流式传输

从深度智能体运行和子智能体执行中流式传输实时更新

对于新应用，我们推荐 事件流——Deep Agents v0.6 中引入的 typed-projection API。事件流为每个投影（子智能体、消息、工具调用、值）提供独立的迭代器，因此您可以独立消费它们，而不是在 stream_mode 块上分支。

Deep Agents 基于 LangGraph 的流式基础设施构建，并针对子智能体流提供了一流支持。当深度智能体将工作委托给子智能体时，您可以从每个子智能体独立地流式传输更新——实时跟踪进度、LLM Token 和工具调用。

深度智能体流式传输可以实现的功能：

• 流式传输子智能体进度—跟踪每个子智能体在并行运行时的执行情况。
• 流式传输 LLM Token—从主智能体和每个子智能体流式传输 Token。
• 流式传输工具调用—查看子智能体执行中的工具调用和结果。
• 流式传输自定义更新—从子智能体节点内部发出用户定义的信号。

启用子图流式传输

Deep Agents 使用 LangGraph 的子图流式传输来暴露子智能体执行中的事件。要接收子智能体事件，在流式传输时启用 stream_subgraphs。

:::python

Google

from deepagents import create_deep_agent

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    system_prompt="You are a helpful research assistant",
    subagents=[
        {
            "name": "researcher",
            "description": "Researches a topic in depth",
            "system_prompt": "You are a thorough researcher.",
        },
    ],
)

for chunk in agent.stream(
    {"messages": [{"role": "user", "content": "Research quantum computing advances"}]},
    stream_mode="updates",
    subgraphs=True,  
    version="v2",  
):
    if chunk["type"] == "updates":
        if chunk["ns"]:
            # Subagent event - namespace identifies the source
            print(f"[subagent: {chunk['ns']}]")
        else:
            # Main agent event
            print("[main agent]")
        print(chunk["data"])

:::

:::js

Google

import { createDeepAgent } from "deepagents";

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  systemPrompt: "You are a helpful research assistant",
  subagents: [
    {
      name: "researcher",
      description: "Researches a topic in depth",
      systemPrompt: "You are a thorough researcher.",
    },
  ],
});

for await (const [namespace, chunk] of await agent.stream(
  {
    messages: [
      { role: "user", content: "Research quantum computing advances" },
    ],
  },
  {
    streamMode: "updates",
    subgraphs: true, 
  },
)) {
  if (namespace.length > 0) {
    // Subagent event - namespace identifies the source
    console.log(`[subagent: ${namespace.join("|")}]`);
  } else {
    // Main agent event
    console.log("[main agent]");
  }
  console.log(chunk);
}

View example trace

为此示例打开一个公开的 LangSmith 运行。

:::

命名空间

当 subgraphs 启用时，每个流式传输事件都包含一个 命名空间，用于标识哪个智能体生成了它。命名空间是节点名称和任务 ID 的路径，表示智能体层次结构。

命名空间	源
() (空)	主智能体
("tools:abc123",)	主智能体通过 task 工具调用 abc123 生成的子智能体
("tools:abc123", "model_request:def456")	子智能体内部的模型请求节点

使用命名空间将事件路由到正确的 UI 组件：

:::python

for chunk in agent.stream(
    {"messages": [{"role": "user", "content": "Plan my vacation"}]},
    stream_mode="updates",
    subgraphs=True,
    version="v2",
):
    if chunk["type"] == "updates":
        # Check if this event came from a subagent
        is_subagent = any(
            segment.startswith("tools:") for segment in chunk["ns"]
        )

        if is_subagent:
            # Extract the tool call ID from the namespace
            tool_call_id = next(
                s.split(":")[1] for s in chunk["ns"] if s.startswith("tools:")
            )
            print(f"Subagent {tool_call_id}: {chunk['data']}")
        else:
            print(f"Main agent: {chunk['data']}")

:::

:::js

for await (const [namespace, chunk] of await agent.stream(
  { messages: [{ role: "user", content: "Plan my vacation" }] },
  { streamMode: "updates", subgraphs: true },
)) {
  // Check if this event came from a subagent
  const isSubagent = namespace.some((segment: string) =>
    segment.startsWith("tools:"),
  );

  if (isSubagent) {
    // Extract the tool call ID from the namespace
    const toolCallId = namespace
      .find((s: string) => s.startsWith("tools:"))
      ?.split(":")[1];
    console.log(`Subagent ${toolCallId}:`, chunk);
  } else {
    console.log("Main agent:", chunk);
  }
}

