- Replaced standard library signal modules with custom implementations to allow for named patterns and improved voting.
- Added new input parameters for module weights, allowing for optimization of individual signal contributions.
- Enhanced the management of trades with new options for breakeven and management cut.
- Introduced a mechanism for dynamic ranking of signal weights based on historical performance.
- Improved initialization logic to ensure proper registration of filters and handling of trading conditions.
- Added detailed logging for trading permissions and account status during initialization.
Everything from tonight, committed so the restructure that follows is
recoverable: the graded stdlib vote, the Wyckoff modules and feed, the
ALGLIB serializer workaround, the restored DB queue, and the Simple/
prototype that is about to be folded into the real filetree.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Operator: "commission is automatically charged on mt5 during backtest, so
make sure to not include anything related to commissions in the EA. have as
little inputs variables as possible for a clean menu."
COMMISSION. Expert\CostModel.mqh deleted, the six Cost_Comm* inputs with
it, along with the per-bar spread sampler in OnTick and the init COST MODEL
printout. This removes a DUPLICATE, not the cost: MetaTrader applies the
broker's own schedule to every deal in the tester and on the account, so a
hand-typed second copy inside the EA could only ever disagree with it - and
a schedule that drifts from the broker's is worse than none, because it
looks authoritative. Nothing consumed the numbers any more in any case; the
gate that read them went with the era verdict.
Only the asset-class detector survived, moved to Expert\AssetClass.mqh. It
answers a question MT5 does not: which book applies.
THE ROSTER IS ONE INPUT NOW. Fourteen per-setup constants stood in
ClassicSignals.mqh, all false, none reachable without a recompile. They are
replaced by Book_Roster, chosen a BOOK at a time - which is the only
grouping that respects the accountability rule (one book per asset class, a
setup is only accountable on the class its own book covers) and the only
one the agreement count can use, since a roster of one cannot express it.
AUTO reads the class off the instrument. Eight tester values instead of
16,384 mostly meaningless combinations.
INPUTS 63 -> 22 (17 parameters and 5 section headers). Cut or made const:
everything dead after the training deletion, the two API keys (a credential
is not a strategy parameter and must not travel in a .set), and knobs that
cannot change an outcome - Signal_ThresholdOpen above all, since Direction()
now returns exactly 0 or +/-100, so every threshold in (0,100] behaves
identically.
TWO OF THOSE ARE FIXES, NOT TIDYING.
- The 30-bar signal cooldown was still live. Its floor came from the
leg-ride label ("a trade is held 5 + the median ZigZag leg = 18-19 bars").
That label is deleted, and the thing being spaced now is a book setup that
owns its trade end to end. Worse, it would have silently thinned the very
population the agreement count counts. Off, and const.
- Signal_MinAgreement defaults to 2 rather than 1. One trigger alone is the
policy measured NEGATIVE on every asset class.
The session filter is const off for the same class of reason: every setup
carries its own window from its own book, and a global one layered on top
applies one book's clock to another book's market.
SweepGuard's table was rebuilt - it was almost entirely names from the
deleted training layer. It now refuses Asset_Class (a statement about the
instrument, not a strategy choice) and pins the log-volume switches.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
THREE NEW OPTIMIZERS, APPENDED TO ENUM_OPTIMIZATION (never inserted - the ordinal is written into
every .nnw and hashed into the weights filename, so renumbering would silently reinterpret every
saved model). SGD=0 and ADAM=1 keep their values.
WHAT EACH ACTUALLY COSTS, because two of the three are nearly free and it is worth saying why:
RMSPROP = the EXISTING Adam kernel with beta1 = 0. With no first moment mt collapses to the raw
gradient and the step becomes lr*g/sqrt(v), which is RMSprop exactly. Not one kernel
was added in any backend - it is a scalar, not an algorithm. The bias correction had
to move into WarriorOptLearnRate() because the literal (1 - pow(beta1,t)) denominator
is (1 - 0^t) = 1 for t>=1 but ZERO at t==0, a division by zero on an unadvanced
counter.
NESTEROV = the momentum kernels' `optimizer` argument, which had been retained-but-unused since
the DFA entry was deleted, finally selects something. Heavy-ball applies the velocity;
Nesterov applies lr*g + mu*v_new (the Bengio/PyTorch reformulation, which expresses NAG
without evaluating the gradient at a shifted point). No new state, no signature change
on three of the four momentum entry points.
AMSGRAD = the only one needing extra state: a non-decreasing denominator needs the running max of
the second moment (Reddi et al. 2018 - Adam can fail to converge because a rare large
gradient inflates v and then DECAYS away, so the effective step GROWS again just after
the event that should have shrunk it).
IT REUSES DeltaWeights AS THE v-MAX. The Adam family already frees that buffer, it is
the same element count, already zeroed by ZeroOptimizerBuffer, already saved and
loaded. Net memory versus SGD: zero. That mattered: an extra per-tensor allocation is
exactly what took this machine down twelve hours ago.
FOUR TIERS, IN LOCKSTEP, WHICH IS THIS FILE'S OWN STANDING RULE:
* MQL5 host (NeuronCPU.mqh): all three, with CConnection gaining a vMax field (persisted
unconditionally - CConnection cannot know which optimizer owns it, and a conditional would make
the record length depend on state the reader does not have yet).
* CPU DLL (WarriorCPU.cpp + .h): Nesterov in all four momentum kernels; a nullable vm pointer in
all four Adam kernels (vmHandle < 0 leaves it null, so every non-amsgrad caller is
byte-identical to before). Rebuilt and deployed.
* MQL5 host FALLBACK inside ApplyAccumToBlock: the same amsgrad branch. This is the path the DLL
drops to when the element-wise apply fails, and a model that trained differently depending on
whether the DLL was healthy would be unreproducible.
* OpenCL (Network.cl): Nesterov via the same `optimizer` argument; matrix_vm + an amsgrad flag on
all four Adam kernels, bound to a harmless dummy buffer when off so there is still ONE kernel
per operation, matching the DLL's shape rather than forking a second set.
THE OPENCL TIER IS UNVERIFIED AND SAYS SO AT RUNTIME. This machine has no OpenCL device ("cannot get
OpenCL platforms / opencl.dll not found"), so the CPU-DLL tier is what actually executed these. The
kernels are written and wired; they have never run. A throttled line names that on first use rather
than implying a parity that was never tested.
THE BINDINGS THAT WOULD HAVE BROKEN SILENTLY, and why the predicates exist:
`optimization == SGD` and `== ADAM` appeared at 34 sites and meant three different questions - which
buffers to allocate, which to persist, and which step to take. An unlisted optimizer would have
taken the ADAM branch for its buffers and the SGD branch for its persistence. They are now
WarriorOptUsesMoments / WarriorOptUsesDelta / WarriorOptIsMomentumStep, and the allocation and
persistence sites ask TWO INDEPENDENT questions instead of one if/else, because AMSGRAD is the first
optimizer that needs both families.
ASSIGNED PER ARCHITECTURE, so the ensemble's members now differ in their optimizer as well as their
shape - four members that fail in correlated ways average to nothing, and member correlation
(printed every era, r 0.19-0.36) is the measurement that says whether this bought diversity:
Perceptron/MLP -> NESTEROV (no structural prior, so a non-adaptive step is the implicit
regulariser that makes it the conservative ANCHOR vote; the lookahead
damps heavy-ball's overshoot at zero extra state)
Conv -> ADAM (unchanged - AdamW already)
LSTM -> AMSGRAD (the most heavy-tailed gradients here: shared weights across timesteps
mean one bad window contributes a burst of correlated updates, which
is the regime AMSGrad was derived for)
ConvLSTM -> RMSPROP (two very differently-scaled gradient sources; per-weight
normalisation without a first moment stops the conv stage's momentum
dragging the recurrent one)
VERIFIED IN SITU, not by compiling: 5 charts, 18 eras, zero UpdateWeights failures, zero fallback
warnings, one fingerprint per architecture (PAI-0bd8 / CONV-5327 / LSTM-44d1 / HYB-452a). Commit
3,975 MB against 29,982 MB headroom.
COST: every model re-keys and retrains, the optimizer being a field of the weights filename.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The leg-ride target's SIDE is the direction of the ZigZag leg in progress as
of that bar, readable from bars t and older with no lookahead. The 3-class
head made the network re-derive it anyway: that is Lopez de Prado's PRIMARY
MODEL being learned instead of used, and it cost on four axes at once -
chance at 33% instead of 50%, an 8:1 imbalance instead of 3:1 against a tau
already pinned at its cap, every Buy row spent as evidence about "is this a
long leg" rather than about payoff, and a directional error scored the same
as a payoff error though only one of them was a question we asked.
