Add backtest scripts to version control

Track gpu_backtest.py, diagnose_filters.py, and instructions.
Data files (CSVs, parquet cache) remain gitignored.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.gitignore

@@ -21,5 +21,7 @@ Thumbs.db
 # Logs
 *.log
 
-# Backtesting (scripts, data, results)
+# Backtesting data (keep scripts, ignore generated files)
-backtest/
+backtest/cache/
+backtest/*.csv
+backtest/__pycache__/

backtest/diagnose_filters.py

@@ -0,0 +1,609 @@
+"""
+ForexBot2 — Filter Rejection Diagnostic
+========================================
+Replays the same backtest loop as gpu_backtest.py but instead of
+collecting trades, counts how many M15 bars are rejected by each
+gate in the signal pipeline.
+
+Produces a summary table showing where potential trades are being
+lost, helping tune filter thresholds.
+
+Usage:
+    python backtest/diagnose_filters.py --pair XAUUSD --days 365
+    python backtest/diagnose_filters.py --pair XAUUSD --days 365 --sample-every 1
+"""
+
+from __future__ import annotations
+
+import argparse
+import logging
+import sys
+import time
+from collections import Counter, defaultdict
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+from typing import Dict, List, Optional, Tuple
+
+import numpy as np
+import pandas as pd
+
+# Ensure project root on sys.path.
+PROJECT_ROOT = Path(__file__).resolve().parent.parent
+if str(PROJECT_ROOT) not in sys.path:
+    sys.path.insert(0, str(PROJECT_ROOT))
+
+from config import (  # noqa: E402
+    PAIR_INFO,
+    PlatformConfig,
+    SignalStrength,
+    Timeframe,
+)
+from signal_aggregator import SignalAggregator, SignalReport  # noqa: E402
+
+# Reuse GPU backtest infrastructure (data loading, indicator pre-compute, etc.)
+from gpu_backtest import (  # noqa: E402
+    BAR_SECONDS,
+    GPUTechnicalEngine,
+    PAIR_ALIASES,
+    BacktestConfig,
+    IndicatorCache,
+    fetch_history,
+    precompute_indicators,
+    _is_xau_blocked_by_calendar,
+)
+from data_provider import ForexDataProvider  # noqa: E402
+
+logger = logging.getLogger("diagnose_filters")
+
+
+# ═════════════════════════════════════════════════════════════════════
+#  OUTCOME CLASSIFICATION
+# ═════════════════════════════════════════════════════════════════════
+
+def classify_bar(
+    report: SignalReport,
+    is_xau: bool,
+) -> Tuple[str, List[str]]:
+    """Classify a bar's outcome and list which filters killed it.
+
+    Returns:
+        (outcome, [filter_names])
+
+    Outcomes:
+        "TRADE"           — quality C+ and trade_setup exists
+        "QUALITY_OK_NO_SETUP" — quality C+ but trade_setup is None
+        "LOW_QUALITY"     — signal reached BUY/SELL but quality D or F
+        "NEUTRAL"         — signal stayed NEUTRAL (score didn't reach +/-30)
+
+    Filter names are extracted from report.warnings.
