SuperBizAgent-java/openspec/changes/archive/2026-07-06-live-diagnosis-skill-observability/tasks.md

1. Reproduce And Baseline Evidence

• 1.1 Run a real /api/chat diagnosis with a fixed MySQL/HikariCP session id
• 1.2 Inspect Trace API, MySQL rows, and logs for step/tool counts, skill reads, RAG details, and verifier output
• 1.3 Record the live-run finding in change evidence after implementation is verified

2. Skill Read Boundary

• 2.1 Locate Executor prompt/context code that allows repeated read_skill calls
• 2.2 Add guidance/context so Executor reuses the loaded selected skill within one diagnosis path
• 2.3 Add focused test coverage that Planner has no read_skill and Executor reads the selected skill once in a single path

3. Verifier Evidence Summary

• 3.1 Inspect ToolTraceSummaryService merge and truncation behavior for log, metric, and knowledge rows
• 3.2 Preserve bounded concrete facts from successful query_logs and query_metrics rows in tool_trace_summary
• 3.3 Add tests for merged/truncated rows that still contain direct evidence

4. Modular RAG Details

• 4.1 Inspect ToolInvocationRecorder and LookupKnowledgeTool detail assembly
• 4.2 Persist modular RAG keys in tool_invocation.retrieval_details for new lookup_knowledge rows
• 4.3 Add tests that assert query_transform, retrieval_trace, context_pack_summary, rerank_trace, and evidence_blocks

5. Verification

• 5.1 Run focused unit tests for skill, trace summary, and RAG recorder behavior
• 5.2 Run OpenSpec strict validation for live-diagnosis-skill-observability
• 5.3 Rerun the real diagnosis flow and inspect Trace API, MySQL, and logs
• 5.4 Decide whether remaining issues require a product/design decision before further code changes