The head is now binary: slot 0 "riding this leg to the flip pays at least
LEG_LABEL_MIN_RIDE_ATR", slot 1 "it does not". The side comes from
LegDirAsOf() at read time.
TWO OUTPUT NEURONS, NOT ONE, and that is what made this small. Both backward
passes in AI\Impl\NetForward.mqh already carry a `total == 2` softmax+CE arm,
left in deliberately when the old meta head was removed on 2026-08-25 - and a
2-class softmax IS a logistic/BCE head, the logit difference being the
log-odds. So this reuses the exact gradient path the 3-class head uses instead
of growing a second one.
NOTHING DOWNSTREAM CHANGED. ApplyClassificationSoftmax() expands (pGo, side)
back into the [pBuy, pSell, pNeutral] triple every reader already consumes, so
Argmax3, the operating-point histogram, per-class recall, confidence tiers,
the vote currency and the chart arrows are untouched. Neutral stops being a
class the net competes for and becomes what it always meant: pGo below the
operating point. The margin the threshold is expressed in becomes 2*pGo-1,
monotone in pGo, so the calibration walk fits the same statistic.
THE HEAD STAYS BOUNDED, deliberately, and the 2026-07-27 unbinding retry is
NOT bundled here. Reading the gradient showed why it need not be: the softmax
arm OVERWRITES the output neuron's gradient with (target - softmax), so the
sigmoid derivative and MIN_ACTIVATION_DERIVATIVE are already bypassed at the
head. What SIGMOID x CLASS_LOGIT_SCALE actually costs is p in [0.0025,0.9975]
- three orders of magnitude wider than the band where the live question is
0.35 versus 0.60. Unbinding has its own failure history and deserves its own
measurement; batch norm before the head, its precondition, already ships.
THE ZERO-SKILL FLOOR HAD TO MOVE WITH IT. The rate gate's chance was the
better of always-Buy and always-Sell. This head cannot choose a side, so its
no-skill policy is ALWAYS-RIDE - every bar taken in its own leg's direction -
which is right on EVERY directional-label bar, not the better half. Left
alone it would have handed a model with no skill whatsoever a ~+11pp edge.
The book gate already measured against always-ride; the rate gate now agrees
with it about what zero skill means. Same correction in the module-weight
shrinkage prior (Lifecycle.mqh's 50.0 side coin-flip).
RETRAIN-FORCING twice over: |MHEAD:1 joins the fingerprint and the output
count is field 6 of the .nnw filename, so no existing model or pool row can
be adopted. Verified live - all six charts rejected every peer file by
fingerprint and restarted from era 0.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
PHASE 1 of doing the trade-management search inside the EA instead of in the
MT5 optimizer, for the one pair that cannot wait: the stop and the target.
WHY NOT ALGLIB. The space is discrete - 8 stop widths x 8 target widths = 64
cells. At that size you do not search, you ENUMERATE. Exhaustive has no seed,
no convergence question and no tuning of its own, and it answers the thing a
search cannot: whether the good region is a broad plateau or one lucky cell.
WHERE IT RUNS. Inside the era report's existing OOS threshold sweep - same
held-out rows, same purge, same certified rung the deploy gate uses. No tester,
no agents, no .set.
ORDERING IS THE WHOLE POINT. MFE and MAE cannot say which barrier a trade hit
FIRST, and "both were touched" is the common case, so a grid evaluated from the
extremes alone would be guesswork dressed as measurement. MeasureBarPayoff()
already walks the forward window bar by bar; it now records the first-touch bar
offset for each grid level in each direction. One compare per level per bar on
a loop that already runs. The sweep then costs 64 integer compares per fired
row and reads no prices at all.
Same-bar ties resolve to the STOP. Bar data cannot order two touches inside one
bar, and assuming the target would be the optimistic half of an unknowable coin
flip, on exactly the half that flatters the result.
JUDGED AGAINST THE NULL OF THE MAXIMUM, NOT ZERO. Picking the best of 64 cells
and reporting its own z is the best-of-N error this project has already made
four times, including on the deploy decision. SidakFamilyP over the cells
actually scored is the same correction the rung sweep and the baseline
comparator use. A cell needs BARRIER_MIN_CALLS before it may win at all - a
thin cell tops the grid on noise alone. The pair is STORED either way: a reader
must be able to tell "swept and rejected" from "never swept", so the p travels
with the pair (WSTA in .stats) and gates its use at read time, not its record.
SL_Mode and TP_Mode inputs are REMOVED, and STOP_LOSS_MODE/TAKE_PROFIT_MODE
with them - deleted rather than left dangling, per the RISK_REWARD_RATIO rule:
a live enum with no input behind it is the shape of the 2026-07 incident where
a saved .set kept feeding a deleted ordinal back in. With the inputs gone there
is no ordinal left to feed, and ValidateTradeManagementInputs() loses two
members.
Three tiers at read time, most trusted first: the swept pair when it cleared
its own family-wise test; else the mean excursions (cruder, but nothing was
SELECTED to produce them, so they need no such test); else a fixed fallback
that announces itself and is unreachable on a deployed chart, since a chart
with no completed era cannot pass the deploy gate.
Entry offset, expiration, trailing and the exit-vote flag stay inputs for the
MT5 GA - they need entry-fill and path-stepping simulation this phase does not
have.
Compiled 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Two changes, both driven by the same single-backtest profile (6,607,688 ticks,
165 s, SP500 H4 2019-2026).
INDICATORS, 39% OF THE PASS. m_indicators.Refresh() cost 61.4 s at 9.30 us per
tick, running on every quote regardless of Expert_EveryTick. Every indicator
this EA registers is computed from CLOSED bars - ATR, the MA, the ZigZag, the
feature block - so their value cannot change between two ticks of the same bar
and the refresh was recomputing a constant. It is now gated on a new bar, with
its own CNewBar watermark: IsNewBar() consumes the transition and Refresh()
runs before Processing(), so sharing m_newBar would have silently disabled the
SetDirection gate.
The exit invariant holds. What changes intrabar is price and position, and
neither comes from an indicator buffer: m_symbol.RefreshRates() still runs on
every tick and is what CheckClose/CheckTrailingStop/pending maintenance read. A
trailing stop still moves on any tick; it now compares the live price against
an ATR from the last closed bar, which is the ATR it should have been using.
ProtectOpenPosition() keeps its ungated copy - it runs only on ticks Refresh()
declined, and never appeared in the profile.
SL_MEASURED / TP_MEASURED (both value 100), now the shipped defaults. The fixed
pair was SL x2 / TP x6 against a measured SP500 MFE of 2.59 ATR and MAE of
2.71: the stop sat INSIDE the average adverse move and the target BEYOND the
average favourable one, so the average trade was stopped out before reaching a
target it does not reach. That converts winners into losers mechanically at any
precision, and no model work can fix a barrier pair pointing the wrong way.
These are NOT the removed SL_INTELLIGENT/TP_INTELLIGENT. Those scaled the
barriers by the model's own CONFIDENCE - an over-confident model gave itself a
tighter stop and a wider target, which is why they were deleted. These read a
MEASUREMENT of what the market did on the bars this ensemble fired on: the mean
adverse and favourable excursions in ATR at the hold horizon, already computed
by the era report that certifies the deploy and previously printed and thrown
away. Only the WIDTH is measured; the reward:risk that falls out is reported,
never targeted - the ratio is policy, the width is what pays.
A FRESH ENUM VALUE, never the vacated -1 the removed members held: MetaTrader
does not validate enum inputs, so a .set saved by that build still feeds -1 in,
and reusing it would silently give a stale file a new meaning.
ValidateTradeManagementInputs() keeps rejecting -1 and now accepts 100.
Plumbing follows the derived-threshold route exactly, because
ExpertSignalCustom.mqh is the PARENT of the filter that owns g_ensBest* and
cannot read them: stashed inside the isBetter block (so the widths describe the
bars the CHECKPOINT fired on, never a later era's), persisted as WST9 in
.stats (a deployed ensemble runs no further eras - the tier-ladder failure one
layer along), and published per tick via PublishMeasuredBarriers(). The -1/-1
"not measured" state is published too, so a reset-weights cannot leave a stop
sized off a dead ensemble.
With no measurement it falls back to the shipped fixed presets and says so once
per run. It deliberately does not substitute a plausible number: an invented
width would be indistinguishable from a measured one in every log afterwards.
