| 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 a typed approval mode. |
adapter* | TextualUIAdapter | |
backend | Any | Default: None |
image_tracker | MediaTracker | None | Default: None |
context | CLIContext | None | Default: None |
sandbox_type | str | None | Default: None |
message_kwargs | dict[str, Any] | None | Default: None |
graph_input | dict[str, Any] | None | Default: None |
rubric | str | None | Default: None |
goal_active | bool | Default: False |
on_rubric_evaluation_end | Callable[[RubricEvaluationEnd], None] | None | Default: None |
turn_stats | _session_stats.SessionStats | None | Default: None |
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.
The TextualUIAdapter for UI operations.
Optional backend for file operations.
Optional tracker for images.
Optional CLIContext with model override and params. The current
mode is persisted and copied into runtime context before every stream
iteration.
Sandbox provider name for trace metadata, or None
if no sandbox is active.
Extra fields merged into the stream input message
dict (e.g., additional_kwargs for persisting skill metadata
in the checkpoint).
Prepared non-conversation input for a server-side graph operation. When provided, no user message or media is constructed.
Acceptance criteria supplied to RubricMiddleware via graph
input state.
Whether the rubric belongs to an unfinished /goal.
Optional callback receiving a validated
RubricEvaluationEnd (grading run ID and verdict) for each
main-agent rubric_evaluation_end event.
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.
