Event streaming

Stream subagents, messages, tool calls, and final output from Deep Agents.

This page covers streaming concerns specific to Deep Agents—most importantly, streaming from delegated subagents via stream.subagents. For general agent streaming (stream.messages, stream.values, tool calls, custom updates), see LangChain Event Streaming.

Stream subagents

Deep Agents add a subagent projection on top of LangGraph streaming. Use stream.subagents when you want one stream handle per delegated task call. The projection is lightweight: it discovers subagent tasks first, and message, tool-call, and value streams are opened only when you access them on a subagent handle.

const stream = await agent.streamEvents(
  { messages: [{ role: "user", content: "Write me a haiku about the sea" }] },
  { version: "v3" }
);

for await (const subagent of stream.subagents) {
  console.log(subagent.name);
  console.log(await subagent.taskInput);

  for await (const message of subagent.messages) {
    console.log(await message.text);
  }
}

Subagent stream fields

Each subagent stream exposes the same kinds of projections as the parent run, such as messages, tool calls, nested subagents, and final output. For the general parent-run streaming model, see LangChain Event Streaming.

TypeScript uses camelCase projection names such as toolCalls and taskInput.

Field	Description
name	Subagent name.
messages	Messages emitted by the subagent.
subagents	Nested subagent invocations.
output	Final subagent state, or completion signal for the delegated task.

| taskInput | Promise for the prompt passed to the task tool. | | toolCalls | Tool calls scoped to the subagent. |

Track subagent lifecycle

Use stream.subagents when you only need to show which subagents started and finished. You do not need to subscribe to message or value streams unless you access those projections on an individual subagent.

const stream = await agent.streamEvents(input, { version: "v3" });

let running = 0;
let completed = 0;
let failed = 0;
const watchers: Promise<void>[] = [];

for await (const subagent of stream.subagents) {
  running += 1;
  console.log(`${subagent.name}: started`);

  watchers.push(
    subagent.output.then(
      () => {
        running -= 1;
        completed += 1;
        console.log(`${subagent.name}: completed`);
      },
      () => {
        running -= 1;
        failed += 1;
        console.log(`${subagent.name}: failed`);
      }
    )
  );
}

await Promise.all(watchers);
console.log({ running, completed, failed });

Stream messages

Deep Agents can emit messages from the coordinator agent and from delegated subagents. Use stream.messages for top-level messages and subagent.messages for each delegated subagent.

const stream = await agent.streamEvents(input, { version: "v3" });

for await (const message of stream.messages) {
  console.log("[coordinator]", await message.text);
}

for await (const subagent of stream.subagents) {
  for await (const message of subagent.messages) {
    console.log(`[${subagent.name}]`, await message.text);
  }
}

Stream tool calls

Deep Agents expose tool calls at each level of the agent tree. Use the top-level stream.tool_calls for coordinator tools and each subagent.tool_calls for delegated work.

const stream = await agent.streamEvents(input, { version: "v3" });

for await (const call of stream.toolCalls) {
  console.log("[coordinator tool]", call.name, call.input);
  console.log(await call.status);
}

for await (const subagent of stream.subagents) {
  for await (const call of subagent.toolCalls) {
    console.log(`[${subagent.name} tool]`, call.name, call.input);

    const status = await call.status;
    if (status === "finished") {
      console.log(await call.output);
    } else if (status === "error") {
      console.error(await call.error);
    }
  }
}

Stream nested work

You can recurse into a subagent stream to observe nested subagents, messages, and tool calls.

const stream = await agent.streamEvents(input, { version: "v3" });

for await (const subagent of stream.subagents) {
  console.log(`subagent ${subagent.name}: started`);

  for await (const toolCall of subagent.toolCalls) {
    console.log(`${toolCall.name}(${JSON.stringify(toolCall.input)})`);

    const status = await toolCall.status;
    if (status === "finished") {
      console.log(await toolCall.output);
    } else if (status === "error") {
      console.error(await toolCall.error);
    }
  }

  for await (const nested of subagent.subagents) {
    console.log(`nested subagent ${nested.name}: started`);
  }
}

Consume concurrently

Coordinator and subagent output often interleave. Consume projections concurrently when you need live UI updates.

Use concurrent consumers in JavaScript:

const stream = await agent.streamEvents(input, { version: "v3" });

await Promise.all([
  (async () => {
    for await (const message of stream.messages) {
      console.log("[coordinator]", await message.text);
    }
  })(),
  (async () => {
    for await (const subagent of stream.subagents) {
      void (async () => {
        for await (const message of subagent.messages) {
          console.log(`[${subagent.name}]`, await message.text);
        }
      })();
    }
  })(),
]);

When you need exact arrival order across the coordinator and all subagents, iterate raw protocol events and use namespace to identify the source:

Subagents versus subgraphs

stream.subgraphs shows graph execution structure. stream.subagents shows product-level Deep Agents task delegations. Use stream.subagents for user-facing UI because it hides internal graph nodes and exposes the subagent concept directly.

Related

• LangChain Event Streaming covers general agent message and tool-call streaming concepts.
• Subagent frontend streaming shows UI patterns that separate coordinator messages from subagent cards.
• LangGraph Event Streaming covers the underlying graph streaming model.

---

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.