Compiled 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The declustering the charts needed already existed - NmsLiveAccept, per-direction
run-collapse plus cross-direction resolution plus strict alternation - and it was
already set to 10 bars. It could not be TUNED: SignalClusterWindow was a compile-
time const, so finding the right value needed a rebuild. That is the actual gap.
Now three inputs, as enum dropdowns:
Signal_CooldownScope per-direction, or a hard any-direction gate on top
Signal_CooldownBars SCB_OFF..SCB_50, default 10
Signal_CooldownMinutes SCM_OFF..SCM_1440, overrides bars when set
Minutes resolve against the CHART period and round UP, so a cooldown asked for in
wall-clock is never silently shorter than requested and survives a timeframe
change.
SCB_/SCM_ prefixes are deliberately unique. M15/M30/M60 are ALREADY members of
NF_LOOKBACK_PRESETS, and MQL5 binds a duplicated enum member to the first-declared
enum silently - the obvious names would have compiled straight into the news
filter's values.
THE ANY-DIRECTION GATE IS ADDITIVE, NOT A REPLACEMENT, and the first cut of this
had it backwards. Measured on the live log: the current rules draw 222 arrows over
4999 bars, while a BARE 10-bar cooldown permits up to 454 - because ALTERNATION is
what declutters today, not the window. Swapping the rules out would have roughly
doubled the clutter it was asked to remove. Layered, it can only ever suppress
more. Suppressed bars still advance the per-direction last-SEEN cursors, so a run
straddling the boundary does not restart as if it were fresh.
Applied at all THREE sites that must agree - live inference, OOS pass-3 scoring
and the chart renderer. Their own comments say why: an arrow set that does not
obey the same rule as the traded set shows calls the EA would never take.
Also corrects a stale comment that called this window "display only". It is not:
when it suppresses, the live path zeroes the signal outright - no arrow, no vote,
no position. Training never sees it, so these cost no retrain and are correctly
absent from the fingerprint.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Allow_Hedging (default ON, live only on a RETAIL_HEDGING account) gives the EA
an independent long book and short book on its symbol: at most one long and at
most one short, each opened on its own side's vote and each held to its own
barrier. On a netting account, or with the input off, the original
single-position path runs bit-for-bit unchanged and init says which one is live.
WHY THIS INSTEAD OF A VOTE EXIT. The deploy gate certifies
P(label agrees | vote fired) and the label runs to the barrier, so closing early
on a reversal makes the realised outcome stop being the labelled one - the
certified precision no longer describes what is traded. Opening the other side
acts on the new signal and leaves the old position's certification intact, and
costs no more than reversing: both pay the new side's spread, the difference is
only that the existing position runs on to a barrier already measured as
positive-expectancy. So Signal_ThresholdClose is DELETED rather than tuned,
along with its SIGNAL_CLOSE_PRESETS enum; the threshold is pinned to an
arithmetically unreachable 101 (the stock default of 100 is reachable by a
weighted mean of values capped at 100).
Note the two books can never both fill from one signal: CheckOpenLong and
CheckOpenShort test opposite signs of the same m_direction, so at most one clears
per tick. A hedge only forms when a LATER opposite vote fires - which is what
keeps it from being a guaranteed-loss wash pair.
The mechanism is a SelectPosition() override keyed on the active book's magic;
every inherited close/trail path then operates on that book untouched. The long
book keeps Expert_MagicNumber, so no existing position, journal row or
risk-budget state file is re-addressed. Short book is +1.
Four ownership filters had to widen from "== m_magic" to WarriorOwnsMagic(),
or the short book would have been invisible to the code that must reach it:
the scheduled close-all (positions and orders), the risk budget's emergency
flatten, and the journal's MAE/MFE walk. WarriorOwnsMagic() is deliberately NOT
gated on Allow_Hedging - turning the input off while a short-book position is
open would otherwise orphan it with nothing left to close it.
Risk sizing needed no change: CapRiskAmount already subtracts OpenRiskAtStops(),
which counts every position regardless of magic, so the second book is sized
inside what the first one left. Conservative for a hedged pair, which cannot
lose both stops - the safe direction.
Retrain-neutral: neither input is in BuildModelFingerprint() or
ComputeDbConfigFingerprint(). Compiled clean; NOT yet run.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Five modes went, all of them staking real risk on the model's confidence:
Intelligent entry (ENTRY_INTELLIGENT), stop (SL_INTELLIGENT), target
(TP_INTELLIGENT), trailing (CTrailingIntelligent) and lot size
(CMoneyIntelligent's quarter-Kelly). With them, the Confidence_Source
input and the CONFIDENCE_SOURCE enum, whose only job was choosing which
number those five read.
The reason is calibration, not correctness: the confidence magnitude is
known to be miscalibrated against the label prior, so every one of these
modes multiplied money by a quantity whose units were never established.
The DB arm had a second, independent defect - since the tester DB guard
(SignalDatabaseActive) it reads 0 in tester and optimizer but non-zero
live, so any backtest of CONF_DB/CONF_BLENDED could not reproduce live
trading. And what the DB produces is a filter-RANKING win rate, not a
per-trade win probability.
Both confidence numbers are still recorded per trade (aiConfidence /
dbConfidence) and still bucketed against outcome in TradeJournalReport.
Recording is what keeps the question answerable; acting on it was the
part with no evidence behind it. ConfidenceBridge.mqh now carries an
explicit telemetry-only rule at the top.
ENUM ORDINALS PINNED. Removing a member vacated a value in four enums at
once and MT5 does not validate an enum input replayed from a saved .set
or a stored optimization pass. TRAILING_STRATEGY and
MONEY_MANAGEMENT_STRATEGY now carry explicit values so the survivors keep
the numbers they were saved as, and ValidateBarrierInputs is widened into
ValidateTradeManagementInputs covering SL_Mode, TP_Mode,
Entry_Multiplier, TrailingStrategy and MM_STRATEGY. Without that gate a
chart saved with the Intelligent stop would feed SL_Mode = -1 into a
multiplier now used verbatim, placing the stop on the wrong side of entry.
RETRAIN-NEUTRAL: neither SL_Mode nor TP_Mode appears in
BuildModelFingerprint() or ComputeDbConfigFingerprint() since the
swing-pivot target replaced the barrier labels. No .nnw, .cfg or .db
re-keys. Also drops the now-dead g_TradeRewardRiskRatio bridge, the
CMoneyRiskBase::AdjustRiskAmount hook and the unsigned AIConfidence().
Compile-verified in _claude_stage: 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
~2,300 lines. META had real, repeatedly measured ranking skill and ZERO
operating points that ever cleared break-even (0/350 H1 eras, 1/999 H4
pre-2-sigma, 0/8 pooled fitted points). The clinching arithmetic was edge x
width = 0.095 ATR/trade against spread 0.099 ATR/trade, and the
dose-response showed the high-conviction tail is temporally unstable -
the precision-vs-threshold slope flips sign between calib and test on 3 of
4 symbols, so no ex-ante threshold rule exists. It shipped default-off and
never gated a live entry. The self-measured tier weights are what actually
rank the vote, and all six H4 instruments converged on them alone.
RETRAIN-NEUTRAL, and that is the property that made this safe:
- The weights fingerprint emitted "|TGT:META2" or "|TGT:SWG1" from an
if/else. Every direction model already took the SWG1 arm, so
collapsing it to an unconditional append is byte-identical. No .nnw or
.cfg is orphaned or re-keyed.
- NetInputWidth() lost its "+ MetaDescWidth()" term. MetaDescWidth()
returned 0 for every direction model, so the input layer is unchanged.
- DbLegacyAiSlot()'s slot 5 was reachable only with all four Use_* NNs
off AND meta on - a config that never shipped. Every existing .db keeps
its filename.
Deleted outright: Signals/SignalMETA.mqh, Expert/Trading/MetaGate.mqh (the
directory is now empty), Expert/Training/{MetaCorpus,MetaCandidateStore,
MetaFamilies}.mqh, Tests/Test_MetaFamilies.mq5, Meta_Labeling_Design.md.
Unwound in place, the delicate part: Training.mqh carried four
IsMetaTarget() branches whose else-arm WRAPPED the direction body (pass 1
queueing, pass 2 backprop, pass 2.5 calibration, pass 3 OOS scoring). Each
wrapper is removed and the direction body promoted back to its original
nesting - the bodies were never re-indented when the wrappers were added,
so the promoted code is byte-identical to what ran before META existed.
Also gone: the ensemble verdict's meta-veto replay and its
approved/vetoed/unscored counters, the per-family/per-side OOS
decomposition arrays, the m_isTrainQueueCand parallel queue and its
lockstep shuffle, and the S2 era report.
