victorarias/shitty-reviewing-agent
Agent-driven PR reviewer using LLMs
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| provider | LLM provider (openrouter, gemini, anthropic, openai, etc.). Aliases: gemini→google, vertex→google-vertex. | no | — |
| api-key | API key for the LLM provider (required for non-Vertex providers; optional for Vertex AI) | no | — |
| model | Model to use (e.g., anthropic/claude-sonnet-4) | no | — |
| compaction-model | Optional model to use for context compaction summaries (defaults to gemini-3-flash-preview for Google, else same as model) | no | — |
| fallback-provider | Fallback LLM provider (defaults to primary provider if only fallback-model is set) | no | — |
| fallback-model | Fallback model to use when the primary model hits sustained rate limits | no | — |
| fallback-api-key | API key for the fallback provider (defaults to primary api-key if omitted) | no | — |
| max-files | Max files to review (skips if exceeded) | no | — |
| ignore-patterns | Comma-separated glob patterns to skip | no | — |
| debug | Enable debug logging | no | — |
| reasoning | Thinking level (off, minimal, low, medium, high, xhigh) | no | — |
| temperature | Sampling temperature (0-2). Gemini 3 defaults to 1.0 and may behave unexpectedly at lower values. | no | — |
| allow-pr-tools | Allow PR-creation tools in PR review mode (default false; always allowed in schedule mode). | no | — |
| experimental-pr-explainer | Experimental: post a PR review guide comment and one explainer comment per changed file. | no | — |
| bot-name | Bot/app mention name for @bot command triggers (e.g., my-app). | no | — |
| app-id | GitHub App ID (optional; default uses implicit GITHUB_TOKEN) | no | — |
| app-installation-id | GitHub App installation ID | no | — |
| app-private-key | GitHub App private key PEM | no | — |
Outputs
no outputs