kensa eval runs anywhere your Python tests already run. kensa init scaffolds a GitHub Actions workflow; here’s a minimal version.
GitHub Actions
.github/workflows/kensa.yml
What needs credentials
Deterministic assertions run entirely locally and cost nothing, so you can gate on tool usage, output shape, cost, and latency without any secrets.
If your evals call
judge(...), add the provider secret and (optionally) pin the model:
Judge step with secrets
Reports and PR comments
Write a Markdown summary and post it as a sticky PR comment:PR comment step
--json-report eval.json when you want a machine-readable artifact to upload or feed a dashboard.
Running on a schedule
Pull-request runs catch regressions in changed code. A nightly run catches drift from model and dependency updates that no diff touched:Nightly drift check
trials on the evals you run nightly to surface flakiness that a single run would miss. See Pytest plugin for trial verdicts.