Also removed: the CMetaGate abstraction and the live CheckOpenPosition
veto; m_gates plus AddFilter's non-voter routing and IsVotingSignal()
(META was the only non-voting child, so m_gates was always empty);
m_parentSignal/SetParentSignal (existed only to reach the root's gate);
SweepPrepare/SweepPrepareIndicator (only caller was the corpus sweep);
IsMetaTarget() from all four view interfaces and their adapters;
Use_MetaLabeling, EnableMETA, Meta_ExportDataset, m_trainTarget.
EvalShift is KEPT - HistoricalNetVote() uses it for the filtered overlay,
not just the corpus sweep; only its comment changed. The 2-output softmax
arm in NetForward.mqh is kept too: it costs nothing and is the reusable
binary-head path, now commented as unclaimed rather than as META's.
Compile-verified in _claude_stage: 0 errors, 0 warnings, matching the
pre-edit baseline.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Step 3 of the swing-pivot plan, whole-hog. The swing label is now the ONE
target and the era verdict is precision + recall per class against the
label's own base rate - no win rate, no break-even, no expectancy, no
geometry anywhere in training.
DELETED
- Expert/Excursion/ (4), Expert/BarrierHorizon/ (4), GeometrySweep,
FirstPassageLadder, Labeling/TripleBarrier.mqh (CLabelOverlap survives
in Labeling/LabelOverlap.mqh), 3 test EAs.
- TripleBarrierLabel + walk, fractal label, geometry derivation/scan/
adoption, exit-policy replay, excursion MI targets, the drift verdict
(DIRECTION_INTELLIGENT), the recall floor, balanced-accuracy telemetry,
the barrier defines, the .cfg geometry adopt (slots kept as zeros for
the positional layout), the derived-geometry live-order override.
- TRAINING_TARGET input/enum: direction models are always swing; META2
re-keys the meta head onto label agreement (descriptor loses its two
geometry slots).
REWORKED
- Labels.mqh (1795 -> ~370 lines): AdvanceSwingLabelState with
FINALITY-GATED CACHING - an unresolved bar (pivot pair uncommitted) is
never cached, so it can never freeze as a false Neutral; training,
calibration, OOS scoring and online learning all skip unresolved bars.
- SDeployVerdict: significance-only; SOosTally chance = larger
directional class share; pooled gate poolability = timeframe (record v2).
- Purge/embargo/declustering gaps: the measured mean label resolution
lag (LabelResolutionBars), not a barrier horizon.
- Pool purge key + backfill DB rows: marked at the bar the label
resolved on (m_labelResolveAge), not a fabricated barrier touch.
- Online learning frontier: finality, not a horizon delay.
- m_bestBalancedOos -> m_bestSelectionScore, m_erasSinceBestBalanced ->
m_erasSinceBest, ensemble vote outcome arrays -> label arrays.
STEP 4 folded in: Entry_Multiplier / SL_Mode / TP_Mode / tradingdirection
are inputs again - trade management is the tester GA's search space.
Fingerprints: every direction model re-keys (TGT:SWG1 now unconditional,
CUT token gone); META1 -> META2. Full retrain, as planned.
Compile-verified in _claude_stage: Warrior_EA + both surviving test EAs,
0 errors, 0 warnings each.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- TrainingTarget defaults to TARGET_SWING.
- LogitAdjustTau input, preset enum and all plumbing deleted: tau is fixed
at 1.0 (the full log-prior, Menon et al.'s consistent value); the
delivered strength is capped to the head's usable logit range from the
priors the prebuild measures. The CAPPED journal line is the step-1
measurement. |LA💯BS becomes a frozen legacy fingerprint slot, so no
existing model re-keys.
- The swing label measures its own resolution lag (idx - P2, the earliest
bar P1 can be final on) into the overlap/SE machinery, capped at
SWING_SCAN_CAP_BARS instead of a barrier horizon it does not have.
- The prebuild line is target-aware: both-won, timeout and horizon-lifespan
fragments are barrier-walk facts and no longer decorate swing counts.
Compile-verified in _claude_stage: 0 errors, 0 warnings.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
TARGET_SWING: the direction models learn which way the next CONFIRMED SWING
PIVOT lies from the current close. Geometry-free - the label owes nothing to a
stop, target or horizon - which is what lets trade management be tuned
separately instead of being baked into what the net learns.
SwingPivotDirectionLabel reuses the ZigZag pivot the horizon and leg-size
measurement already walk, so there is ONE notion of "pivot" in the codebase. It
walks forward in time and stops at m_swingConfirmationBars: a pivot nearer than
that is still repainting, so its label is not knowable yet and the bar stays
Neutral. That boundary is the whole lookahead control for this target.
TrainingTarget input is back (TARGET_BARRIER default, unchanged behaviour) with
TARGET_FRACTAL and TARGET_SWING beside it; |TGT:SWG1 joins the fingerprint so
switching trains a separate model rather than relabelling an existing one.
ADZigZag was renamed to ZigZag throughout (30 identifiers). It has loaded
MetaTrader's stock Examples\ZigZag at its stock defaults for some time - the
migration was done, only the name was left behind, and a name that says "AD"
about a stock indicator is exactly the legacy pointer this codebase should not
carry. No behaviour change: same #resource, same params.
Compile-verified in the staging copy: 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
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>
Two UX changes the operator asked for.
THRESHOLDS. Signal_ThresholdOpen/Close were raw ints with the legal range
written in the label ("[0...100, 101 = never]") - the one input style this
codebase converted away from everywhere else. Open now takes the existing
PERCENTAGE_PRESETS, whose comment already declared itself to be "Signal_
ThresholdOpen's scale" but was never wired to it; Close takes a new
SIGNAL_CLOSE_PRESETS carrying the same rungs plus CLOSE_DISABLED = 101, which
is why it cannot just reuse the other enum. Member names are prefixed because
MQL5 enum members share ONE flat namespace - a bare PCT_25 in the second enum
would silently resolve to the first one's, warning only. Values are unchanged,
so existing .set files keep their settings. Both call sites now cast
explicitly at the CExpertSignal boundary rather than leaning on an implicit
enum-to-int conversion that only warns.
ARROWS. 2026-08-19 replaced the low/high arrows WITH trigger-price lines; that
was a swap where it should have been an addition, and it cost the zoomed-out
view. A mark is now both objects: the line is the precise entry/exit level,
the arrow off the candle's extreme is the finder that says there is something
here to zoom into. The arrow's name is the line's plus a suffix, so it stays
inside SIG_ARROW_PREFIX and every prefix-scoped purge already reaches it.
The two type-filtered sweeps had to widen or they would clear one half and
leave the other: the Hide/Show visibility loop and the pre-rescan scoped
delete both walked OBJ_TREND only. Both are typed-blind and prefix-scoped now
- the same widening this file's 2026-08-09 note describes, for the same reason
it gives. Deletes go through one WarriorDeleteSignalMark() so an arrow cannot
outlive the line it belongs to, and the sidecar deliberately still records one
row per mark off the line (the half carrying the price), with the restore
redrawing the pair.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The control panel drove training by looping g_aiSignals[] - a
hand-maintained, MAX_AI_SIGNALS-capped, AI-only registry that had
already dropped an ensemble member on the floor once (609be10). A model
missing from it still trains and still votes, it just cannot be paused,
stopped, deployed or reset, and every button label is computed from the
same short list, so the panel described one set of models while acting
on another. Classic signals could not respond to a panel action at all.
Commands now walk the signal tree CExpert already owns:
Expert.DispatchSignalCommand(cmd) -> root signal -> every filter,
recursively, returning how many actually acted.
CExpertSignalCustom carries the seam (OnSignalCommand / HasSignalTrait,
both no-ops by default), so a classic signal opts in by overriding two
methods and needs no registration and no cap. CExpertSignalAIBase
implements the training commands over its existing Pause/Stop/Deploy/
Reset methods - the behaviour is unchanged, only its reach reported.
Button labels ask the same tree via CountSignalTrait, with
SIGTRAIT_TRAINABLE as an explicit denominator: "all paused" is
meaningless without knowing how many could be paused. Pause/Stop resolve
their toggle direction ONCE in the EA and hand every model the same
plain command, instead of each re-deriving the direction from its own
local state - which is how a mixed set ends up half paused. The alerts
now report the count acted on rather than assuming it.
Two dispatch bugs found on the way, both from a database guard copied
onto event delivery: CExpertSignalCustom::OnTickHandler and
::OnChartEventHandler each skipped any filter whose GetFilterID() is
"NULL". That id is a DB folder name, and CSignalNewsFilter,
CSignalSessionFilter and CSignalRiskGuard never set one - so all three
were silently receiving neither ticks nor chart events. The guard stays
where it belongs, on the paths that write pattern tables.
