Add diagnosis eval baseline diff

This commit is contained in:
aruo
2026-07-05 00:59:53 +08:00
parent 4c7c53b024
commit 69deb15330
22 changed files with 1069 additions and 0 deletions
+14
View File
@@ -8,6 +8,7 @@ This folder contains the first fixed-case evaluation set for the MVP diagnosis A
- Offline trace fixtures: `fixtures/*.json`
- Field definitions: `schema.md`
- Baseline reports: `reports/baseline-report.json` and `reports/baseline-report.md`
- Baseline diff sample: `reports/baseline-diff-sample.json` and `reports/baseline-diff-sample.md`
- Evaluator implementation: `DiagnosisTraceEvaluator`
- Report writer: `DiagnosisEvalReportWriter`
@@ -45,3 +46,16 @@ fixed diagnosis case
-> JSON / Markdown report
-> regression signal for prompts, tools, retrieval, and verifier behavior
```
## Baseline Diff
Baseline diff compares a current report against `reports/baseline-report.json`.
```text
baseline report
current report
-> deterministic diff
-> regressions, improvements, and changed signals
```
Use it to answer: did a prompt, tool, retrieval, or verifier change make the Agent worse than the fixed baseline?