theoverengineer/over-review

AI-powered Pull Request reviewer using your own model

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
llm-modelLLM model to use for review (e.g., gpt-4o, claude-3.5-sonnet)yes
llm-api-keyAPI key for the LLM provideryes
llm-base-urlBase URL for the LLM API (optional, for OpenAI-compatible APIs)no
llm-providerLLM provider (ai-sdk only in V1)noai-sdk
review-modeReview mode: auto, manual, or clinoauto
full-modeForce full review instead of incrementalnofalse
llm-structured-outputsEnable structured JSON outputs (set to false for custom OpenAI-compatible endpoints without schema support)notrue
style-guide-rulesAdditional repository-specific review guidance text appended to the review promptno
llm-timeout-msTimeout in milliseconds for LLM requests (0 to disable)no30000
github-api-urlGitHub API URL (for GitHub Enterprise or custom endpoints)no
github-server-urlGitHub server URL (for GitHub Enterprise)no
github-tokenGitHub token for API authenticationno
debugEnable debug loggingnofalse
dry-runSkip GitHub write operationsnofalse

no outputs