+    """
+    filters_hit: List[str] = []
+
+    # Scan warnings for known filter tags
+    filter_tags = {
+        "H4 RSI GATE":       "H4_RSI_GATE",
+        "H1 MACD GATE":      "H1_MACD_GATE",
+        "RSI ZONE GATE":     "RSI_ZONE_GATE",
+        "XAU BUY FILTER":    "XAU_BUY_FILTER",
+        "SESSION FILTER":    "SESSION_FILTER",
+        "DAY FILTER":        "DAY_FILTER",
+        "LOW ATR FILTER":    "LOW_ATR_FILTER",
+        "SELL SUPPRESSED":   "SELL_SUPPRESSED",
+        "EXHAUSTION":        "EXHAUSTION_PENALTY",
+        "TREND EXHAUSTION":  "TREND_EXHAUSTION",
+        "NO PULLBACK":       "NO_PULLBACK_PENALTY",
+        "Weak pullback":     "WEAK_PULLBACK_PENALTY",
+        "Extended entry":    "EXTENDED_ENTRY_PENALTY",
+        "Counter-trend":     "COUNTER_TREND_PENALTY",
+        "EXTREME volatility":"EXTREME_VOL_PENALTY",
+        "NEAR EMA200":       "NEAR_EMA200_PENALTY",
+        "FAR FROM EMA200":   "FAR_EMA200_PENALTY",
+        "EVENT RISK":        "EVENT_RISK",
+        "REGIME FILTER":     "REGIME_FILTER",
+        "Timeframes CONFLICT": "MTF_CONFLICT",
+    }
+
+    for w in report.warnings:
+        for tag, name in filter_tags.items():
+            if tag in w:
+                filters_hit.append(name)
+
+    # Determine outcome
+    non_neutral = report.final_signal not in (SignalStrength.NEUTRAL,)
+    quality_ok = report.signal_quality in ("A+", "A", "B", "C")
+
+    if quality_ok and report.trade_setup is not None:
+        return "TRADE", filters_hit
+    elif quality_ok and report.trade_setup is None:
+        return "QUALITY_OK_NO_SETUP", filters_hit
+    elif non_neutral and not quality_ok:
+        return "LOW_QUALITY", filters_hit
+    else:
+        return "NEUTRAL", filters_hit
+
+
+# ═════════════════════════════════════════════════════════════════════
+#  SCORE DISTRIBUTION TRACKER
+# ═════════════════════════════════════════════════════════════════════
+
+class ScoreTracker:
+    """Tracks score/confidence distributions for analysis."""
+
+    def __init__(self):
+        self.scores: List[float] = []
+        self.confidences: List[float] = []
+        self.abs_scores: List[float] = []
+        # How many bars had score in various ranges
+        self.score_bins = Counter()
+        self.conf_bins = Counter()
+        # Track "near miss" bars — score close to thresholds
+        self.near_miss_score: int = 0  # score 20-29 (almost BUY/SELL)
+        self.near_miss_conf: int = 0   # confidence 45-54 (almost passing)
+
+    def record(self, score: float, confidence: float):
+        self.scores.append(score)
+        self.confidences.append(confidence)
+        self.abs_scores.append(abs(score))
+
+        # Score bins
+        a = abs(score)
+        if a < 10:
+            self.score_bins["0-9"] += 1
+        elif a < 20:
+            self.score_bins["10-19"] += 1
+        elif a < 30:
+            self.score_bins["20-29"] += 1
+            self.near_miss_score += 1
+        elif a < 40:
+            self.score_bins["30-39"] += 1
+        elif a < 50:
+            self.score_bins["40-49"] += 1
+        else:
+            self.score_bins["50+"] += 1
+
+        # Confidence bins
+        if confidence < 30:
+            self.conf_bins["0-29"] += 1
+        elif confidence < 45:
+            self.conf_bins["30-44"] += 1
+        elif confidence < 55:
+            self.conf_bins["45-54"] += 1
+            self.near_miss_conf += 1
+        elif confidence < 65:
+            self.conf_bins["55-64"] += 1
+        elif confidence < 75:
+            self.conf_bins["65-74"] += 1
+        else:
+            self.conf_bins["75+"] += 1
+
+
+# ═════════════════════════════════════════════════════════════════════
