Amaury Levé 5f5da59978 Improve grade-tests eval quality (#1049) ...

Replace vocabulary and technique checks with outcome-focused evidence, add two distinct grading scenarios, and preserve the per-test report schema.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

2026-08-25 14:13:00 +02:00

..

fixtures

Fix migrate-mstest-v1v2-to-v3 activation and test-skill eval quality (#974)

2026-07-31 16:27:36 +02:00

eval.yaml

Improve grade-tests eval quality (#1049)

2026-08-25 14:13:00 +02:00