix: the deploy gate was benchmarking a win rate against a label frequency The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test. That invariant needs reward >= risk, and the measured geometry no longer satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but both-won bars were stripped out of Buy and Sell so the label base rate read 37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma against 37.5% and loses money on every single trade. Live since 217b9bc. Root cause is that label agreement stopped being the same question as trade profitability. Buy implies winLong, but the converse fails on every both-won bar, and the label can only name one of two directions that both pay. So stop asking the model whether it matched a label and start asking whether its trade paid: - cache winLong/winShort per bar beside the label, under the same validity flag; published from the barrier walk before the collapse to 3 classes - dirPrecPct now counts wins on the side actually called - chancePrecPct is max(P(winLong), P(winShort)), MEASURED - the textbook m/(m+k) would credit SP500's drift to the model - the NMS "what would I have made" pair, the live-fired precision, and the IS/OOS cumulative win rates all move to the same test. IS and OOS are read side by side as the overfitting signal, so measuring one in wins and the other in agreement would put a fixed gap between them that has nothing to do with generalization - the confidence threshold is FITTED on wins too, so the operating point maximises what the gate grades - per-class label-agreement precision is still computed and logged; it is the right diagnostic for class separation, just not for a deploy decision - era line renamed dir-precision -> win-rate, chance -> chance=break-even Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 16:00:51 -04:00
if(oWinShort)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.sellPredictedWins++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
break;
default:
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.neutralPredicted++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
if(hit)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.neutralPredictedHits++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
break;
}
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- Live-decision precision: scores the bars on which the deployed EA would
//--- actually cast a directional vote, using the prior-corrected (logit-adjusted)
//--- posterior - see AdjustedSignalFromSoftmax()/RefreshLatestSignal().
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
if(m_outputNeuronsCount == 3)
{
double adjSig = AdjustedSignalFromSoftmax();
ENUM_SIGNAL adjEnum = DoubleToSignal(adjSig);
if(adjEnum != Neutral)
{
fix: the deploy gate was benchmarking a win rate against a label frequency The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test. That invariant needs reward >= risk, and the measured geometry no longer satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but both-won bars were stripped out of Buy and Sell so the label base rate read 37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma against 37.5% and loses money on every single trade. Live since 217b9bc. Root cause is that label agreement stopped being the same question as trade profitability. Buy implies winLong, but the converse fails on every both-won bar, and the label can only name one of two directions that both pay. So stop asking the model whether it matched a label and start asking whether its trade paid: - cache winLong/winShort per bar beside the label, under the same validity flag; published from the barrier walk before the collapse to 3 classes - dirPrecPct now counts wins on the side actually called - chancePrecPct is max(P(winLong), P(winShort)), MEASURED - the textbook m/(m+k) would credit SP500's drift to the model - the NMS "what would I have made" pair, the live-fired precision, and the IS/OOS cumulative win rates all move to the same test. IS and OOS are read side by side as the overfitting signal, so measuring one in wins and the other in agreement would put a fixed gap between them that has nothing to do with generalization - the confidence threshold is FITTED on wins too, so the operating point maximises what the gate grades - per-class label-agreement precision is still computed and logged; it is the right diagnostic for class separation, just not for a deploy decision - era line renamed dir-precision -> win-rate, chance -> chance=break-even Both build variants compile 0 errors, 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 16:00:51 -04:00
//--- Same substitution as everywhere else in this block: what a buyer gets forward is
//--- whether the trade paid, not whether it agreed with a collapsed label.
bool fireHit = (adjEnum == Buy) ? oWinLong : oWinShort;
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- Bucket the same fire by confidence tier - see m_oosTierFired. It does
//--- not. ConfidenceTier() reads dPrevSignal, and dPrevSignal is assigned in
//--- PASS 1 only (the in-sample pass) - never anywhere in this OOS scan.
feat(rank): AI models rank their own confidence tiers from held-out outcomes Closes the caveat 4858507 shipped with: the vote is a confidence percentage, but only to the extent the pattern weights are measured. AI tier weights sat at their designed defaults (25/50/75/100) because AI rows only ever arrive from LIVE journaling, of which a training run produces almost none. AND A STALE-TIER BUG THAT MADE THE EVIDENCE MEANINGLESS. The OOS scan bucketed every scanned bar by ConfidenceTier(), which reads dPrevSignal - and dPrevSignal is assigned in PASS 1 only, never anywhere in the OOS scan. So an entire era's fires were bucketed by one stale, unrelated bar's confidence and landed in a SINGLE tier. That is the "tier prec T0:72%(828) T1:n/a(0) T2:n/a(0) T3:n/a(0)" symptom recorded on 2026-08-16 and attributed to the calibration clamp. The clamp was real and was fixed then; this is a second, independent cause of the identical output that survived that fix untouched - which is why the log kept reading the same afterwards. Two causes, one symptom. Now ConfidenceTierFor(adjSig): the bar this iteration actually scored. WHY THIS DOES NOT WRITE ROWS TO THE SIGNAL DB, which was the obvious reading of "fill the database during training". The user's own observation is the reason: a classic Pattern_2 is a fixed geometric condition, so its win rate is legitimately accumulated over years, but an AI Pattern_2 means "confidence landed in tier 2" and tier 2 under era 100's weights is a different statement from tier 2 under era 500's. The DB's value is ACCUMULATION, and accumulation is exactly what is wrong here - it would average together models that no longer exist, while colliding with the per-table row cap and mixing measured-on-holdout outcomes into the live ledger's own tables. What the DB actually supplies is a measured win rate per pattern, and pass 3 already computes that on held-out bars, thousands at a time. So the model ranks itself once per era, REPLACING rather than accumulating, which makes the weights describe the current weights by construction. ESTIMATOR. Not WinRateFromCounts(): it returns NO_DATA below 100 raw trades BEFORE shrinking, which here would fire on every tier every era and hand all four the pooled rate - the tiers could never separate and the mechanism would be inert. Shrinkage is the answer to a small sample; a floor in front of it means the shrinkage never runs. Instead: a Beta prior of TIER_PRIOR_EFF_N pseudo-observations centred on the model's pooled holdout rate, counted in EFFECTIVE observations, because overlapping triple-barrier labels mean 800 raw fires can be worth ~12 independent ones. Rounded to the integer, not to the decade NormalizeWinRate() uses, which would collapse the shrunk tiers back into one number. NO SAME-ERA CIRCULARITY, and it falls out of the ordering rather than a guard: weights are computed at the END of era N, so the vote scored during era N was cast with era N-1's weights. The deploy gate never grades a vote whose weights were fitted on the bars it is scoring. Residual leakage remains - the same OOS bars each era under a different model - and is stated in the code rather than papered over. Both DB clobber paths are closed: ApplyPatternWeight() declines once self-ranked, and UpdateSignalsWeights()' filter.Weight() call is guarded by SelfRanked() - guarding only the tiers would have let the hourly ranking pass undo half the self-ranking. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-18 16:00:32 -04:00
int fireTier = ConfidenceTierFor(adjSig);
feat(ai): measure precision per confidence tier; fix stale metric labels Two things the 2026-07-30 run exposed. 1. Every user-facing message still called the selection metric "balanced accuracy". It has ranked on directional precision since a142749, so "CONVERGED ... balanced accuracy 32.5%" was reporting a 32.5% PRECISION as if it were macro-recall, while the same era logged an actual balanced accuracy of 49%. Two different numbers under one name, in the line that announces a deploy. Relabelled at every site, including the stage-3 refusal, which still described the per-class recall floor that stopped being the gate. 2. Precision is now bucketed by confidence tier and logged per era, both per-tier and cumulatively from each tier upward: | tier prec T0:19%(410)[>=28%/1204] T1:31%(520)[>=34%/794] ... The per-tier number says whether confidence is calibrated to correctness at all; if it does not rise T0->T3, raising the floor buys nothing and that is the finding. The ">=" number is what a floor would actually deliver, with its fire count, so the coverage cost is visible in the same line. Tier weights are 25/50/75/100, so for an AI-only config Min_Vote_Open maps straight across: 50 = ">=T1", 75 = ">=T2", 100 = ">=T3". Bucketing happens at the existing live-fired accounting site, so it measures exactly the population that trades - not the raw argmax. Both builds compile 0 errors, 0 warnings. No retrain needed for either. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-30 11:47:15 -04:00
if(fireTier >= 0 && fireTier < 4)
{
m_oosTierFired[fireTier]++;
if(fireHit)
m_oosTierHits[fireTier]++;
}
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
if(adjEnum == Buy)
{
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.buyFired++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
if(fireHit)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.buyFiredHits++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
else
{
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.sellFired++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
if(fireHit)
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_oos.sellFiredHits++;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
}
}
if(hit)
{
dOosForecast += (100 - dOosForecast) / Net.recentAverageSmoothingFactor;
dOosError -= dOosError / Net.recentAverageSmoothingFactor;
}
else
{
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
dOosForecast -= dOosForecast / Net.recentAverageSmoothingFactor;
dOosError += (100 - dOosError) / Net.recentAverageSmoothingFactor;
}
}
//--- Predicted-class tally for the OOS window, which pass 1 used to compute from its
//--- own (now-removed) redundant feedForward on this same bar - see the
//--- laterPassForwards comment there.
switch(DoubleToSignal(oPrevSignal))
{
case Buy:
m_countBuySignals++;
break;
case Sell:
m_countSellSignals++;
break;
default:
m_countNeutralSignals++;
break;
}
// Chart annotation for this (OOS) bar, using post-training weights - pass 1 no longer
// draws these at all (it used to, from a pre-training snapshot that this then overwrote).
m_lastBarTime = m_Time.GetData(oi);
if(oi > 0)
{
// NMS on: record only (the era-end sweep renders); off: draw inline. See pass 1's note.
if(m_signalClusterWindow > 0)
{
if(oi < ArraySize(m_arrowSignalCache))
m_arrowSignalCache[oi] = oDeploySignal;
}
else
if(DoubleToSignal(oDeploySignal) == Neutral)
DeleteObject(m_lastBarTime);
else
DrawObject(m_lastBarTime, oDeploySignal, m_Close.GetData(oi));
}
}
} // end direction (non-meta) OOS scoring body
//--- Time OR stop - see pass 2's matching comment.
fix(training): the wall-clock budget was left behind in Train() Compile error, four sites: TRAIN_TIME_BUDGET_MS was a const local to Train(), and the four passes that yield on it are now defined above Train(). I checked every pass for the eight locals STrainEra replaced and missed the ninth, because it was a const rather than a variable. It is per-call state like everything else in STrainEra, so it moves there as budgetMs. All four sites asked the same question the same way GetTickCount() - era.chunkStartTick >= TRAIN_TIME_BUDGET_MS so the struct answers it once as BudgetSpent(). Swept for the same class of mistake rather than waiting for another compile: Train() now has exactly two top-level locals left (STABILITY_WINDOW, STABILITY_TOLERANCE) and neither appears in any extracted body. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:40:15 -04:00
if(m_oosScoreIndex - 1 >= 2 && (IsStopped() || era.BudgetSpent()))
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
{
//--- yield: save enough to resume PASS 3 mid-walk on the next call - m_isPass3Active and
//--- m_oosScoreIndex (both members) carry the actual resume position.
StashEraResume(era.bars, era.totalIter, era.oosCutoff, era.addLoop, era.i);
return;
}
}
m_isPass3Active = false;
//--- THE EXIT SIMULATION, and it has to run HERE rather than inline in the scan above. So at
//--- the moment bar r is graded its own exit has not been decided yet. Only now is
//--- m_oosDecisionSeries complete over the whole OOS window.
SimulateExitPolicyOutcomes();
ReportExitPolicyDivergence();
ReportCandidateGeometry();
//--- Excursion head's verdict for this era, printed while its accumulators are complete and
//--- before the next era's fresh-era block clears them.
ExcursionReport();
//--- Scoring finished - resume the normal always-adapting statistics (see the freeze at pass-3
//--- start) before anything else runs a forward pass.
Net.SetBatchNormFrozen(false);
//--- Pass 3 done => every scored bar's prediction is now in m_arrowSignalCache. Collapse each
//--- same-direction cluster to its earliest bar so the chart shows one arrow per real turn.
PruneDirectionalClusters(era.bars);
//--- ...and now that this era's per-tier outcomes are complete, turn them into the vote weights
//--- the NEXT era (and live trading) will use. See RankTiersFromOos().
RankTiersFromOos();
//--- ...and re-derive the Intelligent-direction drift verdict on the same cadence: the label
//--- cache it scans shifts with new bars, and a verdict that only refreshed at full rebuilds
//--- could sit stale for weeks (flagged in the 2026-08-19 review). Prints only on change.
RefreshDriftVerdict();
//--- ...and, once per run and only if asked, put two completely different learners on this exact
refactor(baselines): the first real module - a class, not an #included partial Baselines was 951 lines of CExpertSignalAIBase method bodies in a file that only looked like a module. It is now CBaselineComparator: a class the signal OWNS, which reads a CTrainingDataView and prints. It does not name the signal anywhere in its code. What the seam forced out into the open: - Thirty-odd ArraySize() bounds tests, each carried by its caller, are now one test per accessor next to the data. The two `hasValueN` and one `arrowN` locals are gone with them. - The -2.0 "never scored" sentinel on the arrow cache was tested at the call site. It is now inside DataDirectionalCall, where it cannot be read as a small confidence. - DoubleToSignal needs m_outputNeuronsCount, so a raw double could not be turned into a side by any reader. The view answers DirectionalCall(bar, isBuy, magnitude) instead - the conversion happens where the head width lives, and the module no longer needs ENUM_SIGNAL at all. - m_baselineDone was a latch on the signal for a decision only this module makes. It is m_done, private, where it belongs. Correction to my own earlier claim: I said Baselines had nine exclusive members "polluting the signal class". It had none. m_x, m_f, m_ngrad, m_AvgCE and the rest are FIELDS OF ALGLIB REPORT OBJECTS (state.m_x, mrep.m_AvgCE) that my `\bm_\w+` scan matched after the dot. The module needs no private state but its view pointer and that latch - which is why it came out this cleanly. The include sits below the g_ens* vote globals and the Alglib headers it reads, because unlike the AIBase\*.mqh partials this is a real class declaration compiled where it stands. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 12:00:18 -04:00
//--- matrix so "the net is flat" can be told apart from "the matrix is flat". See CBaselineComparator.
m_baselines.RunBaselineComparison(era.bars, era.totalIter, era.oosCutoff);
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
}
}
//+------------------------------------------------------------------+
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
//| Shared preamble for the three exclusive walks. |
//| |
//| Each takes a whole Train() call, and each has to tell TWO |
//| watchdogs the same thing: the stall reporter which branch is |
//| running, and the era-barrier watchdog that this member is BUSY |
//| rather than stuck. Written out three times, it was three chances |
//| for a new walk to be added with only one of them. |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::ClaimCallForWalk(const string branch)
{
ReportTrainStall(branch);
NoteBarrierProgress();
}
//+------------------------------------------------------------------+
//| Why this member is idle at the ensemble era barrier. |
//| |
//| Resetting the stall watchdog was once the only thing the hold |
//| branch did, so a held member left no record anywhere. It reports |
//| on a cadence rather than on entry: a brief hold every era is the |
//| DESIGN - the fast member waits a few seconds here every era - |
//| and printing on entry logged ~950 lines per member per day. |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::ReportBarrierHold(void)
{
//--- AND SAY SO IN THE JOURNAL. Resetting the watchdog above is right (a held member is idle,
//--- not stalled) but it was the ONLY thing this branch did, so a held member left no record
//--- anywhere.
uint nowTick = GetTickCount();
//--- ARM SILENTLY, REPORT ONLY WHEN THE HOLD OUTLASTS THE INTERVAL (2026-08-19). Printing on
//--- entry logged ~950 lines/member/day, because a brief hold at the barrier is the DESIGN -
//--- the fast member waits a few seconds here every era.
bool justHeld = (m_barrierHoldReportTick == 0);
if(justHeld)
m_barrierHoldReportTick = nowTick;
if((VerboseMode && justHeld) ||
nowTick - m_barrierHoldReportTick >= ENSEMBLE_BARRIER_REPORT_MS)
{
m_barrierHoldReportTick = nowTick;
long minEra = EnsembleMinTrainingEra();
string blockers = "";
for(int bi = 0; bi < ArraySize(g_warriorEnsemble); bi++)
{
CExpertSignalAIBase *bm = g_warriorEnsemble[bi];
if(CheckPointer(bm) == POINTER_INVALID)
continue;
if(bm.m_trainingComplete || bm.m_trainingStopRequested || bm.m_trainingPaused ||
!bm.m_isInitialized || bm.m_barrierExcluded)
continue;
if(bm.m_eraCount <= minEra)
blockers += (blockers == "" ? "" : ", ") + bm.ID;
}
if(EnsembleLeadCapHolds())
PrintFormat("%s: HELD BY THE ENSEMBLE LEAD CAP - this member is at era %d, the slowest member"
" on the chart is at era %d, and %d eras is as far ahead as any member may get."
" That slower member has ALREADY been dropped from the barrier for not advancing,"
" so nothing will resolve this on its own: diagnose it. Until it catches up the"
" combined vote cannot be scored and no joint checkpoint can be taken, so training"
" past this point would produce weights no gate could ever certify.",
ID, (int)m_eraCount, (int)EnsembleMinEraAnyMember(), ENSEMBLE_MAX_ERA_LEAD);
else
PrintFormat("%s: HELD AT THE ERA BARRIER - this member is at era %d and the ensemble minimum is"
" %d, so it is idle until [%s] catch up. It is NOT stalled and its weights are"
" untouched. If this line keeps repeating, the member(s) named are the ones to"
" diagnose - after %d minutes with no era AND no preparation-phase progress they"
" are dropped from the barrier and this member resumes, up to %d eras ahead.",
ID, (int)m_eraCount, (int)minEra, blockers == "" ? "(none - resolving)" : blockers,
(int)(ENSEMBLE_BARRIER_STUCK_MS / 60000), ENSEMBLE_MAX_ERA_LEAD);
}
}
//+------------------------------------------------------------------+
//| Does this call belong to training at all? |
//| |
//| Six ways it does not: paused, stopping, deploying an approved |
//| ensemble checkpoint, held at the era barrier, or occupied by one |
//| of the three exclusive walks. Each answers for the WHOLE call. |
//| |
//| None of this is training, which is why it is no longer inside |
//| Train(). What is left there now reads as the era lifecycle it |
//| always was, instead of opening with a hundred and twenty lines |
//| of reasons not to run. |
//| |
//| Writes era.stop, which the caller needs either way. |
//+------------------------------------------------------------------+
bool CExpertSignalAIBase::TrainCallPreempted(STrainEra &era)
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
{
//---
//--- Never block the calling thread while paused/stopped - just decline this call (or finalize a
//--- run that just got stopped) and let the next scheduled call check again, so Pause/Resume/Stop
//--- and everything else on the control panel stays responsive instead of Sleep()-ing the one
//--- MQL5 thread this chart has.
if(m_trainingPaused && !IsStopped() && !m_trainingStopRequested)
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
return true;
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
era.stop = IsStopped() || m_trainingStopRequested;
if(era.stop)
{
if(m_trainRunActive)
FinalizeTrainRun();
if(m_simOosRunActive)
{
delete m_simOosNet;
m_simOosNet = NULL;
m_simOosRunActive = false;
}
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
return true;
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
}
//--- ENSEMBLE DEPLOY, approved by the ensemble gate on some member's era end (see
//--- EnsembleEraVerdict). Each member restores its own half of that checkpoint, so the quartet
//--- that goes live is the one the vote was measured on.
if(m_ensembleMember && g_ensDeployApproved && !m_trainingComplete &&
m_haveOosCheckpoint && m_checkpointEra == g_ensBestEra)
{
m_trainingComplete = true;
Print(ID + ": ENSEMBLE DEPLOY - restoring this model's weights from the joint checkpoint at era " +
IntegerToString((int)g_ensBestEra) + " and switching to live inference. The combined vote,"
" not this model alone, is what cleared the gate.");
if(m_trainRunActive)
FinalizeTrainRun();
//--- Same one-shot pattern-database backfill the solo path arms at its era end, and for the
//--- same reason (see StartPatternDatabaseBackfill): a deployed model has to be RANKED the
//--- instant it goes live, not an hour of real trades later.
StartPatternDatabaseBackfill(m_resumeBars, m_resumeTotalIter, m_resumeOosCutoff);
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
return true;
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
}
//--- ENSEMBLE ERA BARRIER (user request 2026-08-16): members advance era by era TOGETHER,
//--- because the number that matters - the combined-vote OOS score - is only well-defined when
//--- every member's pass 3 describes the same era, and because live trading is the members
//--- voting together, not four models drifting apart in training age.
