Warrior_EA/Expert/AIBase/Inference.mqh

//+------------------------------------------------------------------+
//|                                                       Warrior_EA |
//|                                                     AnimateDread |
//|                                                                  |
//| Read-time signal production: softmax, prior calibration, class p|
//|                                                                  |
//| PARTIAL IMPLEMENTATION FILE - not standalone.                     |
//| This holds CExpertSignalAIBase method BODIES only. The class      |
//| declaration lives in Expert\ExpertSignalAIBase.mqh, which         |
//| #includes this file at the bottom, after the declaration. Do not  |
//| include it anywhere else and do not compile it on its own.        |
//|                                                                  |
//| Split out purely to make the 8216-line original navigable; the    |
//| code inside was moved verbatim, not rewritten.                    |
//+------------------------------------------------------------------+
#ifndef WARRIOR_AIBASE_INFERENCE_MQH
#define WARRIOR_AIBASE_INFERENCE_MQH
//+------------------------------------------------------------------+
//| Post-convergence "new bar" handler - see ScheduleTrainingIfNeeded()|
//| for why this exists: once m_trainingComplete is true, a plain new  |
//| bar must NOT re-enter Train()'s full era loop (which resets the    |
//| best-checkpoint/eta-decay tracking and runs real Net.backProp()    |
//| passes again, silently perturbing an already-converged model      |
//| forever, once per bar, with no way to ever actually finish). This  |
//| only refreshes the price/indicator buffers and re-runs inference   |
//| for the newest bar so dPrevSignal/the chart arrow stay current -   |
//| identical cost to what Train() does per-bar, minus every bit of    |
//| training (label caching, backProp, checkpointing).                 |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::RefreshConvergedSignal(void)
  {
   //--- Size the buffers from what the FEATURE BUILDER actually needs, not from a date delta.
   //--- This used to be `Bars(sym, period, dtStudied, TimeCurrent()) + m_historyBars`. dtStudied is a
   //--- training watermark, and in the Strategy Tester it is loaded from a LIVE-chart save whose
   //--- timestamp is AHEAD of the simulated date - so the interval inverts, Bars() returns ~0, and the
   //--- buffer came out at exactly m_historyBars. That is just deep enough for the OHLC window to
   //--- succeed and far too shallow for the swing-context block behind it: the Donchian-50, the 20-bar
   //--- return and the SMA extension all reach further back than m_historyBars, hit the end of the
   //--- loaded series, and take their graceful degraded path. The result was silent - no error, no short
   //--- window, just inference computing DIFFERENT features from the ones training learned on. Live it
   //--- was the same bug with a milder constant (the delta is ~1 bar, giving m_historyBars + 1).
   //--- SWING_SCAN_CAP_BARS is the deepest lookback any feature performs (FindConfirmedZigZagPivot's
   //--- bound); everything else in BufferTempDataCompute reaches less far.
   int need = (int)m_historyBars + SWING_SCAN_CAP_BARS + MathMax(m_barrierHorizonBars, 1) + 2;
   int barsNow = (int)MathMin(need, Bars(m_symbol.Name(), PERIOD_CURRENT));
   if(!ResizeBuffers(barsNow) || !RefreshData())
      return;
   //--- INVALIDATE THE NOW-RELATIVE BAR CACHES. Non-obvious and load-bearing: the feature cache is keyed
   //--- by MQL5 series index, and index 0 means "newest bar", so every closed candle shifts what every
   //--- cached row stands for. Train() is the only other caller of this, and once m_trainingComplete is
   //--- set ScheduleTrainingIfNeeded() routes every subsequent bar HERE instead - Train() is never
   //--- re-entered, so without this call nothing ever clears the cache again for the rest of the process.
   //--- A chart that trained to convergence (or was deployed via DeployNow()) would then keep replaying
   //--- the rows computed for the last training era's bar grid: BufferTempData(0..m_historyBars-1) all hit
   //--- the cache, the feature window never changes, and dPrevSignal freezes at its convergence-time value
   //--- forever - silently, since every buffer above refreshed correctly and the vector is the right SHAPE.
   //--- OnlineLearnStep() below would compound it by backpropping those stale features against freshly
   //--- resolved labels, i.e. actively training the deployed model on mismatched pairs.
   //--- A freshly started inference-only process (a backtest, or a buyer loading a deployed .nnw) was
   //--- never affected: it never allocates these arrays, so BufferTempData()'s `cacheable` test is false
   //--- and it always recomputes. This is a live/forward-chart fix, not a backtest one.
