agent-axiom/Agent Anvil

Run Agent Anvil scenario suites in GitHub Actions.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
scenarioPath to the Agent Anvil YAML scenario suite.yes
runs-dirDirectory where run artifacts should be written.noruns/agent-anvil
offlineUse local heuristic semantic grading instead of OpenAI grading.nofalse
agent-modeDemo agent mode, such as offline, openai, or auto.no""
trialsOptional trial-count override.no""
expected-exit-codeExpected anvil run exit code. Use 1 for intentional regression demos.no0
github-summaryAppend a Markdown run summary to GITHUB_STEP_SUMMARY.notrue
pr-commentWrite PR-ready Markdown for optional gh pr comment publishing.nofalse
post-pr-commentPublish the generated PR comment with gh pr comment during pull_request workflows.nofalse
pr-comment-pathPath for the generated PR comment Markdown file.noagent-anvil-pr-comment.md
compare-baselineOptional baseline run directory for compare-aware PR comments.no""
compare-pathPath for the generated compare JSON artifact.noagent-anvil-compare.json
python-versionPython version used by uv for running Agent Anvil.no3.12
uv-cacheEnable setup-uv caching. Keep false when invoking this action multiple times in one job.nofalse

no outputs