rbkunnela/FriendlyAI Review

Public GitHub Action wrapper that sends PR diffs to a private validation API and reports the returned verdict.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
review-api-keyAPI key for the private validation service. Provide via secrets.FRIENDLYAI_REVIEW_API_KEY.yes
review-api-urlAbsolute URL of the private review endpoint.yes
github-tokenGitHub token for reading PR files and posting comments/check-runs.no${{ github.token }}
max-diff-tokensApproximate max token budget for inline PR patches sent to the API.no15000
request-timeout-secondsTimeout for the review API request.no120
bypass-labelDeliberate soft-override label that bypasses validation.nofriendlyai-bypass-ack-by-maintainer
methodologyReview methodology: "standard" (normal code review — default) or "story-driven" (adds linked-story and acceptance-criteria checks). Set "story-driven" only on repos that use a story-driven process.nostandard
namedescription
conclusionFinal check-run conclusion: success | failure | neutral.
finding-countNumber of findings returned by the review service.
blocking-finding-countNumber of medium/high/critical findings returned by the review service.
max-riskMaximum risk level returned by the review service, when provided.
report-urlOptional report URL returned by the review service.
unavailable-reasonSet when the review could not run and the check failed open to neutral: credits | timeout | upstream | malformed.