BarrierEraHeartbeat();
if(EnsembleEraBarrierHolds())
{
//--- deliberate idleness, not a stall - keep the stall watchdog's era clock current and say
//--- what is happening on the member's panel line instead of freezing its last progress text
m_lastEraCompleteTick = GetTickCount();
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
ReportBarrierHold();
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
PublishStatus(StringFormat("Waiting at era %d for slower ensemble members (min era %d) - donating its compute until they catch up",
(int)m_eraCount, (int)EnsembleMinTrainingEra()));
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
return true;
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
}
m_barrierHoldReportTick = 0;
//--- Evaluation-only continual-learning OOS simulation walk in progress (see
//--- StartOosContinualSimulation): give it exclusive occupancy of this call, same chunked budget
//--- as the real era loop below, so a large OOS window can't freeze the UI in one shot.
if(m_simOosRunActive)
{
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
ClaimCallForWalk("OOS continual-learning simulation walk");
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
AdvanceOosSimulationChunk();
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
return true;
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
}
//--- One-shot pattern-database backfill in progress (see StartPatternDatabaseBackfill) - same
//--- exclusive-occupancy/chunking treatment as the simulation walk above.
if(m_dbBackfillActive)
{
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
ClaimCallForWalk("pattern-database backfill walk");
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
AdvancePatternDatabaseBackfill();
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
return true;
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
}
//--- Eager label-cache pre-build in progress (see StartLabelCachePrebuild/AdvanceLabelCachePrebuild) -
//--- same exclusive-occupancy/chunking treatment as the OOS simulation walk above, so it can't freeze
//--- the UI on a large study window either. m_trainRunActive stays false for its whole duration, so
//--- once it completes, Train() falls through to the normal !m_trainRunActive setup below and era 0
//--- starts from the measured class distribution it just seeded.
if(m_labelPrebuildActive)
{
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
ClaimCallForWalk("label-cache prebuild scan");
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
AdvanceLabelCachePrebuild();
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
return true;
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
}
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
//--- Nothing claimed this call: it is a training call.
return false;
}
//+------------------------------------------------------------------+
//| EVERYTHING AN ERA DOES AFTER ITS LAST PASS SCORES. |
//| |
//| Calibrate confidence, read the recalls, run the deploy gate, |
//| fill the telemetry, rank this era against the best so far, |
//| capture or restore a checkpoint, advance the learning-rate and |
//| plateau ladders, test stability, and persist. One era's verdict. |
//| |
//| Lifted whole rather than split, and deliberately so: its parts |
//| share thirty-odd locals - the recalls, the gate verdict, the |
//| better/worse flags - and threading those through three signatures |
//| would recreate the eight-locals-across-four-passes problem that |
//| STrainEra was built to end. Splitting this further needs an |
//| era-outcome object first, not more parameters. |
//| |
//| Nothing here returns early, which is why it could move at all: |
//| Train() still runs the era line, the finalizer and the backfill |
//| after it on every path. |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::CompleteEra(STrainEra &era, SEraTelemetry &tel)
{
const int STABILITY_WINDOW = 3; // consecutive eras the OOS accuracy must hold steady for
const double STABILITY_TOLERANCE = 2.0; // max spread (percentage points) across that window
if(!era.stop)
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
{
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
dError = Net.getRecentAverageError();
if(era.addLoop)
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
{
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
if(m_oosSamples > 0)
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
{
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
// Confidence calibration (classification head only - see m_confidenceCalScale's
// declaration comment): compare this era's actual OOS accuracy against the average
// confidence magnitude the model claimed, EMA-blend the resulting scale into
// m_confidenceCalScale so SignedAIConfidence() reports something closer to a real
// probability instead of the raw, uncalibrated softmax value.
if(m_outputNeuronsCount == 3 && m_oos.confidenceSum > 0.0)
refactor(training): each of an era's four passes is its own method Train() was still 2,572 lines because the four passes it runs - the scan/queue sweep, the shuffled replay, the purged calibration walk and the OOS scoring walk - were written inline as four consecutive blocks sharing one scope. STrainEra removed the only obstacle to moving them. Each pass now keeps its own guard inside its own body, so it is self-contained: RunPass2 still tests !era.stop && era.addLoop && !m_isPass2Done itself rather than being called conditionally. Train() reads as the sequence it always was. RunOosPass MEASURES and nothing more - the recall gate, plateau ladder, deploy gate and era checkpoint read its numbers afterwards and stay in Train(). The first version of its header comment claimed it ran those too; the body is 504 lines and does not, so the comment was corrected rather than shipped. Verified by stripping comments and whitespace from both revisions: ZERO statements removed, sixteen added - four signatures, their eight braces and four call sites. Every other statement byte-identical. Train() 2,572 -> 1,282 lines. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:30:31 -04:00
{
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
//--- accuracy / mean claimed confidence. Both terms would divide by the same sample
//--- count, so it cancels - which matters, because m_oosSamples is RUN-level while
//--- these tallies are per-era. Writing the ratio directly removes the chance that
//--- someone later logs or gates on one half and gets a number that decays with era
//--- count. If either term is ever needed alone, it needs a per-era denominator.
double eraScale = MathMax(0.3, MathMin(1.5, (double)m_oos.Hits() / m_oos.confidenceSum));
m_confidenceCalScale += (eraScale - m_confidenceCalScale) / Net.recentAverageSmoothingFactor;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
// Per-class recall gate, symmetric across all three classes: a model that "wins" on
// blended dOosForecast purely by calling everything Neutral (or, just as biased, by
// over-calling Buy/Sell at Neutral's expense) would still pass a plain accuracy check -
// require Buy, Sell, AND Neutral OOS recall to each individually clear
// m_minDirectionalRecallPct so the network can't converge while biased toward any one
// output. A class with FEWER than MIN_OOS_CLASS_SAMPLES_FOR_GATE true OOS samples this
// era doesn't block (recallPct == -1 => treated as passing) so a thin OOS window doesn't
// deadlock convergence early in a run. Computed BEFORE the checkpoint/g_eta-decay block
// below (not just the final m_objectiveMet gate) so "best" ranking is recall-aware too -
// see isBetterEra's comment for why that matters.
//
// The threshold matters: a bare ">0" here (the original behavior) let a run converge at
// era 44-46 with the OOS window containing exactly ZERO true Buy/Sell bars that era
// (logged as "OOS recall Buy:n/a Sell:n/a Neutral:100%") - a full Neutral-only collapse
// that the gate waved through because there was nothing to measure recall against, not
// because the model was actually unbiased. Requiring a real minimum sample count means
// an unlucky/thin OOS slice blocks convergence instead of silently passing it.
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
int buyRecallPct = m_oos.BuyRecallPct(MIN_OOS_CLASS_SAMPLES_FOR_GATE);
int sellRecallPct = m_oos.SellRecallPct(MIN_OOS_CLASS_SAMPLES_FOR_GATE);
int neutralRecallPct = m_oos.NeutralRecallPct(MIN_OOS_CLASS_SAMPLES_FOR_GATE);
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
tel.buyRecall = buyRecallPct;
tel.sellRecall = sellRecallPct;
tel.neutralRecall = neutralRecallPct;
m_lastBuyRecallPct = buyRecallPct;
m_lastSellRecallPct = sellRecallPct;
//--- Predicted-rate (share of ALL OOS bars this era the model called this class,
//--- regardless of whether that call was right) and precision (of just those calls,
//--- how many were right) - see tel.buyPred's declaration comment above for why
//--- this is worth logging alongside recall.
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
int oosEraBars = m_oos.Bars();
//--- ONE denominator for all of these, so the log's columns are directly comparable
//--- rather than nearly so; -1 = nothing to divide by. Neutral is the RESIDUAL on both
//--- layers: every OOS bar gets exactly one call, so what is not Buy and not Sell is
//--- Neutral by construction.
tel.buyTrue = m_oos.PctOfBars(m_oos.buyTotal);
tel.sellTrue = m_oos.PctOfBars(m_oos.sellTotal);
tel.neutralTrue = m_oos.PctOfBars(m_oos.neutralTotal);
tel.neutralPred = m_oos.NeutralPredictedShare();
//--- The traded layer: candidates that cleared m_dirConfThreshold. A bar the operating
//--- point rejects is a bar the model sits out.
tel.buyFired = m_oos.PctOfBars(m_oos.buyFired);
tel.sellFired = m_oos.PctOfBars(m_oos.sellFired);
tel.neutralFired = m_oos.NeutralFiredShare();
tel.buyPred = m_oos.PctOfBars(m_oos.buyPredicted);
tel.sellPred = m_oos.PctOfBars(m_oos.sellPredicted);
tel.buyPrec = SOosTally::Pct(m_oos.buyPredictedHits, m_oos.buyPredicted);
tel.sellPrec = SOosTally::Pct(m_oos.sellPredictedHits, m_oos.sellPredicted);
//--- Live-fired precision (what actually trades - see m_oos.buyFired): of the directional
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
//--- calls that cleared the confidence floor under the live/prior-corrected rule this era,
//--- how many were right. Cached for the panel/log; -1 = the model fired none this era.
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
tel.buyFiredPrec = SOosTally::Pct(m_oos.buyFiredHits, m_oos.buyFired);
tel.sellFiredPrec = SOosTally::Pct(m_oos.sellFiredHits, m_oos.sellFired);
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
m_lastBuyFiredPrecPct = tel.buyFiredPrec;
m_lastSellFiredPrecPct = tel.sellFiredPrec;
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
m_lastBuyFired = m_oos.buyFired;
m_lastSellFired = m_oos.sellFired;
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
//--- SELECTION METRIC. Ranking moved off balanced accuracy (macro-recall) 2026-07-30
//--- because that metric is maximized by exactly the model this system must never
//--- deploy.
refactor(gate): the member gate and the ensemble gate were one rule written twice SDeployVerdict::EvaluateRates() is now the deploy arithmetic - coverage floor, chance + EDGE_MIN_SIGMAS x SE, tradeability, and the coverage- discounted ranking score - and both gates call it. The duplicate was self-documenting. The ensemble copy carried three comments asking a reader to keep it in step with the member copy by hand: "same intent as the member gate's coverage floor + bothSidesLive", "the two gates have to apply the identical correction or the ensemble becomes the easier one to clear", "same lexicographic ordering as isBetterEra". They had already fallen out of step once - 2c443ba found the ensemble certifying a vote the EA never casts, in the wrong currency and against the wrong denominator. THE TWO REAL DIFFERENCES ARE NOW ARGUMENTS, not branches: chancePct - the ensemble filters its zero-skill reference by the direction policy, because with shorts blocked "always short" is not a book anyone could run. twoSided - a member reads per-side RECALL against a floor; the vote reads whether it actually fired both ways. Everything else was identical and is now literally identical. effN stays an argument so the label-overlap deflation lives where it is measured - and so the remaining inconsistency stays visible rather than buried: the two FAMILY-WISE selection gates still take their SE from RAW n. Recorded in the header, deliberately not changed; tightening them is a policy call, not a refactor. The decision now reads no chart, holds no net, prints nothing and opens no file, so it can be exercised against a made-up tally. BEHAVIOUR UNCHANGED: every expression keeps its formula, its guard and its -1 sentinel; the ensemble's chance-reference and two-sidedness rules are passed through untouched. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:19:44 -04:00
//--- THE WHOLE DEPLOY DECISION, evaluated off the tally in one call. Tradeability,
//--- the bar it had to clear and the ranking key all come out together, because they
//--- are one decision - see Training\DeployGate.mqh for why splitting them was wrong.
SDeployVerdict gate;
gate.Evaluate(m_oos, EffectiveSampleSize((double)m_oos.DirCalls()),
buyRecallPct, sellRecallPct);
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
int oosDirCalls = m_oos.DirCalls();
//--- WINS, not label agreement - see SOosTally::buyPredictedWins for the full argument.
int oosDirHits = m_oos.DirHits();
int oosDirTrue = m_oos.DirTrue();
refactor(gate): the member gate and the ensemble gate were one rule written twice SDeployVerdict::EvaluateRates() is now the deploy arithmetic - coverage floor, chance + EDGE_MIN_SIGMAS x SE, tradeability, and the coverage- discounted ranking score - and both gates call it. The duplicate was self-documenting. The ensemble copy carried three comments asking a reader to keep it in step with the member copy by hand: "same intent as the member gate's coverage floor + bothSidesLive", "the two gates have to apply the identical correction or the ensemble becomes the easier one to clear", "same lexicographic ordering as isBetterEra". They had already fallen out of step once - 2c443ba found the ensemble certifying a vote the EA never casts, in the wrong currency and against the wrong denominator. THE TWO REAL DIFFERENCES ARE NOW ARGUMENTS, not branches: chancePct - the ensemble filters its zero-skill reference by the direction policy, because with shorts blocked "always short" is not a book anyone could run. twoSided - a member reads per-side RECALL against a floor; the vote reads whether it actually fired both ways. Everything else was identical and is now literally identical. effN stays an argument so the label-overlap deflation lives where it is measured - and so the remaining inconsistency stays visible rather than buried: the two FAMILY-WISE selection gates still take their SE from RAW n. Recorded in the header, deliberately not changed; tightening them is a policy call, not a refactor. The decision now reads no chart, holds no net, prints nothing and opens no file, so it can be exercised against a made-up tally. BEHAVIOUR UNCHANGED: every expression keeps its formula, its guard and its -1 sentinel; the ensemble's chance-reference and two-sidedness rules are passed through untouched. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:19:44 -04:00
bool coverageMeasurable = gate.measurable;
double coveragePct = gate.coveragePct;
double dirPrecPct = gate.precPct;
double chancePrecPct = gate.chancePct;
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
tel.coverage = (int)MathRound(coveragePct);
tel.dirPrec = (int)MathRound(dirPrecPct);
tel.chancePrec = (chancePrecPct >= 0.0) ? (int)MathRound(chancePrecPct) : -1;
//--- Deployability. Replaces the per-class recall floor as the gate the checkpoint
//--- selection and the plateau ladder's "is there anything safe to deploy" test
//--- read. Observed 2026-08-01: the perceptron deployed at edge +0pp.
refactor(gate): the member gate and the ensemble gate were one rule written twice SDeployVerdict::EvaluateRates() is now the deploy arithmetic - coverage floor, chance + EDGE_MIN_SIGMAS x SE, tradeability, and the coverage- discounted ranking score - and both gates call it. The duplicate was self-documenting. The ensemble copy carried three comments asking a reader to keep it in step with the member copy by hand: "same intent as the member gate's coverage floor + bothSidesLive", "the two gates have to apply the identical correction or the ensemble becomes the easier one to clear", "same lexicographic ordering as isBetterEra". They had already fallen out of step once - 2c443ba found the ensemble certifying a vote the EA never casts, in the wrong currency and against the wrong denominator. THE TWO REAL DIFFERENCES ARE NOW ARGUMENTS, not branches: chancePct - the ensemble filters its zero-skill reference by the direction policy, because with shorts blocked "always short" is not a book anyone could run. twoSided - a member reads per-side RECALL against a floor; the vote reads whether it actually fired both ways. Everything else was identical and is now literally identical. effN stays an argument so the label-overlap deflation lives where it is measured - and so the remaining inconsistency stays visible rather than buried: the two FAMILY-WISE selection gates still take their SE from RAW n. Recorded in the header, deliberately not changed; tightening them is a policy call, not a refactor. The decision now reads no chart, holds no net, prints nothing and opens no file, so it can be exercised against a made-up tally. BEHAVIOUR UNCHANGED: every expression keeps its formula, its guard and its -1 sentinel; the ensemble's chance-reference and two-sidedness rules are passed through untouched. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:19:44 -04:00
double precSE = gate.precSE;
double edgeFloorPct = gate.edgeFloorPct;
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
//--- PUBLISHED so the era line can state the bar instead of leaving it implicit.
refactor(gate): the member gate and the ensemble gate were one rule written twice SDeployVerdict::EvaluateRates() is now the deploy arithmetic - coverage floor, chance + EDGE_MIN_SIGMAS x SE, tradeability, and the coverage- discounted ranking score - and both gates call it. The duplicate was self-documenting. The ensemble copy carried three comments asking a reader to keep it in step with the member copy by hand: "same intent as the member gate's coverage floor + bothSidesLive", "the two gates have to apply the identical correction or the ensemble becomes the easier one to clear", "same lexicographic ordering as isBetterEra". They had already fallen out of step once - 2c443ba found the ensemble certifying a vote the EA never casts, in the wrong currency and against the wrong denominator. THE TWO REAL DIFFERENCES ARE NOW ARGUMENTS, not branches: chancePct - the ensemble filters its zero-skill reference by the direction policy, because with shorts blocked "always short" is not a book anyone could run. twoSided - a member reads per-side RECALL against a floor; the vote reads whether it actually fired both ways. Everything else was identical and is now literally identical. effN stays an argument so the label-overlap deflation lives where it is measured - and so the remaining inconsistency stays visible rather than buried: the two FAMILY-WISE selection gates still take their SE from RAW n. Recorded in the header, deliberately not changed; tightening them is a policy call, not a refactor. The decision now reads no chart, holds no net, prints nothing and opens no file, so it can be exercised against a made-up tally. BEHAVIOUR UNCHANGED: every expression keeps its formula, its guard and its -1 sentinel; the ensemble's chance-reference and two-sidedness rules are passed through untouched. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:19:44 -04:00
//--- Nothing will ever clear an unreachable bar, and until this line printed it the
//--- symptom was indistinguishable from "the models are close but not quite".
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
m_lastEdgeFloorPct = edgeFloorPct;
m_lastPrecSE = precSE;
refactor(gate): the member gate and the ensemble gate were one rule written twice SDeployVerdict::EvaluateRates() is now the deploy arithmetic - coverage floor, chance + EDGE_MIN_SIGMAS x SE, tradeability, and the coverage- discounted ranking score - and both gates call it. The duplicate was self-documenting. The ensemble copy carried three comments asking a reader to keep it in step with the member copy by hand: "same intent as the member gate's coverage floor + bothSidesLive", "the two gates have to apply the identical correction or the ensemble becomes the easier one to clear", "same lexicographic ordering as isBetterEra". They had already fallen out of step once - 2c443ba found the ensemble certifying a vote the EA never casts, in the wrong currency and against the wrong denominator. THE TWO REAL DIFFERENCES ARE NOW ARGUMENTS, not branches: chancePct - the ensemble filters its zero-skill reference by the direction policy, because with shorts blocked "always short" is not a book anyone could run. twoSided - a member reads per-side RECALL against a floor; the vote reads whether it actually fired both ways. Everything else was identical and is now literally identical. effN stays an argument so the label-overlap deflation lives where it is measured - and so the remaining inconsistency stays visible rather than buried: the two FAMILY-WISE selection gates still take their SE from RAW n. Recorded in the header, deliberately not changed; tightening them is a policy call, not a refactor. The decision now reads no chart, holds no net, prints nothing and opens no file, so it can be exercised against a made-up tally. BEHAVIOUR UNCHANGED: every expression keeps its formula, its guard and its -1 sentinel; the ensemble's chance-reference and two-sidedness rules are passed through untouched. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:19:44 -04:00
m_lastEffN = gate.effN;
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
//--- CONTRIBUTE THIS ERA'S EVIDENCE TO THE CROSS-INSTRUMENT POOL, then read the pool
//--- back. See PooledGate.mqh.
if(coverageMeasurable && dirPrecPct >= 0.0 && chancePrecPct > 0.0)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
PublishPoolRecord(chancePrecPct, dirPrecPct, m_lastEffN);
m_lastPoolPasses = PooledGatePasses(m_lastPoolReport);
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
//--- BOTH sides must still be alive - see DEPLOY_MIN_SIDE_RECALL_PCT. A negative recall
//--- means "not measurable this era" (no true bars of that class in the OOS window), and
//--- that must not be read as a dead side, so it passes.
fix(gate): a field renamed on the definition side left one reader behind SDeployVerdict's bothSidesLive became twoSided when the member and ensemble gates were unified, and the member call site kept reading gate.bothSidesLive. SECOND TIME THIS EXACT SHAPE HAS BILLED THIS SESSION - the first was `s == 0` surviving the deletion of the loop that declared `s` (1d7ebbd). Renaming a declaration does not find its readers, and the compiler only finds them when no other binding happens to fit. So this is now checked rather than reviewed: every `instance.field` read against the six value objects is resolved against what the struct actually declares. Six structs, zero unresolved reads. Also renames the ensemble local `vote` to `voteGate`. SVoteAccumulator is already called `vote` in the base class, and two different `vote`s one inheritance step apart is a reader trap even where the scopes do not clash. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:40:29 -04:00
bool bothSidesLive = gate.twoSided;
refactor(gate): the member gate and the ensemble gate were one rule written twice SDeployVerdict::EvaluateRates() is now the deploy arithmetic - coverage floor, chance + EDGE_MIN_SIGMAS x SE, tradeability, and the coverage- discounted ranking score - and both gates call it. The duplicate was self-documenting. The ensemble copy carried three comments asking a reader to keep it in step with the member copy by hand: "same intent as the member gate's coverage floor + bothSidesLive", "the two gates have to apply the identical correction or the ensemble becomes the easier one to clear", "same lexicographic ordering as isBetterEra". They had already fallen out of step once - 2c443ba found the ensemble certifying a vote the EA never casts, in the wrong currency and against the wrong denominator. THE TWO REAL DIFFERENCES ARE NOW ARGUMENTS, not branches: chancePct - the ensemble filters its zero-skill reference by the direction policy, because with shorts blocked "always short" is not a book anyone could run. twoSided - a member reads per-side RECALL against a floor; the vote reads whether it actually fired both ways. Everything else was identical and is now literally identical. effN stays an argument so the label-overlap deflation lives where it is measured - and so the remaining inconsistency stays visible rather than buried: the two FAMILY-WISE selection gates still take their SE from RAW n. Recorded in the header, deliberately not changed; tightening them is a policy call, not a refactor. The decision now reads no chart, holds no net, prints nothing and opens no file, so it can be exercised against a made-up tally. BEHAVIOUR UNCHANGED: every expression keeps its formula, its guard and its -1 sentinel; the ensemble's chance-reference and two-sidedness rules are passed through untouched. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:19:44 -04:00
//--- Tradeability is ALSO the lexicographic ranking key (isBetterEra) and the g_eta-
//--- decay trigger, not merely a deploy-time check - see DeployGate.mqh.