+#  MAIN DIAGNOSTIC LOOP
+# ═════════════════════════════════════════════════════════════════════
+
+def run_diagnosis(
+    pair: str,
+    start: datetime,
+    end: datetime,
+    sample_every: int = 4,
+    use_cache: bool = True,
+    primary_tf: Timeframe = Timeframe.M15,
+    confirm_tfs: Optional[List[Timeframe]] = None,
+    warmup_bars: int = 250,
+) -> None:
+    if confirm_tfs is None:
+        confirm_tfs = [Timeframe.H1, Timeframe.H4]
+
+    pair_info = PAIR_INFO[pair]
+    display = pair_info["display"]
+    is_xau = display == "XAU/USD"
+
+    platform_cfg = PlatformConfig(
+        symbol=pair,
+        display_name=display,
+        pip_value=pair_info["pip_value"],
+        primary_timeframe=primary_tf,
+        confirmation_timeframes=list(confirm_tfs),
+    )
+
+    provider = ForexDataProvider(platform_cfg)
+
+    # ── Load data ──
+    timeframes = [primary_tf] + list(confirm_tfs)
+    pad_days = max(60, warmup_bars // 4)
+    fetch_start = start - timedelta(days=pad_days)
+
+    dfs_full: Dict[Timeframe, pd.DataFrame] = {}
+    for tf in timeframes:
+        df = fetch_history(
+            provider, pair, tf,
+            start=fetch_start, end=end,
+            use_cache=use_cache,
+        )
+        if df.empty:
+            raise RuntimeError(f"No data for {pair} {tf.value}")
+        dfs_full[tf] = df
+
+    # ── Pre-compute indicators ──
+    t0 = time.perf_counter()
+    caches: Dict[str, IndicatorCache] = {
+        tf.value: precompute_indicators(dfs_full[tf], platform_cfg.technical, gpu_log=True)
+        for tf in timeframes
+    }
+    logger.info(f"Indicator pre-compute: {time.perf_counter() - t0:.2f}s")
+
+    # ── Build aggregator with GPU engine ──
+    aggregator = SignalAggregator(platform_cfg)
+    aggregator.tech_engine = GPUTechnicalEngine(platform_cfg.technical, caches)
+
+    # ── Walk primary TF ──
+    primary_df = dfs_full[primary_tf]
+    bt_start_ts = pd.Timestamp(start)
+    bt_end_ts = pd.Timestamp(end)
+
+    first_eligible = max(
+        warmup_bars,
+        int(primary_df.index.searchsorted(bt_start_ts)),
+    )
+    last_pos = min(
+        int(primary_df.index.searchsorted(bt_end_ts, side="right")),
+        len(primary_df),
+    )
+
+    primary_dur = pd.Timedelta(seconds=BAR_SECONDS[primary_tf])
+
+    # Counters
+    total_bars_in_window = 0
+    total_bars_sampled = 0
+    outcome_counts = Counter()
+    filter_counts = Counter()
+    # Filters that killed bars that were otherwise directional (non-NEUTRAL score)
+    directional_filter_counts = Counter()
+    # Pre-pipeline rejections (XAU calendar filters applied before analyze_from_dataframes)
+    pre_pipeline = Counter()
+
+    # Track signal directions
+    signal_dir_counts = Counter()
+    quality_counts = Counter()
+
+    # Score tracker
+    tracker = ScoreTracker()
+
+    # Track "would-have-been" trades: bars where the primary score was
+    # directional but got killed by a specific filter
+    filter_kill_breakdown = defaultdict(Counter)
+
+    logger.info(
+        f"Diagnosing {display} {primary_tf.value}: "
+        f"bars {first_eligible}-{last_pos} (every {sample_every}th bar)"
+    )
+
+    t_loop = time.perf_counter()
+    for pos in range(first_eligible, last_pos, sample_every):
+        total_bars_in_window += 1
+        ts = primary_df.index[pos]
+        decision_time = ts + primary_dur
+
+        # ── XAU calendar pre-filter (same as gpu_backtest.py) ──
+        if is_xau:
+            block = _is_xau_blocked_by_calendar(ts, platform_cfg)
+            if block:
+                pre_pipeline[block] += 1
+                continue
+
+        total_bars_sampled += 1
+
+        # ── Build sliced dfs (same logic as gpu_backtest.py) ──