   EnsureBarCachesCapacity(barsNow);
   //--- Same bar grid, same panel. A deployed model never enters Train(), so this is the only place
   //--- its cross-asset panel gets built - and it must be built from the SAME reference set training
   //--- used, or inference reads a different feature vector than the weights were fitted to.
   //--- Only as deep as inference actually reads. RefreshLatestSignal() touches bars 0..m_historyBars-1
   //--- and the panel's own slow window reaches CROSSASSET_SLOW_BARS further back - nothing else. Asking
   //--- for the full `barsNow` here would rebuild a training-depth panel on EVERY bar, which in the
   //--- tester means one full multi-symbol resample per simulated bar. The cache check in
   //--- BuildCrossAssetPanel is >=, so a deeper panel left over from training still satisfies this.
   BuildCrossAssetPanel((int)m_historyBars + CROSSASSET_SLOW_BARS + 2);
   EnsureSpreadSeries(barsNow);
   //--- A deployed model never enters Train(), so this is the only place its barrier horizon gets
   //--- measured - and OnlineLearnStep() below depends on it being right. First call sizes buffers
   //--- against the fallback, which is harmless: `need` is dominated by SWING_SCAN_CAP_BARS either way.
   EnsureBarrierHorizon(barsNow);
   RefreshLatestSignal();
   //--- Continual learning: on a LIVE chart (never the tester/optimizer - OnlineLearnStep() self-guards
   //--- on m_inferenceOnly) a deployed model keeps adapting to newly-confirmed structure. Runs AFTER the
   //--- live signal is drawn (so the arrow uses the shadow as it was for THIS bar's decision) and BEFORE
   //--- dtStudied advances (OnlineLearnStep keeps its own time watermark, independent of dtStudied).
   OnlineLearnStep();
   dtStudied = m_Time.GetData(0);
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::RefreshLatestSignal(void)
  {
   int i = 0;
   //--- Window ends AT (includes) bar i - see Train()'s matching r declaration comment for why: this
   //--- must be the same window Train() learned from, or the deployed model is being queried on a task
   //--- it was never trained for. Both go through BuildFeatureWindow(), which is what guarantees that.
   int r = i;
   if(!BuildFeatureWindow(r))
     {
      //--- One combined failure now (partial window OR short total) where there used to be two counters.
      //--- Kept distinct in the tally by testing what actually landed: a window that built every bar but
      //--- came up short is the "short" case, anything else is a feature-build failure.
      if(TempData.Total() > 0 && TempData.Total() < (int)m_historyBars * m_neuronsCount)
         m_refreshFailShort++;
      else
         m_refreshFailFeatures++; // see PrintInferenceTally()
      return;
     }
   //--- Live trading/inference reads from the EMA shadow net, not Net directly - see m_shadowNet's
   //--- declaration comment. Falls back to Net if the shadow isn't bootstrapped yet (should only be
   //--- momentarily, on a genuinely fresh start before EnsureShadowNet() has run).
   EnsureShadowNet();
   CNet *deployNet = (CheckPointer(m_shadowNet) != POINTER_INVALID) ? m_shadowNet : Net;
   deployNet.feedForward(TempData);
   deployNet.getResults(TempData);
   if(m_outputNeuronsCount == 1)
      dPrevSignal = TempData[0];
   else
      if(m_outputNeuronsCount == 3)
        {
         //--- Live decision. ApplyClassificationSoftmax() computes the softmax INTO TempData and returns
         //--- the decision; AdjustedSignalFromSoftmax() re-reads that same TempData and applies the same
         //--- strict-majority/ties-to-Neutral rule, so since the read-time prior correction was removed
         //--- (2026-07-31) the two provably agree. The call is kept because a dozen sites name it as
         //--- "the live decision rule" and that is still exactly what it is - the correction now lives
         //--- in the trained weights instead of here.
         //--- The "raw softmax was neutralized by prior correction" diagnostic that used to sit here went
         //--- with it: with nothing between the two values it could never fire again.