bool tradeableOK = gate.tradeable;
double selectionScore = gate.selectionScore;
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
//--- THE S2 REPORT (Meta_Labeling_Design.md): the meta head's era verdict in the
//--- design's own terms - coverage x (win rate - break-even) against the no-skill
//--- null.
if(IsMetaTarget() && coverageMeasurable && oosEraBars > 0)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
double mSl, mTp;
BarrierMultiples(mSl, mTp);
double mBePct = (mSl + mTp > 0.0) ? 100.0 * mSl / (mSl + mTp) : 50.0;
double mScore = (dirPrecPct >= 0.0 && coveragePct >= 0.0)
? coveragePct * (dirPrecPct - mBePct) / 100.0 : 0.0;
PrintFormat("%s: META era %d - %d candidates OOS, base win %.1f%% | trades %d (%.1f%%"
" coverage) at %.1f%% win vs %.1f%% break-even -> cov x (p-BE) = %+.2f |"
" skill vs base %+.1fpp (needs > %+.1fpp at %d sigma) %s",
ID, (int)m_eraCount, oosEraBars, chancePrecPct, oosDirCalls, coveragePct,
dirPrecPct, mBePct, mScore,
dirPrecPct - chancePrecPct, EDGE_MIN_SIGMAS * precSE, (int)EDGE_MIN_SIGMAS,
tradeableOK ? "| DEPLOYABLE this era" : "");
//--- The decomposition the aggregate can hide (see the member declaration): each
//--- cell reads "traded/candidates base->traded win rate".
string famLine = "";
for(int mf = 0; mf < 4; mf++)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
double fb = (m_metaFamCand[mf] > 0) ? 100.0 * m_metaFamWins[mf] / m_metaFamCand[mf] : 0.0;
double fw = (m_metaFamFired[mf] > 0) ? 100.0 * m_metaFamFiredWins[mf] / m_metaFamFired[mf] : 0.0;
refactor(meta): one owner for the pattern taxonomy and its table names MetaCorpus was already a class, so the raw-include problem was not the one here. The problem was that the rule for naming a signal-DB pattern table MetaFamilyName(f) + "_Pattern_" + p + ("_Buy" | "_Sell") was written out FOUR times, each wrapped in its own identical family/pattern/side triple loop: the corpus loader, the stale-DB guard, META's row counter and META's exporter. Four chances for a rename to leave three of them querying an absent table and reporting it as "family disabled" - which is what that code says when a table is missing, so the failure would have looked like normal operation. CMetaFamilies now owns the taxonomy and that rule. Callers walk ONE flat index over all 52 tables and never spell a name: for(int ti = 0; CMetaFamilies::TableAt(ti, table, f, p, isBuy); ti++) Enumeration order is unchanged - Buy then Sell within a pattern, families in order - so the corpus is assembled in exactly the same sequence as before. META's OneHotSlot had a second hardcoded 0/4/8/14 ladder with a comment reading "matches MetaFamilyPatterns' 4/4/6/12" - a note asking a reader to keep two constants in step by hand. The ladder is now summed from the pattern counts, so they agree by construction. The bound against META_ONE_HOT_SLOTS stays in META: the head's input width is that class's business, and a taxonomy grown past it must be caught rather than silently truncated. Caught while re-reading the rewritten loop: my first counter was `t`, and the body declares `MqlDateTime t`. Renamed to `ti` at all four sites before it reached a compile. MetaCorpus.mqh moves to Expert\Training\ with the other real classes. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 12:26:33 -04:00
famLine += StringFormat("%s %d/%d %.1f->%.1f%% ", CMetaFamilies::Name(mf),
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
m_metaFamFired[mf], m_metaFamCand[mf], fb, fw);
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
double lb = (m_metaSideCand[0] > 0) ? 100.0 * m_metaSideWins[0] / m_metaSideCand[0] : 0.0;
double lw = (m_metaSideFired[0] > 0) ? 100.0 * m_metaSideFiredWins[0] / m_metaSideFired[0] : 0.0;
double sb = (m_metaSideCand[1] > 0) ? 100.0 * m_metaSideWins[1] / m_metaSideCand[1] : 0.0;
double sw = (m_metaSideFired[1] > 0) ? 100.0 * m_metaSideFiredWins[1] / m_metaSideFired[1] : 0.0;
PrintFormat("%s: META breakdown (traded/cands base->traded win, BE %.1f%%): %s|"
" LONG %d/%d %.1f->%.1f%% SHORT %d/%d %.1f->%.1f%%",
ID, mBePct, famLine,
m_metaSideFired[0], m_metaSideCand[0], lb, lw,
m_metaSideFired[1], m_metaSideCand[1], sb, sw);
}
//--- NEUTRAL CANNOT BLOCK WHEN IT IS TOO RARE TO LEARN. At that prevalence, almost
//--- never calling Neutral is CORRECT rather than biased, so the floor was demanding
//--- the model be wrong in a specific way before it could converge.
int neutralGatePct = neutralRecallPct;
if(oosEraBars > 0 &&
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
(100.0 * m_oos.neutralTotal / oosEraBars) < MIN_GATE_CLASS_SHARE_PCT)
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
neutralGatePct = -1;
//--- DERIVED, per class, from that class's own effective sample - see
//--- CollapseRecallFloorPct() for why it sits BELOW chance rather than above it, and for
//--- the two occasions a fixed constant here made convergence structurally impossible.
refactor(oos): twenty-one counters with one lifetime become one object SOosTally holds this era's OOS confusion counts and the rates they imply. The signal keeps one member where it kept twenty-one, and the era-reset block loses twenty of its twenty-one clearing lines. THE SHAPE THIS ENDS is the one that produced 7452bd1: a group of tallies read together but cleared one-per-line, so a second reset path could clear a subset and leave stale numerators over restarted denominators. Reset() is now the only way to clear them and it clears all of them. The pair had already started to drift. m_oosBuyFired/m_oosBuyFiredHits sat at line 1085 and their Sell twins at line 1140 - 55 lines and an unrelated member apart, with the Buy comment still claiming to describe both. DERIVED RATES MOVE WITH THE DATA. `(bars > 0) ? (int)MathRound(100.0 * x / bars) : -1` was written out twelve times, and the "-1 means not measurable, never 0" convention re-spelled at each - a convention the deploy gate depends on, since every caller tests `< 0` to mean "this does not block". One rounding rule and one sentinel now. GROUPED BY LIFETIME, NOT BY NAME. m_oosSamples looks like it belongs here and does not: it is RUN-level, reset only with the weights, and the status panel prints it beside dOosError which is also a run-level EMA. That pairing is correct and stays. But the confidence-calibration block divided per-era numerators by it, naming the results `empiricalAccuracy` and `avgClaimedConfidence` when neither is that - the run-level denominator cancels in their ratio, so eraScale was right and the two named intermediates were not. Now written as the ratio it actually is, with the cancellation stated, so nobody logs or gates on a half that decays with era count. BEHAVIOUR UNCHANGED: every moved expression preserves its formula, its denominator and its sentinel. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:15:22 -04:00
double buyFloor = CollapseRecallFloorPct(m_oos.buyTotal);
double sellFloor = CollapseRecallFloorPct(m_oos.sellTotal);
double neutralFloor = CollapseRecallFloorPct(m_oos.neutralTotal);
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
m_lastRecallFloorPct = (buyFloor + sellFloor + neutralFloor) / 3.0;
bool directionalRecallOK = (buyRecallPct < 0 || buyRecallPct >= buyFloor) &&
(sellRecallPct < 0 || sellRecallPct >= sellFloor) &&
(neutralGatePct < 0 || neutralGatePct >= neutralFloor);
//--- Balanced accuracy (macro-recall): the mean of the three per-class recalls - the
//--- metric the checkpoint SELECTION ranks on (see m_bestBalancedOos).
double balancedOosEra = (buyRecallPct >= 0 && sellRecallPct >= 0 && neutralRecallPct >= 0)
? (buyRecallPct + sellRecallPct + neutralRecallPct) / 3.0
: dOosForecast;
tel.balancedAcc = (buyRecallPct >= 0 && sellRecallPct >= 0 && neutralRecallPct >= 0)
? (int)MathRound(balancedOosEra) : -1;
//--- A real (non-thin-sample, i.e. not the -1 "n/a" sentinel) 0% recall on any class
//--- means the model never once got that class right this era - a majority-class
//--- collapse (predict-everything-Neutral, or symmetrically a Buy/Sell-only
//--- collapse), not progress toward separating classes.
//--- Under precision ranking the degenerate era is the one that called NOTHING
//--- directional (precision undefined, nothing to trade), not one whose per-class
//--- recall touched zero - a sparse high-precision model legitimately has low recall.
refactor(gate): the member gate and the ensemble gate were one rule written twice SDeployVerdict::EvaluateRates() is now the deploy arithmetic - coverage floor, chance + EDGE_MIN_SIGMAS x SE, tradeability, and the coverage- discounted ranking score - and both gates call it. The duplicate was self-documenting. The ensemble copy carried three comments asking a reader to keep it in step with the member copy by hand: "same intent as the member gate's coverage floor + bothSidesLive", "the two gates have to apply the identical correction or the ensemble becomes the easier one to clear", "same lexicographic ordering as isBetterEra". They had already fallen out of step once - 2c443ba found the ensemble certifying a vote the EA never casts, in the wrong currency and against the wrong denominator. THE TWO REAL DIFFERENCES ARE NOW ARGUMENTS, not branches: chancePct - the ensemble filters its zero-skill reference by the direction policy, because with shorts blocked "always short" is not a book anyone could run. twoSided - a member reads per-side RECALL against a floor; the vote reads whether it actually fired both ways. Everything else was identical and is now literally identical. effN stays an argument so the label-overlap deflation lives where it is measured - and so the remaining inconsistency stays visible rather than buried: the two FAMILY-WISE selection gates still take their SE from RAW n. Recorded in the header, deliberately not changed; tightening them is a policy call, not a refactor. The decision now reads no chart, holds no net, prints nothing and opens no file, so it can be exercised against a made-up tally. BEHAVIOUR UNCHANGED: every expression keeps its formula, its guard and its -1 sentinel; the ensemble's chance-reference and two-sidedness rules are passed through untouched. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:19:44 -04:00
bool isFullyCollapsedEra = gate.degenerate;
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
//--- N for the family-wise deployment gate. Every era that COULD have won is
//--- counted, whether it did or not - that is precisely the set the maximum was
//--- taken over.
if(coverageMeasurable && !isFullyCollapsedEra)
m_deployCandidateEras++;
//--- Lexicographic "better than the best-so-far" ordering: passing the directional
//--- recall floor always outranks not passing it, regardless of blended
//--- dOosForecast; only WITHIN the same pass/fail category does blended accuracy
//--- break the tie.
//--- tradeableOK / selectionScore, not directionalRecallOK / balancedOosEra - see
//--- the SELECTION METRIC note above.
bool isBetterEra = (tradeableOK && !m_bestPassedRecall) ||
(tradeableOK == m_bestPassedRecall && bothSidesLive && !m_bestBothSidesLive) ||
(tradeableOK == m_bestPassedRecall && bothSidesLive == m_bestBothSidesLive &&
!isFullyCollapsedEra && selectionScore > m_bestBalancedOos);
//--- The recall-pass-loss clause used to fire on ANY drop out of a full 3-way recall
//--- pass, even a near-miss on one class at unchanged accuracy (e.g. observed:
//--- Buy:56% Sell:41% Neutral:34% - Neutral alone missing the 40% floor by a few
//--- points) - treating that identically to a total collapse back to Neutral-only.
bool isWorseEra = selectionScore < m_bestBalancedOos - ETA_DECAY_REGRESSION_PCT;
//--- ENSEMBLE: ranking and checkpointing belong to the ensemble as a unit (see
//--- EnsembleCommitJointCheckpoint). The g_eta recovery bump still applies: that is
//--- this net's own learning-rate dynamics, not a deployment decision.
if(isBetterEra && m_ensembleMember)
g_eta = MathMin(m_etaCeiling, g_eta / ETA_DECAY_FACTOR);
if(isBetterEra && !m_ensembleMember)
{
//--- Snapshot BOTH scores at the checkpoint: m_bestBalancedOos is what ranking compares
//--- against next era; m_bestOosForecast keeps the blended value FinalizeTrainRun() and
//--- the restore branch reset dOosForecast to (see m_bestBalancedOos' declaration).
m_bestOosForecast = dOosForecast;
m_bestBalancedOos = selectionScore;
m_bestPassedRecall = tradeableOK;
m_bestBothSidesLive = bothSidesLive;
//--- Raw significance inputs for the family-wise gate, taken at the same instant as the
//--- weight snapshot below so the test always describes the weights that would ship.
//--- selectionScore cannot substitute: it is precision x coverage credit, and the test
//--- needs the unweighted precision plus the n that sets its standard error.
m_bestDirPrecPct = dirPrecPct;
m_bestChancePrecPct = chancePrecPct;
m_bestDirCalls = oosDirCalls;
//--- The operating point is part of the model, not of the run: these OOS numbers were
//--- produced by these weights UNDER this threshold, and restoring one without the
//--- other would deploy a model whose coverage and precision are not the ones the gate
//--- cleared. Captured at the same instant as the weight snapshot below.
m_bestDirConfThreshold = m_dirConfThreshold;
//--- eval candidates are throwaway - track the score (above) but never write a
//--- checkpoint file; m_haveOosCheckpoint=false then also skips the worse-era
//--- RestoreWeights() restore.
m_haveOosCheckpoint = Net.CaptureWeights();
//--- Recovery bump: ETA_DECAY_FACTOR-only ever shrinks g_eta, and previously
//--- nothing ever grew it back - a losing streak early in a run (even a since-
//--- corrected one) would permanently cap how fast every later era could learn
//--- for the rest of the run, all the way down to ETA_MIN with no way back.
g_eta = MathMin(m_etaCeiling, g_eta / ETA_DECAY_FACTOR);
}
else
if(isWorseEra && m_bestOosForecast > 0)
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus The NN now has a target that is not per-bar direction (closed, best-of-999 p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of cost). One net for all 52 pattern-sides, AIType=AI_META. - NetForward.mqh: the host-side softmax+CE gradient generalized total==3 -> 2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no compute backend changes. - SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on disk (decoupled from the config fingerprint that burned four S1 runs); the GMT->server offset is measured PER ROW against entryPrice vs bar open (DST-immune, histogram logged); a window-span regime filter drops the pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR). - Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell lets checkpoint selection, the edge floor, the plateau ladder and the family-wise deploy gate run UNCHANGED: precision reads as win rate among traded candidates, chance as the base win rate, recalls as sensitivity/ specificity. Era-end META line: coverage x (p - break-even) vs the null. - Labels are the side-conditional triple-barrier win caches - never the DB's stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base rate). Live inference + online learning guarded off until S3. - Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename slot keep meta models fully separate from direction models. Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with AIType=AI_META; S3 wires the votes via the per-side hooks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 06:52:31 -04:00
{
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
// Decaying g_eta alone only softens FUTURE steps - it does nothing to undo the
// regression this era already baked into the weights, so a run could (and in
// practice did) spend 15+ eras compounding forward from one bad era's damage,
// each new era fighting the last one's overshoot instead of building on the best
// state found so far. Restore the last checkpointed-good weights before continuing
// (mirrors what FinalizeTrainRun() does at the END of a run, just applied live so
// the oscillation can't compound within a single run) - this is what actually turns
// "reduce LR on regression" into "step back, then retry slower", not just "drift
// slower".
//
// BOTH the restore AND the g_eta decay below are gated on m_bestPassedRecall: before
// ANY era has ever cleared the per-class recall floor, isBetterEra's own
// lexicographic ordering degrades to a pure blended-accuracy tiebreak
// (directionalRecallOK==false on both sides of the comparison), so "best checkpoint"
// during that phase just means "called Neutral most confidently so far" - restoring
// it would actively defend the majority-class collapse against any era that trades
// some accuracy for real Buy/Sell recall, which is exactly the bias this whole
// recall-gate mechanism exists to prevent (see isBetterEra's own comment above).
// Observed in practice: era 1-3 all "improved" on accuracy alone
// (24.9%->41.4%->52.3%) while Buy/Sell recall stayed at a flat 0% the entire time -
// restoring pre-pass would have locked training into that trajectory instead of
// letting it explore past it. Decaying g_eta has the same bias one step removed:
// every regression relative to a Neutral-collapse "best" shrinks g_eta a little more,
// steadily strangling the exploration needed to escape that collapse until g_eta
// bottoms out at ETA_MIN with no real solution ever found and no checkpoint to fall
// back on either - observed in practice as a run whose best-ever blended accuracy
// kept landing on 0%/0%/100% Buy/Sell/Neutral recall eras, each one triggering
// another decay on the very next era, until g_eta floored out around era 20 and the
// remaining eras just oscillated between collapse states with no way to make a
// large-enough move to escape and no way to reset. Once m_bestPassedRecall is true,
// there IS a genuinely good state worth protecting, and both restoring the
// checkpoint and decaying g_eta on regression are safe/correct again.
// 2026-07-29: the m_bestPassedRecall gate above has an escape now, because its
// stated premise expired. It was written when the pre-pass tiebreak really was
// blended-accuracy-only; the balanced-selection change (m_bestBalancedOos) replaced
// that with `balancedOosEra > m_bestBalancedOos` AND an isFullyCollapsedEra
// exclusion, so a Neutral-only era now scores ~33% (the FLOOR of the balanced
// metric) and cannot anchor the checkpoint at all. "Best checkpoint" pre-pass
// therefore no longer means "called Neutral most confidently" - it means "most
// class-balanced state found so far", which is worth defending, and isWorseEra is
// itself a balanced-accuracy regression, so it cannot fire merely for trading
// Neutral calls for Buy/Sell.
//
// Leaving the gate absolute had a failure mode of its own, and it is not
// hypothetical: if NO checkpoint ever clears the recall floor, m_bestPassedRecall
// stays false forever, so there is never any restore and never any g_eta decay.
// Observed on SP500 H1 2026-07-29 across three topologies - CONV ran 228 eras with
// g_eta pinned at its 0.000300 start while balanced accuracy slid 40% -> 35% and Buy
// recall 11% -> 2%. The run had no regression control whatsoever, and the plateau
// ladder could not end it either (stage 3 refuses to deploy without a recall pass),
// so it was a 1000-era one-way trip into a Neutral collapse.
//
// The original concern still applies while the best-so-far IS near-collapse:
// decaying g_eta against such a "best" strangles the exploration needed to escape it.
// So the escape is margin-guarded - defend the checkpoint only once it sits clearly
// above the one-class floor, which is exactly when there is something real to lose.
bool bestWorthDefending = (m_bestBalancedOos >
BALANCED_COLLAPSE_PCT + BALANCED_WORTH_DEFENDING_MARGIN_PCT);
//--- PATIENCE (see ETA_DECAY_PATIENCE_ERAS). The loop is self-sustaining and
//--- cannot discover anything, because rolling the weights back is precisely
//--- what removes the exploration that would end it.
m_consecutiveRegressions++;
if((m_bestPassedRecall || bestWorthDefending) &&
m_consecutiveRegressions >= ETA_DECAY_PATIENCE_ERAS)
feat: per-family x per-side OOS breakdown in the META era report 350-era S2 verdict on SP500 H1: the meta head carries REAL ranking skill (+1.0-1.3pp mean over base, 101/350 eras clear their own 2-sigma bar, traded subset wins 66.1% at <30% coverage vs 64.5% base) but 0/350 eras produced a positive cov x (p - BE): the candidate stream sits 3pp under the derived geometry's 67.5% break-even and ~2.6pp of recovered skill cannot bridge it. Skill plateaued by mid-run (1.28pp -> 1.05pp), so more eras only buy multiplicity, and the deploy gate correctly shipped nothing. The aggregate can hide a deployable subset (one family/side clearing BE blended with junk), so the META era line now decomposes the SAME traded population into MA/RSI/MACD/Ichimoku x LONG/SHORT cells, each as traded/candidates base->traded win rate. 32 cells is a best-of-N search by construction - any candidate cell faces the family-wise rule before belief. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 09:03:40 -04:00
{
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
m_consecutiveRegressions = 0;
if(m_haveOosCheckpoint && Net.RestoreWeights())
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
dOosForecast = m_bestOosForecast;
//--- The operating point goes back with the weights it was fitted for.
//--- Leaving the current one in place would pair restored weights with a
//--- threshold chosen for the rejected ones - see m_bestDirConfThreshold.
m_dirConfThreshold = m_bestDirConfThreshold;
//--- 2026-08-09 audit, F3: the snapshot restores WEIGHTS only, so without
//--- this the Adam moments still encode the just-rejected trajectory and
//--- the first updates after the restore push straight back toward the
//--- state that was rolled back - the restore -> regress-again -> restore
//--- oscillation. A restore is a new starting point; it gets a fresh
//--- optimizer.
