Add backtest pipeline, betting_brain filters, score coherence + social v3

betting_brain.py:
- HARD_MIN_SAMPLES=50 floor for calibrator bypass
- ev_edge < 0 + >= 0.20 hard vetoes
- BTTS muted (grid search found no profitable config)
- Per-market optimal envelopes (MS, OU25)
- Score coherence filter: main_pick must agree with score prediction
- HTFT reversal cross-check for MS picks

feature_builder.py / data_loader.py:
- Real home/away_position from data (was hardcoded 10)
- Cup detection wired into UpsetEngine
- _estimate_league_position with 300-day season filter

New scripts:
- diagnostic_backtest.py: per-bet diagnostic backtest with loss patterns
- optimize_filters.py: grid search per-market optimal thresholds
- analyze_backtest_csv.py: root-cause hypothesis testing on CSV
- compare_backtests.py: side-by-side validation with verdict
- test_score_coherence.py: smoke test for coherence filter (20/20 pass)

Reports:
- diagnostic_backtest_20260525_024437 (50-match smoke)
- diagnostic_backtest_20260525_035649 (1000-match in-sample)
- filter_optimization_patch.json (grid search winners per market)

Social poster v3:
- satori + resvg HTML/CSS rendering pipeline
- Twemoji football/basketball + flag SVGs
- caption SEO: 12 curated hashtags per post
- image SEO: descriptive filenames + .json metadata sidecar
- /health, /preview-png, /run-now endpoints

Docs:
- mds/SESSION_HANDOFF.md: full session state for cross-machine continuity
- mds/SOCIAL_POSTER_SETUP.md: API keys + test commands

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

ai-engine/reports/diagnostic_backtest_20260525_024437.txt

@@ -0,0 +1,71 @@
+==============================================================================
+DIAGNOSTIC BACKTEST REPORT
+==============================================================================
+Generated:      2026-05-25T02:44:37
+Sample window:  start=-3d, end=now
+Max matches:    50
+Excluded days:  ['2026-04-29', '2026-05-03']
+
+OVERALL
+------------------------------------------------------------------------------
+  n_total                  : 50
+  n_playable_settled       : 27
+  wins                     : 15
+  losses                   : 12
+  hit_rate_pct             : 55.56
+  unit_profit              : -0.862
+  staked                   : 5.4
+  roi_pct                  : -15.96
+
+PER MARKET
+------------------------------------------------------------------------------
+  market        n    hit%    profit    roi%
+  OU25         13   53.85      -0.6  -23.08
+  BTTS         12    50.0    -0.392  -16.33
+  MS            2   100.0      0.13    32.5
+
+PER CALIBRATED CONFIDENCE BAND
+------------------------------------------------------------------------------
+  band            n    hit%    roi%
+  55-60           4    50.0  -23.75
+  60-65           1     0.0  -100.0
+  65-70          22   59.09  -10.73
+
+PER ODDS BAND
+------------------------------------------------------------------------------
+  band            n    hit%    roi%
+  1.3-1.5        11   81.82   12.73
+  1.5-1.8        10    50.0   -17.6
+  1.8-2.2         6   16.67  -65.83
+
+LEAGUE vs CUP
+------------------------------------------------------------------------------
+  league   n=  27 hit=55.56% roi=-15.96%
+
+LOSS DIAGNOSTICS
+------------------------------------------------------------------------------
+  total losses:        12
+  total lost units:    -2.4
+  By market:           [('BTTS', 6), ('OU25', 6)]
+  Loss patterns (count, % of losses):
+    high_htft_reversal_prob (>=0.20)                           0 (0.0%)
+    cup_match                                                  0 (0.0%)
+    low_league_reliability (<0.45)                             0 (0.0%)
+    v27_disagree                                               3 (25.0%)
+    trap_market_flagged                                        4 (33.33%)
+    low_calibrated_conf (<55)                                  0 (0.0%)
+    high_odds_underdog (>=2.5)                                 0 (0.0%)
+    low_data_quality (<0.55)                                   0 (0.0%)
+    high_risk_level                                            3 (25.0%)
+    inferred_features                                         12 (100.0%)
+  Top betting_brain issues seen in losses:
+    inferred_statistical_features                           12
+    triple_value_not_confirmed                              12
+    trap_market_market_overpriced                           4
+  Top betting_brain vetoes (in losses — i.e. veto fired but bet still went through value-sniper override):
+
+RECOMMENDATIONS
+------------------------------------------------------------------------------
+  (none surfaced — sample too small or no clear pattern)
+
+==============================================================================