feat(recommender): Thompson-sampling bandit over candidate sources (M6)

Nightly Beta(α, β) per user and source from wave impressions (reward:
complete or like, ×0.99 daily decay) stored in user_profiles_rec.bandit;
the wave adds 0.2·(θ − 0.5) per candidate source, sources without data
stay neutral. The user's exploration share now follows how well `fresh`
does against the other sources.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

services/recommender/pipu_rec/wave/store.py

@@ -156,10 +156,11 @@ def load_profile(conn: psycopg.Connection[Any], user_id: str) -> Profile:
         )
     }
     row = conn.execute(
-        "SELECT exploration, taste_cf::text FROM user_profiles_rec WHERE user_id = %s", (user_id,)
+        "SELECT exploration, taste_cf::text, bandit FROM user_profiles_rec WHERE user_id = %s", (user_id,)
     ).fetchone()
     exploration = float(row[0]) if row else 0.15
     taste_cf = parse_vector(row[1]) if row else None
+    bandit = {str(k): [float(x) for x in v] for k, v in (row[2] or {}).items()} if row else {}
     if len(played) < 30:
         exploration = max(exploration, 0.4)  # холодный старт: больше исследования на первых треках
     day = 86400
@@ -173,6 +174,7 @@ def load_profile(conn: psycopg.Connection[Any], user_id: str) -> Profile:
         rediscover={t for t, s in scores.items() if s > 1.5 and now - last.get(t, now) > 60 * day},
         exploration=exploration,
         taste_cf=taste_cf.tolist() if taste_cf is not None else None,
+        bandit=bandit,
         recent_likes=recent_likes,
     )