Net.ResetOptimizerState();
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
if(g_eta > ETA_MIN)
g_eta = MathMax(ETA_MIN, g_eta * ETA_DECAY_FACTOR);
Print(ID + ": OOS selection score (coverage-weighted dir-precision) regressed from best " + DoubleToString(m_bestBalancedOos, 1) +
"% to " + DoubleToString(selectionScore, 1) + "% (blended " + DoubleToString(m_bestOosForecast, 1) +
"%->" + DoubleToString(dOosForecast, 1) + "%) - restoring best checkpoint and decaying learning rate to " + DoubleToString(g_eta, 6));
feat(search): stop on the IN-SAMPLE plateau, and shrink every best-of-K effect before quoting it Points 3 and 4 of the four-point plan. 1. IN-SAMPLE EARLY STOP - and the reason it is worth having is not compute. The plateau ladder stops on the OOS SELECTION score. That is a peek: by the time it fires, every one of those eras has been evaluated out of sample, so all of them sit in the family the deploy gate corrects over (g_ensCandidateEras, Sidak). Training longer therefore does not merely cost time - it RAISES the bar the eventual winner has to clear. The new stop reads the TRAINING error, which the gate never looks at. When the optimiser has stopped improving on data it can see, more eras will not find a better model; they will only enlarge the OOS family. Ending there shrinks the correction, and the shrinkage is legitimate precisely BECAUSE the stopping rule never consulted an out-of-sample number. That distinction is the whole point and it is the one this project has got wrong four times: stop on IS and the family really is smaller; stop on OOS and those eras were searched and still count. Both stops now exist; only this one buys a lower bar. Deliberately more patient than the OOS ladder (IS_ERROR_PATIENCE_MULT = 3x): training error is noisy per era - mini-batch order alone moves it - and ending a run that is still learning costs far more than a few wasted eras. Improvement is RELATIVE (IS_ERROR_IMPROVE_FRAC = 1%), so it does not depend on the loss's absolute scale, and it only acts when a checkpoint exists, since otherwise it would end a run with nothing to deploy. Reset per RUN alongside the ladder, so a resumed run cannot early-stop on its first era against a previous run's best. 2. WINNER'S-CURSE SHRINKAGE ON THE BARRIER-GEOMETRY WINNER. The family-wise permutation gate already establishes that the RANKING is not noise. It says nothing about the SIZE of the winner's effect - and a best-of-K maximum is biased upward by construction, being the largest of K noisy draws. The adoption message quotes that raw maximum and compares it against the incumbent, so the number a reader plans on is the inflated one. The penalty is now measured, not assumed: the same permutation draws that produce the p-value also produce, per draw, the MAXIMUM excess across all candidates under pure noise. The mean of those maxima is exactly what a best-of-K selection is expected to report when there is nothing there. This is the empirical form of the sqrt(2 ln K) x SE penalty the SQX EdgeFinder plugin applies to every maximum it reports (Stats.java:79-88), and it needs no normality assumption because the draws ARE the null distribution. Applied in James-Stein form - effect x max(0, 1 - penalty^2/effect^2) - so a large effect is nearly untouched and a marginal one collapses toward zero. Reported, not gated. The adoption decision still turns on the permutation p-value, which is the right test for "is the ranking real"; the shrunk number is there so the magnitude quoted beside it is one worth planning on. Closes the first of the two EdgeFinder ports identified on 2026-08-12. NOTE on the second EdgeFinder port, deliberately not done here: "let the measurement steer the target" is already true where it matters most - ReportGeometryExpectancyScan ADOPTS the winning barrier geometry under the family-wise gate rather than advising it, and the MI excursion suite publishes a verdict per instrument per config. What is still missing is steering the TRAINING TARGET itself (direction vs excursion) off those verdicts, and that is a design change rather than a surgical one - direction is a closed verdict while excursion SIZE keeps clearing, so the honest version of that change is a target-selection policy, not a flag. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-17 16:29:00 -04:00
}
else
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
//--- THROTTLED (2026-08-19): this no-action branch repeated ~600x/day while
//--- noise wandered below a best it was never going to displace. The acting
//--- branch above (restore + g_eta decay) still always prints - it changes state.
if(TrainLogDue())
Print(ID + ": OOS selection score (coverage-weighted dir-precision) regressed from best " + DoubleToString(m_bestBalancedOos, 1) +
"% to " + DoubleToString(selectionScore, 1) + "% (blended " + DoubleToString(m_bestOosForecast, 1) +
"%->" + DoubleToString(dOosForecast, 1) + "%) - best so far is still within " +
DoubleToString(BALANCED_WORTH_DEFENDING_MARGIN_PCT, 1) + "pp of the " +
DoubleToString(BALANCED_COLLAPSE_PCT, 1) + "% one-class floor, so there is nothing worth" +
" restoring yet - continuing to explore without decaying the learning rate (still " + DoubleToString(g_eta, 6) + ")");
feat(search): stop on the IN-SAMPLE plateau, and shrink every best-of-K effect before quoting it Points 3 and 4 of the four-point plan. 1. IN-SAMPLE EARLY STOP - and the reason it is worth having is not compute. The plateau ladder stops on the OOS SELECTION score. That is a peek: by the time it fires, every one of those eras has been evaluated out of sample, so all of them sit in the family the deploy gate corrects over (g_ensCandidateEras, Sidak). Training longer therefore does not merely cost time - it RAISES the bar the eventual winner has to clear. The new stop reads the TRAINING error, which the gate never looks at. When the optimiser has stopped improving on data it can see, more eras will not find a better model; they will only enlarge the OOS family. Ending there shrinks the correction, and the shrinkage is legitimate precisely BECAUSE the stopping rule never consulted an out-of-sample number. That distinction is the whole point and it is the one this project has got wrong four times: stop on IS and the family really is smaller; stop on OOS and those eras were searched and still count. Both stops now exist; only this one buys a lower bar. Deliberately more patient than the OOS ladder (IS_ERROR_PATIENCE_MULT = 3x): training error is noisy per era - mini-batch order alone moves it - and ending a run that is still learning costs far more than a few wasted eras. Improvement is RELATIVE (IS_ERROR_IMPROVE_FRAC = 1%), so it does not depend on the loss's absolute scale, and it only acts when a checkpoint exists, since otherwise it would end a run with nothing to deploy. Reset per RUN alongside the ladder, so a resumed run cannot early-stop on its first era against a previous run's best. 2. WINNER'S-CURSE SHRINKAGE ON THE BARRIER-GEOMETRY WINNER. The family-wise permutation gate already establishes that the RANKING is not noise. It says nothing about the SIZE of the winner's effect - and a best-of-K maximum is biased upward by construction, being the largest of K noisy draws. The adoption message quotes that raw maximum and compares it against the incumbent, so the number a reader plans on is the inflated one. The penalty is now measured, not assumed: the same permutation draws that produce the p-value also produce, per draw, the MAXIMUM excess across all candidates under pure noise. The mean of those maxima is exactly what a best-of-K selection is expected to report when there is nothing there. This is the empirical form of the sqrt(2 ln K) x SE penalty the SQX EdgeFinder plugin applies to every maximum it reports (Stats.java:79-88), and it needs no normality assumption because the draws ARE the null distribution. Applied in James-Stein form - effect x max(0, 1 - penalty^2/effect^2) - so a large effect is nearly untouched and a marginal one collapses toward zero. Reported, not gated. The adoption decision still turns on the permutation p-value, which is the right test for "is the ranking real"; the shrunk number is there so the magnitude quoted beside it is one worth planning on. Closes the first of the two EdgeFinder ports identified on 2026-08-12. NOTE on the second EdgeFinder port, deliberately not done here: "let the measurement steer the target" is already true where it matters most - ReportGeometryExpectancyScan ADOPTS the winning barrier geometry under the family-wise gate rather than advising it, and the MI excursion suite publishes a verdict per instrument per config. What is still missing is steering the TRAINING TARGET itself (direction vs excursion) off those verdicts, and that is a design change rather than a surgical one - direction is a closed verdict while excursion SIZE keeps clearing, so the honest version of that change is a target-selection policy, not a flag. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-17 16:29:00 -04:00
}
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
//=== IN-SAMPLE ERROR PLATEAU: THE HONEST EARLY STOP ====================================
//--- The ladder below stops on the OOS SELECTION score. This stop reads the TRAINING
//--- error instead, which the gate never looks at. Both stops exist; only this one
//--- buys a lower bar.
if(dError >= 0.0 && MathIsValidNumber(dError))
{
//--- Relative improvement, so this does not depend on the loss's absolute scale.
if(m_bestIsError < 0.0 || dError < m_bestIsError * (1.0 - IS_ERROR_IMPROVE_FRAC))
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
{
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
m_bestIsError = dError;
m_erasSinceBestIsError = 0;
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
}
else
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
m_erasSinceBestIsError++;
//--- Deliberately more patient than the OOS ladder: training error is noisy
//--- per era (mini-batch order alone moves it), and ending a run that is still
//--- learning is far more expensive than a few wasted eras.
if(m_erasSinceBestIsError >= TrainPlateauPatienceEras() * IS_ERROR_PATIENCE_MULT &&
m_haveOosCheckpoint && !m_isErrorPlateaued)
{
Print(ID + ": IN-SAMPLE ERROR PLATEAU - training error has not improved by " +
DoubleToString(100.0 * IS_ERROR_IMPROVE_FRAC, 1) + "% in " +
IntegerToString(m_erasSinceBestIsError) + " eras (best " +
DoubleToString(m_bestIsError, 4) + ", now " + DoubleToString(dError, 4) +
"). The optimiser has stopped learning from the data it CAN see, so further"
" eras cannot find a better model - they would only add candidates to the"
" family the deploy gate corrects over, raising the bar the winner has to"
" clear. Ending the search and deploying the best checkpoint. This stop"
" never read an out-of-sample number, which is what makes the smaller"
" family legitimate rather than a peek.");
//--- LATCH FIRST, and let the LATCH - not m_plateauStage - be what the deploy
//--- conditions read. m_plateauStage is mirrored from the shared ensemble ladder
//--- on every era (EnsembleEraVerdict), so writing the decision there meant it
//--- survived until the next verdict and no longer. See m_isErrorPlateaued.
m_isErrorPlateaued = true;
m_plateauStage = PLATEAU_STAGE_DEPLOY;
}
perf(autotune): replace the genetic search with a filter score - hours to seconds MEASURED COST OF THE GA, which is what retired it. Per generation: rung 0: 8 cand x 3 seeds x 3 eras = 72 eras rung 1: 4 cand x 3 seeds x 8 eras = 96 rung 2: 2 cand x 3 seeds x 20 eras = 120 = 288 eras/generation x 4 generations = 1152 eras BEFORE the winner's real training began. Against the observed era times on SP500 H1: PAI 29.1 s/era -> 9.3 h (matches the observed 00:37 -> 09:22) CONV 41.3 s/era -> 13.2 h LSTM 150.4 s/era -> 48.1 h HYBRID 154.6 s/era -> 49.5 h Two days to tune is not a first-run experience, and it is the phase in which the panel goes quiet, which is what made it look like a hang. It also bought nothing. The space is 90 points (10 MA periods x 9 MA types), so 1152 evaluations revisited each point ~13 times; and rungs of 3 and 8 eras cannot separate two MA periods at all. The 2026-08-01 run proves it: every finalist scored 25.0-25.9% balanced accuracy - below the 33.3% one-class floor, i.e. indistinguishable noise - and the search then "deployed the winner" of that. THE ERROR WAS THE SCORING FUNCTION, not its constants. Using a full training run to choose a feature's period is a wrapper method paying wrapper prices for a decision that does not need one. The reference book does not do this: ch. 3.3 selects inputs by measuring each candidate indicator's CORRELATION with the target and dropping the ones with none, with no network involved. So: rank candidates by the MUTUAL INFORMATION between the resulting feature vector and the triple-barrier label. MI rather than correlation because the label is 3-class categorical and the features are not monotonically related to it. Equal-FREQUENCY binning (rank-based), because these features are ATR-normalised and heavy-tailed - fixed-width bins put nearly everything in one bucket and report ~0 information for a genuinely useful feature. Scoring is arithmetic over the feature cache, so it costs seconds and its cost is independent of topology: LSTM now tunes as fast as the MLP. Coordinate sweep, not product sweep - cost is the SUM of per-parameter candidate counts, so enabling every indicator stays affordable - with a second pass that breaks early once nothing moves. Sampling is IS-ONLY. Letting the OOS window influence which indicator settings ship would mean the holdout had been used for selection and had stopped being a holdout. HONEST LIMIT, recorded because it is the price: MI is marginal, so a parameter that only pays off in combination with another can be missed (Guyon & Elisseeff 2003, filter vs wrapper). Given the wrapper it replaces was ranking pure noise at 48 h a run, this is strictly better. Deleted with it: GaRungEras/GaExtract/GaStore/GaMutate/GaRandomCandidate/ GaBlockCrossover/GaSortAliveByScoreDesc/GaBreedNextGeneration, 14 m_ga* members, the GA_*/TUNE_POP_* constants, and ComputeTuneTrialBudget. AND m_evalMode/m_evalEraBudget, because nothing set them any more - 28 read sites all permanently inert. That is not a tidy-up: the `if (!m_evalMode)` guard on UpdateClassPriors is exactly what silently disabled the imbalance correction for entire runs two commits ago. Dead machinery that still reads like live machinery is this codebase's most expensive recurring bug, and leaving 28 more instances of it would have been indefensible. The panel's tuning-progress state goes too - tuning no longer takes long enough to need one. Both builds compile 0 errors / 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-01 10:29:31 -04:00
}
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
}
//=== PLATEAU LADDER ====================================================================
//--- Neither branch above fires in the dead zone between "new best" and "regressed
//--- by more than ETA_DECAY_REGRESSION_PCT". This is the response to sitting in it:
//--- count eras since the last new best and escalate.
if(m_ensembleMember)
{
EnsembleStashEraStats(dirPrecPct, chancePrecPct, oosDirCalls, tradeableOK, bothSidesLive,
selectionScore, dOosForecast);
//--- m_eraCount was already incremented at the top of this block, so the era that just
//--- finished - the one the vote buffer is stamped with - is m_eraCount - 1.
EnsembleOosPassComplete(m_eraCount - 1, g_eta);
}
else
if(isBetterEra)
{
//--- Moving again: retire the ladder AND the restart boost. The checkpoint just
//--- snapshotted this era regardless. The normal per-era g_eta schedule takes
//--- over.
if(m_plateauStage > 0)
Print(ID + ": new best selection score (coverage-weighted dir-precision) " + DoubleToString(m_bestBalancedOos, 1) +
"% - plateau escape worked, clearing plateau stage " + IntegerToString(m_plateauStage));
m_erasSinceBestBalanced = 0;
m_plateauStage = 0;
m_restartBoostErasLeft = 0;
//--- Patience is about CONSECUTIVE regressions - an era that improves clears it, so a
//--- run that alternates improve/regress never accumulates its way into a decay.
m_consecutiveRegressions = 0;
}
else
{
m_erasSinceBestBalanced++;
int dueStage = m_erasSinceBestBalanced / TrainPlateauPatienceEras();
if(dueStage > m_plateauStage)
perf(autotune): replace the genetic search with a filter score - hours to seconds MEASURED COST OF THE GA, which is what retired it. Per generation: rung 0: 8 cand x 3 seeds x 3 eras = 72 eras rung 1: 4 cand x 3 seeds x 8 eras = 96 rung 2: 2 cand x 3 seeds x 20 eras = 120 = 288 eras/generation x 4 generations = 1152 eras BEFORE the winner's real training began. Against the observed era times on SP500 H1: PAI 29.1 s/era -> 9.3 h (matches the observed 00:37 -> 09:22) CONV 41.3 s/era -> 13.2 h LSTM 150.4 s/era -> 48.1 h HYBRID 154.6 s/era -> 49.5 h Two days to tune is not a first-run experience, and it is the phase in which the panel goes quiet, which is what made it look like a hang. It also bought nothing. The space is 90 points (10 MA periods x 9 MA types), so 1152 evaluations revisited each point ~13 times; and rungs of 3 and 8 eras cannot separate two MA periods at all. The 2026-08-01 run proves it: every finalist scored 25.0-25.9% balanced accuracy - below the 33.3% one-class floor, i.e. indistinguishable noise - and the search then "deployed the winner" of that. THE ERROR WAS THE SCORING FUNCTION, not its constants. Using a full training run to choose a feature's period is a wrapper method paying wrapper prices for a decision that does not need one. The reference book does not do this: ch. 3.3 selects inputs by measuring each candidate indicator's CORRELATION with the target and dropping the ones with none, with no network involved. So: rank candidates by the MUTUAL INFORMATION between the resulting feature vector and the triple-barrier label. MI rather than correlation because the label is 3-class categorical and the features are not monotonically related to it. Equal-FREQUENCY binning (rank-based), because these features are ATR-normalised and heavy-tailed - fixed-width bins put nearly everything in one bucket and report ~0 information for a genuinely useful feature. Scoring is arithmetic over the feature cache, so it costs seconds and its cost is independent of topology: LSTM now tunes as fast as the MLP. Coordinate sweep, not product sweep - cost is the SUM of per-parameter candidate counts, so enabling every indicator stays affordable - with a second pass that breaks early once nothing moves. Sampling is IS-ONLY. Letting the OOS window influence which indicator settings ship would mean the holdout had been used for selection and had stopped being a holdout. HONEST LIMIT, recorded because it is the price: MI is marginal, so a parameter that only pays off in combination with another can be missed (Guyon & Elisseeff 2003, filter vs wrapper). Given the wrapper it replaces was ranking pure noise at 48 h a run, this is strictly better. Deleted with it: GaRungEras/GaExtract/GaStore/GaMutate/GaRandomCandidate/ GaBlockCrossover/GaSortAliveByScoreDesc/GaBreedNextGeneration, 14 m_ga* members, the GA_*/TUNE_POP_* constants, and ComputeTuneTrialBudget. AND m_evalMode/m_evalEraBudget, because nothing set them any more - 28 read sites all permanently inert. That is not a tidy-up: the `if (!m_evalMode)` guard on UpdateClassPriors is exactly what silently disabled the imbalance correction for entire runs two commits ago. Dead machinery that still reads like live machinery is this codebase's most expensive recurring bug, and leaving 28 more instances of it would have been indefensible. The panel's tuning-progress state goes too - tuning no longer takes long enough to need one. Both builds compile 0 errors / 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-01 10:29:31 -04:00
{
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
m_plateauStage = dueStage;
string stageNote = IntegerToString(m_erasSinceBestBalanced) + " eras with no new best selection score (best " +
DoubleToString(m_bestBalancedOos, 1) + "%)";
if(m_plateauStage == PLATEAU_STAGE_RESTART || m_plateauStage == PLATEAU_STAGE_ANNEAL)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
//--- BOOSTED WARM RESTART: a plateau needs a bigger step to climb out of
//--- its basin, not a smaller one - and "back to the ceiling" was a NO-OP
//--- whenever the run plateaued without ever tripping the regression decay,
//--- because g_eta was still AT the ceiling (2026-08-09 audit, F2).
double etaBefore = g_eta;
g_eta = m_etaCeiling * PLATEAU_RESTART_BOOST;
m_restartBoostErasLeft = TrainPlateauPatienceEras();
//--- A restart is a new schedule: replaying the plateau's own accumulated
//--- Adam momentum at 5x the rate would retrace the same basin, harder.
Net.ResetOptimizerState();
//--- The focal-gamma anneal that used to accompany this went with focal
//--- loss on 2026-07-31.
Print(ID + ": PLATEAU stage " + IntegerToString(m_plateauStage) + " - " + stageNote +
". Boosted warm restart: learning rate " + DoubleToString(etaBefore, 6) + "->" + DoubleToString(g_eta, 6) +
" (annealing back to " + DoubleToString(m_etaCeiling, 6) + " over " + IntegerToString(TrainPlateauPatienceEras()) +
" eras), optimizer momentum reset. Best checkpoint is safe - this only changes how the NEXT eras train.");
}
else
if(m_plateauStage >= PLATEAU_STAGE_DEPLOY)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
{
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
//--- Exhausted: both escapes were tried and neither found a better
//--- model, so this IS the best this configuration reaches. Safety: only
//--- ever auto-deploys a checkpoint that CLEARED the per-class recall
//--- floor (m_bestPassedRecall).
double zBest = 0.0, pFam = 1.0;
int nTried = 0;
bool survivesSelection = BestCheckpointSurvivesSelection(zBest, pFam, nTried);
string selectionNote = " | best-of-" + IntegerToString(nTried) + " test: edge " +
DoubleToString(m_bestDirPrecPct - m_bestChancePrecPct, 1) + "pp on " +
IntegerToString(m_bestDirCalls) + " calls = " + DoubleToString(zBest, 2) +
" sigma, family-wise p=" + DoubleToString(pFam, 4) +
" (need <=" + DoubleToString(DEPLOY_FAMILY_WISE_ALPHA, 2) + ")";
//--- THE SCREEN HAS A VETO. Everything else in this block asks whether
//--- the MODEL is good enough; this asks whether there was anything to
//--- find.
if(!m_dirEvidence)
Print(ID + ": DEPLOY REFUSED BY THE MEASUREMENT SCREEN - " + m_dirEvidenceWhy +
". Neither the feature/label mutual information nor the normalised"
" excursion asymmetry cleared its permutation null on this"
" configuration, so there is no measured directional information here"
" for a model to have learned. The checkpoint is kept and training"
" state is untouched - this is a refusal to go LIVE, not a failure."
