{ "run_date": "2026-05-26", "golden_set_version": "v1.0", "spec": "A", "status": "FAIL", "recall_at_5": 0.4545, "hits": 5, "positive_queries": 11, "avg_top1_rerank_hits_only": 0.860, "pass_gate": false, "gate_threshold": 0.7, "results": [ {"id":"q01","query":"gotcha #39 act_runner TCP timeout manual checkout bypass","hit":true,"top1_source":"docs/architecture.md","top1_rerank":0.887,"case":null}, {"id":"q02","query":"gotcha #41 paths-ignore docs-only CI skip path filter","hit":true,"top1_source":"docs/architecture.md","top1_rerank":0.910,"case":null}, {"id":"q03","query":"gotcha #44 silent 403 class-level Authorize policy endpoint","hit":true,"top1_source":"docs/changelog/sessions/2026-05-08-1945-s18-pe-v2-polish-clone-b.md","top1_rerank":0.859,"case":null}, {"id":"q04","query":"gotcha #17 EF migration 3-file rule Designer Snapshot commit","hit":false,"top1_source":"docs/STATUS.md","top1_rerank":0.488,"case":"A","note":"Expected ef-core-migration skill or gotchas.md. STATUS.md matched but rerank < 0.7. Short chunk density issue."}, {"id":"q05","query":"gotcha #25 IIS WebSocket SignalR negotiate module exclusion","hit":false,"top1_source":null,"top1_rerank":null,"case":"C","note":"0 results. Content exists in docs/gotchas.md ### 25 but query uses '#25' notation vs '### 25.' format. Also 'module exclusion' wrong term — actual is 'applicationHost webSocket section lock'."}, {"id":"q06","query":"CQRS MediatR Features.cs Command Validator Handler single file","hit":false,"top1_source":null,"top1_rerank":null,"case":"C","note":"0 results. Content exists in docs/rules.md §2.2 but 'Features.cs' not mentioned, 'single file' vs Vietnamese 'cùng 1 file'. Language + term mismatch."}, {"id":"q07","query":"Smart Friend adversarial reviewer quality ceiling independent","hit":false,"top1_source":null,"top1_rerank":null,"case":"D","note":"0 results. .claude/agents/reviewer.md contains Smart Friend guard but agents/*.md NOT in corpus_paths. Harvest gap — add agents to corpus."}, {"id":"q08","query":"PE V2 ApprovalWorkflow Steps Levels OR-of-N ApproverUserId","hit":true,"top1_source":".claude/agent-memory/investigator/MEMORY.md","top1_rerank":0.824,"case":null}, {"id":"q09","query":"Implementer isolation worktree DROPPED Windows MAX_PATH Dropbox","hit":false,"top1_source":null,"top1_rerank":null,"case":"D","note":"0 results. .claude/agents/implementer.md contains worktree decision but agents/*.md NOT in corpus_paths. Harvest gap — add agents to corpus."}, {"id":"q10","query":"sub-agent model inherit 1M Opus context parent spawn","hit":false,"top1_source":"docs/HANDOFF.md","top1_rerank":0.641,"case":"A","note":"Rerank 0.641 borderline < 0.7 threshold. HANDOFF.md has content but rerank filtered out. Rephrase with more specific anchor."}, {"id":"q11","query":"ApprovalWorkflow V1 V2 dual schema backward compatible fallback","hit":true,"top1_source":".claude/agent-memory/investigator/MEMORY.md","top1_rerank":0.824,"case":null}, {"id":"q12","query":"GraphQL subscription realtime resolver Apollo","hit":true,"top1_source":null,"top1_rerank":null,"case":null,"note":"CORRECT EXCLUSION — 0 results as expected"}, {"id":"q13","query":"Redis cache distributed session eviction TTL","hit":true,"top1_source":null,"top1_rerank":null,"case":null,"note":"CORRECT EXCLUSION — 0 results as expected"}, {"id":"q14","query":"Kubernetes Helm chart microservice deployment","hit":true,"top1_source":null,"top1_rerank":null,"case":null,"note":"CORRECT EXCLUSION — 0 results as expected"} ], "_diagnosis": { "root_cause_summary": "DIFFERENT from AI_INFRA Anti #9 keyword stacking. SOLUTION_ERP v1.0 fails due to: (1) Corpus gap — agents/*.md NOT indexed [q07, q09 Case D]; (2) Query language mismatch — Vietnamese content vs English query terms [q05, q06 Case C]; (3) Borderline rerank — short chunks below 0.7 threshold [q04, q10 Case A].", "case_breakdown": { "case_A": ["q04 (EF 3-file rule)", "q10 (sub-agent model inherit)"], "case_B": [], "case_C": ["q05 (gotcha #25 IIS WebSocket)", "q06 (CQRS MediatR)"], "case_D": ["q07 (Smart Friend reviewer)", "q09 (Implementer worktree DROPPED)"] }, "fix_actions": { "corpus_fix": "Add .claude/agents/**/*.md to corpus_paths in rag.json → re-bootstrap → fixes q07 + q09", "query_rephrase": "v1.1 rephrase q04/q05/q06/q10 with: Vietnamese keyword anchors + correct notation (### 25 not #25) + drop absent terms (Features.cs, single file)" } }, "_lessons": [ "Anti #9 keyword stacking was AI_INFRA problem — SOLUTION_ERP has different failure mode: corpus gap + language mismatch", "Notation matters: gotcha query must use '25. IIS' not '#25 IIS' to match actual docs/gotchas.md format", "Vietnamese corpus requires Vietnamese keywords OR canonical English terms (ApprovalWorkflow, NOT 'approval flow')", ".claude/agents/*.md files are valuable content — should be in corpus_paths" ] }