+        slice_dfs: Dict[Timeframe, pd.DataFrame] = {}
+        for tf in timeframes:
+            full = dfs_full[tf]
+            bar_dur = pd.Timedelta(seconds=BAR_SECONDS[tf])
+            cutoff = decision_time - bar_dur
+            cut = int(full.index.searchsorted(cutoff, side="right"))
+            if cut == 0:
+                continue
+            slice_dfs[tf] = full.iloc[:cut]
+
+        if primary_tf not in slice_dfs:
+            continue
+
+        # ── Run the full signal pipeline ──
+        report: SignalReport = aggregator.analyze_from_dataframes(
+            symbol=pair,
+            dfs=slice_dfs,
+            context=None,
+            use_news=False,
+        )
+
+        # Record score/confidence
+        tracker.record(report.final_score, report.final_confidence)
+
+        # Signal direction
+        signal_dir_counts[report.final_signal.name] += 1
+        quality_counts[report.signal_quality] += 1
+
+        # Classify
+        outcome, filters_hit = classify_bar(report, is_xau)
+        outcome_counts[outcome] += 1
+
+        for f in filters_hit:
+            filter_counts[f] += 1
+
+        # If the primary score was directional (>= 15 or <= -15), the bar
+        # had some potential — track what killed it
+        if abs(report.primary_score) >= 15:
+            for f in filters_hit:
+                directional_filter_counts[f] += 1
+
+        # For bars that got quality D/F but had a directional signal,
+        # track which filter warnings appeared
+        if outcome in ("LOW_QUALITY", "QUALITY_OK_NO_SETUP"):
+            for f in filters_hit:
+                filter_kill_breakdown[outcome][f] += 1
+
+    elapsed = time.perf_counter() - t_loop
+
+    # ═════════════════════════════════════════════════════════════════
+    #  PRINT RESULTS
+    # ═════════════════════════════════════════════════════════════════
+
+    bar = "=" * 80
+    print(f"\n{bar}")
+    print(f"  FILTER REJECTION DIAGNOSTIC — {display}")
+    print(f"  {start.date()} to {end.date()} | {primary_tf.value} "
+          f"(sampled every {sample_every}th bar)")
+    print(f"{bar}")
+
+    # Scale counts if sampling
+    scale_note = ""
+    if sample_every > 1:
+        scale_note = f"  (sampled {total_bars_sampled} of ~{total_bars_in_window * sample_every} eligible bars)"
+    print(f"\n  Total bars in backtest window: {total_bars_in_window}")
+    if pre_pipeline:
+        for reason, count in sorted(pre_pipeline.items()):
+            print(f"  Pre-pipeline rejection ({reason}): {count}")
+    print(f"  Bars analyzed: {total_bars_sampled}{scale_note}")
+    print(f"  Analysis took: {elapsed:.1f}s "
+          f"({total_bars_sampled / max(elapsed, 0.001):.0f} bars/s)")
+
+    # ── Outcome breakdown ──
+    print(f"\n{'-' * 80}")
+    print("  OUTCOME BREAKDOWN")
+    print(f"{'-' * 80}")
+    outcome_order = ["TRADE", "QUALITY_OK_NO_SETUP", "LOW_QUALITY", "NEUTRAL"]
+    outcome_labels = {
+        "TRADE":               "Actual trades (quality C+ & setup exists)",
+        "QUALITY_OK_NO_SETUP": "Quality C+ but NO trade setup generated",
+        "LOW_QUALITY":         "Directional signal but quality D/F",
+        "NEUTRAL":             "NEUTRAL (score didn't reach +/-30 or conf < 55)",
+    }
+    for o in outcome_order:
+        count = outcome_counts.get(o, 0)
+        pct = count / max(total_bars_sampled, 1) * 100
+        label = outcome_labels.get(o, o)
+        print(f"  {count:6d} ({pct:5.1f}%)  {label}")
+
+    # ── Signal direction breakdown ──
+    print(f"\n{'-' * 80}")
+    print("  SIGNAL DIRECTION BREAKDOWN")
+    print(f"{'-' * 80}")
+    for name in ["STRONG_BUY", "BUY", "NEUTRAL", "SELL", "STRONG_SELL"]:
