alvis/oO
1
0
Fork 0
Code Issues 34 Pull Requests Actions Packages Projects Releases Wiki Activity

docs: update CLAUDE.md with rich per-agent inference completions (#112–#116)

Browse Source 
- Inference framework table updated: all agents at v1.2.0 with full param list
- Documents UserHistory.task_completions and AgentInferRequest.task_completions
- Marks #112/114/115/116 complete in recent completions
- Active work updated: #78 closed, #61 and #97/#113 as next priorities

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
alvis
2026-05-06 06:28:30 +00:00
parent 1d9a395591
commit 336644a90a
1 changed files with 12 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
CLAUDE.md
View File

@@ -107,10 +107,11 @@ Recent completions:
- Admin UX refinements: feedback consolidation, settings placement (#100–102) - Admin UX refinements: feedback consolidation, settings placement (#100–102)
- ADR-0012 — ε-greedy v2 (D=12) — 2026-04-26 (now superseded by ADR-0013) - ADR-0012 — ε-greedy v2 (D=12) — 2026-04-26 (now superseded by ADR-0013)
- ADR-0014 complete: unified Profile schema + backfill, manifest plumbing, `/api/profile` read-through, registry-driven eligibility filter, inference framework + per-agent inference, legacy consent column drop — 2026-05-05 - ADR-0014 complete: unified Profile schema + backfill, manifest plumbing, `/api/profile` read-through, registry-driven eligibility filter, inference framework + per-agent inference, legacy consent column drop — 2026-05-05
- Rich per-agent inference for all four active agents (#112, #114, #115, #116) — 2026-05-06: quiet/peak hours (time-of-day), z-score baseline (momentum), p50 lateness + project realness (overdue-task), adaptive lookback + weekly/daily cycles (recent-patterns)
Active work (M2): Active work (M2):
- Signal abstraction for multi-source support (#78)
- Per-user feature freshness SLAs (#61, ADR-0011 phase B) - Per-user feature freshness SLAs (#61, ADR-0011 phase B)
- Embedding-based task clustering for focus-area inference (#97, #113)
## ADR-0014 endpoint map (as of step 6) ## ADR-0014 endpoint map (as of step 6)
@@ -131,15 +132,18 @@ Lives in `ml/agents/inference/`. `run_inference(manifest, history)` evaluates al
- `infer()` error → emit `cold_start_default` (never crashes) - `infer()` error → emit `cold_start_default` (never crashes)
- Results written to `user_preferences` with `source='inferred'`; keys with `source='user'` are never overwritten - Results written to `user_preferences` with `source='inferred'`; keys with `source='user'` are never overwritten
All five agents are at v1.1.0. Per-agent inferred params: All five agents are at v1.2.0. Per-agent inferred params (all live in `ml/agents/<name>.py`):
| Agent | Inferred param | Logic |
|-------|---------------|-------| | Agent | Inferred params | Notes |
| `time-of-day` | `preferred_hour` | Mode done-hour from feedback history | |-------|----------------|-------|
| `momentum` | `engagement_trend` | Done-rate last 7d vs prior 7d | | `time-of-day` | `preferred_hour`, `quiet_start`, `quiet_end`, `peak_hours`, `tz` | Quiet window = longest below-baseline hour run; peak = top-quartile done hours; tz cold-start only (from auth provider) |
| `overdue-task` | `lateness_tolerance_days` | Snooze rate → 0/1/2 days | | `momentum` | `engagement_trend`, `baseline_completions_per_day`, `stdev` | Baseline = 28d rolling mean done/day; snippet uses z-score language |
| `recent-patterns` | `window_days` | Event density → 7/14/30 days | | `overdue-task` | `lateness_tolerance_days`, `project_realness` | Tolerance = p50 lateness from TaskCompletion history; realness = project median vs global median |
| `recent-patterns` | `lookback_days`, `weekly_cycle`, `daily_cycle` | Lookback sized to ≥30 done events; cycles use peak-to-mean ratio; snippet hints when strength > 0.5 |
| `focus-area` | *(none yet)* | Needs project-level feedback linkage (#78) | | `focus-area` | *(none yet)* | Needs project-level feedback linkage (#78) |
`UserHistory` carries both `events: list[FeedbackEvent]` and `task_completions: list[TaskCompletion]`. `AgentInferRequest` (ml/serving) accepts `task_completions: list[dict]` alongside `feedback_history`.
## What NOT to do ## What NOT to do
- Don't copy Todoist's data into our DB. Store the OAuth token + computed features/derivatives we need, fetch raw on demand. - Don't copy Todoist's data into our DB. Store the OAuth token + computed features/derivatives we need, fetch raw on demand.