--- source: smith-cli/tests/e2e_help.rs assertion_line: 67 expression: "String::from_utf8(help(&[\"eval\", \"--help\"])).unwrap()" --- Run one prompt without the TUI Usage: smith eval [OPTIONS] Arguments: The prompt to run Options: --profile Exact subscription profile; required for subscription connections --fixture-issuer Explicit isolated loopback subscription fixture namespace --credential-module Trusted credential-module package selected for this subscription only --json Print the structured outcome as JSON --session Explicitly resume this existing session ID --mock Use the scripted mock provider instead of a real endpoint --provider Provider kind; required for real endpoints Possible values: - openai: OpenAI-compatible endpoints - openai-chatgpt-plan: `ChatGPT` plan through Responses; requires explicit profile and model - anthropic-claude-plan: Claude subscription; explicit local profile, no API-key fallback - google-gemini-cli-plan: Google Gemini CLI subscription; no API-key fallback - anthropic: Anthropic Messages API - google: Google Gemini API - zai: Metered Z.ai API connection - zai-coding-plan: Z.ai Coding Plan connection; never falls back to metered API billing [env: SMITH_PROVIDER] --model Model id; required for real endpoints [env: SMITH_MODEL] --base-url Endpoint base URL override [env: SMITH_BASE_URL] --include-usage Request streamed usage; explicit value replaces user and trusted project settings [possible values: true, false] --tool-policy Host-owned state for one qualified component tool: `name=advertised|hidden|disabled` --tool-delegation Delegate a descendant directory: qualified-caller=qualified-target#directory -h, --help Print help (see a summary with '-h')