+        count = signal_dir_counts.get(name, 0)
+        pct = count / max(total_bars_sampled, 1) * 100
+        print(f"  {count:6d} ({pct:5.1f}%)  {name}")
+
+    # ── Quality grade breakdown ──
+    print(f"\n{'-' * 80}")
+    print("  QUALITY GRADE BREAKDOWN")
+    print(f"{'-' * 80}")
+    for grade in ["A+", "A", "B", "C", "D", "F"]:
+        count = quality_counts.get(grade, 0)
+        pct = count / max(total_bars_sampled, 1) * 100
+        print(f"  {count:6d} ({pct:5.1f}%)  Grade {grade}")
+
+    # ── Filter hit counts (all bars) ──
+    print(f"\n{'-' * 80}")
+    print("  FILTER HIT COUNTS (all bars, a bar can hit multiple filters)")
+    print(f"{'-' * 80}")
+    if filter_counts:
+        for name, count in filter_counts.most_common():
+            pct = count / max(total_bars_sampled, 1) * 100
+            print(f"  {count:6d} ({pct:5.1f}%)  {name}")
+    else:
+        print("  (no filters triggered)")
+
+    # ── Filters that killed directional bars (primary_score >= 15) ──
+    print(f"\n{'-' * 80}")
+    print("  FILTERS KILLING DIRECTIONAL BARS (|primary_score| >= 15)")
+    print(f"{'-' * 80}")
+    if directional_filter_counts:
+        for name, count in directional_filter_counts.most_common():
+            print(f"  {count:6d}  {name}")
+    else:
+        print("  (none)")
+
+    # ── Filter breakdown for LOW_QUALITY bars ──
+    if filter_kill_breakdown.get("LOW_QUALITY"):
+        print(f"\n{'-' * 80}")
+        print("  FILTERS ON LOW_QUALITY BARS (had BUY/SELL but quality D/F)")
+        print(f"{'-' * 80}")
+        for name, count in filter_kill_breakdown["LOW_QUALITY"].most_common():
+            print(f"  {count:6d}  {name}")
+
+    # ── Filter breakdown for QUALITY_OK_NO_SETUP bars ──
+    if filter_kill_breakdown.get("QUALITY_OK_NO_SETUP"):
+        print(f"\n{'-' * 80}")
+        print("  FILTERS ON QUALITY_OK_NO_SETUP BARS (quality C+ but no trade setup)")
+        print(f"{'-' * 80}")
+        for name, count in filter_kill_breakdown["QUALITY_OK_NO_SETUP"].most_common():
+            print(f"  {count:6d}  {name}")
+
+    # ── Score distribution ──
+    print(f"\n{'-' * 80}")
+    print("  SCORE DISTRIBUTION (|score|)")
+    print(f"{'-' * 80}")
+    for bin_name in ["0-9", "10-19", "20-29", "30-39", "40-49", "50+"]:
+        count = tracker.score_bins.get(bin_name, 0)
+        pct = count / max(total_bars_sampled, 1) * 100
+        marker = " <-- near miss (almost BUY/SELL)" if bin_name == "20-29" else ""
+        print(f"  {count:6d} ({pct:5.1f}%)  |score| {bin_name}{marker}")
+
+    # ── Confidence distribution ──
+    print(f"\n{'-' * 80}")
+    print("  CONFIDENCE DISTRIBUTION")
+    print(f"{'-' * 80}")
+    for bin_name in ["0-29", "30-44", "45-54", "55-64", "65-74", "75+"]:
+        count = tracker.conf_bins.get(bin_name, 0)
+        pct = count / max(total_bars_sampled, 1) * 100
+        marker = " <-- near miss (almost passing)" if bin_name == "45-54" else ""
+        print(f"  {count:6d} ({pct:5.1f}%)  confidence {bin_name}{marker}")
+
+    # ── Near misses ──
+    print(f"\n{'-' * 80}")
+    print("  NEAR MISSES")
+    print(f"{'-' * 80}")
+    print(f"  {tracker.near_miss_score:6d}  Bars with |score| 20-29 (threshold is 30)")
+    print(f"  {tracker.near_miss_conf:6d}  Bars with confidence 45-54 (threshold is 55)")
+
+    # ── Summary statistics ──
+    if tracker.scores:
+        scores_arr = np.array(tracker.scores)
+        conf_arr = np.array(tracker.confidences)
+        print(f"\n{'-' * 80}")
+        print("  SCORE/CONFIDENCE STATISTICS")
+        print(f"{'-' * 80}")
+        print(f"  Score:      mean={np.mean(scores_arr):+.1f}  "
+              f"median={np.median(scores_arr):+.1f}  "