View example trace

为此示例打开一个公开的 LangSmith 运行。

:::

子智能体进度

使用 stream_mode="updates" 跟踪子智能体进度，每当一个步骤完成时。这对于显示哪些子智能体处于活动状态以及它们已完成的工作很有用。

:::python

Google

from deepagents import create_deep_agent

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    system_prompt=(
        "You are a project coordinator with no research knowledge. "
        "For every user request, you must call the task() tool with "
        "subagent_type set to researcher. Never answer research questions yourself. "
        "Keep your final response to one sentence."
    ),
    subagents=[
        {
            "name": "researcher",
            "description": "Researches topics thoroughly",
            "system_prompt": (
                "You are a thorough researcher. Research the given topic "
                "and provide a concise summary in 2-3 sentences."
            ),
        },
    ],
)

for chunk in agent.stream(
    {"messages": [{"role": "user", "content": "Write a short summary about AI safety"}]},
    stream_mode="updates",
    subgraphs=True,
    version="v2",
):
    if chunk["type"] == "updates":
        # Main agent updates (empty namespace)
        if not chunk["ns"]:
            for node_name, data in chunk["data"].items():
                if node_name == "tools":
                    # Subagent results returned to main agent
                    for msg in data.get("messages", []):
                        if msg.type == "tool":
                            print(f"\nSubagent complete: {msg.name}")
                            print(f"  Result: {str(msg.content)[:200]}...")
                else:
                    print(f"[main agent] step: {node_name}")

        # Subagent updates (non-empty namespace)
        else:
            for node_name, data in chunk["data"].items():
                print(f"  [{chunk['ns'][0]}] step: {node_name}")

Output

[main agent] step: model_request
  [tools:call_abc123] step: model_request
  [tools:call_abc123] step: tools
  [tools:call_abc123] step: model_request

Subagent complete: task
  Result: ## AI Safety Report...
[main agent] step: model_request

:::

:::js

Google

import { createDeepAgent } from "deepagents";

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  systemPrompt:
    "You are a project coordinator with no research knowledge. " +
    "For every user request, you must call the task() tool with " +
    "subagent_type set to researcher. Never answer research questions yourself. " +
    "Keep your final response to one sentence.",
  subagents: [
    {
      name: "researcher",
      description: "Researches topics thoroughly",
      systemPrompt:
        "You are a thorough researcher. Research the given topic " +
        "and provide a concise summary in 2-3 sentences.",
    },
  ],
});

for await (const [namespace, chunk] of await agent.stream(
  {
    messages: [
      { role: "user", content: "Write a short summary about AI safety" },
    ],
  },
  { streamMode: "updates", subgraphs: true },
)) {
  // Main agent updates (empty namespace)
  if (namespace.length === 0) {
    for (const [nodeName, data] of Object.entries(chunk)) {
      if (nodeName === "tools") {
        // Subagent results returned to main agent
        for (const msg of (data as any).messages ?? []) {
          if (msg.type === "tool") {
            console.log(`\nSubagent complete: ${msg.name}`);
            console.log(`  Result: ${String(msg.content).slice(0, 200)}...`);
          }
        }
      } else {
        console.log(`[main agent] step: ${nodeName}`);
      }
    }
  }
  // Subagent updates (non-empty namespace)
  else {
    for (const [nodeName] of Object.entries(chunk)) {
      console.log(`  [${namespace[0]}] step: ${nodeName}`);
    }
  }
}

View example trace

为此示例打开一个公开的 LangSmith 运行。

Output

Main agent step: model_request
  [tools:call_abc123] step: model_request
  [tools:call_abc123] step: tools
  [tools:call_abc123] step: model_request
Subagent complete: task
Result: ## AI Safety Report...
Main agent step: model_request
  [tools:call_def456] step: model_request
  [tools:call_def456] step: model_request
Subagent complete: task
Result: # Comprehensive Report on AI Safety...
Main agent step: model_request

:::

LLM Token

使用 stream_mode="messages" 从主智能体和子智能体流式传输单个 Token。每个消息事件都包含标识源智能体的元数据。

:::python

current_source = ""

for chunk in agent.stream(
    {"messages": [{"role": "user", "content": "Research quantum computing advances"}]},
    stream_mode="messages",
    subgraphs=True,
    version="v2",
):
    if chunk["type"] == "messages":
        token, metadata = chunk["data"]

