feat: v1.3.0 — retrieval metrics, judge calibration, online monitoring#45

Merged

lopadova merged 6 commits into

mainfrom

feat/eval-harness-v1.3.0-enhancements

Jun 16, 2026

Commits on Jun 16, 2026

feat(support): add RuntimeOptions::normalizeUnitInterval clamp helper

lopadova
and
claude
committed
feat: add ordinal/retrieval metrics, judge calibration, online monitoring

lopadova
and
claude
committed
docs: document v1.3.0 retrieval metrics, calibration and online monitoring

lopadova
and
claude
committed
test(calibration): add calibrate-judge command test + fixture

lopadova
and
claude
committed
fix: address PR #45 first-round Copilot/Codex review

lopadova
and
claude
committed
fix: address PR #45 second-round Copilot review

lopadova
and
claude
committed