+              f"std={np.std(scores_arr):.1f}  "
+              f"min={np.min(scores_arr):+.1f}  "
+              f"max={np.max(scores_arr):+.1f}")
+        print(f"  Confidence: mean={np.mean(conf_arr):.1f}  "
+              f"median={np.median(conf_arr):.1f}  "
+              f"std={np.std(conf_arr):.1f}  "
+              f"min={np.min(conf_arr):.1f}  "
+              f"max={np.max(conf_arr):.1f}")
+
+    # ── Blocked hours analysis (for XAU) ──
+    if is_xau:
+        blocked = set(platform_cfg.xau_strategy.blocked_hours_utc)
+        all_hours = set(range(24))
+        open_hours = sorted(all_hours - blocked)
+        print(f"\n{'-' * 80}")
+        print("  XAU HOUR/DAY CONFIG")
+        print(f"{'-' * 80}")
+        print(f"  Blocked hours:  {sorted(blocked)}")
+        print(f"  Open hours:     {open_hours}")
+        print(f"  Allowed days:   {platform_cfg.xau_strategy.allowed_weekdays} "
+              f"(0=Mon..4=Fri)")
+        print(f"  Open fraction:  {len(open_hours)/24:.0%} of hours x "
+              f"{len(platform_cfg.xau_strategy.allowed_weekdays)}/5 weekdays = "
+              f"{len(open_hours)/24 * len(platform_cfg.xau_strategy.allowed_weekdays)/5:.0%} of trading time")
+
+    # ── Interpretation / key takeaways ──
+    print(f"\n{bar}")
+    print("  KEY TAKEAWAYS")
+    print(f"{bar}")
+
+    neutral_pct = outcome_counts.get("NEUTRAL", 0) / max(total_bars_sampled, 1) * 100
+    low_q_pct = outcome_counts.get("LOW_QUALITY", 0) / max(total_bars_sampled, 1) * 100
+    trade_count = outcome_counts.get("TRADE", 0)
+
+    print(f"  - {neutral_pct:.1f}% of bars never reach a directional signal (NEUTRAL)")
+    print(f"  - {low_q_pct:.1f}% of bars get a BUY/SELL but confidence/quality too low")
+    print(f"  - {trade_count} bars produce actual trades")
+
+    if filter_counts:
+        top3 = filter_counts.most_common(3)
+        print(f"  - Top rejection filters:")
+        for name, count in top3:
+            print(f"      {name}: {count} bars hit")
+
+    if tracker.near_miss_score > 50:
+        print(f"  - SIGNIFICANT: {tracker.near_miss_score} bars had |score| 20-29 "
+              f"(lowering threshold from 30 to 25 would capture many)")
+
+    if tracker.near_miss_conf > 50:
+        print(f"  - SIGNIFICANT: {tracker.near_miss_conf} bars had confidence 45-54 "
+              f"(lowering threshold from 55 to 50 would capture many)")
+
+    print(f"\n{bar}\n")
+
+
+# ═════════════════════════════════════════════════════════════════════
+#  CLI
+# ═════════════════════════════════════════════════════════════════════
+
+def _resolve_pair(s: str) -> str:
+    s_up = s.upper().strip()
+    if s_up in PAIR_ALIASES:
+        return PAIR_ALIASES[s_up]
+    if s_up in PAIR_INFO:
+        return s_up
+    raise SystemExit(f"Unknown pair '{s}'. Valid: {', '.join(sorted(PAIR_ALIASES))}")
+
+
+def _resolve_tf(s: str) -> Timeframe:
+    for tf in Timeframe:
+        if tf.value == s:
+            return tf
+    raise SystemExit(f"Unknown timeframe '{s}'")
+
+
+def main(argv: Optional[List[str]] = None) -> int:
+    p = argparse.ArgumentParser(
+        description="Diagnose which filters reject the most bars in the backtest pipeline",
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+    )
+    p.add_argument("--pair", required=True, help="EURUSD | GBPUSD | USDJPY | XAUUSD")
+    p.add_argument("--days", type=int, default=365, help="Days of history")
+    p.add_argument("--start", help="ISO date YYYY-MM-DD (overrides --days)")
+    p.add_argument("--end", help="ISO date YYYY-MM-DD (defaults to today)")
+    p.add_argument("--primary-tf", default="15min", help="Primary TF")
+    p.add_argument("--confirm-tfs", default="1h,4h", help="Comma-separated confirmation TFs")
