sarvariharshitha/AI Assisted PR Reviewer
Runs an LLM-based review on pull requests using project.md, diffs, and scan logs
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| llm-endpoint | Base URL for chat completion endpoint (OpenAI-compatible) | yes | — |
| llm-api-key | API key for the LLM endpoint | yes | — |
| model | Model name to use (e.g., gpt-4o-mini) | no | gpt-4o-mini |
| project-md-path | Path to project architecture doc | no | project.md |
| scan-log-paths | Comma-separated list of scan log file paths to include | no | "" |
| max-files | Maximum number of changed files to inspect | no | 50 |
| max-hunk-size | Maximum characters to keep from each patch hunk | no | 8000 |
| post-mode | comment | summary (comment posts to PR, summary sets job summary) | no | comment |
Outputs
no outputs