fix(retrieval): preserve project ids across unscoped ingest

This commit is contained in:
2026-04-24 11:22:13 -04:00
parent c03022d864
commit ce6ffdbb63
12 changed files with 550 additions and 83 deletions

View File

@@ -2,7 +2,7 @@
Update 2026-04-24: audit-improvements deployed as `f44a211`; live harness is
19/20 with 0 blocking failures and 1 known content gap. Active follow-up branch
`codex/project-id-metadata-retrieval` is at 556 passing tests.
`codex/project-id-metadata-retrieval` is at 565 passing tests.
Live deploy: `2b86543` · Dalidou health: ok · Harness: 18/20 with 1 known
content gap and 1 current blocking project-bleed guard · Tests: 553 passing.

View File

@@ -152,7 +152,7 @@ deferred from the shared client until their workflows are exercised.
- query-relevance memory ranking with overlap-density scoring
- retrieval eval harness: 20 fixtures; current live has 19 pass, 1 known
content gap, and 0 blocking failures after the audit-improvements deploy
- 556 tests passing on the active `codex/project-id-metadata-retrieval` branch
- 565 tests passing on the active `codex/project-id-metadata-retrieval` branch
- nightly pipeline: backup → cleanup → rsync → OpenClaw import → vault refresh → extract → triage → **auto-promote/expire** → weekly synth/lint → **retrieval harness****pipeline summary to project state**
- Phase 10 operational: reinforcement-based auto-promotion (ref_count ≥ 3, confidence ≥ 0.7) + stale candidate expiry (14 days unreinforced)
- pipeline health visible in dashboard: interaction totals by client, pipeline last_run, harness results, triage stats