+    p.add_argument("--warmup-bars", type=int, default=250)
+    p.add_argument("--sample-every", type=int, default=4,
+                   help="Analyze every Nth bar (1=all, 4=25%% sample for speed)")
+    p.add_argument("--no-cache", action="store_true", help="Skip parquet cache")
+    p.add_argument("--log-level", default="INFO")
+    args = p.parse_args(argv)
+
+    logging.basicConfig(
+        level=args.log_level.upper(),
+        format="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
+    )
+
+    pair = _resolve_pair(args.pair)
+    primary_tf = _resolve_tf(args.primary_tf)
+    confirm_tfs = [_resolve_tf(s.strip()) for s in args.confirm_tfs.split(",") if s.strip()]
+
+    end = (
+        datetime.fromisoformat(args.end).replace(tzinfo=timezone.utc)
+        if args.end else datetime.now(timezone.utc)
+    )
+    if args.start:
+        start = datetime.fromisoformat(args.start).replace(tzinfo=timezone.utc)
+    else:
+        start = end - timedelta(days=args.days)
+
+    logger.info(
+        f"Diagnosing {PAIR_INFO[pair]['display']} | "
+        f"Window: {start.date()} -> {end.date()} | "
+        f"Sample: every {args.sample_every}th bar"
+    )
+
+    run_diagnosis(
+        pair=pair,
+        start=start,
+        end=end,
+        sample_every=args.sample_every,
+        use_cache=not args.no_cache,
+        primary_tf=primary_tf,
+        confirm_tfs=confirm_tfs,
+        warmup_bars=args.warmup_bars,
+    )
+
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

backtest/instructions_for_backtest.txt

@@ -0,0 +1,59 @@
+Note down entery and exit Why we took trade?
+What were each indicator signal on that specific time when we took trade
+How many indicators agreed at trade time
+Always backtest using engine.py and signal_aggregator.py
+Dont take trades on weekends and Fridays
+Keep TP small 1.3 Reward ratio
+At the end of test make table of results and print all values you observed.
+Trade context
+
+Time of day and trading session (Asian/London/NY/overlap)
+Day of week (track Mon/Tue/Wed/Thu performance separately)
+Market regime at entry: trending, ranging, or choppy (use ATR or ADX)
+Volatility level (ATR value or ATR percentile vs recent average)
+Pair/instrument traded
+News proximity (high-impact news within 30 min before/after entry)
+
+Trade execution details
+
+Spread at entry in pips
+Slippage on entry and exit (planned vs actual fill)
+Time in trade (minutes/hours from entry to exit)
+Maximum Adverse Excursion (MAE): how far against you it went
+Maximum Favorable Excursion (MFE): how far in profit before pullback
+
+Risk metrics
+
+Max consecutive losses (streak)
+Max consecutive wins (streak)
+Expectancy: (Win% x Avg Win) minus (Loss% x Avg Loss)
+Expectancy per hour in trade
+Recovery factor: Total R divided by Max DD
+
+Indicator/signal analysis
+
+Each indicator's standalone win rate when it agreed with the trade
+Confluence level performance (2 vs 3 vs 4+ indicators agreeing)
+Which indicator disagreed on losing trades (find the "canary")
+
+Decision quality
+
+Rate each setup A/B/C at entry, before knowing outcome
+Verify A-grade setups actually win more often
+Track system trades vs discretionary deviations separately
+
+Process notes
+
+Screenshot or chart snapshot at entry and exit
+Emotional state (calm, FOMO, revenge, tired)
+What would have happened if you held longer or exited sooner
+
+Aggregate analysis at end of backtest
+
+Equity curve, not just total R
+Performance breakdown by session, day, volatility regime
+Win rate over rolling 20-trade windows (check for edge decay)
+
+Critical extra
+"Do not trade" log: setups flagged but skipped, and what happened after
+