ENUM_CP_ACTION moves to Enumerations\GlobalEnums.mqh (now include-
guarded) because the Expert bases have to name it and the panel is
included long after them.
The AI-only lifecycle loops - PollTraining, the weight autosave,
AltDataReload, OnDeinit's shutdown cascade - still use g_aiSignals[] and
are untouched here.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The MECHANISM was already stdlib and is untouched: ThresholdOpen() ->
m_threshold_open, tested as `m_direction >= m_threshold_open` exactly as
CExpertSignal does it. What was wrong was the presentation. Both inputs
were preset ENUMS labelled "Min confidence to open/close (%)", which
names the wrong quantity - m_direction is a WEIGHTED MEAN OF PATTERN
WEIGHTS, not a probability, and nothing in this path is a confidence.
They are now plain ints named the way the MQL5 wizard names them:
input int Signal_ThresholdOpen = 25; // [0...100]
input int Signal_ThresholdClose = 101; // [0...100, 101 = never]
Values are exactly what shipped, so behaviour is unchanged. 101 rather
than the library's default of 100 for close: a weighted mean of pattern
weights cannot REACH 101, which is how the shipped config disables the
vote exit, and quietly lowering it to 100 would re-arm a live exit route
as a side effect of a naming change.
VOTE_CLOSE_PRESETS is deleted (its only user is gone). PERCENTAGE_PRESETS
stays - MinRecall genuinely is a percentage.
** ACTION NEEDED ON DEPLOYED CHARTS: the inputs are RENAMED, so saved
.set files no longer match and charts fall back to the defaults above.
Those defaults are the current shipped values, so a chart on 25/Disabled
needs nothing; a tuned one does.
Comment cleanup in the same pass, and this part was not cosmetic - three
blocks documented mechanisms that no longer exist:
- the AI early-exit route (deleted in 38a12a2) described as live and
still firing every bar;
- the m_lastNonNeutralSignal alternation gate (removed 2026-08-01)
described as consuming the AI's vote;
- 16 lines of VOTE_CLOSE_PRESETS documentation orphaned by that enum's
deletion, ending with "see that enum's note directly above" pointing
at nothing.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
First of the AI vote layers to go. CheckClosePosition had two exit routes:
the stock blended vote, and an AI-only one reading the AI members' sub-vote
undiluted. The second existed because an AI reversal averaged in with the
classic filters could be diluted below the threshold before it could close
a position.
It is gone, and with it m_lastAiVote and the aiResult/aiWeightSum pair
Direction() carried to feed it.
This CLOSES the certified-vs-traded gap rather than widening it. The
deploy gate certifies a win rate measured on hold-to-resolution outcomes,
and CheckClosePosition already gated the blended route off whenever an AI
model's derived geometry was on the order - so the AI route was the only
vote exit an AI-certified trade could take, and the exit replay existed to
reproduce it. With it removed, an AI-certified position holds to its
barrier by construction instead of by reconstruction, so Warrior_EA.mq5
now pushes ExitPolicy(0.0, true) unconditionally. Previously it forwarded
Min_Vote_Close and relied on Disabled arriving as 1.01 to switch the
simulated exit off by arithmetic - correct at the shipped default, and one
input change away from the simulation and the live path describing
different games.
Min_Vote_Close keeps its meaning for the classic route and is now
documented as inert wherever an AI certificate governs, rather than
appearing to drive an exit it can no longer reach.
Comment debt cleared while here: a tombstone block for m_ai_exit_threshold
(a member deleted 2026-08-18) still sat in the header, and four sites still
named LiveSignedConfidence's "two consumers" - it had one, the intelligent
trailing stop, since that same date.
NOT touched, and deliberately: NMS declustering is NOT a quality layer. It
gates the live signal at Inference.mqh:226 (NmsLiveAccept), and the
undeclustered population is ~8x what the EA trades. Removing it would
multiply live position count, not simplify a scoring path.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
MA: CustomIndicators\ADMovingAverage is replaced by the built-in iMA (CiMA) on
both consumers - the classic vote and the NN MA input feature. This drops the
five advanced types ALMA/DEMA/ZLEMA/T3/Kalman, which have no iMA equivalent;
MA_TYPE_PRESETS is now ENUM_MA_METHOD's own codes and the tuner searches all
four. It also removes a documented failure mode: a custom indicator's depth is
bounded by TERMINAL_MAXBARS, and m_MA was the one whose feature block REJECTS
the bar on a short read - the "feature 25 fails on every bar" incident of
2026-08-17. A built-in is served at any depth.
MIGRATION. SMA moves from code 5 to 0, so persisted type codes change meaning.
SanitizeMaType() is the single validity rule; TunedPeriods records now carry a
version field and a v1 record remaps 5..8 -> 0..3, falling back to SMA for a
stored advanced type (unrecoverable - old 0..4 are indistinguishable from valid
new codes). Existing .nnw files re-key on their own, because MA_Type is hashed
into the topology fingerprint, so models retrain rather than silently running
on different MA values. EXPECT A FULL RETRAIN.
ZigZag: ADZigZag was a byte-identical rename of MetaQuotes' Examples\ZigZag -
verified by normalising identifiers and stripping comments, 233 significant
lines each with only renamed symbols differing. It now loads the stock one, so
nothing is bundled and MetaQuotes' fixes arrive without a rebuild here. Both
#resource entries are gone.
Classic_Shift: a new input, the BAR the four classic votes evaluate on (0 =
forming, 1 = last closed, default 1). One implementation on CExpertSignalCustom,
inherited by all four rather than repeated per module. Defaults to a sentinel
meaning "unset", so the AI signals and the aggregate keep the stock every_tick
rule and their feature/label alignment is untouched. The META corpus sweep still
takes precedence. CExpertBase::StartIndex turns out to be virtual, so this is a
real override, not the name-hiding the old comment claimed.
Not compiled - MetaEditor compile pending.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Reported by the user's MetaEditor compile of f64e0f8 (26 errors, 4 warnings). The four
warnings mattered more than the errors.
1. INTELLIGENT WAS TWO ENUMS. MONEY_MANAGEMENT_STRATEGY::INTELLIGENT (=1) is declared
BEFORE TRADING_DIRECTION::INTELLIGENT (=3) in InputEnums.mqh, so MQL5 resolved every
'tradingdirection == INTELLIGENT' to the MM member and converted it to value 1 =
TRADING_DIRECTION::LONG_ONLY. Wrong in both directions at once: selecting Intelligent
(3) matched NOTHING and silently traded both sides, while selecting Long only (1)
matched and handed the decision to the measured drift verdict - which can answer
SHORT_ONLY, so the one setting that must never go short could have. Reported by the
compiler as a WARNING only, never an error. Renamed to DIRECTION_INTELLIGENT; the
VALUE stays 3, so saved .set files are unaffected. Swept every enum in the repo for
sibling collisions (38 enums, detector validated against the pre-fix source, which it
flags): none remain.
2. g_warriorMetaGate sits above the class it points at - added the forward declaration,
the same pattern g_warriorEnsemble already uses in ExpertSignalAIBase.mqh.
3. The broker-time rename (b63e39f) never reached BufferNewTickSignal's PARAMETER or its
two call sites: the local became brokerTime, the parameter stayed gmtTime, and the
body was rewritten to read brokerTime. All five sites now agree.
4. ConfigureAISignal calls IsMetaTarget() from a free function - moved it to the public
section (identity, not an implementation seam); the other meta seams stay protected.
NOT COMPILED - user compiles in MetaEditor.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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>
Two user requests, one authority: SymbolInfoSessionTrade, read fresh on
every call so DST and per-symbol schedule changes track themselves.
- WarriorMarketOpenNow(): CheckOpenPosition refuses entries outside the
symbol's trading sessions (Sunday reopen, index CFDs' daily breaks) -
a vote can no longer fire into a closed book and collect a broker
error. ENTRIES ONLY: exits, SL/TP and the scheduled close-all stay
unguarded - closing risk must never be blocked by a session boundary.
- CH_MARKET_CLOSE = 24 (appended, .set-safe): the close-all fires
"Close-all minute" minutes before that day's LAST session close.
Friday + Market close + xxH05 = flatten 5 minutes before Friday's
actual close. Resolved identically in three places: the live executor
(CExpertCustom::OnTick), the label walk's vertical barrier
(NextScheduledCloseAll - the symbol's CURRENT table stands in for
history; MT5 keeps none, and a fixed hour is wrong by more), and the
fingerprint (the |CUT: token already carries hour=24, so switching to
the dynamic mode re-keys the model exactly like any schedule change).
