Relocate RAG and diagnosis decision/E2E writeups from docs/ root into
mvp/engineering so architecture, issues, and engineering narrative stay
together. Update indexes and cross-links; leave docs/learning as legacy.
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.
Add current RAG architecture covering MilvusClientV2 hybrid search,
chunk evidence identity, rebuild ops, and update the MVP architecture
index and system overview links.
Switch default knowledge collection back to biz (drop+recreate on rebuild),
replace PowerShell rebuild runner with Python, skip README.md imports, and
merge duplicate rag keys in application.yml.
Add repairable INVALID_PROGRESS_PROTOCOL observations, independent
PROGRESS_PROTOCOL_VIOLATED saturation, and controlled release paths.
Archive the OpenSpec change after syncing main specs and devflow.
Add confirm-gated rebuild-hybrid endpoint that drops biz_hybrid, clears
api_document and L0, then force-imports knowledge_base markdown into the
dense+BM25 store. Include PowerShell runner and ops README.
Replace legacy MilvusServiceClient knowledge search/write with a single
MilvusClientV2 hybrid store (BM25 function + dense ANN + RRFRanker).
Use collection biz_hybrid and require knowledge reindex.
Preserve same-document multi-chunk evidence with evidenceKey identity,
per-document caps, retrieve-k/return-n split, and a dense KnowledgeSearchPort.
Archives Delivery 1 OpenSpec change as the foundation for hybrid retrieval.
Document the lookup_knowledge flow from L0 hints through L1 retrieval,
post-processing, packing, and Agent projection so the boundaries and
current limitations are easier to follow.
zhuyongxin