EUR M5: commit best-found config after realism re-tune — no validated edge

12mo grid campaign (2025-07-08 → 2026-07-08, 1-pip round-trip cost,
train/val split at 2026-01-08). Donor config scored -6.7R/34 trades.
Findings: transitioning regime -27R/88 wide-open; A-grade entries lose
(-26R) while B-grade wins; Fridays -17R; hours 8/12/13/18/19 UTC bleed;
score 30-35 band holds the train-half losses; trailing (0.45R arm/0.5R
dist) beats static TP1 and gold's 0.6/0.75.

Best-found config: -1.06R / 53 trades / PF 0.93 / 62.3% WR — breakeven,
FAILS acceptance (positive both halves, PF>=1.3). Per plan, EUR ships
functional but stays out of default scan_pairs. Grid results and
methodology documented in the module docstring; full numbers in
backtest/cache/eurv2_*.csv.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

pair_signals/eurusd.py

@@ -1,9 +1,24 @@
 """EUR/USD signal producer config.
 
-Ported from feature/eurusd-support. All tuned values here are a
-pre-realism baseline (tuned before spread charging and next-open fills)
-and are re-tuned against the realistic backtester at 1-pip round-trip
-cost — see EurUsdStrategyConfig in config.py.
+Re-tuned 2026-07-10 against the realistic backtester (1-pip round-trip
+cost, next-open fills, raw-path resolution) on 2025-07-08 → 2026-07-08
+M5 with M15/H1 confirmations. RESULT: no configuration passed the
+acceptance rule (positive in BOTH train and val halves, PF >= 1.3).
+
+The M5 defaults below are the best found — roughly breakeven
+(-1.1R / 53 trades / PF 0.93 / 62% WR on 12mo) versus the donor
+branch's -6.7R. Findings that shaped them:
+  - transitioning regime bled -27R/88 trades wide-open → blocked
+  - A-grade entries LOSE (-26R) while B-grade wins — max conviction
+    fires at move extremes (same pathology as gold M5)
+  - Fridays (-17R) and hours 8, 12, 13, 18, 19 UTC negative
+  - score 30-35 band is where the train-half losses live → floor 35
+  - trailing exits beat static TP1 (arm 0.45R / dist 0.5R best)
+
+EUR/USD therefore ships FUNCTIONAL BUT OFF by default: it is not in
+PlatformConfig.scan_pairs. Scan it on demand (main.py --pair EURUSD,
+or add to scan_pairs) but do not treat M5 signals as having a
+validated edge. M15 tuning is a future session.
 """
 
 from typing import Optional, List
@@ -89,11 +104,17 @@ def make_config(
         config.eur_strategy.sl_atr_floor = 0.7
         config.eur_strategy.sl_atr_multiplier = 0.3
         config.eur_strategy.min_quality_grades = ["A+", "A", "B"]
+        # Best-found 2026-07-10 (breakeven, see module docstring):
         config.eur_strategy.min_entry_score = 35.0
-        config.eur_strategy.min_entry_confidence = 50.0
-        config.eur_strategy.blocked_vol_regimes = ["high"]
-        config.eur_strategy.min_indicator_agreement = 6
-        config.backtest.blocked_hours_utc = [22, 23, 0, 1, 2, 3, 4, 6, 9, 11, 19, 21]
+        config.eur_strategy.min_entry_confidence = 45.0
+        config.eur_strategy.blocked_vol_regimes = []
+        config.eur_strategy.min_indicator_agreement = 0
+        config.eur_strategy.allowed_weekdays = [0, 1, 2, 3]  # Fridays bled -17R
+        config.backtest.allowed_weekdays = [0, 1, 2, 3]
+        config.backtest.blocked_hours_utc = [22, 23, 0, 1, 2, 3, 8, 12, 13, 18, 19]
+        # Trailing exit beat static TP1; earlier/tighter than gold's 0.6/0.75.
+        config.signals.trail_arm_r = 0.45
+        config.signals.trail_dist_r = 0.5
     else:
         config.technical.regime_weights_override = EUR_REGIME_WEIGHTS