         ApplyClassificationSoftmax();
         dPrevSignal = AdjustedSignalFromSoftmax();
        }
   m_refreshOk++;
   switch(DoubleToSignal(dPrevSignal))
     {
      case Buy:
         m_refreshBuy++;
         break;
      case Sell:
         m_refreshSell++;
         break;
      default:
         m_refreshNeutral++;
         break;
     }
   datetime bt = m_Time.GetData(i);
   //--- Keep a pure inference-side watermark of the newest bar this model has already evaluated. The
   //--- tester may load dtStudied from a live-chart save whose timestamp is AHEAD of the simulated
   //--- backtest date range; using that training watermark to decide whether a "new bar" exists then
   //--- freezes dPrevSignal at its init-bar value for the whole run. m_lastBarTime is this runtime's own
   //--- latest evaluated bar instead, so it stays aligned to whichever history the current process is
   //--- actually traversing.
   m_lastBarTime = bt;
   //--- Live NMS: suppress this newest-bar arrow if a same-direction signal was already kept within
   //--- m_signalClusterWindow bars - the live equivalent of PruneDirectionalClusters' historical sweep,
   //--- so the forward chart declusters the same way the trained history does (see m_signalClusterWindow).
   ENUM_SIGNAL lsig = DoubleToSignal(dPrevSignal);
   if(lsig != Neutral && NmsLiveAccept(bt, lsig, MathAbs(dPrevSignal)))
      DrawObject(bt, dPrevSignal, m_High.GetData(i), m_Low.GetData(i));
   else
      DeleteObject(bt);
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
double CExpertSignalAIBase::ApplyClassificationSoftmax(void)
  {
   // A non-finite logit poisons everything downstream: maxLogit, every exp(), the sum, and all three
   // probabilities become NaN, and since NaN fails every comparison the two directional tests below
   // are both false - so a NaN'd net returns Neutral on every bar forever and looks EXACTLY like a
   // model that has simply gone quiet. That is the failure mode this project has chased repeatedly
   // from the outside (panel says "no directional calls", nobody can tell whether the model is
   // cautious or dead). Detect it here, at the one place the raw logits are first read, and say so.
   if(!MathIsValidNumber(TempData.At(0)) || !MathIsValidNumber(TempData.At(1)) || !MathIsValidNumber(TempData.At(2)))
     {
      static int nanLogitReports = 0;
      // Bounded: this cannot heal on its own (the weights are already corrupt), so unlimited logging
      // would fill the journal for as long as the chart stays attached. Three is enough to prove it.
      if(nanLogitReports < 3)
        {
         nanLogitReports++;
         PrintFormat("%s: %s NON-FINITE network output (%g / %g / %g) - forcing Neutral. The weights are "
                     "corrupt; reload the last good .nnw or reset and retrain. Report %d of 3.",
                     __FUNCTION__, ID, TempData.At(0), TempData.At(1), TempData.At(2), nanLogitReports);
        }
      return 0;
     }
   // CLASS_LOGIT_SCALE (AI\Network.mqh) must match the training-gradient softmax in
   // backProp/backPropOCL exactly - this is the same normalization the loss was trained against.
   double maxLogit = CLASS_LOGIT_SCALE * MathMax(TempData.At(0), MathMax(TempData.At(1), TempData.At(2)));
   double sum = 0;
   for(int res = 0; res < 3; res++)
     {
      double temp = exp(CLASS_LOGIT_SCALE * TempData.At(res) - maxLogit);
      sum += temp;
      TempData.Update(res, temp);
     }
   for(int res = 0; res < 3; res++)
      TempData.Update(res, TempData.At(res) / sum);
   double pBuy = TempData.At(0);
   double pSell = TempData.At(1);
   double pNeutral = TempData.At(2);
   // TempData.Maximum(0,3) scans left-to-right and keeps the FIRST index on a tie, so any tie
   // (including the degenerate all-equal 0.3333/0.3333/0.3333 case from a collapsed/untrained net)
   // always resolved to Buy (index 0) - silently turning "the model has no idea" into a directional
   // trade. Buy/Sell now only win with a strict majority over BOTH other classes; every tie,
   // 2-way or 3-way, falls through to Neutral.
