docs: record fully green retrieval harness

docs/current-state.md

@@ -1,10 +1,10 @@
 # AtoCore - Current State (2026-04-25)
 
-Update 2026-04-25: project-id chunk/vector metadata is deployed and backfilled.
-Live Dalidou is on `a87d984`; `/health` is ok with 33,253 vectors and sources
-ready. Live retrieval harness is 19/20 with 0 blocking failures and 1 known
-content gap (`p04-constraints` missing `Zerodur` / `1.2`). Full local suite:
-571 passed.
+Update 2026-04-25: project-id chunk/vector metadata is deployed and backfilled,
+and the final p04 Trusted Project State budget/ranking gap is closed. Live
+Dalidou is on `d3de9f6`; `/health` is ok with 33,253 vectors and sources
+ready. Live retrieval harness is 20/20 with 0 blocking failures and 0 known
+issues. Full local suite: 572 passed.
 
 The project-id backfill was applied per populated project after a
 Chroma-inclusive backup at
@@ -76,10 +76,10 @@ Last nightly run (2026-04-19 03:00 UTC): **31 promoted · 39 rejected · 0 needs
 | 7G | Re-extraction on prompt version bump | pending |
 | 7H | Chroma vector hygiene (delete vectors for superseded memories) | pending |
 
-## Known gaps (honest, refreshed 2026-04-24)
+## Known gaps (honest, refreshed 2026-04-25)
 
 1. **Capture surface is Claude-Code-and-OpenClaw only.** Conversations in Claude Desktop, Claude.ai web, phone, or any other LLM UI are NOT captured. Example: the rotovap/mushroom chat yesterday never reached AtoCore because no hook fired. See Q4 below.
 2. **Project-scoped retrieval guard is deployed and passing.** Explicit `project_id` chunk/vector metadata is now present in SQLite and Chroma for the 33,253-vector corpus. Retrieval prefers exact metadata ownership and keeps path/tag matching as a legacy fallback.
 3. **Human interface is useful but not yet the V1 Human Mirror.** Wiki/dashboard pages exist, but the spec routes, deterministic mirror files, disputed markers, and curated annotations remain V1-D work.
-4. **Harness known issue:** `p04-constraints` wants "Zerodur" and "1.2"; live retrieval surfaces related constraints but not those exact strings. Treat as content/state gap until fixed.
+4. **Harness is currently green.** The former `p04-constraints` known issue is closed; query-relevant Trusted Project State entries now rank before state-budget truncation.
 5. **Formal docs lag the ledger during fast work.** Use `DEV-LEDGER.md` and `python scripts/live_status.py` for live truth, then copy verified claims into these docs.

docs/master-plan-status.md

@@ -133,7 +133,7 @@ deferred from the shared client until their workflows are exercised.
 
 ## What Is Real Today (updated 2026-04-25)
 
-- canonical AtoCore runtime on Dalidou (`a87d984`, deploy.sh verified)
+- canonical AtoCore runtime on Dalidou (`d3de9f6`, deploy.sh verified)
 - 33,253 vectors across 6 registered projects, with explicit `project_id`
   metadata backfilled into SQLite and Chroma after snapshot
   `/srv/storage/atocore/backups/snapshots/20260424T154358Z`
@@ -154,10 +154,10 @@ deferred from the shared client until their workflows are exercised.
 - query-relevance memory ranking with overlap-density scoring and widened
   query-time candidate pools so older exact-intent project memories can rank
   ahead of generic high-confidence notes
-- retrieval eval harness: 20 fixtures; current live has 19 pass, 1 known
-  content gap, and 0 blocking failures after the project-id backfill and
-  memory-ranking stabilization deploy
-- 571 tests passing on `main`
+- query-relevance Trusted Project State ranking before state-budget truncation
+- retrieval eval harness: 20 fixtures; current live has 20 pass, 0 known
+  issues, and 0 blocking failures
+- 572 tests passing on `main`
 - 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
@@ -178,10 +178,7 @@ These are the current practical priorities.
    Target: 100+ active memories.
 3. **Multi-model triage** (Phase 11 entry) — switch auto-triage to a
    different model than the extractor for independent validation
-4. **Fix p04-constraints harness failure** — retrieval doesn't surface
-   "Zerodur" for p04 constraint queries. Investigate if it's a missing
-   memory or retrieval ranking issue.
-5. **Fix Dalidou Git credentials** — the host checkout can fetch but cannot
+4. **Fix Dalidou Git credentials** — the host checkout can fetch but cannot
    push to Gitea over HTTP in non-interactive SSH sessions. Prefer switching
    the deploy checkout to a Gitea SSH key; PAT-backed `credential.helper store`
    is the fallback.