Files
OpenJarvis/tests
Jon Saad-FalconandClaude Opus 4.6 8437fccbb3 feat(optimize): add personal benchmark system for trace-driven eval
Synthesize reusable benchmarks from interaction traces with feedback
scores. Mines high-quality traces, groups by query class, picks the
best reference per class, and exposes results through DatasetProvider
and LLM-judge Scorer so EvalRunner can evaluate against personal
workflow patterns.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-04 23:46:53 +00:00
..