AskUserExtension#

Build extensions, choose hooks, and manage request-scoped state. See the guide.

class zett_agent.extensions.ask_user.AskUserExtension[source]#

Register ask_user and suspend its execution until accept() receives a reply.

The normal tool lifecycle remains intact; waiting happens before TOOL_STARTED.

        sequenceDiagram
    participant Model
    participant Agent
    participant Extension
    participant UI
    Model->>Agent: ask_user ToolCall
    Agent->>Extension: before_tool() + context.emit()
    Extension-->>UI: AskUserEvent
    Note over Agent,Extension: waiting before TOOL_STARTED
    UI->>Extension: ExternalEvent via accept()
    Extension-->>Agent: resume
    Agent->>Extension: TOOL_STARTED and ask_user()
    Extension-->>Model: ToolMessage

Ask-user pause and resume protocol#

While waiting, RunCancelledEvent cancels the Future and on_error() completes it with that error. Both paths wake the suspended coroutine.

Closing or cancelling the stream removes the pending route, so a late UI response cannot resume an abandoned request.

Examples

Register the extension and forward its custom event to a UI:

ask_user = AskUserExtension()
client = await create_agent(model, extensions=[ask_user])

async for event in client.stream("Help me choose a format"):
    if event.name == "ask_user":
        show_question(event.payload)

Outbound protocol:

AgentEvent(
    type=CUSTOM,
    name="ask_user",
    session_id="session-42",
    payload={
        "session_id": "session-42",
        "tool_call_id": "call-7",
        "question": "Which format?",
        "options": ["Markdown", "Plain text"],
        "allow_multiple": False,
        "response_event": "ask_user_response",
    },
)

Inbound protocol:

agent.emit_external_event(
    ExternalEvent(
        name="ask_user_response",
        payload={"tool_call_id": "call-7", "answer": "Markdown"},
    ),
    config=AgentRunConfig(session_id="session-42"),
)

ExternalEventExtension owns routing, synchronization, wake-up, and cleanup. The response payload is application-defined and returned unchanged to the model. Agent.emit_external_event() returns an empty list when no extension accepts an unrelated, malformed, duplicate, stale, or cancelled event.

Warning

A UI must route the response with the matching session and tool-call ID. Displaying a question is not equivalent to authorizing an action.

See also

ExternalEventExtension owns waiting and wake-up; Emit events and accept user input contains a complete approval example.

async on_tool(context)[source]#

Register a request-scoped ask_user tool bound to this context.

Parameters:

context (AgentRunContext)

Return type:

None

async before_tool(context, call)[source]#

Emit AskUserEvent, then wait for the matching external response.

Parameters:
Return type:

None

accept(config, event)#

Claim a matching response and wake its waiter on the Future’s loop.

Usually called by Agent.emit_external_event, not directly by the UI. True means this extension accepted delivery; False leaves other extensions free to recognize the event. Neither argument is modified.

Parameters:
Return type:

bool

async after_model(context, response)#

Run after the complete assistant message is appended.

Parameters:
Return type:

None

async after_run(context, result)#

Run after a successful final answer is appended.

Parameters:
Return type:

None

async after_tool(context, call, result, error)#

Inspect or modify a tool result before it is appended.

error is the original execution exception for a failed result and None after successful execution. Changes made to result are included in context, persistence, and the next model request. Raising prevents the result from being appended.

Parameters:
Return type:

None

async after_turn(context, result)#

Run once the turn’s assistant message and tool results are settled.

result is the assistant message that opened the turn: either the final answer, or the tool-calling message whose ToolMessages were appended. Every requested call is settled first, including calls that failed, and calls that steering skipped, which arrive as unsuccessful or skipped ToolMessages.

Steering that interrupts a turn is accepted while the runtime settles that batch, so its UserMessage is already appended when this hook runs and the steering turn follows as the next turn.

A turn that never completed, because the request failed or was cancelled, has no after_turn call; use on_error and RunCancelledEvent for those paths.

Parameters:
Return type:

None

async before_model(context, request)#

Inspect the current request before preprocessing a primary model call.

Request fields are frozen. Change messages through AgentRunContext.add_message() or AgentRunContext.replace_messages(), local tools through context.tools, and provider tools through context.server_tools; the runtime rebuilds these fields before the next hook and before calling the provider. This is a shallow request view, not an immutable copy of each message or tool definition.

Examples

Inspect the tools offered in this iteration:

async def before_model(self, context, request):
    offered = {definition.name for definition in request.tools}
    if "write_file" in offered:
        context.add_message(
            SystemMessage(content="Read existing files before editing."),
        )
Parameters:
Return type:

None

async before_run(context)#

Run after the transformed user input is appended and published.

Parameters:

context (AgentRunContext)

Return type:

None

async before_turn(context)#

Run before this turn’s model call.

Runs after before_run() on the first turn and after the previous turn’s after_turn() on later ones. Model request assembly, compaction, and before_model() follow this hook, so context edited here reaches the provider.

Parameters:

context (AgentRunContext)

Return type:

None

property name: str#

Unique registration identity, defaulting to the concrete class name.

Override with a class attribute or assign an instance name to register independently configured instances of the same extension type.

async on_compact(context)#

Summarize restored context when a caller asks for compaction.

Agent.compact restores the session through on_tool and on_state exactly as a request does, appends no input message, and makes no primary model call: the only work a compaction pass does is what this hook performs. The default does nothing, so an extension with nothing to compact pays nothing.

Examples

Usage:

async def on_compact(self, context):
    await self.compact(context)
Parameters:

context (AgentRunContext)

Return type:

None

async on_error(context, error)#

Complete active waits with the request’s original error.

Parameters:
Return type:

None

async on_event(context, event)#

Cancel active waits when their request enters CANCELLED.

Parameters:
Return type:

None

async on_message(context)#

Transform context.input_message after state restoration, before append.

Replace the pending UserMessage to implement externally selected modes. Do not append or persist it here: the runtime appends the final message exactly once after all input hooks finish. before_run sees that message through AgentRunContext.add_message() or AgentRunContext.replace_messages(), and persistence subscribers have already received it.

Parameters:

context (AgentRunContext)

Return type:

None

async on_model_request(context, request, call_next)#

Wrap one provider request and its complete streamed response.

Pass request (or a dataclass replacement) to call_next. The default closes the inner stream so cancellation reaches the provider.

Parameters:
Return type:

AsyncIterator[ModelEvent]

async on_state(context)#

Restore history and initialize state before any input conversion.

Examples

Usage:

async def on_state(self, context):
    context.add_message(SystemMessage(content="Use concise answers."), index=0)
Parameters:

context (AgentRunContext)

Return type:

None

async on_success(context, result)#

Run once after all after_run hooks succeed, before RUN_COMPLETED.

This callback observes a completed request, not an intermediate model step. Failed or cancelled requests do not trigger it. Callback errors propagate through on_error and prevent RUN_COMPLETED from being emitted.

Examples

Usage:

async def on_success(self, context, result):
    await save_answer(context.session_id, result.content)
Parameters:
Return type:

None

async on_tool_call(context, call, call_next)#

Wrap one registered local tool handler and return its ToolResult.

An extension may adjust call.arguments, return without calling the next layer, transform its result, or raise into normal tool-failure handling.

Parameters:
Return type:

ToolResult

property pending: bool#

Return whether this extension is participating in an active request.

The Agent updates this state for every registered extension, including extensions whose hooks are currently idle. One extension instance may be shared by multiple Agents and sessions; pending remains true until all requests using that instance have finished, failed, or been cancelled. Persistent data retained between requests does not count.