Model availability
On TypeScript Agent SDK 0.3.233 and later, or Python Agent SDK 0.2.139 and later, the following tools aren’t available on Opus 4.8, Sonnet 5, Fable 5, Mythos 5, or later versions of those families unless you opt in:
TodoWriteTaskCreateTaskGetTaskUpdateTaskList
TodoWrite only when you set CLAUDE_CODE_ENABLE_TASKS=0.tool_use blocks for the tools in the message stream. The Agent SDK applies these defaults through the Claude Code binary that it bundles. If you point pathToClaudeCodeExecutable (TypeScript) or cli_path (Python) at your own Claude Code install, you get whichever tools that install provides, under its own defaults. To see the exact set in a running session, check which tools are available. To opt a session in, do one of the following:
- Name one of the tools in the
allowedTools(TypeScript) orallowed_tools(Python) option - List the tools in the
toolsoption, which restricts the session’s built-in tools to the ones it names. Include the tools you want alongside the other built-in tools you use - Set
CLAUDE_CODE_ENABLE_TODO_TOOLS=1in theenvoption, as the examples on this page do. In TypeScript,envreplaces the subprocess environment, so spread...process.envto keep inherited variables. In Python,envis merged on top of the inherited environment
Todo lifecycle
Claude moves each todo through a predictable lifecycle:- Created: Claude adds the todo as
pendingwhen it identifies a task - Activated: Claude sets the todo to
in_progresswhen it starts the work - Completed: Claude marks it completed when the task finishes successfully
- Removed: Claude deletes a todo it no longer needs by setting
status: "deleted"in aTaskUpdatecall
When Claude creates todos
In a session that has the task-tracking tools, Claude creates todos for most multi-step work, such as:- Complex multi-step tasks requiring three or more distinct actions
- User-provided task lists when multiple items are mentioned
- Longer operations that benefit from progress tracking
- Explicit requests when users ask for todo organization
Examples
Before running these examples, install the Claude Agent SDK by following the quickstart. Every example on this page shares the same permission setup and exit behavior:- Permission mode: the example prompts ask Claude to do real work on a project, so each example sets
permissionMode: "acceptEdits"(TypeScript) orpermission_mode="acceptEdits"(Python) to auto-approve the file edits that work produces. See Permission modes for the alternatives. - Turn limit: each example runs until the agent finishes and yields its final result message. If a session reaches its turn limit first, that result message has the
error_max_turnssubtype. Checksubtypeto detect that ending. - Error handling: these examples use single-shot
query()calls. After yielding anerror_max_turnsresult,query()raises an error that includesReached maximum number of turns. Each example wraps its loop in a try block to exit cleanly when that happens. See Handle the result for the result subtypes.
The task system messages,
SDKTaskNotificationMessage (TypeScript) or TaskNotificationMessage (Python) among them, report background tasks such as backgrounded commands and subagents. In the message stream, you see todo activity as tool_use blocks in the assistant messages.Monitor todo changes
The following example watches the assistant stream forTaskCreate and TaskUpdate tool_use blocks and prints a + line with each new task’s subject and an update line with each status change’s task ID and new status. Use this shape when you want a log of task activity rather than a rendered display. The + lines don’t include the assigned IDs, so this log can’t match updates back to their creates. To keep that correlation, capture the IDs as Display progress in real time does.
The streamed tool_use input is the raw shape the model emitted. Claude Code repairs some close-but-incorrect key names before execution, mapping id or task_id to taskId and active_form to activeForm, but that repair is not reflected in the stream. Read TaskUpdate input fields defensively, as both examples on this page do, rather than assuming the canonical name is always present.
Display progress in real time
The following example watches the assistant stream forTaskCreate and TaskUpdate tool_use blocks and keeps a map of tasks keyed by task ID in a TaskTracker class, rerendering a progress summary on every change. The summary counts completed and in-progress tasks and shows each active item’s activeForm label in place of its subject. Use this shape when your application maintains a progress display instead of logging each event.
The assigned task ID isn’t in the TaskCreate input. Claude Code delivers each tool’s structured output on the user message that carries its tool_result block, in the tool_use_result field. For TaskCreate, that object is documented for TypeScript as TaskCreateOutput under Tool Output Types, and in Python the field is a plain dict of the same shape. The tracker pairs each tool_result block with its tool_use call by tool_use_id and reads task.id from the paired message’s tool_use_result. Claude can read the list back with TaskList and one task’s full details with TaskGet.
Related documentation
- Agent SDK reference - TypeScript: the options, types, and tool schemas for the TypeScript SDK, including the Task tool input and output types
- Agent SDK reference - Python: the options, types, and tool documentation for the Python SDK
- Streaming Input: the two input modes, and when to use streaming input instead of the single-shot calls these examples use
- Give Claude custom tools: define your own tools with the SDK’s in-process MCP server