feat(evaluation): migrate evaluation harnesses from playground#279

Merged

miguelgfierro merged 91 commits into

mainfrom

feat/evaluation-framework

Jun 30, 2026

Commits on Jun 18, 2026

feat(evaluation): add evaluation subpackage skeleton and pyproject entry point (#268)
miguelgfierro
authored
feat(evaluation): add matcher primitives and statistics helpers (#269)
miguelgfierro
authored
feat(evaluation): add corpus loader and registry modules (#270)
miguelgfierro
authored
feat(evaluation): add G1-G5 gate framework (#271)
miguelgfierro
authored
feat(evaluation): add scorecard renderer (#272)
miguelgfierro
authored
feat(evaluation): add LLM-as-judge and judge client (#273)
miguelgfierro
authored
feat(evaluation): add champion tracking and flyeval CLI (#274)
miguelgfierro
authored
feat(lab): add retrieval metrics (hit@k, recall@k, MRR, MAP, nDCG) (#275)
miguelgfierro
authored
feat(examples): add flyradar and flycanon evaluation examples (#276)
miguelgfierro
authored
test(evaluation): add unit tests for evaluation package and retrieval metrics (#277)
miguelgfierro
authored
docs(evaluation): add evaluation package documentation (#278)
miguelgfierro
authored

Commits on Jun 19, 2026

Commits on Jun 25, 2026

Commits on Jun 29, 2026

Commits on Jun 30, 2026