rock 3c301d7e91 fix: enable LLM entity extraction + handle reasoning model output ...

Root causes of zero entity extraction:
1. IngestWorker used WikiLinkFallbackExtractor (wiki links only)
   Fix: Use LlmEntityExtractor when LLM_ENDPOINT is set
2. ExtractedEntity.entity_type vs LLM returning "type"
   Fix: serde alias "type" -> entity_type, default confidence
3. Reasoning models output <think>...</think> before JSON
   Fix: strip_thinking_tags() extracts JSON from response
4. Reflection verification crashes pipeline on parse failure
   Fix: graceful fallback, keep all entities if reflection fails

Tested with reasoning-predictor (qwen2.5:3b) via port-forward.

2026-09-09 17:05:48 +09:00

..

mem-chunk

Implement M3.6.1: DocCorpusSource with heading-boundary chunking (196 tests)

2026-08-23 09:42:09 -07:00

mem-cli

fix: enable LLM entity extraction + handle reasoning model output

2026-09-09 17:05:48 +09:00

mem-core

feat(phase-3.1): agent entity types + metadata structs

2026-09-08 19:53:22 -07:00

mem-ingest

fix: enable LLM entity extraction + handle reasoning model output

2026-09-09 17:05:48 +09:00

mem-llm

fix: default auth to Bearer token (riotpiao gateway uses JWT now)

2026-08-30 18:02:25 -07:00

mem-store

fix: resolve 75 mem-cli compilation errors

2026-09-08 01:11:14 +00:00