TodoWriteExtension#

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

class zett_agent.extensions.todo.TodoWriteExtension[source]#

Register todo_write and enforce strictly sequential task progress.

The model submits the complete ordered list on every call. The first write starts the first task as in_progress and leaves every later task pending. Each later write may preserve the state or complete exactly one task, in which case the next task becomes in_progress; after the last task every item is completed. Task content and order are fixed once the list is created.

The list is request-working state, not durable task storage. It is cleared after the request succeeds, fails, or is cancelled, so the model builds a fresh list on the next request.

Example progression:

[in_progress, pending,     pending]
[completed,   in_progress, pending]
[completed,   completed,   in_progress]
[completed,   completed,   completed]

Examples

Inspect progress from application code while a request is active:

extension = TodoWriteExtension()
client = await create_agent(model, extensions=[extension])
async for event in client.stream("Implement and test the change"):
    if event.type is AgentEventType.TOOL_COMPLETED:
        progress = extension.todos(event.session_id)
        if progress is not None and progress.in_progress is not None:
            print(progress.in_progress.content)

Note

The list is request-working state, not durable task storage. It is cleared after success, failure, or cancellation.

See also

TodoItem and TodoWriteResult expose validated progress to application code.

async on_tool(context)[source]#

Register a request-scoped todo_write tool bound to this session.

Parameters:

context (AgentRunContext)

Return type:

None

async after_run(context, result)[source]#

Release todo state after a successful request finishes.

Parameters:
Return type:

None

async on_error(context, error)[source]#

Release todo state when a request terminates with an error.

Parameters:
Return type:

None

async on_event(context, event)[source]#

Release todo state when cancellation terminates a request.

Parameters:
Return type:

None

todos(session_id)[source]#

Return the latest validated list for one session, if it has one.

Parameters:

session_id (str)

Return type:

TodoWriteResult | None

clear(session_id)[source]#

Forget one session’s todo list without affecting other sessions.

Parameters:

session_id (str)

Return type:

None

accept(config, event)#

Handle one external event and report whether it was accepted.

The Agent broadcasts each event to every registered extension. Override this synchronous hook when an extension waits for input from another thread, HTTP request, TUI, or Web UI. The default ignores the event. Config is passed separately and can be None before initialization. Each extension decides whether the supplied identity and payload match its protocol. Return True to include this extension’s name in the broadcast result; returning False does not stop later receivers.

Parameters:
Return type:

bool

async after_model(context, response)#

Run after the complete assistant message 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_tool(context, call)#

Run before one requested tool is invoked.

Parameters:
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_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.