jnzader/GHAGGA Code Review

AI-powered multi-agent code review for PRs with built-in static analysis. Runs 16 static analysis tools directly on the GitHub Actions runner (cached). 3 provider modes: gateway (mcp-llm-bridge), cli-bridge (local CLIs), ollama.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
providerLLM provider to use. Options: gateway (default — route via mcp-llm-bridge), cli-bridge (local CLI tools: Claude Code, OpenCode, Copilot), ollama (local). Legacy values (github, anthropic, openai, google, etc.) are automatically remapped to "gateway" for backward compatibility.nogateway
modelLLM model identifier. For gateway/cli-bridge, use "auto" to let the provider select the best available model.no
modeReview mode. "simple" = single LLM call, "workflow" = 5 specialist agents, "consensus" = for/against/neutral voting.nosimple
api-keyLLM provider credential. For gateway: bearer token. For cli-bridge: tool API key (optional). For ollama: not required.no
github-tokenGitHub token for fetching PR diffs and posting comments. Defaults to the automatic GITHUB_TOKEN.no${{ github.token }}
enabled-toolsComma-separated list of tool names to force-enable (overrides auto-detect). Example: "ruff,clippy,bandit". See README for the full list of 16 tools.no""
disabled-toolsComma-separated list of tool names to force-disable (overrides always-on and auto-detect). Example: "gitleaks,cpd". See README for the full list of 16 tools.no""
enable-semgrep[DEPRECATED — use disabled-tools instead] Enable Semgrep security analysis. Runs directly on the runner. First run installs via pip (~2 min), subsequent runs use cache (~10s).notrue
enable-trivy[DEPRECATED — use disabled-tools instead] Enable Trivy vulnerability scanning. Runs directly on the runner. First run installs via official script (~1 min), subsequent runs use cache (~5s).notrue
enable-cpd[DEPRECATED — use disabled-tools instead] Enable PMD/CPD copy-paste detection. Runs directly on the runner. First run downloads PMD (~1 min), subsequent runs use cache (~5s).notrue
enable-memoryEnable review memory. Caches observations between runs via @actions/cache. Set to 'false' to disable.notrue
embedding-providerOptional semantic-search embedding provider for review memory. Options: none (default — keyword-only), openai-compatible (any /v1/embeddings-compatible HTTP API: OpenAI, Voyage-compatible endpoints, self-hosted servers). "local" is NOT available in the Action (no bundled model) and is coerced to "none" with a warning.nonone
embedding-modelEmbedding model identifier for embedding-provider "openai-compatible" (e.g. "text-embedding-3-small").no
embedding-base-urlBase URL for the embedding-provider "openai-compatible" HTTP API (e.g. "https://api.openai.com/v1").no
embedding-api-keyAPI key/bearer token for the embedding-provider "openai-compatible" HTTP API. Omit for unauthenticated self-hosted endpoints.no
embedding-dimensionExpected vector dimension for embedding-provider "openai-compatible" (e.g. "1536" for text-embedding-3-small).no
embedding-candidate-kBounded cosine candidate set size for semantic memory search. Defaults to 200.no
namedescription
statusReview status: PASSED, FAILED, NEEDS_HUMAN_REVIEW, or SKIPPED
findings-countNumber of findings from the review