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.

devflow/projects/2026-07-28-rag-quality-score-unify/evidence.md

@@ -0,0 +1,25 @@
+# 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` / `RetrievalScoreNormalizer`
+- `MilvusHybridKnowledgeStore`（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