bdb42dba05
Expand active project wave and serialize refreshes
2026-04-06 14:58:14 -04:00
46a5d5887a
Update plan status for organic routing
2026-04-06 14:06:54 -04:00
9943338846
Document organic OpenClaw routing layer
2026-04-06 14:04:49 -04:00
26bfa94c65
Add project-aware boost to raw query
2026-04-06 13:32:33 -04:00
4aa2b696a9
Document next-phase execution plan
2026-04-06 13:10:11 -04:00
af01dd3e70
Add engineering architecture docs
2026-04-06 12:45:28 -04:00
8f74cab0e6
Sync live project registry descriptions
2026-04-06 12:36:15 -04:00
06aa931273
Add project registry update flow
2026-04-06 12:31:24 -04:00
c9757e313a
Harden runtime and add backup foundation
2026-04-06 10:15:00 -04:00
9715fe3143
Add project registration endpoint
2026-04-06 09:52:19 -04:00
1f1e6b5749
Add project registration proposal preview
2026-04-06 09:11:11 -04:00
827dcf2cd1
Add project registration policy and template
2026-04-06 08:46:37 -04:00
d8028f406e
Sync live corpus counts in current state doc
2026-04-06 08:19:42 -04:00
3b8d717bdf
Ship project registry config in image
2026-04-06 08:10:05 -04:00
8293099025
Add project registry refresh foundation
2026-04-06 08:02:13 -04:00
0f95415530
Clarify source staging and refresh model
2026-04-06 07:53:18 -04:00
82c7535d15
Refresh current state and next steps docs
2026-04-06 07:36:33 -04:00
8a94da4bf4
Clarify operating model and project corpus state
2026-04-06 07:25:33 -04:00
5069d5b1b6
Update current state and next steps docs
2026-04-05 19:12:45 -04:00
440fc1d9ba
Document ecosystem state and integration contract
2026-04-05 18:47:40 -04:00
6bfa1fcc37
Add Dalidou storage foundation and deployment prep
2026-04-05 18:33:52 -04:00
b0889b3925
Stabilize core correctness and sync project plan state
2026-04-05 17:53:23 -04:00
b48f0c95ab
feat: Phase 2 Memory Core — structured memory with context integration
...
Memory Core implementation:
- Memory service with 6 types: identity, preference, project, episodic, knowledge, adaptation
- CRUD operations: create (with dedup), get (filtered), update, invalidate, supersede
- Confidence scoring (0.0-1.0) and lifecycle management (active/superseded/invalid)
- Memory API endpoints: POST/GET/PUT/DELETE /memory
Context builder integration (trust precedence per Master Plan):
1. Trusted Project State (highest trust, 20% budget)
2. Identity + Preference memories (10% budget)
3. Retrieved chunks (remaining budget)
Also fixed database.py to use dynamic settings reference for test isolation.
45/45 tests passing.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-05 09:54:52 -04:00
531c560db7
feat: Phase 1 ingestion hardening + Phase 5 Trusted Project State
...
Phase 1 - Ingestion hardening:
- Encoding fallback (UTF-8/UTF-8-sig/Latin-1/CP1252)
- Delete detection: purge DB/vector entries for removed files
- Ingestion stats endpoint (GET /stats)
Phase 5 - Trusted Project State:
- project_state table with categories (status, decision, requirement, contact, milestone, fact, config)
- CRUD API: POST/GET/DELETE /project/state
- Upsert semantics, invalidation (supersede) support
- Context builder integrates project state at highest trust precedence
- Project state gets 20% budget allocation, appears first in context
- Trust precedence: Project State > Retrieved Chunks (per Master Plan)
33/33 tests passing. Validated end-to-end with GigaBIT M1 project data.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-05 09:41:59 -04:00
6081462058
fix: critical bugs and hardening from validation audit
...
- Fix infinite loop in chunker _hard_split when overlap >= max_size
- Fix tag filter false positives by quoting tag values in ChromaDB query
- Fix score boost semantics (additive → multiplicative) to stay within 0-1 range
- Add error handling and type hints to all API routes
- Update README with proper project documentation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-05 09:35:37 -04:00
b4afbbb53a
feat: implement AtoCore Phase 0 + Phase 0.5 (foundation + PoC)
...
Complete implementation of the personal context engine foundation:
- FastAPI server with 5 endpoints (ingest, query, context/build, health, debug)
- SQLite database with 5 tables (documents, chunks, memories, projects, interactions)
- Heading-aware markdown chunker (800 char max, recursive splitting)
- Multilingual embeddings via sentence-transformers (EN/FR)
- ChromaDB vector store with cosine similarity retrieval
- Context builder with project boosting, dedup, and budget enforcement
- CLI scripts for batch ingestion and test prompt evaluation
- 19 unit tests passing, 79% coverage
- Validated on 482 real project files (8383 chunks, 0 errors)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-05 09:21:27 -04:00
32ce409a7b
Initial commit
2026-04-05 12:28:07 +00:00