Training itself is deliberately NOT gated on market hours: weekend
compute is free and labels only ever exist on real bars - what the
session table gates is order placement and, via the close-all barrier,
what the labels may count as holdable.
NOT COMPILED - user compiles in MetaEditor.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
SQX EdgeFinder precedent (user request): adjust for the drift instead of
fighting it. The 2026-08-19 telemetry found the models leaning SHORT
(Buy recall 21% vs Sell 40%) against a long-favored market (always-long
34.3% vs always-short 29.5% at the adopted geometry).
TRADING_DIRECTION gains INTELLIGENT = 3 (appended, explicit value,
.set-safe). It resolves at runtime from the label cache's per-side win
rates - the Buy/Sell shares ARE the win rates of taking every bar
long/short at the REAL stop/target with spread charged. A side is
dropped only when BOTH hold: the drift gap clears 2 combined SEs on the
overlap-deflated effective sample (EffectiveSampleSize - labels overlap
~18x), AND the weaker side sits below cost-adjusted break-even (a side
that still clears costs is kept; drift tilt alone is not a reason to
refuse a profitable side). Fails open to BOTH: unmeasured, tiny
effective n (<30), insignificant gap, or classic-only charts (no label
cache).
One resolution point - WarriorEffectiveDirection() - feeds all three
gates so they cannot drift apart: CheckOpenLong/Short (live entries),
the filtered-view sweep (a blocked side falls into the delete branch,
mirroring live), and the vote HUD's "-> TRADE" verdict. The verdict
re-derives at every label-cache rebuild, prints only on change, and is
computed even when the input is not Intelligent (marked informational).
NOT COMPILED - user compiles in MetaEditor.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Under CONSENSUS arithmetic the vote is quantized by agreement: with four
members at pooled tier weights ~29, unanimity reads ~29, 3-of-4 ~22,
2-of-4 ~14.5. The 10-point dropdown straddled every one of those rungs -
20 admitted 3-of-4, 30 admitted nothing - so the thresholds an operator
actually wants (between rungs, e.g. 25 = "unanimity or a top-tier 3-of-4")
did not exist. PERCENTAGE_PRESETS and VOTE_CLOSE_PRESETS both gain
5/15/25/35/45; members are only ever ADDED (explicit values, .set-safe),
never removed - MT5 does not validate saved enum values.
Min_Vote_Open default 40 -> 25: the 40 was priced under union arithmetic
and now sits above the unanimity ceiling (~29), i.e. a fresh attach would
silently never trade - the same fired-on-0-bars defect the 50 -> 40 move
fixed once already.
NOT COMPILED - user compiles in MetaEditor.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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>
The user is right that no special combination logic is needed: the AI
signals are ordinary voting filters, and the aggregate already has
union semantics - abstaining filters do not dilute the average, so an
ensemble chart trades whenever ANY deployed member clears the vote
threshold and disagreeing members net out. What the ensemble preset
actually adds:
- AI_CHOICE value 4 renamed AI_CONVLSTM (the name says the front-end);
enum VALUES stable, CSignalHYBRID class and State\HYBRID\ folder kept,
so saved configs and trained models keep their identity.
- New AI_HYBRID = 6: enables PAI+CONV+LSTM+CONVLSTM together on one
chart - replaces four separate charts of the same symbol. Each member
trains and self-gates independently; only certified members ever vote.
- |ENS1 fingerprint token on every member, so an ensemble member's
weight files can never collide with a solo model of identical
settings on another chart of the same symbol (the duplicate-chart
guard would otherwise correctly fight over one .nnw).
- Private default AIType = AI_HYBRID: one D1 drop now yields every
topology's gate verdict for that symbol.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
User direction (2026-08-15): back to predicting swing turns, D1 charts,
fractals over ZigZag pivots (their call - balances classes, matches the
reference library target, and a 5-bar fractal confirms 2 bars after its
extreme so labels resolve nearly to the present with no repaint embargo).
- TRAINING_TARGET enum + TrainingTarget input: TARGET_BARRIER (Market
default - existing models keep their meaning and fingerprints) or
TARGET_FRACTAL (private default).
- FractalDirectionLabel (Labels.mqh): per-bar 3-class label = direction
from the bar close to the next confirmed strict 5-bar fractal extreme,
costs charged in the same bid-series convention as the barrier label,
Neutral when the move cannot clear max(2 spreads, 0.10 ATR) or on an
outside bar (both-extreme bars are unorderable within OHLC).
- The barrier walk still runs in full: measured SL/TP geometry, the
expectancy scan, excursion caches and the era gate all keep scoring
what a trade at the EA's own stop/target actually collected - only the
TRAINING label changes. NOT the pre-b4a704d "is this bar the pivot"
form; that target's 31:1 imbalance stays retired.
- Fingerprint token |TGT:FRA1 so switching targets trains a separate
model; AI_META unaffected (guarded setter).
- Private defaults: AIType back to AI_HYBRID (direction topology needed)
+ TrainingTarget=TARGET_FRACTAL = drop-on-D1-chart workflow.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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>
The barrier geometry is derived from the instrument's own excursion
distribution (stop at q75 of adverse travel, target at q50 of favourable),
and then a 1:2 floor was applied on top, raising the target to twice whatever
the stop happened to be. On SP500 H1 that pushed the target to 6.66*ATR,
reached on 3.3% of bars inside the horizon - so the label became "almost
never a win" and every topology was trained to predict an event that
essentially does not occur. A measured target has to stay measured.
The ratio never bought what it was believed to buy. A reward:risk floor does
not create expectancy; it trades hit rate against payoff at a break-even the
geometry already fixes - which this project has separately MEASURED (payoff
0.92 -> 5.72 with expectancy flat). What it did buy was two outages: four
consecutive Market validation rejections for "no trading operations" when it
rejected 100% of setups, and the label corruption above.
Removed:
- the input and the RISK_REWARD_RATIO enum (deleted, not left dangling - a
live enum with no input behind it is the shape of the stale-.set incident
that trained ~250 eras on the wrong target)
- the forced target raise in the label geometry
- the rrOK eligibility gate in the barrier-geometry scan, so every unclamped
pairing now competes on the measurement alone. Clamping stays disqualifying
for its own unrelated reason.
- the reward < minRR*risk veto in OpenParams
Kept: g_TradeRewardRiskRatio still computed and still bridged to Kelly sizing
in MoneyIntelligent - the ratio as a SIZING input was always the sound use.
Risk stays bounded where it actually is - account risk % and CRiskBudget.
The low-reachability warning survives but is re-aimed: with nothing inflating
the target, a target the market rarely reaches can only mean the horizon is
truncating the excursions the geometry is derived from.
Both build variants compile 0 errors / 0 warnings.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- Implemented sqx_audit.py to audit StrategyQuant X trade lists, focusing on performance metrics and cost analysis.
- Created sqx_portfolio.py to evaluate portfolio performance based on uncorrelated components and their impact on risk and return.
- Developed swing.py to analyze cost ratios across different holding periods and assess swing trading structures.
- Introduced test_management.py to investigate the effectiveness of exit rules on random entries and their impact on expectancy.
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>
Every removal below is FINGERPRINT-NEUTRAL by construction: each retired
input is pinned to the exact value it already shipped with, so running
models keep their filenames and resume rather than restarting at era 0.
Verified field by field against BuildConfigFingerprint.
Removed as inputs, kept as pinned constants (the value was never a
preference the user had a basis to change):
- OutputNeuronsCount. The regression head predicts a continuous quantity
the triple-barrier label does not contain; the target is an EVENT, so
the right output is its probability. The regression code paths stay
implemented and dormant - they cost nothing and removing them would
touch every scoring path at once.
- MinRecall. A safety floor, not a preference, and the only direction a
user can move it is the harmful one: raising it past what the config
reaches yields NO model, not a better one (observed repeatedly at 60).
- SwingConfirmationBars. Stopped gating the labels with the relabel, but
is STILL load-bearing for the swing-context input features - it is the
ZigZag repainting embargo, and without it those 9 features read a leg
the live bar could not have had yet. Pinned, not deleted.
- MaxErasPerRun (runaway backstop, never reached in a healthy run),
FreezePriorCalibration (unanswerable by a user; near-balanced labels
make the priors stable anyway), VerboseMode (developer view, joins
DebuggingMode), MACD/Ichimoku periods x6 (both indicators ship
disabled, and as optimizer dimensions they are pure overfitting
surface - the AI auto-tuner is the supported way to move them).
