chemavx adf2917cda feat(attribution): dominant_feature per trade + /api/metrics/attribution ...

Adds alpha attribution by dominant signal feature — which feat_*_lo had
the largest absolute log-odds value on each trade.

Changes:
- _dominant_feature() helper in api/main.py: picks the winning feature
  from signal_components (threshold 0.0001, same as "triggered" in
  /api/metrics/features)
- _enrich_trade() refactored to single exit point; adds dominant_feature
  field to every open trade in /api/trades
- compute_attribution_from_db() in db.py: VALUES subquery finds dominant
  feature per trade in SQL, then aggregates trade_count/avg_edge_net/
  unrealized_pnl_est/realized_pnl/resolved_count/win_rate per group
- /api/metrics/attribution endpoint: returns attribution dict + total_attributed_trades

No schema changes, no strategy changes. Pure observability.

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

2026-04-22 16:35:24 +00:00

..

__init__.py

feat: initial commit — polymarket-bot source + CI/CD pipeline

2026-04-13 16:05:45 +00:00

db.py

feat(attribution): dominant_feature per trade + /api/metrics/attribution

2026-04-22 16:35:24 +00:00

external.py

feat: initial commit — polymarket-bot source + CI/CD pipeline

2026-04-13 16:05:45 +00:00

manifold.py

fix(critical): complementary market family grouping + Manifold inversion guard

2026-04-17 10:26:29 +00:00

news.py

feat(bot): 5-phase strategy upgrade — edge neto, families, GNews priority, regimes

2026-04-16 15:34:46 +00:00

polymarket.py

fix(polymarket): _PARTY_RE: add Republicans? plural support for symmetry

2026-04-17 10:35:07 +00:00

schema.sql

feat(phase6): per-feature signal attribution in log-odds space

2026-04-22 07:04:53 +00:00