quantfive/CodePress Review

Automatic code review using AI models (OpenAI, Anthropic, Google, etc.) with inline PR comments

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
github_tokenGitHub token for API accessyes${{ github.token }}
model_providerAI model provider (openai, anthropic, gemini, cohere, mistral, perplexity, fireworks, groq, xai, deepseek, openai-compatible, ollama, etc.)yesopenai
model_nameAI model name or alias. Use exact names (gpt-5.2, claude-sonnet-4-5) or aliases like 'latest', 'sonnet-latest', 'gpt-mini-latest' to auto-resolve to the newest version.yesgpt-5.1
openai_api_keyOpenAI API key (required if using OpenAI)no
anthropic_api_keyAnthropic API key (required if using Anthropic)no
gemini_api_keyGoogle Gemini API key (required if using Gemini/Google)no
cohere_api_keyCohere API key (required if using Cohere)no
mistral_api_keyMistral API key (required if using Mistral)no
perplexity_api_keyPerplexity API key (required if using Perplexity)no
fireworks_api_keyFireworks API key (required if using Fireworks)no
groq_api_keyGroq API key (required if using Groq)no
xai_api_keyxAI API key (required if using xAI)no
deepseek_api_keyDeepSeek API key (required if using DeepSeek)no
openai_compatible_api_keyAPI key for OpenAI-compatible endpoints (required if using openai-compatible provider)no
openai_compatible_base_urlBase URL for OpenAI-compatible endpoints (required if using openai-compatible provider)no
ollama_api_keyOllama API key (optional, often not needed for local Ollama instances)no
ollama_base_urlOllama base URL (defaults to http://localhost:11434/v1)no
reasoning_effortOpenAI reasoning effort level (none, minimal, low, medium, high). 'none' is only for GPT-5.1 models.nohigh
anthropic_effortAnthropic effort level (low, medium, high). Only for claude-opus-4-5. Affects thinking, text responses, and function calls.no""
thinking_enabledEnable Anthropic extended thinking (true/false). Only for Claude claude-opus-4-5, claude-sonnet-4-5, claude-3-7-sonnet models.nofalse
thinking_budgetToken budget for Anthropic extended thinking (e.g., 10000, 20000). Only used when thinking_enabled is true.no10000
max_turnsMaximum number of turns for the interactive agent (0 = unlimited)no0
update_pr_descriptionWhether to update the PR description with AI-generated summary (true/false)notrue
debugEnable debug mode to show detailed console logs (true/false)nofalse
run_on_pr_openedRun review when PR is opened (true/false)notrue
run_on_pr_reopenedRun review when PR is reopened (true/false)notrue
run_on_review_requestedRun review when re-review is requested from github-actions[bot] (true/false)notrue
run_on_comment_triggerRun review when comments contain trigger phrase (true/false)notrue
comment_trigger_phrasePhrase that triggers review in comments (e.g., '@codepress/review')no@codepress/review
blocking_onlyOnly output blocking/required comments, filter out optional/nit/fyi/praise comments (true/false)nofalse
force_full_reviewForce a full review of all files, ignoring re-review optimizations (true/false)nofalse
pr_numberPR number to review (for workflow_dispatch). If not provided, will try to find PR from current branch.no""
enable_web_searchEnable web search and fetch capabilities for the agent (true/false)notrue
related_reposYAML list of related repositories for cross-repo context. Example: related_repos: | - repo: owner/backend ref: main description: Backend API - check API contracts - repo: owner/shared ref: v2 description: Shared types and utilities no""
related_repos_tokenToken for accessing related repos (falls back to github_token for same-org repos)no""

no outputs