   if(pBuy > pSell && pBuy > pNeutral)
      return pBuy; // Buy signal
   if(pSell > pBuy && pSell > pNeutral)
      return -pSell; // Sell signal
   return 0; // Neutral signal (also the fallback on any tie)
  }
//+------------------------------------------------------------------+
//| Post-hoc logit adjustment (prior correction) of the 3-class      |
//| decision. Reads the raw softmax probabilities ApplyClassification|
//| Softmax() left in TempData[0..2] and returns the prior-corrected |
//| signed decision (+P'(buy)/-P'(sell)/0-neutral), the exact rule    |
//| live trading fires on and the live-fired precision metric scores. |
//|                                                                   |
//| RAW ARGMAX, deliberately. The prior correction this function used |
//| to apply at read time (Saerens et al. 2002) was REMOVED           |
//| 2026-07-31 along with the AILogitPriorStrength input.             |
//|                                                                   |
//| Why there is nothing to correct here: the logit-adjusted loss     |
//| adds tau*log(prior_c) to each class logit inside the TRAINING     |
//| gradient, so the network learns to absorb the offset and its raw  |
//| argmax is ALREADY the balanced-error-optimal decision. Applying a |
//| second correction at inference would account for the same base    |
//| rate twice and push the decision back toward Neutral - undoing    |
//| exactly what the loss bought. The old code knew this: the whole   |
//| adjustment sat behind an `if(m_useLogitAdjustedLoss) return raw`  |
//| guard and had been unreachable for the entire shipped default     |
//| configuration. Kept as a named function rather than inlined       |
//| because a dozen call sites document themselves by calling "the    |
//| live decision rule" - and that is exactly what this is.           |
//+------------------------------------------------------------------+
double CExpertSignalAIBase::AdjustedSignalFromSoftmax(void)
  {
   if(TempData.Total() < 3)
      return 0.0;
   double pBuy = TempData.At(0), pSell = TempData.At(1), pNeutral = TempData.At(2);
   //--- Strict majority, ties to Neutral - the same rule as ApplyClassificationSoftmax(). The returned
   //--- magnitude is a genuine probability, which the confidence floor and ConfidenceTier() read.
   if(pBuy > pSell && pBuy > pNeutral)
      return pBuy;
   if(pSell > pBuy && pSell > pNeutral)
      return -pSell;
   return 0.0;
  }
//+------------------------------------------------------------------+
//| EMA-updates the persisted true class base rates from a finished   |
//| era's true class counts. First real measurement seeds directly;   |
//| thereafter blended with the same smoothing as the accuracy/       |
//| confidence EMAs so one noisy era can't swing the live decision.   |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::UpdateClassPriors(long buyCnt, long sellCnt, long neutralCnt)
  {
   long tot = buyCnt + sellCnt + neutralCnt;
   if(tot <= 0)
      return;
   double pb = (double)buyCnt / tot, ps = (double)sellCnt / tot, pn = (double)neutralCnt / tot;
   if(m_priorNeutral <= 0.0) // first real measurement
     {
      m_priorBuy = pb;
      m_priorSell = ps;
      m_priorNeutral = pn;
      return;
     }
   //--- (Was `m_useStaticPrior || m_freezePriorCalibration`. Those were two separate user-facing inputs
   //--- whose only effect anywhere in the codebase was this one OR - two controls for one decision.
   //--- UseStaticPrior was removed 2026-07-31; see the class-imbalance audit in Variables\Inputs.mqh.)
   if(m_freezePriorCalibration)
      return;
   double k = Net.recentAverageSmoothingFactor;
   if(k < 1.0)
      k = 1.0;
   m_priorBuy     += (pb - m_priorBuy) / k;
   m_priorSell    += (ps - m_priorSell) / k;
   m_priorNeutral += (pn - m_priorNeutral) / k;
  }
//+------------------------------------------------------------------+
//| Installs the training-time logit offsets - see the declaration.   |
//+------------------------------------------------------------------+
void CExpertSignalAIBase::ApplyLogitAdjustment(void)
  {
   if(CheckPointer(Net) == POINTER_INVALID)
      return;
   if(m_logitAdjustTau <= 0.0)
     {
      //--- Clear rather than merely skip: the input can be turned off on a chart that already installed
      //--- offsets this session, and a stale adjustment would keep biasing the gradient silently.
      Net.ClearLogitAdjustment();
      return;
     }
   //--- Priors not measured yet (era 0 before the first tally, or a model with no .stats): leave the
   //--- gradient unadjusted rather than guessing a distribution. The next era installs them.
   //--- THIS USED TO BE SILENT, and that silence hid a whole-run failure: while the auto-tune search ran,
   //--- UpdateClassPriors() was skipped in eval mode, so this branch was taken on EVERY era and the
   //--- imbalance correction never once ran - with nothing in the log to say so. A mechanism that
   //--- declines to act must announce it; the alternative is indistinguishable from working. Third time
   //--- this codebase has been bitten by a quiet no-op, so it now warns every time it is not merely the
   //--- expected era-0 case.
