vanessasvictoria/PR Review Bot

Deterministic checks + LLM-assisted PR review with sticky comments

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
github_tokenGitHub token for API access (defaults to github.token)no${{ github.token }}
openai_api_keyOpenAI API key for LLM review (optional, skipped if not provided)no
modelLLM model identifier (e.g., gpt-4o-mini)nogpt-4o-mini
max_diff_bytesMaximum total diff size in bytesno200000
max_filesMaximum number of files to processno200
include_file_contextInclude full file content for small filesnofalse
file_context_max_bytesMaximum file size to include full contentno20000
risk_rules_pathPath to risk rules YAML file (optional)no.pr-review-bot/risk_rules.yml
sticky_comment_tagTag for identifying sticky commentsnoPR_REVIEW_BOT
fail_on_high_riskFail workflow if risk score exceeds thresholdnofalse
high_risk_thresholdRisk score threshold (0-10)no8
enable_dependency_auditRun dependency audit checksnotrue
enable_testsRun test suitenotrue
enable_lintRun linting checksnotrue
log_levelLogging level (DEBUG, INFO, WARNING, ERROR)noINFO
redact_patternsComma-separated regex patterns for redactionno
extra_instructionsAdditional instructions for LLM reviewno

no outputs