zhuyongxin
7ae9707a3b
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.
1.0 KiB
1.0 KiB
Evidence: rag-quality-score-unify
Code (pre-change)
MilvusHybridKnowledgeStore.searchHybrid：RRF 后并行 dense 回填 L2；BM25-only →bm25_only_no_dense+ maxL2。KnowledgeEvidencePostProcessor：一律normalizeL2(score)+ domain/entity/keyword/source_type 加分，按finalScore降序；PRECISE 需hasHintSupport。
User decisions (grill)
| ID | 结论 |
|---|---|
| Q1 | 一级 label 仅 dense/hybrid；bm25_only 不作正式 label |
| Q2 | 后处理去掉 contains 加分改序，保 originalRank |
| Q3 | 唯一 toQualityScore；后处理统一 |
| Q4 | dense mode 保留作对照 |
| Q7 | 接受 relevance_level / retry 分布变化 |
| Q8 | hybrid quality = 纯 rank 映射 |
Post-change anchors
RetrievalScoreLabels/RetrievalScoreNormalizerMilvusHybridKnowledgeStore（无 L2 overwrite / 无 bm25_only 发射）KnowledgeEvidencePostProcessor（rank sort + explain-only L0 overlap）- OpenSpec delta：
rag-retrieval-quality-score - 架构：
mvp/architecture/RAG知识检索架构.md§6