" The productive move is a different target or a different market,"
" not more eras: excursion SIZE keeps clearing where direction does"
" not, and that is a risk-control head rather than an entry signal.");
if(m_bestPassedRecall && m_haveOosCheckpoint && survivesSelection && m_dirEvidence)
Print(ID + ": PLATEAU stage " + IntegerToString(PLATEAU_STAGE_DEPLOY) + " - " + stageNote +
" across " + IntegerToString(PLATEAU_STAGE_DEPLOY - 1) + " warm restarts. Training has converged on what this"
+ " configuration can reach - deploying the best checkpoint (dir-precision "
+ DoubleToString(m_bestBalancedOos, 1) + "%, blended " + DoubleToString(m_bestOosForecast, 1) + "%)."
+ selectionNote + " - CLEARS.");
else
if(m_bestPassedRecall && m_haveOosCheckpoint)
{
//--- Passed the per-era floor but not the selection correction:
//--- this is a maximum that a pure-noise search of this length
//--- produces routinely.
perf(autotune): replace the genetic search with a filter score - hours to seconds MEASURED COST OF THE GA, which is what retired it. Per generation: rung 0: 8 cand x 3 seeds x 3 eras = 72 eras rung 1: 4 cand x 3 seeds x 8 eras = 96 rung 2: 2 cand x 3 seeds x 20 eras = 120 = 288 eras/generation x 4 generations = 1152 eras BEFORE the winner's real training began. Against the observed era times on SP500 H1: PAI 29.1 s/era -> 9.3 h (matches the observed 00:37 -> 09:22) CONV 41.3 s/era -> 13.2 h LSTM 150.4 s/era -> 48.1 h HYBRID 154.6 s/era -> 49.5 h Two days to tune is not a first-run experience, and it is the phase in which the panel goes quiet, which is what made it look like a hang. It also bought nothing. The space is 90 points (10 MA periods x 9 MA types), so 1152 evaluations revisited each point ~13 times; and rungs of 3 and 8 eras cannot separate two MA periods at all. The 2026-08-01 run proves it: every finalist scored 25.0-25.9% balanced accuracy - below the 33.3% one-class floor, i.e. indistinguishable noise - and the search then "deployed the winner" of that. THE ERROR WAS THE SCORING FUNCTION, not its constants. Using a full training run to choose a feature's period is a wrapper method paying wrapper prices for a decision that does not need one. The reference book does not do this: ch. 3.3 selects inputs by measuring each candidate indicator's CORRELATION with the target and dropping the ones with none, with no network involved. So: rank candidates by the MUTUAL INFORMATION between the resulting feature vector and the triple-barrier label. MI rather than correlation because the label is 3-class categorical and the features are not monotonically related to it. Equal-FREQUENCY binning (rank-based), because these features are ATR-normalised and heavy-tailed - fixed-width bins put nearly everything in one bucket and report ~0 information for a genuinely useful feature. Scoring is arithmetic over the feature cache, so it costs seconds and its cost is independent of topology: LSTM now tunes as fast as the MLP. Coordinate sweep, not product sweep - cost is the SUM of per-parameter candidate counts, so enabling every indicator stays affordable - with a second pass that breaks early once nothing moves. Sampling is IS-ONLY. Letting the OOS window influence which indicator settings ship would mean the holdout had been used for selection and had stopped being a holdout. HONEST LIMIT, recorded because it is the price: MI is marginal, so a parameter that only pays off in combination with another can be missed (Guyon & Elisseeff 2003, filter vs wrapper). Given the wrapper it replaces was ranking pure noise at 48 h a run, this is strictly better. Deleted with it: GaRungEras/GaExtract/GaStore/GaMutate/GaRandomCandidate/ GaBlockCrossover/GaSortAliveByScoreDesc/GaBreedNextGeneration, 14 m_ga* members, the GA_*/TUNE_POP_* constants, and ComputeTuneTrialBudget. AND m_evalMode/m_evalEraBudget, because nothing set them any more - 28 read sites all permanently inert. That is not a tidy-up: the `if (!m_evalMode)` guard on UpdateClassPriors is exactly what silently disabled the imbalance correction for entire runs two commits ago. Dead machinery that still reads like live machinery is this codebase's most expensive recurring bug, and leaving 28 more instances of it would have been indefensible. The panel's tuning-progress state goes too - tuning no longer takes long enough to need one. Both builds compile 0 errors / 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-01 10:29:31 -04:00
Print(ID + ": PLATEAU stage " + IntegerToString(PLATEAU_STAGE_DEPLOY) + " - " + stageNote +
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
". The best checkpoint clears the per-era deployability floor but DOES NOT clear the"
+ " null of the MAXIMUM over the eras it was chosen from" + selectionNote +
". A best-of-N this large happens routinely when every era is a noise draw, so the"
+ " ranking carries no evidence of an edge and this model is not safe to trade."
+ " Restarting the plateau ladder and continuing to train; the "
+ IntegerToString(m_maxErasPerRun) + "-era cap remains the backstop.");
m_erasSinceBestBalanced = 0;
m_plateauStage = 0;
}
perf(autotune): replace the genetic search with a filter score - hours to seconds MEASURED COST OF THE GA, which is what retired it. Per generation: rung 0: 8 cand x 3 seeds x 3 eras = 72 eras rung 1: 4 cand x 3 seeds x 8 eras = 96 rung 2: 2 cand x 3 seeds x 20 eras = 120 = 288 eras/generation x 4 generations = 1152 eras BEFORE the winner's real training began. Against the observed era times on SP500 H1: PAI 29.1 s/era -> 9.3 h (matches the observed 00:37 -> 09:22) CONV 41.3 s/era -> 13.2 h LSTM 150.4 s/era -> 48.1 h HYBRID 154.6 s/era -> 49.5 h Two days to tune is not a first-run experience, and it is the phase in which the panel goes quiet, which is what made it look like a hang. It also bought nothing. The space is 90 points (10 MA periods x 9 MA types), so 1152 evaluations revisited each point ~13 times; and rungs of 3 and 8 eras cannot separate two MA periods at all. The 2026-08-01 run proves it: every finalist scored 25.0-25.9% balanced accuracy - below the 33.3% one-class floor, i.e. indistinguishable noise - and the search then "deployed the winner" of that. THE ERROR WAS THE SCORING FUNCTION, not its constants. Using a full training run to choose a feature's period is a wrapper method paying wrapper prices for a decision that does not need one. The reference book does not do this: ch. 3.3 selects inputs by measuring each candidate indicator's CORRELATION with the target and dropping the ones with none, with no network involved. So: rank candidates by the MUTUAL INFORMATION between the resulting feature vector and the triple-barrier label. MI rather than correlation because the label is 3-class categorical and the features are not monotonically related to it. Equal-FREQUENCY binning (rank-based), because these features are ATR-normalised and heavy-tailed - fixed-width bins put nearly everything in one bucket and report ~0 information for a genuinely useful feature. Scoring is arithmetic over the feature cache, so it costs seconds and its cost is independent of topology: LSTM now tunes as fast as the MLP. Coordinate sweep, not product sweep - cost is the SUM of per-parameter candidate counts, so enabling every indicator stays affordable - with a second pass that breaks early once nothing moves. Sampling is IS-ONLY. Letting the OOS window influence which indicator settings ship would mean the holdout had been used for selection and had stopped being a holdout. HONEST LIMIT, recorded because it is the price: MI is marginal, so a parameter that only pays off in combination with another can be missed (Guyon & Elisseeff 2003, filter vs wrapper). Given the wrapper it replaces was ranking pure noise at 48 h a run, this is strictly better. Deleted with it: GaRungEras/GaExtract/GaStore/GaMutate/GaRandomCandidate/ GaBlockCrossover/GaSortAliveByScoreDesc/GaBreedNextGeneration, 14 m_ga* members, the GA_*/TUNE_POP_* constants, and ComputeTuneTrialBudget. AND m_evalMode/m_evalEraBudget, because nothing set them any more - 28 read sites all permanently inert. That is not a tidy-up: the `if (!m_evalMode)` guard on UpdateClassPriors is exactly what silently disabled the imbalance correction for entire runs two commits ago. Dead machinery that still reads like live machinery is this codebase's most expensive recurring bug, and leaving 28 more instances of it would have been indefensible. The panel's tuning-progress state goes too - tuning no longer takes long enough to need one. Both builds compile 0 errors / 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-01 10:29:31 -04:00
else
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
{
Print(ID + ": PLATEAU stage " + IntegerToString(PLATEAU_STAGE_DEPLOY) + " - " + stageNote +
", but no checkpoint has ever cleared the deployability floor (directional calls on" +
" at least a quarter as many bars as actually swing, at a precision above that base rate, with BOTH Buy and Sell"
+ " recall at or above " + DoubleToString(DEPLOY_MIN_SIDE_RECALL_PCT, 0) + "%), so there is nothing safe to"
+ " deploy. Restarting the plateau ladder and continuing to train rather than deploying a"
+ " one-class model; the " + IntegerToString(m_maxErasPerRun) + "-era cap remains the backstop.");
m_erasSinceBestBalanced = 0;
m_plateauStage = 0;
}
}
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
}
//--- Restart-boost anneal (see PLATEAU_RESTART_BOOST): walk g_eta geometrically from
//--- boost x ceiling back down to the ceiling over PLATEAU_PATIENCE_ERAS eras, one
//--- step per completed era - the SGDR-style decaying half of the cycle, which is
//--- what makes the boost a bounded kick instead of a new permanent rate.
if(m_restartBoostErasLeft > 0)
{
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
g_eta = MathMax(m_etaCeiling, g_eta * MathPow(PLATEAU_RESTART_BOOST, -1.0 / TrainPlateauPatienceEras()));
m_restartBoostErasLeft--;
}
m_oosWindow.Add(dOosForecast);
while(m_oosWindow.Total() > STABILITY_WINDOW)
m_oosWindow.Delete(0);
m_oosStable = false;
if(m_oosWindow.Total() >= STABILITY_WINDOW)
{
double oosMin = m_oosWindow.At(0), oosMax = m_oosWindow.At(0);
for(int w = 1; w < m_oosWindow.Total(); w++)
{
oosMin = MathMin(oosMin, m_oosWindow.At(w));
oosMax = MathMax(oosMax, m_oosWindow.At(w));
}
m_oosStable = (oosMax - oosMin) <= STABILITY_TOLERANCE;
}
//--- The dError<0.1 RMS-error floor is meaningful for the single-neuron regression
//--- head (m_outputNeuronsCount==1), where it's the only convergence signal
//--- available.
bool errorGateOK = (m_outputNeuronsCount == 3) ? true : (dError < 0.1);
//--- Convergence (unlike isBetterEra's ranking) FINALIZES the model, so both
//--- directional classes must have actually been MEASURED this era.
bool directionalRecallMeasured = (m_outputNeuronsCount != 3) || (buyRecallPct >= 0 && sellRecallPct >= 0);
//--- VALIDITY of this era's model, no longer "did it hit a target accuracy". Neither
//--- is what "train to the best result" means.
m_objectiveMet = errorGateOK && directionalRecallOK && directionalRecallMeasured;
}
//--- Only mark the persisted model "complete" once it actually converged this era - an
//--- interruption (stop) or an ordinary in-progress era must stay flagged incomplete so
//--- a restart resumes training instead of quietly treating a partial run as done.
//--- ...and the family-wise selection gate, for the same reason the deploy branch applies it:
//--- these two conditions MUST stay identical or the flag persisted into the .nnw disagrees
//--- with the decision to stop, and a reload would run inference on a model the ladder had
//--- refused to deploy. Cheap enough to re-evaluate per era (one normal-tail evaluation).
double zConv = 0.0, pConv = 1.0;
int nConv = 0;
//--- ENSEMBLE: the verdict is the ensemble's, so the flag persisted into this member's
//--- .nnw has to be the ensemble's too - otherwise a reload would run one member live
//--- against three still training, which is not the model that was measured.
m_trainingComplete = m_ensembleMember
? (g_ensDeployApproved && m_haveOosCheckpoint && m_checkpointEra == g_ensBestEra)
: ((m_plateauStage >= PLATEAU_STAGE_DEPLOY || m_isErrorPlateaued) && m_bestPassedRecall && m_haveOosCheckpoint
&& m_dirEvidence
&& BestCheckpointSurvivesSelection(zConv, pConv, nConv));
double currentIndicatorParams[];
m_indicatorTuner.Flatten(currentIndicatorParams);
if(!Net.Save(m_activeFileName + ".nnw", dError, dUndefine, dForecast, dtStudied, m_activeFileCommon, m_eraCount, m_trainingComplete, currentIndicatorParams))
Print(__FUNCTION__ + ": ERROR - era-end Net.Save failed for " + m_activeFileName + ".nnw (era " + IntegerToString(m_eraCount) + "). Training continues but this era's checkpoint was NOT persisted - a crash/restart now would resume from an older era.");
if(!SaveModelStats(m_activeFileName, m_activeFileCommon)) // keep calibration state paired with the just-saved weights
Print(__FUNCTION__ + ": ERROR - SaveModelStats failed for " + m_activeFileName + " (era " + IntegerToString(m_eraCount) + "). Calibration/online-learning state not persisted this era.");
SaveShadowNet(currentIndicatorParams);
}
}
}
//+------------------------------------------------------------------+
//| START OF A TRAINING RUN - everything that happens once, before |
//| era 0 rather than before every era. |
//| |
//| Waits (bounded, non-blocking across calls) for the terminal to |
//| finish syncing history, sizes the study window, and arms the |
//| one-shot preparatory walks. Several of its branches DEFER: they |
//| decline this call and let the next scheduled one try again, which |
//| is why this reports whether Train() should return rather than |
//| falling through. |
//| |
//| True = this call is spent. False = the run is live, carry on. |
//+------------------------------------------------------------------+
fix(train): BeginTrainRun read Train()'s parameter from a scope it no longer had The run-start block calls TrainWindowStart(StartTrainBar), and StartTrainBar is Train()'s parameter. Moving the block into its own method left the read behind. Now passed explicitly. THIRD TIME THIS FAMILY HAS BILLED THIS SESSION, and the third distinct sub-shape: 1d7ebbd a DELETED loop's variable still read by its body d7469c6 a RENAMED field still read by its call site here a MOVED block still reading its old enclosing scope Same root cause each time: I verify the side I edited. What I had been checking - statement multisets, brace balance, field-name resolution - all passed, because none of them models SCOPE. The move was faithful; the scope was not. So scope is now checked too. For every CExpertSignalAIBase::Method, collect the identifiers its body reads and subtract what can actually resolve: names declared in the body (any type, and every name in a multi-declarator), the method's own parameters, class members, file-scope globals and #defines. Parameter names from OTHER declarations must NOT count as resolvable - that is the bug in the first version of this check, which let StartTrainBar through because Train() declares it in the header. Validated against the broken commit before being trusted: it reports StartTrainBar there and not here. The only residual output is MQL5 enum members and EA inputs declared outside the scanned headers. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:58:35 -04:00
bool CExpertSignalAIBase::BeginTrainRun(STrainEra &era, const datetime startTrainBar)
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
{
if(!m_trainRunActive)
{
//--- Wait (briefly, bounded, non-blocking across calls) for the terminal to finish syncing
//--- this symbol/period's history from the broker before computing the training window.
if(!SeriesInfoInteger(m_symbol.Name(), PERIOD_CURRENT, SERIES_SYNCHRONIZED))
{
uint syncNowTick = GetTickCount();
if(m_syncWaitStartTick == 0)
m_syncWaitStartTick = syncNowTick;
if(syncNowTick - m_syncWaitStartTick < 5000)
{
ReportTrainStall("waiting for history sync");
return true; // retry on the next scheduled call instead of blocking here
}
Print(ID + ": WARNING - history for " + m_symbol.Name() + " " + EnumToString(PERIOD_CURRENT) + " did not finish syncing after 5s; training window may still grow as more history arrives");
}
m_syncWaitStartTick = 0;
//--- 3 no-op passes before the era loop ever runs for a fresh start (see m_warmupPassesRemaining's
//--- declaration comment) - each is its own separately-scheduled Train() call (this whole method
//--- just returns, deferring to the next "New Bar"/timer-driven call), giving MT5's history sync
//--- several real, wall-clock-separated chances to settle on top of the 5s soft wait just above,
//--- before training commits to a bar count and starts populating the label cache below.
if(m_warmupPassesRemaining > 0)
{
ReportTrainStall("history-settle warm-up pass");
m_warmupPassesRemaining--;
PrintVerbose(ID + ": warm-up pass " + IntegerToString(3 - m_warmupPassesRemaining) + " of 3 (letting history sync settle before training starts)");
return true;
}
//--- ALL available history, floored by MinTrainYear - see TrainWindowStart().
fix(train): BeginTrainRun read Train()'s parameter from a scope it no longer had The run-start block calls TrainWindowStart(StartTrainBar), and StartTrainBar is Train()'s parameter. Moving the block into its own method left the read behind. Now passed explicitly. THIRD TIME THIS FAMILY HAS BILLED THIS SESSION, and the third distinct sub-shape: 1d7ebbd a DELETED loop's variable still read by its body d7469c6 a RENAMED field still read by its call site here a MOVED block still reading its old enclosing scope Same root cause each time: I verify the side I edited. What I had been checking - statement multisets, brace balance, field-name resolution - all passed, because none of them models SCOPE. The move was faithful; the scope was not. So scope is now checked too. For every CExpertSignalAIBase::Method, collect the identifiers its body reads and subtract what can actually resolve: names declared in the body (any type, and every name in a multi-declarator), the method's own parameters, class members, file-scope globals and #defines. Parameter names from OTHER declarations must NOT count as resolvable - that is the bug in the first version of this check, which let StartTrainBar through because Train() declares it in the header. Validated against the broken commit before being trusted: it reports StartTrainBar there and not here. The only residual output is MQL5 enum members and EA inputs declared outside the scanned headers. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:58:35 -04:00
dtStudied = TrainWindowStart(startTrainBar);
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
//--- OOS-based objective + stability tracking: training only "converges" once the objective
//--- is met AND OOS accuracy has held inside a tight band for the last few eras, so a single
//--- lucky era can't get locked in as the final model.
m_oosWindow.Clear();
m_bestOosForecast = -1;
m_bestBalancedOos = -1;
m_bestPassedRecall = false;
m_bestBothSidesLive = false;
m_haveOosCheckpoint = false;
m_checkpointEra = -1; // the joint-checkpoint era stamp goes with the snapshot it describes
m_oosStable = false;
m_objectiveMet = false;
//--- Family-wise deployment gate state, reset with the checkpoint tracking it describes: N counts
//--- the eras THIS run selects a maximum over, so carrying it across runs would test the winner
//--- against a search that never happened.
m_bestDirPrecPct = -1.0;
m_bestChancePrecPct = -1.0;
m_bestDirCalls = 0;
m_deployCandidateEras = 0;
m_erasSinceCooldown = 0;
m_eraResumePending = false;
//--- Plateau ladder starts fresh with this run, so it re-walks the escalation from its own
//--- starting point. (The focal-gamma anneal that used to reset here went with focal loss on
//--- 2026-07-31 - the ladder's real escape is the learning-rate warm restart.)
m_erasSinceBestBalanced = 0;
m_plateauStage = 0;
m_restartBoostErasLeft = 0;
//--- Per-RUN like the ladder above, and for the same reason: a resumed run restarts the search, so
//--- carrying a previous run's best training error would let it early-stop on the first era.
m_bestIsError = -1.0;
m_erasSinceBestIsError = 0;
m_isErrorPlateaued = false;
//--- THE EXIT-REPLAY LATCHES ARE PER-RUN TOO, and they were the one thing a panel reset could
//--- not clear. Masked whenever the reset is followed by a recompile (a re-attach constructs
//--- new objects), which is why pressing the button never exposed it: the failing case is the
//--- ordinary one, reset with no recompile.
m_lastTimeoutShare = -1.0;
m_lastTimeoutMeanR = 0.0;
//--- and the once-per-run throttle, or a fresh run's FIRST replay line goes missing.
m_exitReplayReported = false;
//--- ENSEMBLE: the shared gate state is per-RUN for the same reason the per-member state
//--- above is - N must count the eras THIS run's maximum was taken over, so carrying it
//--- across runs would test the winner against a search that never happened.
bool ensembleRunAlreadyOpen = false;
if(m_ensembleMember)
for(int mi = 0; mi < ArraySize(g_warriorEnsemble); mi++)
{
CExpertSignalAIBase *mm = g_warriorEnsemble[mi];
if(CheckPointer(mm) != POINTER_INVALID && mm != GetPointer(this) && mm.m_trainRunActive)
{
ensembleRunAlreadyOpen = true;
break;
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
}
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
}
if(m_ensembleMember && !ensembleRunAlreadyOpen)
{
g_ensLastVerdictEra = -1;
g_ensBestScore = -1.0;
g_ensBestTradeable = false;
g_ensBestTwoSided = false;
g_ensBestPrecPct = -1.0;
g_ensBestChancePct = -1.0;
g_ensBestCalls = 0;
g_ensBestEra = -1;
g_ensGateTestedEra = -1; // no gate test belongs to a run that has not happened yet
g_ensCandidateEras = 0;
g_ensErasSinceBest = 0;
g_ensPlateauStage = 0;
g_ensIsPlateauAnnounced = false;
g_ensDeployApproved = false;
}
//--- One-time eager pre-scan for a fresh start (see m_labelCachePrebuilt's declaration
//--- comment) - kick it off and defer era 0 until it's done, so era 0 can start with a real
//--- class-balance oversampling ratio instead of the reps=1 fallback.
