tushardhole/Safe PR Review Agent
Provider-agnostic AI PR reviews with schema-safe output normalization, diff-anchor filtering, and inline fallback safety.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| github_token | GitHub token for reading PR data and posting review comments. | yes | — |
| openai_api_key | API key for the OpenAI-compatible provider. | yes | — |
| openai_base_url | Base URL for OpenAI-compatible API endpoint. | no | — |
| model | Model name to use for code review. | no | — |
| exclude_patterns | Comma-separated glob patterns for files to exclude. | no | — |
| max_files | Maximum number of changed files to review. | no | — |
| review_level | Review depth. One of quick, thorough, security-focused. | no | — |
| extra_prompt | Extra instructions appended to the system prompt. | no | — |
| max_context_rounds | Maximum file-reading tool call rounds for context gathering. | no | — |
Outputs
no outputs