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>
This commit is contained in:
2026-04-25 10:00:38 +00:00
parent b8113d4bda
commit 2d7cf217a9
6 changed files with 629 additions and 20 deletions

View File

@@ -6,7 +6,15 @@ import math
import pytest
from httpx import AsyncClient, ASGITransport
from main import app, build_feature_vector
from main import (
app,
build_feature_vector,
build_feature_vector_12,
_norm_dwell,
_norm_preferred_hour,
_norm_rate,
_norm_volume,
)
class TestFeatureVector:
@@ -243,6 +251,176 @@ async def test_stats_for_fresh_user():
assert body["estimated_mean_reward"] == 0.0
class TestV2Normalization:
def test_rate_passthrough(self):
assert _norm_rate(0.0) == 0.0
assert _norm_rate(0.42) == 0.42
assert _norm_rate(1.0) == 1.0
def test_rate_none_zero(self):
assert _norm_rate(None) == 0.0
def test_rate_clipped(self):
assert _norm_rate(1.5) == 1.0
assert _norm_rate(-0.1) == 0.0
def test_dwell_none_zero(self):
assert _norm_dwell(None) == 0.0
def test_dwell_scales_to_0_1(self):
assert _norm_dwell(0) == 0.0
# 600_000 ms (10 min) is the clip ceiling
assert _norm_dwell(600_000) == 1.0
assert _norm_dwell(1_200_000) == 1.0
assert _norm_dwell(60_000) == pytest.approx(0.1)
def test_volume_monotonic_and_clipped(self):
assert _norm_volume(None) == 0.0
assert _norm_volume(0) == 0.0
assert _norm_volume(10) < _norm_volume(100)
# 100 tips ≈ full saturation
assert _norm_volume(100) == pytest.approx(1.0)
assert _norm_volume(10_000) == 1.0
def test_preferred_hour_alignment(self):
# Exact match → 1.0
assert _norm_preferred_hour(9, 9) == pytest.approx(1.0)
# 12h opposite → 0.0
assert _norm_preferred_hour(21, 9) == pytest.approx(0.0, abs=1e-10)
# 6h off → 0.5 (cos(π/2) = 0, scaled to 0.5)
assert _norm_preferred_hour(15, 9) == pytest.approx(0.5, abs=1e-10)
def test_preferred_hour_null_neutral(self):
# Null preference → neutral 0.5 rather than misleading "alignment at 0"
assert _norm_preferred_hour(None, 9) == 0.5
class TestFeatureVector12:
def test_shape(self):
v = build_feature_vector_12(
{"hour_of_day": 9, "is_overdue": True, "task_age_days": 2, "priority": 3},
day_of_week=2,
profile={
"completion_rate_30d": 0.5,
"dismiss_rate_30d": 0.1,
"mean_dwell_ms_30d": 60_000,
"preferred_hour": 9,
"tip_volume_30d": 20,
},
)
assert v.shape == (12,)
def test_first_seven_match_v1(self):
"""v2 must reduce to v1-style features on the first 7 dims so rollout
behaviour is predictable when profile is absent."""
from main import build_feature_vector_7
feat = {"hour_of_day": 14, "is_overdue": True, "task_age_days": 5, "priority": 2}
v1 = build_feature_vector_7(feat, day_of_week=3)
v2 = build_feature_vector_12(feat, day_of_week=3, profile=None)
assert (v1 == v2[:7]).all()
def test_missing_profile_defaults(self):
v = build_feature_vector_12({"hour_of_day": 9}, day_of_week=0, profile=None)
# completion, dismiss, dwell, volume → 0; preferred_hour → 0.5 neutral
assert v[7] == 0.0
assert v[8] == 0.0
assert v[9] == 0.0
assert v[10] == pytest.approx(0.5)
assert v[11] == 0.0
@pytest.mark.asyncio
async def test_score_egreedy_v2_returns_candidate():
payload = {
"user_id": "v2-user",
"candidates": [
{"id": "t:a", "content": "A", "source": "todoist",
"features": {"is_overdue": True, "task_age_days": 2, "priority": 3}},
{"id": "t:b", "content": "B", "source": "todoist",
"features": {"is_overdue": False, "task_age_days": 0, "priority": 1}},
],
"context": {"hour_of_day": 9, "day_of_week": 1},
"profile_features": {
"completion_rate_30d": 0.4,
"dismiss_rate_30d": 0.1,
"mean_dwell_ms_30d": 45_000,
"preferred_hour": 9,
"tip_volume_30d": 8,
},
}
async with AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as client:
r = await client.post("/score/egreedy/v2", json=payload)
assert r.status_code == 200
body = r.json()
assert body["tip_id"] in {"t:a", "t:b"}
assert body["policy"] == "egreedy-v2"
@pytest.mark.asyncio
async def test_score_egreedy_v2_accepts_missing_profile():
payload = {
"user_id": "v2-no-profile",
"candidates": [
{"id": "t:solo", "content": "Solo", "source": "todoist",
"features": {"is_overdue": False, "task_age_days": 0, "priority": 1}},
],
"context": {"hour_of_day": 10, "day_of_week": 0},
}
async with AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as client:
r = await client.post("/score/egreedy/v2", json=payload)
assert r.status_code == 200
assert r.json()["tip_id"] == "t:solo"
@pytest.mark.asyncio
async def test_reward_egreedy_v2_updates_stats():
user_id = "v2-reward-stats"
async with AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as client:
r0 = await client.get(f"/stats/egreedy/v2/{user_id}")
before = r0.json()["cumulative_reward"]
await client.post("/reward/egreedy/v2", json={
"user_id": user_id,
"tip_id": "t:r",
"reward": 1.0,
"features": {"hour_of_day": 9, "is_overdue": True, "task_age_days": 2, "priority": 3},
"day_of_week": 1,
"profile_features": {
"completion_rate_30d": 0.3,
"dismiss_rate_30d": 0.2,
"mean_dwell_ms_30d": 30_000,
"preferred_hour": 9,
"tip_volume_30d": 5,
},
})
r1 = await client.get(f"/stats/egreedy/v2/{user_id}")
body = r1.json()
assert body["cumulative_reward"] == pytest.approx(before + 1.0)
assert body["policy"] == "egreedy-v2"
assert len(body["theta"]) == 12
assert len(body["feature_labels"]) == 12
@pytest.mark.asyncio
async def test_reset_clears_v2_state():
user_id = "v2-reset"
async with AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as client:
await client.post("/score/egreedy/v2", json={
"user_id": user_id,
"candidates": [
{"id": "t:v2r", "content": "x", "source": "todoist",
"features": {"is_overdue": False, "task_age_days": 0, "priority": 1}},
],
"context": {"hour_of_day": 10, "day_of_week": 0},
})
r0 = await client.get(f"/stats/egreedy/v2/{user_id}")
assert r0.json()["pulls"] >= 1
await client.post(f"/reset/{user_id}")
r1 = await client.get(f"/stats/egreedy/v2/{user_id}")
assert r1.json()["pulls"] == 0
@pytest.mark.asyncio
async def test_reward_negative_value():
"""Dismissing a tip should decrease cumulative_reward."""