ATOCore/docs/current-state.md

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.

The project-id backfill was applied per populated project after a Chroma-inclusive backup at /srv/storage/atocore/backups/snapshots/20260424T154358Z. The immediate post-apply dry-run reported 33,253 already tagged, 0 updates, 0 missing, and 0 malformed. A later repeat dry-run after the code-only ranking deploy was aborted because the one-off container ran too long; the earlier post-apply idempotency result remains the migration acceptance record.

V1-0 landed 2026-04-22

Engineering V1 completion track has started. V1-0 write-time invariants merged and deployed: F-1 shared-header fields (extractor_version, canonical_home, hand_authored) added to entities, F-8 provenance enforcement at both create_entity and promote_entity, F-5 synchronous conflict-detection hook on every active-entity write path (create, promote, supersede) with Q-3 fail-open. Prod backfill ran cleanly — 31 legacy active/superseded entities flagged hand_authored=1, follow-up dry-run returned 0 remaining rows. Test count 533 → 547 (+14).

R14 is closed: POST /entities/{id}/promote now translates the new caller-fixable V1-0 ValueError into HTTP 400.

Next in the V1 track: V1-A (minimal query slice + Q-6 killer-correctness integration). Gated on pipeline soak (~2026-04-26) + 100+ active memory density target. See docs/plans/engineering-v1-completion-plan.md for the full 7-phase roadmap and docs/plans/v1-resume-state.md for the "you are here" map.

---

Snapshot from previous update (2026-04-19)

The numbers

	count
Active memories	266 (180 project, 31 preference, 24 knowledge, 17 adaptation, 11 episodic, 3 identity)
Candidates pending	0 (autonomous triage drained the queue)
Interactions captured	605 (250 claude-code, 351 openclaw)
Entities (typed graph)	50
Vectors in Chroma	33K+
Projects	6 registered (p04, p05, p06, abb-space, atomizer-v2, atocore) + apm emerging (2 memories, below auto-register threshold)
Unique domain tags	210
Tests	440 passing

Autonomous pipeline — what runs without me

When	Job	Does
every hour	hourly-extract.sh	Pulls new interactions → LLM extraction → 3-tier auto-triage (sonnet → opus → discard/human). 0 pending candidates right now = autonomy is working.
every 2 min	dedup-watcher.sh	Services UI-triggered dedup scans
daily 03:00 UTC	Full nightly (batch-extract.sh)	Extract · triage · auto-promote reinforced · synthesis · harness · dedup (0.90) · emerging detector · transient→durable · confidence decay (7D) · integrity check · alerts
Sundays	+Weekly deep pass	Knowledge-base lint · dedup @ 0.85 · tag canonicalization (7C)

Last nightly run (2026-04-19 03:00 UTC): 31 promoted · 39 rejected · 0 needs human. That's the brain self-organizing.

Phase 7 — Memory Consolidation status

Subphase	What	Status
7A	Semantic dedup + merge lifecycle	live
7A.1	Tiered auto-approve (sonnet ≥0.8 + sim ≥0.92 → merge; opus escalation; human only for ambiguous)	live
7B	Memory-to-memory contradiction detection (0.70–0.88 band, classify duplicate/contradicts/supersedes)	deferred, needs 7A signal
7C	Tag canonicalization (weekly; auto-apply ≥0.8 confidence; protects project tokens)	live (first run: 0 proposals — vocabulary is clean)
7D	Confidence decay (0.97/day on idle unreferenced; auto-supersede below 0.3)	live (first run: 0 decayed — nothing idle+unreferenced yet)
7E	/wiki/memories/{id} detail page	pending
7F	/wiki/domains/{tag} cross-project view	pending (wants 7C + more usage first)
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)

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.
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.