- SignalClusterWindow -> 3, no longer an input. Barrier labels make
consecutive setups real, which argued for 0; it is not 0 because on D1+
a 6-bar window spans over a week and two arrows a day apart on a
weekly-scale move are one event. 3 splits it correctly by timeframe.
- EnableOnlineLearning -> ON. Adapting to a changing market is what keeps
a months-attached model from going stale, and the rolling-accuracy
freeze is what makes it safe. See the caveat noted in the handoff: it
had not been forward-tested on a live feed when this became default.
Removed entirely:
- Intraday Time Filter (5 inputs + Signals/SignalITF.mqh). Two of its
five inputs were raw BITMASKS, which is an implementation detail
exposed as a control. The job is covered three times over by things
that are declarative or that learn: the session filter, the
time-of-day/day-of-week input features (the network discovers which
hours are good rather than being told), and the journal's time buckets.
- Market Depth Filter (5 inputs + Signals/SignalMarketDepth.mqh, plus
its OnInit probe and OnDeinit release). It needs real level-2 data
that this broker - and most retail MT5 brokers - do not provide, so
the module has never once executed against real data. Shipping four
tuning dropdowns for an untested path is worse than shipping nothing:
the only users who could enable it would be its first-ever testers,
live. If DOM returns it should be a FEATURE fed to the network, not a
rule-based veto with hand-tuned thresholds - imbalance is data.
- IndicatorTuneTrials, replaced by ComputeTuneTrialBudget(). The useful
budget depends on how many parameters are actually being searched,
which depends on which features are enabled - so one number meant
wildly different things run to run. The shipped 32 was ~10 candidates
per dimension against one enabled indicator (wasteful: each costs
GA_SEEDS full training runs) and under one per dimension against all
nine (blind). Now population ~ 4 x active dimensions, clamped [8,64],
with CADIndicatorTuner::ActiveDimensions() defined immediately above
PerturbRandom() so the two cannot drift apart.
- Six orphaned enums (TUNE_TRIALS_PRESET, DOM_*, ENTRY_HOUR_OF_DAY,
TIME_FILTER_DAY_OF_WEEK), 81 lines.
Other UX:
- SL_ATR_x1 / TP_ATR_x3 now carry the "(classic)" default marker every
other preset enum in the file already used. Nothing in the SL/TP
dropdowns previously told a user which pair was the shipped default -
which matters far more since the relabel, because those two define the
labels and changing either forces a retrain.
- Neural Network section moved directly ABOVE AI Input Features: choose
the architecture, then choose what it sees. NN Optimizer / Performance
stays last - the Adam/Sgd inputs are declared in AI/Network.mqh and
render immediately after that divider.
- News feature + window moved to the end of the AI feature list, below
Wyckoff Bar Inversion.
- Dropped "(0-100)" from Min vote to open - it is an enum, not a number.
Both builds compile 0 errors / 0 warnings. No retrain forced.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The imbalance section offered nine controls for one job. Audited against the
code, five of them did not do what their names said at the shipped defaults:
AILogitPriorStrength DEAD - Inference.mqh's post-hoc prior early-returns
whenever the adjusted loss is on, which is default.
OversampleParity DEAD in training - Training.mqh gated the replay loop
on !useLogitAdjustedLoss (correctly, citing Buda et
al. 2018). Live only in the online-learning path.
EnableMinorityReplay DEAD as replay. It survived ONLY as a focal-gamma
damper - "replay minority bars through pass-2
oversampling" was a focal-loss switch.
ConstrainReplay DEAD as a cap; it only chose damper 0.125 vs 0.25.
UseStaticPrior An exact duplicate of FreezePriorCalibration - the two
were OR'd together in the single place either is read.
So they were not five mechanisms fighting; they were one mechanism plus eight
knobs that mostly described machinery that no longer ran. That is worse than
a real conflict, because the log agreed with the names: the label-cache line
printed "reps up to 28x (90% parity) (seeding era 0's class-balance
oversampling)" on every run, describing an oversampling pass that had been
switched off. It is fixed here too - it cost this session a wrong diagnosis.
The one genuine redundancy was focal loss, running at gamma*0.125 alongside
the adjusted loss: two corrections on the same axis, the exact stacking
failure this file already cited Buda et al. for in two other places, damped
by a replay flag whose replay path was itself dead. Removed rather than
re-tuned. The plateau ladder is unaffected - its escape is the learning-rate
warm restart; the gamma anneal beside it only ever stepped toward zero.
WHAT REMAINS is logit-adjusted loss (Menon et al. 2021) plus a prior freeze:
LogitAdjustTau 0 = off; replaces the separate EnableLogitAdjusted-
Loss boolean, since a strength dial where 0 already
means off does not need an on/off switch beside it.
FreezePriorCalibration unchanged.
It is the only one of the six corrections with a consistency guarantee, and
it is consistent for exactly the balanced-error metric checkpoint selection
already ranks on - so the loss and the deploy decision optimize one thing.
The online continual-learning path keeps its own alpha-balanced focal weight,
now as constants pinned to the removed inputs' shipped defaults, so its
behaviour is unchanged. It legitimately needs its own correction:
ApplyLogitAdjustment() only runs inside a training run, so a deployed model
that was reloaded carries no logit offsets and would otherwise stream 31:1
data into itself uncorrected.
The weights-filename fingerprint is BYTE-IDENTICAL. The focal slot was a
double fed to a %d conversion and had always emitted a literal 0; the |MR:
segment is written as the constant its shipped defaults produced. Dropping
either would have re-keyed every model and forced a from-scratch retrain of
the one topology currently converged and trading.
Also removed as orphans: FOCAL_GAMMA_PRESET, MAX_OVERSAMPLE_REPLICAS,
OVERSAMPLE_PARITY_FRACTION, PLATEAU_GAMMA_STEP, and the now-unreachable
"neutralized by prior correction" diagnostic.
Both builds compile 0 errors, 0 warnings. No retrain forced.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Stops keyed to the recent swing extreme make a trade's risk a function of
how far the last swing happens to sit rather than of current volatility. On
a shallow pullback the swing sits close to the fill, so the stop is tight
enough to be taken out by noise on setups that then run to target - which is
what the Perceptron's signals were showing.
SL: lowest_low/highest_high -/+ mult*ATR -> entry -/+ mult*ATR
TP: TP_PREV_SWING (opposite swing) -> removed; ATR-from-entry
SL_PREV_SWING, TP_PREV_SWING -> removed from the enums
The SL anchors to `price` (the resolved entry), not to base_price: with a
pending entry those differ by the whole entry offset, and the risk Money
sizes against is entry-to-stop.
MIN_SL_ATR_MULTIPLIER 2.0 -> 0.5. That floor existed because a swing-
anchored stop could land arbitrarily close to the entry and needed a bound
unrelated to the chosen multiple. An entry-anchored stop is exactly
mult*ATR by construction and cannot collapse, so leaving it at 2.0 would
have silently overridden SL_ATR_x1 to 2*ATR - making the input a lie AND
forcing TP >= 4*ATR just to clear the default 1:2 rejection filter. The
broker's own stop level is enforced separately and precisely by
TCAdjustStops(), so this is now a pure sanity net.
Default TP_Mode TP_PREV_SWING -> TP_ATR_x3, so SL_ATR_x1 + TP_ATR_x3 gives a
realised 3:1 against the 1:2 filter. TP_ATR_x2 would sit EXACTLY on the 2.0
boundary where price-normalization rounding alone can reject the setup; the
default leaves a deliberate gap. This is the same interaction that once
rejected 100% of setups on every symbol (see TP_INTELLIGENT_BASE_RR).
Swing validity guards now reject only when the configuration actually uses a
swing - i.e. ENTRY_PREV_SWING. Previously an unsynced or thin history
rejected EVERY trade, including configurations whose levels no longer
reference a swing at all. The guards are kept, not deleted: a bad swing must
still never reach an entry price, and iLow/iHigh are no longer called with a
possibly-negative index.
TP_INTELLIGENT stays risk-relative. Now that risk is exactly mult*ATR the
risk- and ATR-relative forms coincide, but risk-relative keeps its
reward:risk guarantee exact after the floor or TCAdjustStops widens a stop.
Both builds compile 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Completes the derived-topology work. Three inputs removed.
AIType loses its depth suffix - AI_MLP/AI_CONV/AI_LSTM/AI_HYBRID, five
entries instead of eight. Depth is now derived from the two endpoints
the taper already has to connect (derived first-layer width, output-tied
final width) at a 2x per-layer compression target, clamped [2..5].
