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>

agent_panel.py

@@ -126,7 +126,7 @@ VERDICT_SOURCES = ("mean", "macro", "chair")
 #: Logged with every verdict and folded into the payload hash. Bump on
 #: ANY prompt or context-schema change so the scorecard can split eras
 #: (analyze_signal_log splits by panel_prompt_version).
-PANEL_PROMPT_VERSION = "v2-2026-09-17"
+PANEL_PROMPT_VERSION = "v2.1-2026-09-26"   # v2.1: beginner wording rules in _TAKE_CONTRACT
 
 #: Symmetric probability bands (percent). A persona's stance and the
 #: mean verdict are DERIVED from p_win with the same thresholds, so
@@ -216,7 +216,14 @@ Write everything in plain everyday English for someone who has never
 traded: short simple sentences, no trading jargon, no acronyms, no
 abbreviations. Say "profit versus loss", not "RR"; "the 4-hour chart",
 not "H4"; describe what an indicator MEANS ("the price has climbed
-unusually fast"), never its name or number.
+unusually fast"), never its name or number. Never use these words:
+"priced in", "bullish", "bearish", "hawkish", "dovish", "macro",
+"sentiment", "momentum", "volatility", "resistance", "support level",
+"breakout", "pullback", "basis points", "yields". Say instead: "the
+price already moved on that news", "news that is good for gold",
+"news that is bad for gold", "higher interest rates", "the price
+fell fast", "the price bounced". Each sentence must make sense to a
+reader who does not know what gold or interest rates usually do.
 Reply with ONLY JSON:
 {"p_win": <0-100>, "reason_for": "<max 12 words>",
  "reason_against": "<max 12 words>", "note": "<max 15 words>"}
@@ -250,8 +257,8 @@ gold this way"; the payload's gold_influence already did that scoring.
 Example: brief direction SELL, price already fell 5 ATR in 4 hours, every
 bearish headline published before move_started_at, base_rate.win_rate 58
 -> {"p_win": 55, "reason_for": "Recent news still leans against gold.",
-"reason_against": "That news is older than the drop, so it is priced in.",
-"note": "The bad news is already in the price; expect the usual odds."}
+"reason_against": "That news came before the drop; the price already moved on it.",
+"note": "The price already moved on the bad news; expect the usual odds."}
 Example: brief direction BUY, a high-impact release came out 20 minutes
 ago with a surprise the code marked bullish for gold, base_rate.win_rate 60
 -> {"p_win": 68, "reason_for": "A fresh surprise in the data favours gold.",
@@ -1244,11 +1251,19 @@ def run_panel(report: "SignalReport",
     if verdict_source == "macro":
         macro = next((t for t in takes if t.persona == "macro"), None)
         if macro is not None:
+            # The macro persona's own p_win is the verdict's probability
+            # (2026-09-26 signals.db review: every v2 row logged under
+            # verdict_source="macro" had panel_probability NULL — the
+            # verdict carried none, _write_fields wrote 0.0 and the logger
+            # dropped the falsy value — so the 100/300-outcome evaluation
+            # would have had no live probabilities to score).
             return _finish(PanelVerdict(
                 verdict=_STANCE_TO_VERDICT[macro.stance],
                 confidence=macro.confidence, rationale=macro.note[:240],
                 takes=takes, created_ts=time.time(),
-                payload_hash=payload_hash, source="macro"))
+                payload_hash=payload_hash, source="macro",
+                probability=(round(float(macro.p_win), 1)
+                             if macro.p_win is not None else None)))
         # Macro take missing (timed out / invalid) — fall back to the chair.
     # Quorum guards the CHAIR only: it weighs several voices, so one lone
     # take is not worth a synthesizer request. The macro path above needs