baz prompt
Send a prompt to the autonomous agent
baz prompt [options] [text]| Option | Description |
|---|---|
--mode <mode> | Generation mode: agent (default), agent-max, multi-scene Default: agent. |
--max | Shorthand for --mode agent-max |
--project <id> | Alias for global --project-id |
--file <path> | Read prompt from file |
--image <path> | Attach an image file (can be used multiple times) |
--url <url> | Attach a URL for the agent to analyze (can be used multiple times) |
--no-stream | Disable streaming output |
--verbose | Show agent's full response text |
--stream-json | Output events as newline-delimited JSON (for bots like Maya) |
--events-only | With --stream-json, only emit structured events (skip text/thinking tokens) |
--spar | Spar planning mode: brainstorming only, no composition mutations |
--plan | Deprecated alias for --spar |
--requirements <list> | Deterministic requirements to verify against (duration, scenes, format) |
--save-context | Save provided URL/image references to reusable project context |
--context-label <label> | Label for saved context entries (default: reference) Default: reference. |
--budget <dollars> | Max budget per run in USD (default: server default) |
--model <model> | Agent model alias or full ID: fast, normal, max, gpt-5.5-low, gpt-5.5-high, gpt-5.5 |
--export | Automatically export the project after successful generation |
--export-quality <quality> | Export quality when using --export: low, medium, high Default: high. |
--export-format <format> | Export format when using --export: mp4, webm, gif Default: mp4. |
--export-timeout <seconds> | Fail if auto-export takes longer than this Default: 600. |
-h, --help | display help for command |