Function●Since v0.0

execute_task_textual

Execute a task with output directed to Textual UI.

This is the Textual-compatible version of execute_task() that uses the TextualUIAdapter for all UI operations.

execute_task_textual(
  user_input: str,
  agent: Any,
  assistant_id: str | None,
  session_state: Any,
  adapter: TextualUIAdapter,
  backend: Any = None,
  image_tracker: MediaTracker | None = None,
  context: CLIContext | None = None,
  *,
  sandbox_type: str | None = None,
  message_kwargs: dict[str, Any] | None = None,
  turn_stats: SessionStats | None = None
) -> SessionStats

Parameters

Name	Type	Description
`user_input`*	`str`	The user's input message
`agent`*	`Any`	The LangGraph agent to execute
`assistant_id`*	`str \| None`	The agent identifier
`session_state`*	`Any`	Session state with auto_approve flag
`adapter`*	`TextualUIAdapter`	The TextualUIAdapter for UI operations
`backend`	`Any`	Default:`None` Optional backend for file operations
`image_tracker`	`MediaTracker \| None`	Default:`None` Optional tracker for images
`context`	`CLIContext \| None`	Default:`None` Optional `CLIContext` with model override and params, passed to the graph via `context=`.
`sandbox_type`	`str \| None`	Default:`None` Sandbox provider name for trace metadata, or `None` if no sandbox is active.
`message_kwargs`	`dict[str, Any] \| None`	Default:`None` Extra fields merged into the stream input message dict (e.g., `additional_kwargs` for persisting skill metadata in the checkpoint).
`turn_stats`	`SessionStats \| None`	Default:`None` Pre-created `SessionStats` to accumulate into. When the caller holds a reference to the same object, stats are available even if this coroutine is cancelled before it can return. If `None`, a new instance is created internally.

View source on GitHub

execute_task_textual

Parameters

LangChain Assistant

Menu

execute_task_textual

Parameters