BehavTest › How-to guides

Fail a GitHub pull request when LLM quality drops

Commit a compact baseline once:

behavtest run behavtest/suite.json --repeat 3 --export behavtest.baseline.json --compact
git add behavtest.baseline.json && git commit -m "Add BehavTest baseline"

Then add the GitHub Action to a workflow that runs on pull requests:

      - uses: dhrumilbhut/behavtest@v0
        with:
          suite: behavtest/suite.json
          repeat: 3

It compares every pull request with the baseline, writes the result to the job summary and fails the check when a case regresses. See it block a pull request. Other CI systems: baselines and CI.