if(!m_labelCachePrebuilt)
{
ReportTrainStall("arming the first label-cache prebuild");
StartLabelCachePrebuild();
return true;
}
m_trainRunActive = true;
}
//--- Set up and ready to run this call's chunk.
return false;
}
//+------------------------------------------------------------------+
//| START OF ONE ERA, or resumption of one that yielded mid-chunk. |
//| |
//| Fresh era: re-measure the class priors, clear every per-era tally |
//| together, size the IS/OOS split, and reset the four passes. The |
//| resume arm restores the bar cursor exactly where the last chunk |
//| left it - the two are one decision and stay in one place. |
//| |
//| Defers on the same contract as BeginTrainRun: true = this call is |
//| spent, false = the era is ready to run passes. |
//+------------------------------------------------------------------+
bool CExpertSignalAIBase::BeginEra(STrainEra &era)
{
if(!m_eraResumePending)
{
//--- COLD-INDICATOR BACKOFF (2026-08-13). Give them a few quiet seconds instead; the stall
//--- reporter stays the loud diagnosis if it persists.
if(m_coldSweepTick != 0)
{
if(GetTickCount() - m_coldSweepTick < 5000)
{
ReportTrainStall("cold-indicator backoff (all windows failed on a transient cause)");
return true;
}
m_coldSweepTick = 0;
}
int barsNow = (int)MathMin(Bars(m_symbol.Name(), PERIOD_CURRENT, dtStudied, TimeCurrent()) + m_historyBars, Bars(m_symbol.Name(), PERIOD_CURRENT));
//--- PRIME, THEN SETTLE, THEN SWEEP.
if(!ResizeBuffers(barsNow) || !RefreshData())
{
PrintFormat("%s: era start ABORTED - price/indicator buffers would not prepare for %d bars"
" (priming ResizeBuffers/RefreshData failed); ending this training run, it re-arms"
" on the next scheduled call", ID, barsNow);
FinalizeTrainRun();
return true;
}
//--- Now wait out the depth rather than snapshotting it. Returns 0 while the count is still moving.
int settled = SettledBars(barsNow, "training sweep");
if(settled <= 0)
{
ReportTrainStall("priming indicator history (holding the sweep until the calculated depth"
" stops changing)");
return true;
}
//--- The floor is the one piece of policy that stays here: below TRAIN_MIN_CLAMPED_BARS a settled
//--- depth is too thin to train anything worth measuring, so the run holds and the stall reporter
//--- stays the loud diagnosis rather than producing a meaningless era.
if(settled < barsNow)
{
if(settled < TRAIN_MIN_CLAMPED_BARS)
{
ReportTrainStall(StringFormat("indicator depth settled at %d bars, below the %d-bar floor"
" for a trainable era", settled, TRAIN_MIN_CLAMPED_BARS));
return true;
}
barsNow = settled;
//--- Re-prepare at the clamped depth, and ONLY when it actually changed: the primer above
//--- already left every buffer refreshed at the full depth, so an unconditional second pass
//--- would be a wasted CopyBuffer over every buffer, every era, on the charts that need none.
if(!ResizeBuffers(barsNow) || !RefreshData())
{
//--- The ONLY exit from Train() that tears down the whole run, and it used to be completely
//--- silent - a transient buffer/history hiccup ended the run, FinalizeTrainRun() pushed
//--- dtStudied to the last scanned bar, and the next era simply never started. Indistinguishable
//--- from a hang while it was quiet, so it says so (2026-08-10).
PrintFormat("%s: era start ABORTED - price/indicator buffers would not prepare for the"
" settled depth of %d bars (ResizeBuffers/RefreshData failed); ending this"
" training run, it re-arms on the next scheduled call", ID, barsNow);
FinalizeTrainRun();
return true;
}
}
era.bars = barsNow;
//--- Cross-asset panel is indexed against exactly this bar grid, so it is (re)built wherever
//--- the grid is - never per bar. Non-fatal on failure; see BuildCrossAssetPanel().
BuildCrossAssetPanel(barsNow);
EnsureSpreadSeries(barsNow);
//--- Meta target: resolve the candidate corpus onto THIS era's bar grid before pass 1 walks it
//--- (series indices shift on every closed bar, so the resolution is per-era, like the caches).
//--- No candidates is not a trainable state - end the run loudly instead of scanning for nothing.
if(IsMetaTarget() && !MetaPrepareEra(barsNow))
{
PrintFormat("%s: era start ABORTED - no usable meta candidates on this chart (see the"
" MetaCorpus lines above for the corpus/offset diagnostics); ending this training"
" run, it re-arms on the next scheduled call", ID);
FinalizeTrainRun();
return true;
}
era.addLoop = false;
//--- Label/feature cache invalidation: MQL5 timeseries indices are always relative to "now"
//--- (index 0 = current bar), so every new closed candle shifts every older bar's index - a
//--- cache keyed by index would silently misalign the moment that happens.
int barsBefore = m_labelCacheBars;
datetime anchorBefore = m_labelCacheAnchorTime;
datetime anchorNow = m_Time.GetData(0);
if(EnsureBarCachesCapacity(era.bars) && m_labelCachePrebuilt)
{
//--- The failure mode: the era and the prebuild disagree about `bars`, or about which bar
//--- is index 0, and re-arm each other forever - caches wiped, relabelled, wiped again, no
//--- era ever runs.
string sizeKey = (era.bars != barsBefore)
? StringFormat("SIZE CHANGED %d -> %d", barsBefore, era.bars) : "size unchanged";
string anchorKey = (anchorNow != anchorBefore)
? StringFormat("ANCHOR MOVED %s -> %s", TimeToString(anchorBefore),
TimeToString(anchorNow)) : "anchor unchanged";
ReportTrainStall(StringFormat("cache invalidated at era start - %s, %s (era sized %d bars, cache"
" held %d). An anchor that moves EVERY era with the size steady is"
" a new candle each pass or a Time buffer that is not being"
" refreshed; a size that moves is the era/prebuild disagreement.",
sizeKey, anchorKey, era.bars, barsBefore));
StartLabelCachePrebuild();
return true;
}
//--- freeze the just-finished era's true class totals for this new era's priors (see
//--- m_prevEraTrueBuyCount's declaration comment) before resetting the live counters below - EXCEPT
//--- right after StartLabelCachePrebuild()/AdvanceLabelCachePrebuild() seeded them for era 0: the
//--- live m_trueBuyCount/Sell/Neutral tally is still all-zero at that point (nothing trained yet),
//--- so copying it here would silently stomp the real upfront tally back to an empty distribution.
if(m_prebuildSeedPending)
m_prebuildSeedPending = false;
else
{
m_prevEraTrueBuyCount = m_trueBuyCount;
m_prevEraTrueSellCount = m_trueSellCount;
m_prevEraTrueNeutralCount = m_trueNeutralCount;
}
//--- Natural class base rates for the live logit-adjusted decision (see
//--- AdjustedSignalFromSoftmax): derived from the same just-finished-era true class totals
//--- the oversampling ratio uses, so live calibrates to exactly the distribution the model
//--- was measured against.
if(!IsMetaTarget())
{
UpdateClassPriors(m_prevEraTrueBuyCount, m_prevEraTrueSellCount, m_prevEraTrueNeutralCount);
//--- Re-install the training-time logit offsets from the priors just measured, so this
//--- era's gradient tracks the distribution the era is scored against.
ApplyLogitAdjustment();
}
m_countBuySignals = 0;
m_countSellSignals = 0;
m_countNeutralSignals = 0;
m_trueBuyCount = 0;
m_trueSellCount = 0;
m_trueNeutralCount = 0;
//--- All twenty-one OOS confusion counts at once. They are read together at era end, so they
//--- must be cleared together - see 7452bd1 for what a partial reset of a tally group costs.
m_oos.Reset();
//--- Simulated-exit accumulators, reset with the rest of the per-era OOS tallies.
m_simRSum = 0.0;
m_simRSumSq = 0.0;
m_simTrades = 0;
m_simVoteExits = 0;
m_simBarrierWins = 0;
m_simTpHits = 0;
m_geo.Reset();
m_simTimeouts = 0;
m_simTimeoutRSum = 0.0;
//--- Declustered tally + its replay cursors. -1 / Neutral is "nothing seen yet this era", which is
//--- what makes the first directional call of an era always survive rule 1.
//--- meta per-family/per-side OOS decomposition - see the member declaration
ArrayInitialize(m_metaFamCand, 0);
ArrayInitialize(m_metaFamWins, 0);
ArrayInitialize(m_metaFamFired, 0);
ArrayInitialize(m_metaFamFiredWins, 0);
ArrayInitialize(m_metaSideCand, 0);
ArrayInitialize(m_metaSideWins, 0);
ArrayInitialize(m_metaSideFired, 0);
ArrayInitialize(m_metaSideFiredWins, 0);
m_oosNmsFired = 0;
m_oosNmsHits = 0;
m_oosNmsLastBuyIdx = -1;
m_oosNmsLastSellIdx = -1;
m_oosNmsKeptIdx = -1;
m_oosNmsKeptConf = 0.0;
m_oosNmsKeptDir = Neutral;
ArrayInitialize(m_oosTierFired, 0);
ArrayInitialize(m_oosTierHits, 0);
// Nearest-to-present slice of this era's bars is held out as OOS and never backprop'd on;
// the rest (older bars) is the IS/training slice.
era.totalIter = (int)MathMax(era.bars - MathMax(m_historyBars, 0), 0);
era.oosCutoff = (int)(MathMax(0, MathMin(100, m_oosSplitPct)) / 100.0 * era.totalIter);
era.i = (int)(era.bars - MathMax(m_historyBars, 0) - 1);
//--- Fresh era: reset pass 2's shuffled-backprop queue (see m_isTrainQueue's declaration
//--- comment).
ArrayResize(m_isTrainQueue, era.totalIter * 4);
ArrayResize(m_isTrainQueueCand, era.totalIter * 4);
m_isTrainQueueCount = 0;
//--- Heartbeat baseline for this era - see the member declarations for why this exists.
m_eraStartTick = GetTickCount();
m_passFeatUs = 0;
m_passNetUs = 0;
m_passWindowOk = 0;
m_passWindowFail = 0;
m_passHeartbeatPrints = 0;
m_lastHeartbeatTick = 0;
m_isTrainCursor = 0;
m_isPass2Active = false;
m_isPass2Done = false;
m_isCalibActive = false;
m_isCalibDone = false;
m_isPass3Active = false;
//--- Excursion head: per-era Brier accumulators only. The base rates it is compared against are a
//--- property of the data, not of the era, so they keep accumulating (see ExcursionResetEraScores).
ExcursionResetEraScores();
//--- Fresh per-era predicted-signal cache for the end-of-era NMS sweep (see PruneDirectionalClusters).
//--- -2 = "not scored this era" so stale bars from a longer prior era can't draw phantom arrows.
if(m_signalClusterWindow > 0)
{
ArrayResize(m_arrowSignalCache, era.bars);
ArrayInitialize(m_arrowSignalCache, -2.0);
}
}
else
{
//--- resuming a chunk that yielded mid-bar-loop last call - pick up exactly where it left off
era.bars = m_resumeBars;
era.totalIter = m_resumeTotalIter;
era.oosCutoff = m_resumeOosCutoff;
era.addLoop = m_resumeAddLoop;
era.i = m_resumeBarIndex;
m_eraResumePending = false;
}
//--- Set up and ready to run this call's chunk.
return false;
}
//+------------------------------------------------------------------+
//| WHAT PASS 1 FOUND, said out loud. Reporting only - it decides |
//| nothing and the era proceeds identically either way. |
//| |
//| Two outcomes worth a line. A sweep that produced NO usable |
//| window at all gets a full autopsy naming the lookback slot, the |
//| guard that rejected it and the per-indicator depth, because the |
//| era is discarded and restarts and the symptom is otherwise a |
//| silent loop - the backoff this arms was dead until 2026-08-17, |
//| which is why the USDJPY/XAUUSD stall never recovered. |
//| |
//| A HEALTHY first sweep is the one moment the assembled feature |
//| vector is known readable and not yet trained on, and the first |
//| point at which the bar grid, the barrier geometry and the label |
//| lifespan are all real numbers rather than defaults - so the |
//| block-level autopsy and the detectability report belong here and |
//| nowhere else. |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::ReportPass1Outcome(STrainEra &era)
{
//--- PASS 1 IS OVER (the yield above is the only other way out of that loop). This is the
//--- point that decides whether the era does any work at all, and until now it said nothing.
//--- add_loop is exactly "m_passWindowOk > 0".
if(!era.stop)
{
if(!era.addLoop)
{
//--- SELF-HEAL BEFORE RESTARTING. A sweep that produced no usable window at all will
//--- produce exactly the same result next time unless something changes, because every
//--- bar it touched is now answered from the feature cache.
ArrayInitialize(m_featureCacheHasValue, false);
//--- Routed through ReportTrainStall rather than printed directly: a discarded era
//--- restarts immediately, so this condition repeats as fast as pass 1 can sweep, and
//--- an unthrottled line would bury the journal.
string whyLine;
if(m_windowFailSlot == -2)
whyLine = "no window has been attempted yet this run (m_windowFailSlot unset) - the"
" failure is upstream of BuildFeatureWindow";
else
if(m_windowFailSlot < 0)
whyLine = StringFormat("every lookback bar was ACCEPTED and the window was still"
" short: %d of %d values. A feature block emitted fewer values"
" than m_neuronsCount promises", m_windowFailTotal,
(int)m_historyBars * m_neuronsCount);
else
//--- THE BLOCK, NOT JUST THE SLOT. A total failure (ok=0) is itself evidence: it
//--- means the newest anchors failed too, which no depth shortfall can cause.
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
{
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
string byBlock = m_featureFailBlock;
if(byBlock == "")
byBlock = "(no guard recorded - the rejection came from a TempData.Add failure,"
" not a data guard)";
whyLine = StringFormat("lookback slot %d of %d REJECTED the bar at series index %d"
" (window had %d of %d values). REJECTED BY: %s. Slot 0 is the"
" DEEPEST lookback of the window, so with ok=0 the newest anchors"
" failed as well - which rules out a plain history-edge read and"
" points at a buffer that is unreadable at every index."
" Per-indicator depth:%s",
m_windowFailSlot, (int)m_historyBars, m_featureFailIdx,
m_windowFailTotal, (int)m_historyBars * m_neuronsCount,
byBlock, IndicatorDepthReport());
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
ReportTrainStall(StringFormat("pass 1 finished but NOT ONE of %d scanned bars produced a"
" usable feature window, so the era is discarded and restarts"
" from scratch (feature cache dropped so the next sweep"
" recomputes) - windows ok=%d failed=%d, BuildFeatureWindow"
" needs %d values per bar (historyBars=%d x featuresPerBar=%d)"
" over %d bars | LAST FAILURE: %s",
era.totalIter, m_passWindowOk, m_passWindowFail,
(int)m_historyBars * m_neuronsCount,
(int)m_historyBars, m_neuronsCount, era.bars, whyLine));
//--- transient cause (cold indicator) -> arm the era-start backoff instead of
//--- resweeping at full speed; see the backoff block at the top of the fresh-era
//--- branch. The mechanism was right; nothing reached it. THIS BACKOFF WAS DEAD UNTIL
//--- 2026-08-17 and that is why the USDJPY/XAUUSD stall never recovered.
m_coldSweepTick = GetTickCount();
}
else
{
//--- Healthy pass 1. FIRST HEALTHY SWEEP is the only moment the assembled feature
//--- vector is known to be readable and not yet been trained on - so it is where the
//--- block-level autopsy belongs.
ReportFeatureHealth(era.bars);
//--- Same moment, same reason: the first sweep that produced usable windows is the
//--- first point at which the era's bar grid, the measured barrier geometry and the
//--- label lifespan are all real numbers rather than defaults.
ReportDetectability(era.oosCutoff);
const uint PASS1_LOUD_AFTER_MS = 10000;
//--- The calibration band is reported here, beside the queue count it is subtracted from, so
//--- the two are read together: a run where the band silently came out empty (see
//--- CalibBandBars) is one whose operating point is no longer being refitted at all, and the
//--- only place that is visible is next to the number it should have reduced.
string pass1Line = StringFormat("%s: era %d pass 1 done in %.0fs - %d of %d bars usable"
" (%d failed, normal over the oldest bars), %d queued for"
" backprop | %d bars held out to calibrate the operating"
" point (+2x%d purged around it)", ID, (int)m_eraCount,
(GetTickCount() - m_eraStartTick) / 1000.0, m_passWindowOk,
m_passWindowOk + m_passWindowFail, m_passWindowFail,
m_isTrainQueueCount,
CalibBandBars(era.totalIter, era.oosCutoff), CalibPurgeBars());
if(GetTickCount() - m_eraStartTick >= PASS1_LOUD_AFTER_MS)
Print(pass1Line);
else
PrintVerbose(pass1Line);
}
}
}
//+------------------------------------------------------------------+
//| THE ERA COMPLETED. Count it, age the shadow net, and decide |
//| whether the RUN ends here. |
//| |
//| Two ways it does. The plateau ladder (or the ensemble gate) says |
//| there is something worth deploying - the normal, wanted ending. |
//| Or the era cap is reached, which is not a verdict about the model |
//| at all: it asks the operator, and a "deploy anyway" is an explicit|
//| choice that the automatic ladder would have refused, so it says |
//| so plainly rather than letting the deploy read as a clean pass. |
//| |
//| Self-guarding on era.addLoop: an era that produced no usable bars |
//| is not an era and must not advance the counter, or the cap and |
//| the plateau ladder both measure work that never happened. |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::AdvanceEra(STrainEra &era, SEraTelemetry &tel)
{
//--- era complete (ran out of bars) or a stop was requested mid-era
if(era.addLoop)
{
m_eraCount++;
m_erasSinceCooldown++;
//--- EMA shadow-weight deployment: blend the shadow a small step (SHADOW_WEIGHT_TAU)
//--- toward Net's just-updated weights, every era - see m_shadowNet's declaration comment.
EnsureShadowNet();
if(CheckPointer(m_shadowNet) != POINTER_INVALID)
m_shadowNet.BlendWeightsFrom(Net, SHADOW_WEIGHT_TAU);
//--- Status-label progress is invisible with no chart (headless/optimization runs), and
//--- even in visual mode a long training run can otherwise look "stuck" for a long time
//--- with no Journal output at all - log progress at most every ~5s (real wall-clock, not
//--- simulated time) so an operator can tell it's actively working, not hung.
uint nowTick = GetTickCount();
tel.shouldLog = (nowTick - m_lastProgressLogTick >= 5000);
if(tel.shouldLog)
m_lastProgressLogTick = nowTick;
//--- Era cap. There used to be a second, much smaller cap here for throwaway auto-tune
//--- candidates; the filter tuner does not train candidates at all, so only the real one remains.
int effectiveEraCap = m_maxErasPerRun;
//--- PLATEAU LADDER, terminal stage: training stopped improving and both escape attempts
//--- (two learning-rate warm restarts) failed to find anything better - see the ladder in
//--- the era-end block below, which is what raised m_plateauStage this far and already
//--- logged why.
bool deployNow = m_ensembleMember
? (g_ensDeployApproved && m_haveOosCheckpoint)
: ((m_plateauStage >= PLATEAU_STAGE_DEPLOY || m_isErrorPlateaued) && m_bestPassedRecall && m_haveOosCheckpoint
//--- AND the market was measured to hold directional information in the
//--- first place. See m_dirEvidence: the MI suite has always printed this
//--- verdict and then deployed regardless of what it said.
&& m_dirEvidence);
if(deployNow)
{
era.stop = true;
m_trainingComplete = true;
}
else if(effectiveEraCap > 0 && m_erasSinceCooldown >= effectiveEraCap)
{
//--- Era cap reached without converging: ask the operator whether to keep training or
//--- deploy the best checkpoint and stop (see PromptContinuePastEraCap / m_maxErasPerRun).
if(PromptContinuePastEraCap(dOosForecast))
{
m_erasSinceCooldown = 0; // keep training - reset the cap window
Print(ID + ": hit the " + IntegerToString(m_maxErasPerRun) + "-era cap (best dir-precision " + DoubleToString(m_bestBalancedOos, 1) + "%, blended OOS " + DoubleToString(dOosForecast, 1) + "%) - CONTINUING training by operator choice.");
}
else
{
//--- stop: end THIS era loop now; FinalizeTrainRun (reached via the stop path below,
//--- because stop==true) deploys the best checkpoint. See OnlineLearnStep()'s gate.
era.stop = true;
//--- Operator DELIBERATELY chose to deploy this best checkpoint as the final model.
//--- Note the m_trainingComplete=(m_objectiveMet&&m_oosStable) line below is inside
//--- if(!stop), so it can't clobber this back to false on this path.
m_trainingComplete = true;
Print(ID + ": hit the " + IntegerToString(m_maxErasPerRun) + "-era cap before the plateau ladder finished (best dir-precision " + DoubleToString(m_bestBalancedOos, 1) + "%, blended OOS " + DoubleToString(dOosForecast, 1) + "%) - operator chose to DEPLOY the best checkpoint as final (marked complete; reloads will run inference, not retrain). Reaching this cap now means the run was still finding new bests, or never cleared the per-class recall floor (need >=" + IntegerToString(m_minDirectionalRecallPct) + "% each) - raise the era cap for the former, relax MinRecall/SwingConfirmationBars for the latter.");
//--- NOT blocked - this branch is an explicit operator decision and stays one. But the
//--- automatic ladder would refuse this model, so say so plainly rather than letting the
//--- deploy read as a clean pass. See DEPLOY_FAMILY_WISE_ALPHA.
