1.8 KiB
1.8 KiB
Why
The MVP can already execute multi-agent diagnosis, persist session traces, and collect feedback, but it is still hard to demonstrate as a complete enterprise-style workflow. A demo profile, a trace query API, and an explicit end-to-end acceptance case make the project runnable, observable, and explainable for interview and portfolio review.
What Changes
- Add an
mvp-demoSpring profile that keeps the existing external infrastructure contract but turns on mock log and metric providers for repeatable demonstrations. - Add a read-only trace query API:
GET /api/diagnosis/{sessionId}/trace. - Aggregate
diagnosis_session,agent_step,tool_invocation, verifier/self-evaluation, final answer, and feedback into one trace response. - Add an end-to-end MVP acceptance case that documents startup, chat request, trace query, and feedback submission.
- Add focused service tests for trace aggregation without requiring MySQL, Redis, Milvus, or a real LLM.
- Record the design decision in MVP notes for interview storytelling.
Capabilities
New Capabilities
mvp-demo-trace-acceptance: Covers the MVP demo profile, trace query API, and end-to-end acceptance workflow for a reproducible agent diagnosis demo.
Modified Capabilities
- None.
Impact
- Affected code: new trace controller/service/DTOs,
application-mvp-demo.yml, unit tests, MVP demo documentation. - Affected API: adds
GET /api/diagnosis/{sessionId}/trace. This is an additive L3 collaboration API because it is intended for frontend, demo, and external reviewer consumption. - Affected runtime behavior: no change to chat execution, verifier, feedback, document upload, or persistence semantics.
- Non-goals: no sensitive configuration cleanup, no database schema migration, no replacement of existing chat endpoints, no full offline mock LLM implementation.