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/2026-07-27-rag-chunk-evidence-identity-dedup/brief.md

@@ -14,7 +14,7 @@ lookup_knowledge 同文档多 chunk 在后处理与投影阶段被 source 级去
 
 ## 范围
 
-Delivery 1 only（见 `docs/milvus-hybrid-search-integration-checklist.md` §1.1）。
+Delivery 1 only（见 `docs/Milvus-Hybrid接入清单.md` §1.1）。
 
 ## 非目标
 

devflow/projects/2026-07-27-rag-chunk-evidence-identity-dedup/decisions.md

@@ -93,7 +93,7 @@ Reference files:
 - `RagResultProjector.java`
 - `LookupKnowledgeToolTest.java`
 - `RagResultProjectorTest.java`
-- `docs/milvus-hybrid-search-integration-checklist.md`
+- `docs/Milvus-Hybrid接入清单.md`
 
 Stack notes:
 

devflow/projects/2026-07-27-rag-chunk-evidence-identity-dedup/evidence.md

@@ -9,7 +9,7 @@
 ## 规格证据
 
 - 旧 `openspec/specs/rag-knowledge-retrieval` 要求 source 级 dedup（本 change 以 delta 修正）
-- `docs/milvus-hybrid-search-integration-checklist.md` §1.1 定义 Delivery 1 地基
+- `docs/Milvus-Hybrid接入清单.md` §1.1 定义 Delivery 1 地基
 
 ## 验证证据