[01] RELEASE NOTES
Eval suites in CI
Run your eval suite on every pull request and block the merge when the pass rate drops below your threshold.
v2.3.0
VERSION
v2.3.0
TYPE
Feature
DATE
Eval suites now run on every pull request. Connect your repo, pick the suites that matter, and set a pass threshold. If a change drops below it, the check fails and the merge is blocked.
Results link straight to the failing traces, so you can see which step regressed and why.