model_providers.<id>.env_key: env var for provider API key. model_providers.<id>

model_providers.<id>.requires_openai_auth: whether provider uses OpenAI auth.

model_providers.<id>.wire_api: protocol; docs say only responses.

model_providers.<id>.query_params: extra query params.

model_providers.<id>.http_headers: static request headers.

model_providers.<id>.env_http_headers: headers from env vars.

model_providers.<id>.request_max_retries: HTTP retry count.

model_providers.<id>.stream_max_retries: SSE retry count.

model_providers.<id>.stream_idle_timeout_ms: SSE idle timeout.

model_providers.<id>.supports_websockets: whether Responses WebSocket transport is supported.

features.codex_hooks: under-development lifecycle hooks.

features.shell_tool: enable shell tool; stable and on by default.

features.enable_request_compression: zstd-compress streaming request bodies; stable and on by default.

features.skill_mcp_dependency_install: prompt/install missing MCP deps for skills; stable and on by default.

features.fast_mode: enables Fast mode selection; stable and on by default.

features.smart_approvals: experimental guardian-reviewer approval routing.

features.web_search: deprecated old toggle; prefer web_search.