zhuyongxin 7ae9707a3b 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

..

specs/rag-eval-offline-baseline

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

2026-07-28 19:43:13 +08:00

.archive-ready

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

2026-07-28 19:43:13 +08:00

.committed

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

2026-07-28 19:43:13 +08:00

.openspec.yaml

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

2026-07-28 19:43:13 +08:00

brief.md

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

2026-07-28 19:43:13 +08:00

decisions.md

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

2026-07-28 19:43:13 +08:00

design.md

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

2026-07-28 19:43:13 +08:00

proposal.md

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

2026-07-28 19:43:13 +08:00

tasks.md

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

2026-07-28 19:43:13 +08:00