Quant review 2026-09-26: alert cooldown, plain-language alerts, M15 grade-A SELL block, 1R printed targets, panel/breach fixes

Live signals.db review (2026-09-04 → 09-25, 100 unique setups replayed on the
scans' stored candles): the stop-hunt claim is refuted (71% of stop-outs ran
≥ 1R past the stop, the same as the books' 70–72%); −25.1R of the −37.8R raw
live book were consecutive-bar re-entries the backtester's 5-bar cooldown never
takes; the cooldown view sits at the 3rd–5th percentile of the books' three-week
windows.

Delivery (book-neutral):
- telegram_bot: 5-bar alert cooldown per timeframe (_ALERT_COOLDOWN_BARS =
  backtest.cooldown_bars); setup block prints the trail first as the tested
  exit, TP1/TP2 as guides with their R, "Planned TP1 RR", and one validated-book
  line per setup class (agent_panel_base_rates.json); the informational 100-pip
  TP line is removed (owner request).
- AI block rewritten for a new trader: "AI check: the odds look better than /
  worse than / about usual", the chance "in 100" against the usual odds, one
  reason for and one against, no verdict word or confidence figure; rendered
  whenever the verdict carries a probability. agent_panel: persona prompts ban
  trading jargon (PANEL_PROMPT_VERSION v2.1-2026-09-26); the macro-source
  verdict now carries its persona's p_win (every live v2 row had
  panel_probability NULL). Dashboard and guides mirror the wording.
- telegram_bot: level-breach rescans skip the settlement-pause window (the
  20:45 M15 bar was re-logged at 22:01/22:06/22:11 every evening).

Signal (pre-registered rule-1 campaign, CUDA twin paired with gpu_backtest.py):
- M15 grade-A SELLs blocked (sell_min_quality ["A+","B"], M15 override 6):
  W2 813/+154.15R PF 1.53 vs 931/+146.14R PF 1.43, OOS +68.5 vs +60.67,
  W3 max DD 20.9 vs 19.3R. PASSED a–f.
- Printed target 1 floored at 1R in every generator (signals.tp_print_floor_rr),
  applied AFTER the min-RR and spread gates so no trade changes; mirrored in
  cuda_signal_kernels.py K2. Label-only re-pin of all four timeframes (only
  tp1/rr_planned columns move). A floor applied before the gate cost −24.6R and
  was rejected.
- FAILED: M15 min_rr_ratio 1.0 (trade-identical, −2.0R). Owner's call: M5
  tp_floor_rr 1.0 (+48.9R W2, max DD 10.1 → 15.9R), not shipped.

New pins: M5 W2 e599c8a8…, M15 W2 5b65ecf6…, M15 OOS 09b8a8e7…, H1 W3
a44fd19b…, H4 W3 f3587bae…; twin and reference MD5s equal on every window.
Base-rate table rebuilt from the new pins. Suite 558 passed.

Evidence: backtest/research/rr_and_sell_campaign_2026-09-26.md (plus the
2026-09-18 loss-anatomy and wrong-direction reports it builds on).

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

pair_signals/xauusd.py

@@ -107,6 +107,29 @@ screen's M5 picks (MACD-down) all FAILED the replay, and ema_trend x 2
 / divergence -> 0 on M15 failed too. Canonical M15 book re-pinned to
 backtest/oanda_m15_2yr_065_20260909.csv.
 
+M15 override 6 — grade-A SELLs blocked (validated 2026-09-26,
+backtest/research/rr_and_sell_campaign_2026-09-26.md, pre-registered
+rule, CUDA twin runs paired with gpu_backtest.py MD5s, $0.65):
+sell_min_quality=["A+", "B"] on M15, so gate 6e downgrades every
+grade-A short to D (A+ and B shorts still trade). The bucket was the
+one cycle-2 candidate from the 2026-09-10 screen: M15 grade-A SELLs
+230 / -14.4R on the 3-year window, negative in every 12-month slice
+and in the OOS window. Candidate vs control: 2-year W2 2024-09-05 ->
+2026-09-05 813/+154.15R PF 1.53 DD 15.6R (halves +70.1/+84.0) vs
+931/+146.14R PF 1.43 DD 16.1R (+66.1/+80.0); OOS 2024-06-01 ->
+2025-03-30 313/+68.50R PF 1.67 DD 12.4R vs 355/+60.67R PF 1.49 DD
+17.1R; 3-year W3 2023-09-05 -> 2026-09-05 1105/+195.79R PF 1.49 DD
+20.9R vs 1273/+186.61R PF 1.39 DD 19.3R (+8%, inside the 10% clause),
+better in 2024, 2025 and 2026, -2.4R in the 4 months of 2023; at $0.30
++167.53R vs +161.44R (W2). Trade diff on W2: 162 removed (-8.1R, all
+grade-A SELLs), 44 added (-0.1R, cooldown displacement). Counter-fact
+on record: M15 A-grade shorts paid in the 2021-22 bear phase
+(m15_5yr_cuda_2026-09-18.md), outside the owner's 3-year window.
+Tested and NOT shipped in the same campaign: signals.min_rr_ratio 1.0
+on M15 (trade-identical, -2.0R W2, -2.8R W3: the swing-anchored
+GENERIC stop is not better than the 2 x ATR stop on the same grade-A
+signals); the combination with this block (-0.7R vs the block alone).
+
 M5 override (validated 2026-07-11, full-history replay 2020-03-17 ->
 2026-07-11 + 12mo book, $0.30 spread): block hour 9 UTC (post-London-
 open whipsaw). Hour-9 entries lost -28.9R/143 over 6 years, negative
@@ -305,6 +328,10 @@ def make_config(
         # RSI regime multiplier × 0.5 in every regime on M15 only — see
         # module docstring (M15 override 5, validated 2026-09-09).
         config.technical.regime_weights_override = _m15_regime_weights()
+        # Grade-A SELLs blocked on M15 only (gate 6e downgrades an
+        # actionable-grade short whose grade is not listed) — see module
+        # docstring (M15 override 6, validated 2026-09-26).
+        config.xau_strategy.sell_min_quality = ["A+", "B"]
     if primary_tf == Timeframe.H1:
         # Block every H1 SELL — the SELL quality gate (6e in
         # signal_aggregator.py) downgrades any actionable-grade short