alvis/oO
1
0
Fork 0
Code Issues 34 Pull Requests Actions Packages Projects Releases Wiki Activity
49 Commits 1 Branch 0 Tags
9bd60a9835ed0a35f41415b34b4d6bda6d954f55
Commit Graph

6 Commits

Author SHA1 Message Date
alvis
4267e6ac68 feat(ml/serving): inject profile features + sort tasks in tip prompt (#79) 
- prompts.py: sort tasks overdue-first → priority desc → age desc before
  rendering into the LLM prompt (same ordering as ml/features/context.py)
- prompts.py: render User profile summary line (completion_rate, dismiss_rate,
  preferred_hour) when profile_features are present
- main.py: add profile_features field to PromptContext; plumb from
  GenerateRequest into the prompt builder via model_copy
- logging_config.py: drop add_logger_name processor (incompatible with
  PrintLoggerFactory — caused test ordering failures)
- test_generate.py: 6 new tests covering sort order, profile rendering,
  partial fields, empty profile, and end-to-end plumbing through /generate

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-27 13:46:16 +00:00
alvis
377373a95d test(schema): unit tests for schemas.py and nats_consumer._handle (#54) 
17 tests covering: pydantic model validation (all payload types, optional
fields, invalid enum values, missing required fields), _handle write path
for task_synced, validation errors surfaced through _make_handler causing
nak instead of ack.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-25 16:51:15 +00:00
alvis
2d7cf217a9 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>
 2026-04-25 10:00:38 +00:00
alvis
430804e9a5 feat(ml): prompt registry + per-request variant selection 
Replaces the hardcoded "v1" label with a real prompt registry:

  ml/serving/prompts.py       — keyed by version: v1 (baseline),
                                v2-mentor (calm/specific persona),
                                v3-few-shot (v1 persona + curated examples)
  ml/serving/main.py          — POST /generate accepts optional prompt_version,
                                422 on unknown, echoes the version actually used
                                back in the response
  services/api/src/config.ts  — TIP_PROMPT_VERSION: empty / single / comma-list
                                (uniform random per request)
  services/api/src/routes/recommender.ts
                              — pickPromptVersion() drives selection; the
                                response's prompt_version (not a stale TS
                                constant) is what lands in tip_scores so the
                                #92 reward-analytics dashboard shows real
                                per-variant reaction rates

Closes #84.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-04-24 15:44:04 +00:00
alvis
ffdf70733f feat: M2 AI tips — LiteLLM gateway, context assembler, end-to-end generation pipeline 
Issues closed: #86, #87, #88, #89, #90, #91, #79, #80, #82

infra:
- docker-compose `ai` profile: Ollama + LiteLLM services
- infra/litellm/litellm_config.yaml: tip-generator / embedder / judge aliases
- .env.example: LITELLM_URL, LITELLM_MASTER_KEY, OLLAMA_URL

ml/serving:
- POST /generate: calls LiteLLM tip-generator alias, returns TipCandidate[]
- JSON retry loop (2 retries with correction prompt on malformed response)
- _parse_llm_json strips markdown fences

ml/features:
- context.py: build_context() assembles user signals → PromptContext
  (sorts overdue/high-priority tasks first for LLM prompt quality)

shared-types:
- TipKind, TipSource, TipCandidate types
- Tip gains kind + rationale fields

services/api:
- recommender: 3-stage pipeline (assemble → score → serve)
  Stage 1: Todoist tasks + LLM candidates fetched in parallel
  Stage 2: egreedy bandit scores merged candidate pool
  Stage 3: serve + log with prompt_version, llm_model, tip_kind
- tip_scores: prompt_version, llm_model, tip_kind columns + migrations
- config: LITELLM_URL added
- integrations: surface token_status in /integrations response

tests:
- ml/serving/tests/test_generate.py: 13 tests (retry, 502/503, fence variants)
- ml/features/test_context.py: 9 tests (sorting, edge cases)
- services/api recommender.unit.test.ts: 16 pure-function tests (inferReward, dueAgeDays)
- services/api recommender.test.ts: 4 integration tests (tip_scores columns, LLM fallback)
- shared-types: TipCandidate, rationale, full TipFeedback action set

docs:
- ADR-0008: LiteLLM AI gateway decision
- overview.md: M2 pipeline description updated
- ml/README.md: serving + features roles updated

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-17 14:09:02 +00:00
alvis
faf44c18fc feat: ε-greedy v1 as active policy; dwell-time reward inference; offline sim framework 
- Promote egreedy-v1 to active serving policy (ADR-0007): /score/egreedy + /reward/egreedy
  replaces linucb-v1 endpoints after offline sim shows +10.7% mean reward (−0.548 vs −0.606)
- Replace explicit helpful/not_helpful feedback with dwell-time inferred reward (inferReward):
  dismiss=−1.0, snooze=+0.1, done<15s=−0.3, done 15s–2min=+1.0, done 2–10min=+0.6, done>10min=+0.3
- Add ml/serving ε-greedy endpoints: /score/egreedy, /reward/egreedy, /stats/egreedy/{user_id}
  with d=7 feature vector (base 5 + sin/cos day-of-week encoding)
- Add offline simulation framework (ml/experiments/sim): rule/LLM/claude-code judges,
  two-phase score+reward, synthetic personas, task generator; results stored in sim_runs/sim_events
- Add /admin/simulations page: start runs, live-poll status, reward curve SVG, action/persona tables
- Fix egreedy day_of_week training skew: reward endpoint now uses actual dow instead of hardcoded 0
- Fix runner.py proxy bypass: httpx.Client(trust_env=False) for localhost ML calls
- Add dwellMs to TipFeedbackEvent contract and bus.test.ts fixture
- Schema: sim_runs, sim_events tables; tip_feedback gains dwell_ms, reward_milli columns
- ADR-0006: admin console framework; ADR-0007: egreedy-v1 policy selection rationale

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-16 07:44:37 +00:00