## Why

The diagnosis evaluation harness is implemented, but the baseline is still incomplete because only two of the five fixed cases have trace fixtures. Completing the fixture set and saving a baseline report makes the harness useful as a practical regression signal for interview demos and future Agent changes.

## What Changes

- Add trace fixtures for the remaining fixed diagnosis cases: Redis timeout, slow response, and JVM memory risk.
- Add a reproducible baseline report generated from the full fixture set.
- Document how to regenerate and interpret the baseline.
- Keep the evaluator deterministic and offline; no live MySQL, Redis, Milvus, or LLM service is required.

## Capabilities

### New Capabilities

- None.

### Modified Capabilities

- `diagnosis-eval-harness`: Extend the existing evaluation harness requirement so the fixed MVP case set has complete fixture coverage and a saved baseline report.

## Impact

- Affects `mvp/eval/cases`, `mvp/eval/fixtures`, and eval documentation.
- May add baseline output files under `mvp/eval/reports`.
- May add or update focused evaluator tests to assert full fixture coverage and report generation.
- No production runtime API or database schema changes are expected.