   if(m_priorBuy <= 0.0 || m_priorSell <= 0.0 || m_priorNeutral <= 0.0)
     {
      if(m_eraCount > 0 && !m_logitAdjustSkipWarned)
        {
         m_logitAdjustSkipWarned = true;
         Print(ID + ": WARNING - class-imbalance correction is NOT running at era " +
               IntegerToString(m_eraCount) + ": the class priors have never been measured (Buy " +
               DoubleToString(m_priorBuy, 4) + " Sell " + DoubleToString(m_priorSell, 4) + " Neutral " +
               DoubleToString(m_priorNeutral, 4) + "). Training is falling back to plain cross-entropy, "
               "which on a skewed label set collapses to the majority class.");
        }
      Net.ClearLogitAdjustment();
      return;
     }
   //--- Effective tau, capped so the offsets cannot swamp the head's usable logit range - see
   //--- LOGIT_ADJUST_MAX_RANGE_FRACTION. The binding quantity is the SPREAD between the largest and
   //--- smallest offset, not their absolute size: softmax is shift-invariant, so a constant added to
   //--- all three classes changes nothing and only their differences move the decision.
   double lb = MathLog(m_priorBuy), ls = MathLog(m_priorSell), lnn = MathLog(m_priorNeutral);
   double spread = MathMax(lb, MathMax(ls, lnn)) - MathMin(lb, MathMin(ls, lnn));
   double tauEff = m_logitAdjustTau;
   if(spread > 0.0)
     {
      double cap = LOGIT_ADJUST_MAX_RANGE_FRACTION * CLASS_LOGIT_SCALE / spread;
      if(tauEff > cap)
         tauEff = cap;
     }
   if(!m_logitAdjustLogged)
     {
      m_logitAdjustLogged = true;
      Print(ID + ": logit adjustment - measured priors Buy " + DoubleToString(m_priorBuy * 100.0, 2) +
            "% Sell " + DoubleToString(m_priorSell * 100.0, 2) + "% Neutral " +
            DoubleToString(m_priorNeutral * 100.0, 2) + "% | log-prior spread " +
            DoubleToString(spread, 2) + " against a logit range of " +
            DoubleToString(CLASS_LOGIT_SCALE, 1) + " | tau " + DoubleToString(m_logitAdjustTau, 2) +
            (tauEff < m_logitAdjustTau
             ? " CAPPED to " + DoubleToString(tauEff, 2) + " (uncapped it would consume " +
               DoubleToString(100.0 * spread * m_logitAdjustTau / CLASS_LOGIT_SCALE, 0) +
               "% of the range and saturate the head)"
             : " (uncapped - within budget)"));
     }
   //--- ORDERED to match the output layer: [0]=Buy, [1]=Sell, [2]=Neutral - the order
   //--- BuildFreshTopology emits and the order the softmax gradient reads (AI\Network.mqh).
   double offsets[3];
   offsets[0] = tauEff * lb;
   offsets[1] = tauEff * ls;
   offsets[2] = tauEff * lnn;
   Net.SetLogitAdjustment(offsets);
  }
//+------------------------------------------------------------------+
//| Converts a double to ENUM_SIGNAL.                                 |
//| 3-output (softmax classification) case: dPrevSignal's *sign*      |
//| alone already encodes the argmax-selected class (+prob for Buy,   |
//| -prob for Sell, exactly 0.0 for Neutral - see Train()/            |
//| RefreshLatestSignal()), so classification here is pure argmax:    |
//| whichever class the network actually picked, full stop. No        |
//| magnitude threshold is applied - confidence magnitude is a         |
//| separate concern, already exposed via AIConfidence()/              |
//| SignedAIConfidence() (MathAbs(dPrevSignal)/dPrevSignal) for the    |
//| signal engine's own confidence-weighted filters/lot sizing/SLTP,   |
//| so this keeps "which class" and "how confident" decoupled.         |
//| 1-output (tanh regression) case: unrelated network shape, keeps    |
//| the original 0.50 magnitude cutoff as a genuine confidence gate.   |
//+------------------------------------------------------------------+
ENUM_SIGNAL CExpertSignalAIBase::DoubleToSignal(double value)
  {
   value = NormalizeDouble(value, 2); // Round 'value' to two decimal places
   if(value < -1.0 || value > 1.0)
      return Undefine; // out of range, e.g. the -2 "not yet studied" sentinel
   if(m_outputNeuronsCount == 3)
     {
      if(value > 0.0)
         return Buy;
      if(value < 0.0)
         return Sell;
      return Neutral;
     }
   if(value > 0.50)
      return Buy;
   if(value < -0.50)
      return Sell;
   return Neutral;
  }
#endif // WARRIOR_AIBASE_INFERENCE_MQH