feat(harness,rag): dual LLM audit fields, run conclusion, and hybrid quality

Persist provider reasoning and assistant text separately on agent_reasoning_audit (DeepSeekAssistantMessage path), extract diagnosis_run.conclusion, enrich RAG tool audit (step_id/query/qualityScore), gate empty mysql tools, drop devtools, and align MVP docs after live E2E verification.
2026-07-28 19:43:13 +08:00
parent 2f40536248
commit 7ae9707a3b
116 changed files with 8364 additions and 1141 deletions
@@ -0,0 +1,17 @@
+# Evidence: rag-eval-hybrid-baseline
+
+## Pre-change
+
+- `generate_rag_lookup_snapshots.ps1` passed `-Dretrieval.vector-store.mode=spring`.
+- Fixtures had `caseId/query/retrievedAt/lookupResult` only.
+- Offline eval already supported Hit levels, recall@K, baseline diff.
+
+## User decisions
+
+- Scope: knife-1 only (no dual fixture dirs).
+- Acceptance: wiring required; fixture refresh best-effort (env allowed full refresh).
+
+## Apply-discovered
+
+- After hybrid refresh, `chat-l0-filter-fallback` failed: pure rank→quality made topSimilarity=1.0 on decoy-only filtered hits → no unfiltered retry.
+- Fix: optional `denseDistance` on hybrid hits; quality gate uses L2 when present; sort order remains RRF.