-f, --file | None | Path to input requirements file (e.g. access.md). |
-o, --output | policy.json | Path to destination policy JSON file. |
-provider, --provider | openai | LLM provider: openai, gemini, groq, openrouter, ollama. |
-model, --model | Provider default | Specific model name (e.g. gpt-4o-mini, gemini-1.5-flash). |
-api_key, --api-key | Env var | API key (or set OPENAI_API_KEY, GEMINI_API_KEY). |
--non-interactive | False | Run in non-interactive batch mode. |
-y, --yes | False | Automatically accept generated policy without confirmation. |
--timeout | 60.0 | API request timeout in seconds. |