ReportSelectionGateVerdict("era-cap deploy");
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
}
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
}
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
}
//+------------------------------------------------------------------+
void CExpertSignalAIBase::Train(datetime StartTrainBar = 0)
{
//--- THIS CALL'S WORKING STATE. One object rather than eight locals threaded through four
//--- passes - see STrainEra for why the passes could not be separated while it was eight.
STrainEra era;
//--- Max wall-clock work per call before yielding - see m_trainRunActive's declaration comment
//--- for why chunking exists at all. Lowered back to 120ms to keep the UI reactive. Backing off
//--- to the documented 120ms.
//--- ENSEMBLE: four members share the one chart thread and their chunks queue back-to-back, so
//--- the worst-case latency between a panel click and a free thread is members x budget - 4 x
//--- 120ms = 480ms, which is exactly the "drags stickily, buttons miss clicks" regime the 200ms
//--- note above documents (user-reported on the first ensemble runs, 2026-08-15).
era.budgetMs = m_ensembleMember ? (uint)(120 / MathMax(EnsembleActiveTrainers(), 1)) : 120;
if(TrainCallPreempted(era))
return;
fix(train): BeginTrainRun read Train()'s parameter from a scope it no longer had The run-start block calls TrainWindowStart(StartTrainBar), and StartTrainBar is Train()'s parameter. Moving the block into its own method left the read behind. Now passed explicitly. THIRD TIME THIS FAMILY HAS BILLED THIS SESSION, and the third distinct sub-shape: 1d7ebbd a DELETED loop's variable still read by its body d7469c6 a RENAMED field still read by its call site here a MOVED block still reading its old enclosing scope Same root cause each time: I verify the side I edited. What I had been checking - statement multisets, brace balance, field-name resolution - all passed, because none of them models SCOPE. The move was faithful; the scope was not. So scope is now checked too. For every CExpertSignalAIBase::Method, collect the identifiers its body reads and subtract what can actually resolve: names declared in the body (any type, and every name in a multi-declarator), the method's own parameters, class members, file-scope globals and #defines. Parameter names from OTHER declarations must NOT count as resolvable - that is the bug in the first version of this check, which let StartTrainBar through because Train() declares it in the header. Validated against the broken commit before being trusted: it reports StartTrainBar there and not here. The only residual output is MQL5 enum members and EA inputs declared outside the scanned headers. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:58:35 -04:00
if(BeginTrainRun(era, StartTrainBar))
refactor(train): Train() is the era lifecycle again, not the whole of it Train() was 1,273 lines. It is now 79, of which about 35 are statements, and they read as what the function is: preempt, begin run, begin era, four passes, advance, complete, report, finalize. Seven methods carry what left it: TrainCallPreempted 107 six ways this call is not a training call at all BeginTrainRun 130 once per run - history sync, window, one-shot walks BeginEra 232 once per era, or resume a chunk that yielded ReportPass1Outcome 105 what pass 1 found, said out loud AdvanceEra 68 count the era, decide whether the RUN ends CompleteEra 590 calibrate, gate, rank, checkpoint, ladders, persist ReportBarrierHold 62 why this member is idle at the era barrier ClaimCallForWalk 15 the preamble the three exclusive walks shared TWO DRY FIXES fell out rather than being looked for. The three exclusive walks each had to tell TWO watchdogs the same thing - the stall reporter which branch is running, the era-barrier watchdog that this member is BUSY rather than stuck - written out three times, so a fourth walk was three chances to be added with only one of them. And the barrier-hold reporting was 44 lines inline in a branch whose only other statement was resetting a tick. CompleteEra is lifted WHOLE and stays that way for now. Its parts share thirty-odd locals - the recalls, the gate verdict, the better/worse flags - and threading those through three signatures would recreate exactly the eight-locals-across-four-passes problem STrainEra was built to end. Splitting it needs an era-outcome object first, not more parameters. VERIFIED AS A PURE MOVE: statement multisets, old file vs new, differ only by the 14 `return;` that became 17 `return true;` plus 3 new returns at the call sites, the 3 collapsed walk preambles, the 8 new signatures and their braces. Nothing else moved, and every function closes at depth 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 14:50:59 -04:00
return;
if(BeginEra(era))
return;
// Restore this model's own learning-rate trajectory into the shared global right before this
// chunk's backProp() calls touch it - see m_modelEta's declaration comment.
g_eta = m_modelEta;
era.chunkStartTick = GetTickCount();
// Iterate over the bars - skipped entirely when resuming straight into pass 2, OR when resuming
// into a still-unfinished pass 3 (see m_isPass2Done's declaration comment for why checking
// m_isPass2Active alone isn't enough to detect the latter case): pass 1 already fully completed
// in an earlier call either way.
if(!m_isPass2Active && !m_isPass2Done)
{
RunPass1(era);
ReportPass1Outcome(era);
}
//--- Pass 2: replay the bars pass 1 queued into m_isTrainQueue for backProp, in a freshly
//--- shuffled order - see m_isTrainQueue's declaration comment for the full rationale.
RunPass2(era);
//--- Pass 2.5: the CALIBRATION walk.
RunCalibrationPass(era);
//--- Pass 3: OOS scoring, chronological, AFTER pass 2 has actually trained on this era's IS data -
//--- see m_isPass3Active's declaration comment for why this can no longer happen inline during
//--- pass 1's scan.
RunOosPass(era);
//--- What this era has to report, filled in below and rendered by ReportEraProgress. Every
//--- field starts at -1 = not measured, which is what era 0 and any stopped era report.
SEraTelemetry tel;
AdvanceEra(era, tel);
CompleteEra(era, tel);
style(training): the era's second half was indented as if nested 673 lines after the OOS pass sat at indent 6 while being at function level. It read as a block inside something, which is how I initially mis-measured pass 3 as 1,178 lines when its closing brace is 504 lines in - the indentation, not the braces, was telling the story. Whitespace only. Verified by comparing every non-blank line of both revisions with leading and internal whitespace collapsed, COMMENTS INCLUDED: zero lines added, zero removed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-23 11:31:04 -04:00
ReportEraProgress(tel);
//--- Genuine convergence THIS era (not a stale m_trainingComplete carried over from a
//--- previous run) - (re)start the evaluation-only continual-learning OOS walk.
if(!era.stop && m_trainingComplete)
{
Print(ID + ": training CONVERGED at era " + IntegerToString(m_eraCount) + " - this is the best this configuration reached: dir-precision " +
DoubleToString(m_bestBalancedOos, 1) + "%, blended OOS " + DoubleToString(dOosForecast, 1) + "%, IS error " + DoubleToString(dError, 2) +
". No new best for " + IntegerToString(m_erasSinceBestBalanced) + " eras across " +
IntegerToString(PLATEAU_STAGE_DEPLOY - 1) + " learning-rate warm restarts." +
" Weights saved, switching to live inference.");
StartOosContinualSimulation(era.bars, era.oosCutoff);
}
if(era.stop || m_trainingComplete)
FinalizeTrainRun();
//--- Deliberately AFTER FinalizeTrainRun(): that call restores the DEPLOYED checkpoint's weights
//--- (which may differ from the last era's, if the plateau ladder's best era wasn't the last one
//--- run), and this backfill must score with exactly what is about to trade live.
if(!era.stop && m_trainingComplete)
StartPatternDatabaseBackfill(era.bars, era.totalIter, era.oosCutoff);
//--- else: this era is done but the run continues - the next Train() call (re-triggered via
//--- ScheduleTrainingIfNeeded()'s custom event, same mechanism as always) starts the next era
//--- fresh, since m_eraResumePending is false while m_trainRunActive stays true
//--- Save this model's own learning-rate trajectory back out of the shared global before
//--- returning - see m_modelEta's declaration comment. Covers every path that reaches here
//--- (natural era completion, whether or not the run itself just finalized).
m_modelEta = g_eta;
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
//+------------------------------------------------------------------+
//| Ends the current Train() run: restores the best-scoring era's |
//| checkpointed weights (if any beat the era the loop happened to |
//| end on), persists final state, and clears the resumable-run |
refactor(comments): box headers to stdlib length The //| box blocks were excluded from 0b06f8e and 5efdb48 and were what remained: 160 of them ran to 10+ lines, the longest to 88. Compressed to their leading topic sentences - 5 lines for a function header, 8 for a file header - keeping the box format and the standard MQL5 name/author lines verbatim. Verified at the BYTE level this time, across every in-scope file: the list of non-comment lines is byte-identical to HEAD and braces balance. The first check compared a locale-decoded 'git show' against a UTF-8 read and flagged 25 files that had not changed at all - every BOM and every non-ASCII line mismatched. 47,696 -> 40,665 lines in scope; comment share 38% -> 26%. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:30:14 -04:00
//| flags. |
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
//+------------------------------------------------------------------+
bool CExpertSignalAIBase::PromptContinuePastEraCap(double bestOos)
{
//--- No GUI in the Strategy Tester/optimizer - MessageBox() is unavailable there and would just
//--- stall a headless run, so deploy the best checkpoint found so far and stop (the safe default).
if(MQLInfoInteger(MQL_TESTER) || MQLInfoInteger(MQL_OPTIMIZATION) || MQLInfoInteger(MQL_FORWARD))
return false;
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- Reaching this cap is now the UNUSUAL outcome: a run normally ends itself when the plateau
//--- ladder runs out of escapes (see the PLATEAU_* constants), which is a statement about the
//--- run having stopped improving rather than about any accuracy number.
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
bool recallMet = (m_lastBuyRecallPct < 0 || m_lastBuyRecallPct >= m_minDirectionalRecallPct) &&
(m_lastSellRecallPct < 0 || m_lastSellRecallPct >= m_minDirectionalRecallPct);
string neutralNote = (m_priorNeutral > 0.0)
? ("inflated by the ~" + IntegerToString((int)MathRound(m_priorNeutral * 100.0)) + "% Neutral base rate")
: "inflated by the dominant Neutral class";
string reasons = "";
if(!m_bestPassedRecall)
reasons += " - No era has ever cleared the per-class recall floor, so there is no model safe to\n" +
" auto-deploy yet (a model that ignores Buy or Sell must never ship)\n";
else
reasons += " - Still improving: " + IntegerToString(m_erasSinceBestBalanced) + " eras since the last new best, plateau stage " +
IntegerToString(m_plateauStage) + " of " + IntegerToString(PLATEAU_STAGE_DEPLOY) + " (the run ends itself at stage " +
IntegerToString(PLATEAU_STAGE_DEPLOY) + ")\n";
if(!recallMet)
reasons += " - Latest era's per-class recall below the floor: Buy " +
(m_lastBuyRecallPct < 0 ? "n/a" : IntegerToString(m_lastBuyRecallPct) + "%") + " / Sell " +
(m_lastSellRecallPct < 0 ? "n/a" : IntegerToString(m_lastSellRecallPct) + "%") +
" (need >=" + IntegerToString(m_minDirectionalRecallPct) + "% each)\n";
if(!m_objectiveMet)
reasons += " - The latest era did not produce a valid model (recall floor not met/not measured)\n";
string balancedStr = (m_bestBalancedOos > 0.0)
feat(ai): measure precision per confidence tier; fix stale metric labels Two things the 2026-07-30 run exposed. 1. Every user-facing message still called the selection metric "balanced accuracy". It has ranked on directional precision since a142749, so "CONVERGED ... balanced accuracy 32.5%" was reporting a 32.5% PRECISION as if it were macro-recall, while the same era logged an actual balanced accuracy of 49%. Two different numbers under one name, in the line that announces a deploy. Relabelled at every site, including the stage-3 refusal, which still described the per-class recall floor that stopped being the gate. 2. Precision is now bucketed by confidence tier and logged per era, both per-tier and cumulatively from each tier upward: | tier prec T0:19%(410)[>=28%/1204] T1:31%(520)[>=34%/794] ... The per-tier number says whether confidence is calibrated to correctness at all; if it does not rise T0->T3, raising the floor buys nothing and that is the finding. The ">=" number is what a floor would actually deliver, with its fire count, so the coverage cost is visible in the same line. Tier weights are 25/50/75/100, so for an AI-only config Min_Vote_Open maps straight across: 50 = ">=T1", 75 = ">=T2", 100 = ">=T3". Bucketing happens at the existing live-fired accounting site, so it measures exactly the population that trades - not the raw argmax. Both builds compile 0 errors, 0 warnings. No retrain needed for either. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-30 11:47:15 -04:00
? ("\nBest directional precision, coverage-weighted (the metric the deployed\ncheckpoint is chosen on): " + DoubleToString(m_bestBalancedOos, 1) +
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
"%\nBest blended OOS accuracy: " + DoubleToString(bestOos, 1) + "% (" + neutralNote + ")\n")
: "";
string msg = ID + ": training reached the " + IntegerToString(m_maxErasPerRun) +
"-era cap before it finished on its own.\n\n" +
"Training now runs until it stops improving, then deploys its best model. Status:\n" +
reasons +
balancedStr +
"\nContinue training?\n\n" +
"Yes = keep training for another " + IntegerToString(m_maxErasPerRun) + " eras\n" +
"No = deploy the best checkpoint so far and stop training";
int res = MessageBox(msg, "Warrior EA - training", MB_YESNO | MB_ICONQUESTION);
return (res == IDYES);
}
//+------------------------------------------------------------------+
//+------------------------------------------------------------------+
//| See the declaration comment - the single deploy-persistence path. |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::PersistDeployedModel(void)
{
if(CheckPointer(Net) == POINTER_INVALID)
return;
double currentIndicatorParams[];
m_indicatorTuner.Flatten(currentIndicatorParams);
if(!Net.Save(m_activeFileName + ".nnw", dError, dUndefine, dForecast, dtStudied, m_activeFileCommon, m_eraCount, m_trainingComplete, currentIndicatorParams))
Print(__FUNCTION__ + ": ERROR - Net.Save failed for " + m_activeFileName + ".nnw. The deployed model was NOT persisted to disk.");
//--- Deploy-time gate: does this model's pure-MQL5 forward pass match the backend? If so, an
//--- inference-only backtest can run DLL-free (see ValidateCpuInference / CNet::SetCpuInference).
//--- Persisted into the .stats written next. Chart-only; safe-false everywhere else.
m_mqlInferenceValidated = ValidateCpuInference();
if(!SaveModelStats(m_activeFileName, m_activeFileCommon)) // keep calibration state paired with the just-saved weights
Print(__FUNCTION__ + ": ERROR - SaveModelStats failed for " + m_activeFileName + ". Calibration state not persisted.");
SaveShadowNet(currentIndicatorParams);
}
//+------------------------------------------------------------------+
void CExpertSignalAIBase::FinalizeTrainRun(void)
{
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- A run stopped mid-pass-2.5 or mid-pass-3 never reached that pass's own unfreeze, so lift
//--- the scoring freeze here before anything else touches the net - the deployed model must
//--- adapt live (see the freeze at pass-3 start, and the identical one the calibration walk
//--- takes for the same reason).
fix: training-stability audit fixes F1/F2/F3/F5 - unbiased shuffle, real plateau escapes, fresh optimizer state on restore, pure OOS metric Four of the six findings from research/training_pipeline_audit_2026-08-09.md (F4 mini-batching and F6 feature re-encode deliberately deferred - see the report's implementation-status section for why): - F1: pass-2 Fisher-Yates (and AutoTune's MI block shuffle) used MathRand()%, which is 15-bit - provably non-uniform on every full-history era over 32,768 queued samples. New 30-bit ShuffleRandomIndex(). - F2: plateau warm restarts were a no-op whenever eta already sat at its ceiling (the normal state of a non-regressing plateau) - the ladder was just a 24-era countdown. Restarts now overshoot to 5x the ceiling (PLATEAU_RESTART_BOOST) and anneal geometrically back over the patience window, SGDR-style; ETA_MIN widened 1e-4 -> 1e-5 so the decay schedule has real range. - F3: checkpoint restores put weights back but kept the rejected trajectory's Adam moments, so the optimizer immediately pushed back toward the rolled-back state (the restore->regress->restore oscillation). CNet::ResetOptimizerState() zeroes moments/momentum/step counters (weights, BN statistics, gamma/beta untouched) on every mid-run restore, every boosted restart, and the deploy-time restore that online learning continues from. - F5: batch-norm running statistics now freeze for the pass-3 OOS scoring walk, so the selection metric the checkpoint ranking and deploy gate read is a pure function of the checkpoint instead of partly measuring BN drift. Defensive unfreeze in FinalizeTrainRun covers stop-mid-pass; live/online adaptation and the OOS continual-learning simulation stay adaptive by design. Compiled clean (0 errors, 0 warnings) via the staged-tree recipe. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 10:54:09 -04:00
if(CheckPointer(Net) != POINTER_INVALID)
feat: mini-batch gradient accumulation (F4), front-end-aware capacity budget (F6), split Wyckoff categoricals (N1) Completes the 2026-08-09 training audit. FORCES A RETRAIN of every Wyckoff-enabled config (N1 re-keys the fingerprint), and BOTH DLLs must be redeployed alongside the .ex5 - they carry new exports. F4 - mini-batch accumulation, TRAIN_BATCH_SIZE=32. Training was pure online SGD (one weight update per bar), which is the mechanical source of the era-to-era whipsaw every downstream guard was built to cope with. The O(n^2) outer product is native - AccumulateWeightGrad / AccumulateWeightGradConv / AccumulateBufferInto in Network.cl, WarriorCPU and WarriorDML - while the optimizer step is host-side MQL5 shared by all tiers (ApplyAccumToBlock), so there is one Adam/SGD implementation instead of four that can drift. - the LSTM needs no outer-product kernel (WeightsGradient already holds the sample's full dW) but could NOT simply be left un-zeroed between samples: CPU_LSTMSeqBackward/DML_LSTMSeqBackward memset it on entry. Hence a separate accumulator plus an elementwise add. - batch-norm gamma/beta accumulate in host arrays, not new BatchOptions slots - BN_OPT_STRIDE is baked into every persisted .nnw. - scoped to pass 2; online learning keeps immediate updates. Every save / checkpoint / scoring boundary flushes, scaling by the real sample count. - degrades to per-sample updates (one log line) on a tier that cannot accumulate, so old devices and DLL-free builds are unaffected. - verified offline: DirectML/batch_accum_check.cpp drives the real exports against an independent reference; at B=1 the accumulator matches the shipped unbatched kernel's own gradient to 1.1e-16. Math only - the in-situ check remains the per-layer dW/W report on a real era. F6 - ComputeFirstLayerWidth budgeted against the RAW input width even where a conv/LSTM front end had already reduced it, so an LSTM's dense stack was charged for 1,280 inputs when it receives 64. Confirmed from the deployed .cfg files: CONV, LSTM and HYBRID were all pinned at the 16-unit floor. Now budgeted against the front-end output and capped at it (never fan out), with the derivation reordered so both stages settle first. N1 - EventCode/EventPhase/StructuralPhase are signed categoricals packing direction and Wyckoff stage into one scalar across a sign discontinuity. Split into direction + [0,1] magnitude, the same convention the base OHLC block uses. Information-preserving; 13 readings now occupy 16 inputs. Compiled clean (0 errors, 0 warnings); both DLLs rebuilt. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 11:48:03 -04:00
{
fix: training-stability audit fixes F1/F2/F3/F5 - unbiased shuffle, real plateau escapes, fresh optimizer state on restore, pure OOS metric Four of the six findings from research/training_pipeline_audit_2026-08-09.md (F4 mini-batching and F6 feature re-encode deliberately deferred - see the report's implementation-status section for why): - F1: pass-2 Fisher-Yates (and AutoTune's MI block shuffle) used MathRand()%, which is 15-bit - provably non-uniform on every full-history era over 32,768 queued samples. New 30-bit ShuffleRandomIndex(). - F2: plateau warm restarts were a no-op whenever eta already sat at its ceiling (the normal state of a non-regressing plateau) - the ladder was just a 24-era countdown. Restarts now overshoot to 5x the ceiling (PLATEAU_RESTART_BOOST) and anneal geometrically back over the patience window, SGDR-style; ETA_MIN widened 1e-4 -> 1e-5 so the decay schedule has real range. - F3: checkpoint restores put weights back but kept the rejected trajectory's Adam moments, so the optimizer immediately pushed back toward the rolled-back state (the restore->regress->restore oscillation). CNet::ResetOptimizerState() zeroes moments/momentum/step counters (weights, BN statistics, gamma/beta untouched) on every mid-run restore, every boosted restart, and the deploy-time restore that online learning continues from. - F5: batch-norm running statistics now freeze for the pass-3 OOS scoring walk, so the selection metric the checkpoint ranking and deploy gate read is a pure function of the checkpoint instead of partly measuring BN drift. Defensive unfreeze in FinalizeTrainRun covers stop-mid-pass; live/online adaptation and the OOS continual-learning simulation stay adaptive by design. Compiled clean (0 errors, 0 warnings) via the staged-tree recipe. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 10:54:09 -04:00
Net.SetBatchNormFrozen(false);
feat: mini-batch gradient accumulation (F4), front-end-aware capacity budget (F6), split Wyckoff categoricals (N1) Completes the 2026-08-09 training audit. FORCES A RETRAIN of every Wyckoff-enabled config (N1 re-keys the fingerprint), and BOTH DLLs must be redeployed alongside the .ex5 - they carry new exports. F4 - mini-batch accumulation, TRAIN_BATCH_SIZE=32. Training was pure online SGD (one weight update per bar), which is the mechanical source of the era-to-era whipsaw every downstream guard was built to cope with. The O(n^2) outer product is native - AccumulateWeightGrad / AccumulateWeightGradConv / AccumulateBufferInto in Network.cl, WarriorCPU and WarriorDML - while the optimizer step is host-side MQL5 shared by all tiers (ApplyAccumToBlock), so there is one Adam/SGD implementation instead of four that can drift. - the LSTM needs no outer-product kernel (WeightsGradient already holds the sample's full dW) but could NOT simply be left un-zeroed between samples: CPU_LSTMSeqBackward/DML_LSTMSeqBackward memset it on entry. Hence a separate accumulator plus an elementwise add. - batch-norm gamma/beta accumulate in host arrays, not new BatchOptions slots - BN_OPT_STRIDE is baked into every persisted .nnw. - scoped to pass 2; online learning keeps immediate updates. Every save / checkpoint / scoring boundary flushes, scaling by the real sample count. - degrades to per-sample updates (one log line) on a tier that cannot accumulate, so old devices and DLL-free builds are unaffected. - verified offline: DirectML/batch_accum_check.cpp drives the real exports against an independent reference; at B=1 the accumulator matches the shipped unbatched kernel's own gradient to 1.1e-16. Math only - the in-situ check remains the per-layer dW/W report on a real era. F6 - ComputeFirstLayerWidth budgeted against the RAW input width even where a conv/LSTM front end had already reduced it, so an LSTM's dense stack was charged for 1,280 inputs when it receives 64. Confirmed from the deployed .cfg files: CONV, LSTM and HYBRID were all pinned at the 16-unit floor. Now budgeted against the front-end output and capped at it (never fan out), with the derivation reordered so both stages settle first. N1 - EventCode/EventPhase/StructuralPhase are signed categoricals packing direction and Wyckoff stage into one scalar across a sign discontinuity. Split into direction + [0,1] magnitude, the same convention the base OHLC block uses. Information-preserving; 13 readings now occupy 16 inputs. Compiled clean (0 errors, 0 warnings); both DLLs rebuilt. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 11:48:03 -04:00
Net.FlushBatch();
Net.SetBatchSize(1);
}
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
//--- deploy the most stable/best-scoring era's weights rather than whatever the run happened to
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- end on (which may reflect drift after the objective was first hit, or an aborted run).
