Self-hosting

AI providers

AI review is optional. The deterministic gate still runs when no provider is configured.

Provider options

anthropic: Native Anthropic Messages API. Requires ANTHROPIC_API_KEY.
openai or openai-compatible: OpenAI chat completions shape. Works with OpenAI, gateway providers, vLLM, Ollama, and compatible endpoints.
ollama: Local model endpoint. Good for private experiments; quality depends on the pulled model.
claude-code: Subscription CLI path. Requires CLI availability and CLAUDE_CODE_OAUTH_TOKEN from an interactive setup.
codex: Subscription CLI path. Treat credentials carefully; do not mount prompt-readable auth into untrusted review sandboxes.

Single provider

.env

AI_PROVIDER=anthropic
ANTHROPIC_API_KEY=<provider-key>
ANTHROPIC_AI_MODEL=claude-sonnet-4-6

OpenAI-compatible endpoint

.env

AI_PROVIDER=openai-compatible
OPENAI_COMPATIBLE_AI_BASE_URL=http://ollama:11434/v1
OPENAI_COMPATIBLE_AI_API_KEY=
OPENAI_COMPATIBLE_AI_MODEL=llama3.1

Fallback and dual review

A comma-list can be a fallback chain or a two-reviewer plan. With two available providers,AI_COMBINE controls how decisions are combined.

.env

AI_PROVIDER=anthropic,ollama
AI_COMBINE=synthesis
AI_ON_MERGE=either

single: One reviewer verdict. This is the automatic mode when one provider is configured.
consensus: Block only when both reviewers flag a critical defect. A lone defect holds for human review.
synthesis: Both reviewers run, then one merged decision is produced. AI_ON_MERGE controls either or both.

Subscription CLI safety

Credential isolation matters

Subscription CLIs store credentials on disk. Do not mount a writable or prompt-readable CLI home into review execution unless you have isolated it from PR-controlled content. Use an API provider or local OpenAI-compatible endpoint when isolation is not clear.

Related context

AI providers produce the review. REES and RAG add context that the reviewer can use.

← PreviousGitHub App & Orb Next →REES enrichment