run_textual_cli_async

run_textual_cli_async(
  assistant_id: str,
  *,
  auto_approve: bool = False,
  sandbox_type: str

Parameters

Name	Type	Description
`assistant_id`*	`str`	Agent identifier for memory storage
`auto_approve`	`bool`	Default:`False` Whether to auto-approve tool usage
`sandbox_type`	`str`	Default:`'none'` Type of sandbox ("none", "modal", "runloop", "daytona", "langsmith")
`sandbox_id`	`str \| None`	Default:`None`
`sandbox_setup`	`str \| None`	Default:`None`
`model_name`	`str \| None`	Default:`None`
`model_params`	`dict[str, Any] \| None`	Default:`None`
`thread_id`	`str \| None`	Default:`None`
`is_resumed`	`bool`	Default:`False`
`initial_prompt`	`str \| None`	Default:`None`

Run the Textual CLI interface (async version).

Optional existing sandbox ID to reuse

Optional path to setup script to run in the sandbox after creation.

Optional model name to use

Extra kwargs from --model-params to pass to the model.

These override config file values.

Thread ID to use (new or resumed)

Whether this is a resumed session

Optional prompt to auto-submit when session starts