feat(ml): egreedy-v2 shadow policy — D=12 with profile features (#99)

Ship the scaffolding for #99 (phase B.3 of #81):

- ml/serving: add /score/egreedy/v2, /reward/egreedy/v2, /stats/egreedy/v2
  endpoints (D=12). New feature dims: completion/dismiss rates, mean dwell
  (clipped 10min), preferred-hour alignment (cosine, 1-dim), tip volume (log).
  Separate state file per user (_egreedy_v2.json). /reset clears v2 state too.
- ADR-0012: documents D=7→12 dimension change, normalization choices, shadow
  rollout protocol, and promotion gate (offline sim win per ADR-0002).
- recommender.ts: register egreedy-v2-shadow in shadow-policy map (disabled by
  default). When enabled, calls /score/egreedy/v2 fire-and-forget and publishes
  shadow:egreedy-v2-shadow serve signal. No reward to shadow — sim is the gate.
- sim runner/personas: personas carry synthetic profile_features per persona;
  _call_score/_call_reward thread profile_features through (None-safe for v1/linucb).
- 18 new Python tests; all 56 Python + 170 TS tests pass.

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

ml/experiments/sim/runner.py

@@ -43,19 +43,22 @@ from task_generator import generate_task_pool
 POLICY_SCORE_ENDPOINTS: dict[str, str] = {
     "linucb-v1": "/score",
     "egreedy-v1": "/score/egreedy",
+    "egreedy-v2": "/score/egreedy/v2",
 }
 POLICY_REWARD_ENDPOINTS: dict[str, str] = {
     "linucb-v1": "/reward",
     "egreedy-v1": "/reward/egreedy",
+    "egreedy-v2": "/reward/egreedy/v2",
 }
 
 
 def _call_score(
     client: httpx.Client, ml_url: str, policy: str,
     user_id: str, tasks: list[dict], hour: int, dow: int,
+    profile_features: dict | None = None,
 ) -> dict | None:
     endpoint = POLICY_SCORE_ENDPOINTS.get(policy, "/score")
-    body = {
+    body: dict = {
         "user_id": user_id,
         "candidates": [
             {
@@ -72,6 +75,8 @@ def _call_score(
         ],
         "context": {"hour_of_day": hour, "day_of_week": dow},
     }
+    if profile_features is not None:
+        body["profile_features"] = profile_features
     try:
         r = client.post(f"{ml_url}{endpoint}", json=body, timeout=5.0)
         r.raise_for_status()
@@ -85,15 +90,17 @@ def _call_reward(
     client: httpx.Client, ml_url: str, policy: str,
     user_id: str, tip_id: str, reward: float, features: dict,
     day_of_week: int = 0,
+    profile_features: dict | None = None,
 ) -> None:
     endpoint = POLICY_REWARD_ENDPOINTS.get(policy, "/reward")
+    body: dict = {
+        "user_id": user_id, "tip_id": tip_id, "reward": reward,
+        "features": features, "day_of_week": day_of_week,
+    }
+    if profile_features is not None:
+        body["profile_features"] = profile_features
     try:
-        client.post(
-            f"{ml_url}{endpoint}",
-            json={"user_id": user_id, "tip_id": tip_id, "reward": reward,
-                  "features": features, "day_of_week": day_of_week},
-            timeout=5.0,
-        )
+        client.post(f"{ml_url}{endpoint}", json=body, timeout=5.0)
     except Exception as e:
         print(f"  [warn] reward {policy}: {e}", file=sys.stderr)
 
@@ -133,9 +140,13 @@ def run_simulation(
                 seed_tasks = rnd * 997 + abs(hash(user_id)) % 997
                 tasks = generate_task_pool(n=tasks_per_round, seed=seed_tasks)
 
+                # Per-persona profile features for v2 (synthetic for sim — see ADR-0012)
+                profile = persona.profile_features(hour) if hasattr(persona, "profile_features") else None
+
                 for policy in policies:
                     p_user = f"{user_id}-{policy}"
-                    scored = _call_score(client, ml_url, policy, p_user, tasks, hour, dow)
+                    scored = _call_score(client, ml_url, policy, p_user, tasks, hour, dow,
+                                         profile_features=profile)
                     if not scored:
                         continue
                     tip_id = scored.get("tip_id")
@@ -149,7 +160,7 @@ def run_simulation(
                         "is_overdue": tip["features"]["is_overdue"],
                         "task_age_days": tip["features"]["task_age_days"],
                         "priority": tip["features"]["priority"],
-                    }, day_of_week=dow)
+                    }, day_of_week=dow, profile_features=profile)
 
                     acc[policy]["total_reward"] += reward
                     acc[policy]["n_pulls"] += 1
@@ -208,9 +219,12 @@ def run_score_phase(
                 seed_tasks = rnd * 997 + abs(hash(user_id)) % 997
                 tasks = generate_task_pool(n=tasks_per_round, seed=seed_tasks)
 
+                profile = persona.profile_features(hour) if hasattr(persona, "profile_features") else None
+
                 for policy in policies:
                     p_user = f"{user_id}-{policy}"
-                    scored = _call_score(client, ml_url, policy, p_user, tasks, hour, dow)
+                    scored = _call_score(client, ml_url, policy, p_user, tasks, hour, dow,
+                                         profile_features=profile)
                     if not scored:
                         continue
                     tip_id = scored.get("tip_id")
@@ -229,6 +243,7 @@ def run_score_phase(
                         "tip_features": tip["features"],
                         "tip_content": tip["content"],
                         "ml_score": scored.get("score"),
+                        "profile_features": profile,
                     })
 
                     judgment_requests.append({
@@ -368,6 +383,7 @@ def run_reward_phase(plan_path: str, out_path: str, ml_url: str) -> dict:
                     session["tip_id"], reward,
                     {"hour_of_day": rnd_data["hour"], **session["tip_features"]},
                     day_of_week=rnd_data["dow"],
+                    profile_features=session.get("profile_features"),
                 )
 
                 p = session["policy"]