Files
MemoryBear/api/app/services
lanceyq d66d601e41 refactor(memory): redesign metadata extraction as async pipeline step
- Replace extract_user_metadata_task with entity-level extract_metadata_batch_task
- Add MetadataExtractionStep following ExtractionStep pattern with Jinja2 prompts
- Flatten MetadataExtractionResponse to 9-field schema (aliases, core_facts, etc.)
- Add Cypher queries for incremental metadata writeback and alias edge redirection
- Wire _extract_metadata into WritePipeline as Step 3.6 (fire-and-forget)
- Add pilot_write() to MemoryService; refactor pilot_run_service to use it
- Extract snapshot logic into WriteSnapshotRecorder
2026-05-08 11:27:51 +08:00
..
2026-03-16 18:00:09 +08:00
2025-12-29 14:51:23 +08:00
2026-01-23 10:50:24 +08:00
2026-01-28 16:07:53 +08:00
2026-03-25 17:54:27 +08:00
2026-03-25 18:06:01 +08:00
2026-03-05 09:55:54 +08:00
2026-03-05 09:55:54 +08:00
2025-12-24 20:35:04 +08:00
2025-12-15 14:09:43 +08:00
2026-03-27 14:36:19 +08:00