Asking a user to pick a layer count while the code derives the widths
those layers taper between was asking for half a decision: at 64 units
tapering to 12, four layers compress by 1.4x per step and five by 1.3x,
so the extra depth bought no abstraction. On the shipping H1/10y default
the derivation lands on 3 layers - the depth that actually won Run 2.
StudyPeriods removed. There is no case for training on less data than
the broker provides at a ~6% directional base rate; the honest
generalization read comes from the OOS holdout, not from withholding
history. Training now starts at the earliest available bar, floored by
MinTrainYear, which answers a different question (excluding dubious
pre-history) and stays.
That required closing the hazard the old code documented: the capacity
budget now MEASURES the symbol's real bar count, and a topology derived
from a measurement would widen as history downloads. Both ends are now
pinned. Every derived value left the weights-filename fingerprint -
keying a filename on a measured quantity means the EA looks for a file
that does not exist, starts from era 0 and orphans a trained model,
silently, because a missing cache is the normal first-run state. The
shape lives in the .cfg instead, where LoadAndCompare now ADOPTS the
four derived fields rather than diffing them; a mismatch there would
discard a fully-trained model over nothing the user did. Two fields
appended to the .cfg for the conv/LSTM stages, length-guarded on read
because FileReadInteger past EOF returns 0 with no error.
ForceHiddenLayers, a compile-time constant like DebuggingMode, pins
depth for diagnostic comparisons. It joins the fingerprint only when
non-zero, so forced depths get their own files - sequential comparisons
only, not simultaneous from one .ex5.
Derived shape, H1/10y defaults (21 features x 20 bars): first layer 64,
3 dense, 8 conv filters, 16 LSTM units. The LSTM block halves from
~58k to ~28k weights.
Both builds compile 0 errors, 0 warnings. Re-keys existing models.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
FeedForwardConv emits POSITION-MAJOR output, matrix_o[out + window_out * i],
so one bar's window_out filter responses are contiguous and consecutive bars
sit window_out apart. Both pooling implementations (FeedForwardProof and
CPU_FeedForwardProof) slide FLAT over that buffer - pos = i * step, reducing
`window` CONSECUTIVE elements. On a position-major layout those neighbours
are different FILTERS of the same bar, never one filter across time.
At the shipped 3/2 the pool computed max(bar0_f0, bar0_f1, bar0_f2), then
max(bar0_f2, bar0_f3, bar0_f4), with every 8th window straddling a bar
boundary. So it collapsed unrelated feature detectors into whichever fired
hardest, passed gradient to that winner only, and halved the feature map
while doing it - all below every learnable layer, where nothing above can
recover it. The removed inputs' own labels ("3 Bars") show time-axis pooling
was the intent throughout.
Measured cost: CONV sat pinned at ~40% balanced accuracy for 510 eras with
Sell recall 0%, while plain MLPs on the same data reached 57-61%. HYBRID,
which also carried this stage, came second-worst of the batch-norm group.
Not fixable in the topology: pooling one filter across time needs a stride
of window_out BETWEEN samples within a window, which a consecutive-window
kernel cannot express at any window/step. That needs a stride-aware kernel
in Network.cl + WarriorCPU.cpp + WarriorDML.cpp and a DLL rebuild, and is
only worth doing if a conv front-end earns its place without downsampling
first - with 20 sliding positions there is little to gain by halving them.
ConvPoolWindow/ConvPoolStep and their enums are removed with it, along with
the |CP: fingerprint term added earlier today.
Both builds compile 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
InitialNeurons was an input whose only defensible value depends on two
things the user cannot see when picking from a dropdown: how wide the input
vector ended up after feature selection, and how much in-sample data the
study period actually yields. Left to a hand-picked constant it was badly
wrong - 500 units against a 420-wide input is 210,500 weights, 72% of a
292,583-weight model, against ~36,500 training bars of which only ~2,236
are directional. That is 6.6 weights per training bar, and it EXPANDS a set
of highly correlated inputs rather than compressing them.
The symptom was already in the logs and had been read as a depth problem:
the shallowest topology consistently beat the deepest (perceptron 52.7%
balanced, hybrid 41.3%). Over-parameterization predicts that ordering just
as well as covariate shift does, and only one of the two had been addressed.
ComputeFirstLayerWidth() budgets roughly one first-layer weight per
in-sample bar. Measured across the configurations in use:
M15 10y -> 256 units, 129,071 weights, 0.73 per bar
H1 10y -> 64 units, 28,727 weights, 0.65 per bar
H4 10y -> 16 units, 7,559 weights, 0.68 per bar
Two design points that matter:
- It estimates in-sample bars from the STUDY PERIOD and timeframe, not
from Bars(). What is downloaded grows over a terminal's lifetime, and a
topology that widened as history filled in would re-key its own weights
file and discard a trained model.
- The result is snapped down to a coarse power-of-two ladder, so the
estimate would have to be wrong by ~2x to change the answer.
Every field it reads is already part of the weights-filename fingerprint,
so the derived value needs no fingerprint entry of its own. The public
setter is removed - it could only have been called after construction, and
would either be ignored or silently re-key the model mid-run.
Where the data cannot support even the floor (D1 over 10 years is under
2,000 bars) it now says so and names the fixes, rather than quietly
training a model with more weights than examples.
The DB config fingerprint drops the term too, which re-keys existing
pattern databases once - correct, since a model an order of magnitude
smaller should not inherit the old one's win-rate history.
Compiles 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The DFA (Direct Feedback Alignment) option was never a correct implementation:
it deterministically flipped the sign of half of all gradients based on
connection index parity, causing permanent gradient ascent for those weights
and guaranteed divergence. The backward pass was also incompatible with the
OpenCL/DirectML neuron model (layer.Total() == 1). This change removes all DFA
logic, including the enum value and `DfaFeedbackSignal` method, and replaces it
with plain gradient descent in all momentum update kernels. The `optimizer`
kernel argument is retained for binary compatibility but is no longer used.
Introduce an `optimizer` parameter to UpdateWeightsMomentum, UpdateWeightsConvMomentum, and UpdateWeightsAdam kernels. When set to a non-zero value, the gradient used for weight updates is multiplied by ±1 based on the parity of the weight index, implementing a basic feedback alignment signal for experimentation. When zero, the standard gradient is used unchanged. This allows A/B testing of alternative learning signals without modifying the rest of the training pipeline.
Eliminate the separate `AI_TOPOLOGY_PRESET` enum and input.
Fold the topology presets directly into `AI_CHOICE` as new combined values (MLP_3L, MLP_4L, CONV_2L, LSTM_2L, HYBRID_2L) plus `AI_NONE`.
Remove the `TopologyPreset` input variable and update default `AIType` assignments.
Update the market description to reflect the simplified single‑selector interface.
**Why:**
Users previously had to choose an AI architecture and a topology preset separately.
Now the UI shows one coherent selector that bundles architecture with its appropriate dense‑layer depth, reducing complexity and preventing mismatches.
- Append '(classic)' to RSI period 14, indicator period 14, risk-reward 1:2, and risk percent 1 preset comments
- Change Min_Vote_Close default from VOTE_CLOSE_80 to VOTE_CLOSE_DISABLED
Add MACD_FAST, MACD_SLOW, MACD_SIGNAL presets and Ichimoku Tenkan, Kijun, Senkou presets to InputEnums.mqh. All combinations are designed to satisfy the respective indicator's validation rules (fast < slow for MACD, Tenkan < Kijun < Senkou B for Ichimoku), eliminating init errors and allowing the auto-tuner to perturb settings independently.
Introduce VOTE_CLOSE_PRESETS enum with a Disabled option (value 101) that bypasses vote-driven position closing via arithmetic thresholding, removing the need for a separate boolean flag. This ensures positions exit only via stop-loss, take-profit, or trailing when disabled.
- Guard CNet::Save to refuse writing a 0-layer network (prevents overwriting ~18MB model with empty stub)
- In CNet::Load and LoadCheckpoint, treat 0-layer files as load failure (older stubs still on disk)
- Introduce LOGIT_PRIOR_STRENGTH_PRESETS enum (0–100%) to control logit adjustment tau
- Prepare member variables and AdjustedSignalFromSoftmax for prior-corrected posterior at inference
- Ensure raw argmax scoring for recall/convergence remains unchanged; correction only affects live signal
Add `MA_TYPE_PRESETS` enum covering advanced (ALMA, DEMA, ZLEMA, T3, Kalman) and standard (SMA, EMA, SMMA, LWMA) moving averages. Integrate `maType` and `bestMaType` into `CADIndicatorTuner` struct, update flatten/unflatten routines, and bump `AD_TUNE_PARAM_COUNT` to 33. This allows the auto-tuner to search over MA type alongside period, improving feature discovery.