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
if(m_haveOosCheckpoint)
{
if(Net.RestoreWeights())
{
dOosForecast = m_bestOosForecast;
feat: fitted directional confidence threshold - selectivity gets a mechanism The training loss and the selection metric wanted different things and only the second one knew it. Logit-adjusted cross-entropy has no term for "how often should I trade", so the head calls a direction on 87-91% of bars. The selection metric is precision x coverage credit, saturating at the coverage floor - above the floor extra calls earn NOTHING and only precision counts. So selection wanted few good calls, the loss produced many mediocre ones, and all selection could do was pick the least-bad era out of what it was handed. Nothing pushed the model toward selectivity. This gives the decision RULE the policy instead of distorting the loss (which is estimating class probabilities correctly, and a probability estimate should not be bent to encode a trading policy - Elkan 2001: estimate, then choose the operating point separately). AdjustedSignalFromSoftmax now abstains unless the winning direction's softmax margin over its best rival clears a fitted threshold. Margin, not the winning probability: the latter moves with overall calibration rather than with how close the decision actually was. Fitted on IS, applied to OOS and live. Pass 2 already forward-passes every IS sample, so the margin histogram is harvested there for free (primary occurrences only, so the oversampled replay queue cannot skew the operating point); the fit runs at the end of pass 2, BEFORE pass 3, so the deploy gate grades the thresholded model on bars the threshold never saw. Fitting on pass 3's own predictions would be choosing the operating point on the data being graded - the best-of-N error corrected in five other places here. Objective: maximise IS directional precision subject to still clearing the SAME coverage floor the deploy gate uses (base rate x 0.25, re-derived locally so the two cannot drift apart). Swept top-down in one pass; ties go to the LOWER threshold, since equal precision for less coverage is strictly worse. Under DIR_CONF_MIN_FIT_CALLS (200) it runs unthresholded rather than on a guess. The threshold is part of the MODEL, not the run: captured with Net.CaptureWeights(), restored with the weights at both restore sites, and appended to the .cfg under the same length-guard convention so a deployed model reloads at the operating point its gate actually cleared. A pre-2026-08-09 .cfg reads 0.0, which is exactly the behaviour it was trained under. Per-era line now prints "@margin>=X.XX" next to coverage, so a coverage drop can be attributed to the operating point rather than guessed at. Both build variants compile 0 errors / 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 15:04:37 -04:00
//--- Deploy the checkpoint's operating point alongside its weights - the OOS coverage and
//--- precision this run is about to report were measured with this pair together.
m_dirConfThreshold = m_bestDirConfThreshold;
fix: training-stability audit fixes F1/F2/F3/F5 - unbiased shuffle, real plateau escapes, fresh optimizer state on restore, pure OOS metric Four of the six findings from research/training_pipeline_audit_2026-08-09.md (F4 mini-batching and F6 feature re-encode deliberately deferred - see the report's implementation-status section for why): - F1: pass-2 Fisher-Yates (and AutoTune's MI block shuffle) used MathRand()%, which is 15-bit - provably non-uniform on every full-history era over 32,768 queued samples. New 30-bit ShuffleRandomIndex(). - F2: plateau warm restarts were a no-op whenever eta already sat at its ceiling (the normal state of a non-regressing plateau) - the ladder was just a 24-era countdown. Restarts now overshoot to 5x the ceiling (PLATEAU_RESTART_BOOST) and anneal geometrically back over the patience window, SGDR-style; ETA_MIN widened 1e-4 -> 1e-5 so the decay schedule has real range. - F3: checkpoint restores put weights back but kept the rejected trajectory's Adam moments, so the optimizer immediately pushed back toward the rolled-back state (the restore->regress->restore oscillation). CNet::ResetOptimizerState() zeroes moments/momentum/step counters (weights, BN statistics, gamma/beta untouched) on every mid-run restore, every boosted restart, and the deploy-time restore that online learning continues from. - F5: batch-norm running statistics now freeze for the pass-3 OOS scoring walk, so the selection metric the checkpoint ranking and deploy gate read is a pure function of the checkpoint instead of partly measuring BN drift. Defensive unfreeze in FinalizeTrainRun covers stop-mid-pass; live/online adaptation and the OOS continual-learning simulation stay adaptive by design. Compiled clean (0 errors, 0 warnings) via the staged-tree recipe. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-09 10:54:09 -04:00
//--- Same F3 reset as the mid-run restore: the deployed weights are the checkpoint's, so the
//--- optimizer state that continues from here (online continual learning backprops on this
//--- same net - see OnlineLearnStep) must not be the dead run's momentum.
Net.ResetOptimizerState();
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
RefreshLatestSignal();
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- NOT during shutdown. RestoreWeights() above is an in-MEMORY swap, so the best
//--- checkpoint is already the live net by this line - and OnDeinit's
//--- PersistWeightsOnShutdown() is about to write exactly those weights anyway.
fix(deinit): a full model write was running ahead of the cheap cleanup "Abnormal termination" is back, and this time it is not the arrows. The timing names the culprit exactly: 16:02:31.547 OnDeinit: shutting down 16:02:36.003 Abnormal termination <- 4.46 s, MetaTrader gave up 16:02:36.226 chart signals - persisted <- cleanup finished 0.2 s LATE OnDeinit called StopTraining() BEFORE the chart cleanup. StopTraining() finalises an in-flight run, and FinalizeTrainRun() restores the best checkpoint and then persists it - a full ~1MB model write per signal. So the expensive step ran ahead of the cheap bounded one, which is precisely the inversion the shutdown ordering exists to prevent. The previous fix put PersistWeightsOnShutdown last and missed that StopTraining smuggles a second save in at the front. Two changes: Cleanup now runs FIRST, then StopTraining, then the weight save. The visible teardown is cheap and bounded, so it always completes even when everything after it is killed. And the deploy-persist inside FinalizeTrainRun is suppressed during shutdown. RestoreWeights() is an in-MEMORY swap, so the best checkpoint is already the live net by that line, and PersistWeightsOnShutdown writes exactly those weights moments later. The old path wrote the same model twice per signal - eight full writes across four charts - for no benefit. A user-pressed Stop still persists immediately, because nothing else would. Compiles 0 errors / 0 warnings. Build tag deinit-order-v2. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-01 16:06:40 -04:00
if(!m_shutdownInProgress)
PersistDeployedModel();
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
}
//--- Clean up any legacy on-disk checkpoint from an older (file-based) build so it can't linger.
int checkpointFlags = m_activeFileCommon ? FILE_COMMON : 0;
if(FileIsExist(m_activeFileName + "_ckpt.tmp", checkpointFlags))
FileDelete(m_activeFileName + "_ckpt.tmp", checkpointFlags);
perf(autotune): replace the genetic search with a filter score - hours to seconds MEASURED COST OF THE GA, which is what retired it. Per generation: rung 0: 8 cand x 3 seeds x 3 eras = 72 eras rung 1: 4 cand x 3 seeds x 8 eras = 96 rung 2: 2 cand x 3 seeds x 20 eras = 120 = 288 eras/generation x 4 generations = 1152 eras BEFORE the winner's real training began. Against the observed era times on SP500 H1: PAI 29.1 s/era -> 9.3 h (matches the observed 00:37 -> 09:22) CONV 41.3 s/era -> 13.2 h LSTM 150.4 s/era -> 48.1 h HYBRID 154.6 s/era -> 49.5 h Two days to tune is not a first-run experience, and it is the phase in which the panel goes quiet, which is what made it look like a hang. It also bought nothing. The space is 90 points (10 MA periods x 9 MA types), so 1152 evaluations revisited each point ~13 times; and rungs of 3 and 8 eras cannot separate two MA periods at all. The 2026-08-01 run proves it: every finalist scored 25.0-25.9% balanced accuracy - below the 33.3% one-class floor, i.e. indistinguishable noise - and the search then "deployed the winner" of that. THE ERROR WAS THE SCORING FUNCTION, not its constants. Using a full training run to choose a feature's period is a wrapper method paying wrapper prices for a decision that does not need one. The reference book does not do this: ch. 3.3 selects inputs by measuring each candidate indicator's CORRELATION with the target and dropping the ones with none, with no network involved. So: rank candidates by the MUTUAL INFORMATION between the resulting feature vector and the triple-barrier label. MI rather than correlation because the label is 3-class categorical and the features are not monotonically related to it. Equal-FREQUENCY binning (rank-based), because these features are ATR-normalised and heavy-tailed - fixed-width bins put nearly everything in one bucket and report ~0 information for a genuinely useful feature. Scoring is arithmetic over the feature cache, so it costs seconds and its cost is independent of topology: LSTM now tunes as fast as the MLP. Coordinate sweep, not product sweep - cost is the SUM of per-parameter candidate counts, so enabling every indicator stays affordable - with a second pass that breaks early once nothing moves. Sampling is IS-ONLY. Letting the OOS window influence which indicator settings ship would mean the holdout had been used for selection and had stopped being a holdout. HONEST LIMIT, recorded because it is the price: MI is marginal, so a parameter that only pays off in combination with another can be missed (Guyon & Elisseeff 2003, filter vs wrapper). Given the wrapper it replaces was ranking pure noise at 48 h a run, this is strictly better. Deleted with it: GaRungEras/GaExtract/GaStore/GaMutate/GaRandomCandidate/ GaBlockCrossover/GaSortAliveByScoreDesc/GaBreedNextGeneration, 14 m_ga* members, the GA_*/TUNE_POP_* constants, and ComputeTuneTrialBudget. AND m_evalMode/m_evalEraBudget, because nothing set them any more - 28 read sites all permanently inert. That is not a tidy-up: the `if (!m_evalMode)` guard on UpdateClassPriors is exactly what silently disabled the imbalance correction for entire runs two commits ago. Dead machinery that still reads like live machinery is this codebase's most expensive recurring bug, and leaving 28 more instances of it would have been indefensible. The panel's tuning-progress state goes too - tuning no longer takes long enough to need one. Both builds compile 0 errors / 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-01 10:29:31 -04:00
//--- (dtStudied used to be held back while scoring a throwaway candidate - that marker belongs
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
//--- to the DEPLOYED model's "studied up to" state; a candidate eval must leave it untouched. The
//--- checkpoint block above is already inert in eval mode (m_haveOosCheckpoint stays false).
perf(autotune): replace the genetic search with a filter score - hours to seconds MEASURED COST OF THE GA, which is what retired it. Per generation: rung 0: 8 cand x 3 seeds x 3 eras = 72 eras rung 1: 4 cand x 3 seeds x 8 eras = 96 rung 2: 2 cand x 3 seeds x 20 eras = 120 = 288 eras/generation x 4 generations = 1152 eras BEFORE the winner's real training began. Against the observed era times on SP500 H1: PAI 29.1 s/era -> 9.3 h (matches the observed 00:37 -> 09:22) CONV 41.3 s/era -> 13.2 h LSTM 150.4 s/era -> 48.1 h HYBRID 154.6 s/era -> 49.5 h Two days to tune is not a first-run experience, and it is the phase in which the panel goes quiet, which is what made it look like a hang. It also bought nothing. The space is 90 points (10 MA periods x 9 MA types), so 1152 evaluations revisited each point ~13 times; and rungs of 3 and 8 eras cannot separate two MA periods at all. The 2026-08-01 run proves it: every finalist scored 25.0-25.9% balanced accuracy - below the 33.3% one-class floor, i.e. indistinguishable noise - and the search then "deployed the winner" of that. THE ERROR WAS THE SCORING FUNCTION, not its constants. Using a full training run to choose a feature's period is a wrapper method paying wrapper prices for a decision that does not need one. The reference book does not do this: ch. 3.3 selects inputs by measuring each candidate indicator's CORRELATION with the target and dropping the ones with none, with no network involved. So: rank candidates by the MUTUAL INFORMATION between the resulting feature vector and the triple-barrier label. MI rather than correlation because the label is 3-class categorical and the features are not monotonically related to it. Equal-FREQUENCY binning (rank-based), because these features are ATR-normalised and heavy-tailed - fixed-width bins put nearly everything in one bucket and report ~0 information for a genuinely useful feature. Scoring is arithmetic over the feature cache, so it costs seconds and its cost is independent of topology: LSTM now tunes as fast as the MLP. Coordinate sweep, not product sweep - cost is the SUM of per-parameter candidate counts, so enabling every indicator stays affordable - with a second pass that breaks early once nothing moves. Sampling is IS-ONLY. Letting the OOS window influence which indicator settings ship would mean the holdout had been used for selection and had stopped being a holdout. HONEST LIMIT, recorded because it is the price: MI is marginal, so a parameter that only pays off in combination with another can be missed (Guyon & Elisseeff 2003, filter vs wrapper). Given the wrapper it replaces was ranking pure noise at 48 h a run, this is strictly better. Deleted with it: GaRungEras/GaExtract/GaStore/GaMutate/GaRandomCandidate/ GaBlockCrossover/GaSortAliveByScoreDesc/GaBreedNextGeneration, 14 m_ga* members, the GA_*/TUNE_POP_* constants, and ComputeTuneTrialBudget. AND m_evalMode/m_evalEraBudget, because nothing set them any more - 28 read sites all permanently inert. That is not a tidy-up: the `if (!m_evalMode)` guard on UpdateClassPriors is exactly what silently disabled the imbalance correction for entire runs two commits ago. Dead machinery that still reads like live machinery is this codebase's most expensive recurring bug, and leaving 28 more instances of it would have been indefensible. The panel's tuning-progress state goes too - tuning no longer takes long enough to need one. Both builds compile 0 errors / 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-01 10:29:31 -04:00
if(m_eraCount > 0)
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
dtStudied = m_lastBarTime;
m_trainRunActive = false;
m_eraResumePending = false;
m_haveOosCheckpoint = false;
feat(ensemble): deploy gate on the COMBINED VOTE, with a joint checkpoint The unit of evaluation in ensemble mode becomes the vote, because the vote is what trades (user: "at the end of the day they will vote together during live trading so that would make sense"). Four decisions move from the member to the ensemble: * which era is "best" -> the era whose COMBINED VOTE scored best * what is checkpointed -> a JOINT snapshot: every member's weights at that one era * when the run gives up -> one shared plateau ladder * whether it may deploy -> family-wise gate on the vote WHY THE JOINT CHECKPOINT IS THE POINT: per-member selection picks each net's own best era, and those eras differ. The resulting quartet was never measured together at any instant, so the vote it casts live is a configuration no OOS number ever described. Capturing all four at the era whose vote won makes the deployed ensemble exactly the measured one. Correct because of the era barrier (b77e7b4): Train() runs at most one era per call and a member that finished era N is held until every member reaches N, so when the last member scores the vote no member's weights have advanced past end-of-era-N. That makes the deferred simultaneous capture a guarantee rather than a race. Each snapshot is era-STAMPED and deploy requires every stamp to equal the winning era - otherwise a member whose capture failed would still hold an older snapshot and the deployed quartet would again be one nothing measured. Partial capture rolls the era back out of "best" so the search continues instead of freezing behind a checkpoint that does not exist. Statistics mirror the per-member gate one for one - same coverage floor (MIN_COVERAGE_FRACTION_OF_BASE_RATE), same always-call-one-direction chance reference, same EDGE_MIN_SIGMAS margin, same Sidak correction over the eras ranked (DEPLOY_FAMILY_WISE_ALPHA). Only the population differs: the bars the VOTE fired on, at Min_Vote_Open, rather than the bars one member called. Two-sidedness is required of the vote itself - a vote that never goes short IS the always-long model the chance reference prices in. Members keep their own per-era statistics and their own learning-rate dynamics (regression restore, eta decay); those are per-net training mechanics, not deployment decisions. The shared ladder is mirrored onto each member so per-era log lines report the state that actually governs them. Solo charts are untouched on every path. Verified: full MetaEditor compile, 0 errors 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 19:25:25 -04:00
m_checkpointEra = -1; // the joint-checkpoint era stamp goes with the snapshot it describes
refactor(comments): stdlib comment style across the remaining in-scope files Same pass as 0b06f8e, applied file by file: comment runs of 4+ lines compressed to their leading topic sentences, capped at 4 lines, whole sentences only. Warning sentences (NEVER / MUST / trap / would-have) survive the budget. Every file was checked the same way before committing: the list of non-comment lines is byte-identical to HEAD, and braces balance. No code was touched. Panel/, Enumerations/ and the already-terse System headers needed little or nothing - PooledGate, TradeChecks, BinomialStats and Random came through with no blocks over the threshold at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-22 00:25:52 -04:00
//--- Persist the arrows now drawn on the chart so a deploy/stop survives a later re-
//--- add/recompile without a retrain (durable even if the terminal never gets a clean OnDeinit).
fix(deinit): O(n^2) arrow prune blew the shutdown budget and littered 3 charts Reported as "the perceptron correctly cleaned its chart on deinit, the other 3 did not, abnormal termination". Measured from the 2026-08-01 log, time from "OnDeinit: shutting down" to MetaTrader force-terminating: PAI 3.75 s -> survived, chart cleaned CONV 4.71 s -> Abnormal termination LSTM 4.28 s -> Abnormal termination HYBRID 4.16 s -> Abnormal termination In all four the last line printed is the inference census, which is the end of StopTraining() - so the overrun is inside ShutdownChartCleanup(), i.e. between saving the arrows and purging them. The cost is the prune loop at the end of SaveChartSignals(): for(int i = 0; i < prunedCount; i++) ObjectDelete(0, SIG_ARROW_PREFIX + TimeToString(pruned[i])); ObjectDelete is O(objects) on a crowded chart, so this is O(n^2). It was harmless while the model called a direction on ~6% of bars. After the triple-barrier relabel the models call on 83-94% of bars, the chart carries many thousands of arrows, and the loop overran MetaTrader's OnDeinit budget - so PurgeChart() never ran and the arrows stayed on screen. The slow tidy-up starved the fast one. The work was pure waste at that moment: ShutdownChartCleanup purges every arrow with a single bulk ObjectsDeleteAll immediately afterwards. Deleting them one at a time first has no effect except to prevent the bulk delete from happening at all. SaveChartSignals takes a pruneChartObjects flag, and the two shutdown call sites pass false: - ShutdownChartCleanup passes `preserveChartArrows`, which is exactly right: prune when the arrows are STAYING (chart and sidecar must agree), skip when they are about to be purged wholesale. - FinalizeTrainRun passes !m_trainingStopRequested. Removing a chart MID-ERA reaches StopTraining -> FinalizeTrainRun, which took the expensive path a second time, even earlier, before anything had been cleared. Same defect one call site up; it only escaped notice because the observed removals happened to land between eras. Normal convergence and the live per-era path are unchanged - they still prune, which is what keeps the chart object count bounded. This also restores the invariant the 2026-07 fix intended ("chart cleanup runs BEFORE the heavy weight save so a stall cannot leave the chart littered"). That fix moved cleanup ahead of the WEIGHT save, but cleanup had since grown its own slow step ahead of its own fast one. Both builds compile 0 errors / 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-01 10:38:36 -04:00
SaveChartSignals(!m_trainingStopRequested);
refactor: split CExpertSignalAIBase implementation by responsibility ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:42:45 -04:00
}
#endif // WARRIOR_AIBASE_TRAINING_MQH
Copy permalink