        # Check if this event came from a subagent (namespace contains "tools:")
        is_subagent = any(s.startswith("tools:") for s in chunk["ns"])

        if is_subagent:
            # Token from a subagent
            subagent_ns = next(s for s in chunk["ns"] if s.startswith("tools:"))
            if subagent_ns != current_source:
                print(f"\n\n--- [subagent: {subagent_ns}] ---")
                current_source = subagent_ns
            if token.content:
                print(token.content, end="", flush=True)
        else:
            # Token from the main agent
            if "main" != current_source:
                print("\n\n--- [main agent] ---")
                current_source = "main"
            if token.content:
                print(token.content, end="", flush=True)

print()

:::

:::js

let currentSource = "";

for await (const [namespace, chunk] of await agent.stream(
  {
    messages: [
      {
        role: "user",
        content: "Research quantum computing advances",
      },
    ],
  },
  { streamMode: "messages", subgraphs: true },
)) {
  const [message] = chunk;

  // Check if this event came from a subagent (namespace contains "tools:")
  const isSubagent = namespace.some((s: string) => s.startsWith("tools:"));

  if (isSubagent) {
    // Token from a subagent
    const subagentNs = namespace.find((s: string) => s.startsWith("tools:"))!;
    if (subagentNs !== currentSource) {
      process.stdout.write(`\n\n--- [subagent: ${subagentNs}] ---\n`);
      currentSource = subagentNs;
    }
    if (message.text) {
      process.stdout.write(message.text);
    }
  } else {
    // Token from the main agent
    if ("main" !== currentSource) {
      process.stdout.write(`\n\n--- [main agent] ---\n`);
      currentSource = "main";
    }
    if (message.text) {
      process.stdout.write(message.text);
    }
  }
}

process.stdout.write("\n");

View example trace

为此示例打开一个公开的 LangSmith 运行。

:::

工具调用

当子智能体使用工具时，您可以将工具调用事件流式传输出来以显示每个子智能体正在做什么。工具调用块出现在 messages 流式传输模式中。

:::python

from langchain.messages import AIMessageChunk, ToolMessage

for chunk in agent.stream(
    {"messages": [{"role": "user", "content": "Research recent quantum computing advances"}]},
    stream_mode="messages",
    subgraphs=True,
    version="v2",
):
    if chunk["type"] == "messages":
        token, metadata = chunk["data"]

        # Identify source: "main" or the subagent namespace segment
        is_subagent = any(s.startswith("tools:") for s in chunk["ns"])
        source = next((s for s in chunk["ns"] if s.startswith("tools:")), "main") if is_subagent else "main"

        # Tool call chunks (streaming tool invocations)
        if isinstance(token, AIMessageChunk) and token.tool_call_chunks:
            for tc in token.tool_call_chunks:
                if tc.get("name"):
                    print(f"\n[{source}] Tool call: {tc['name']}")
                # Args stream in chunks - write them incrementally
                if tc.get("args"):
                    print(tc["args"], end="", flush=True)

        # Tool results
        if isinstance(token, ToolMessage):
            print(f"\n[{source}] Tool result [{token.name}]: {str(token.content)[:150]}")

        # Regular AI content (skip tool call messages)
        if (
            isinstance(token, AIMessageChunk)
            and token.content
            and not token.tool_call_chunks
        ):
            print(token.content, end="", flush=True)

print()

:::

:::js

import { AIMessageChunk, ToolMessage } from "langchain";

for await (const [namespace, chunk] of await agent.stream(
  {
    messages: [
      {
        role: "user",
        content: "Research recent quantum computing advances",
      },
    ],
  },
  { streamMode: "messages", subgraphs: true },
)) {
  const [message] = chunk;

  // Identify source: "main" or the subagent namespace segment
  const isSubagent = namespace.some((s: string) => s.startsWith("tools:"));
  const source = isSubagent
    ? namespace.find((s: string) => s.startsWith("tools:"))!
    : "main";

  // Tool call chunks (streaming tool invocations)
  if (AIMessageChunk.isInstance(message) && message.tool_call_chunks?.length) {
    for (const tc of message.tool_call_chunks) {
      if (tc.name) {
        console.log(`\n[${source}] Tool call: ${tc.name}`);
      }
      // Args stream in chunks - write them incrementally
      if (tc.args) {
        process.stdout.write(tc.args);
      }
    }
  }

  // Tool results
  if (ToolMessage.isInstance(message)) {
    console.log(
      `\n[${source}] Tool result [${message.name}]: ${message.text?.slice(0, 150)}`,
    );
  }

  // Regular AI content (skip tool call messages)
  if (
    AIMessageChunk.isInstance(message) &&
    message.text &&
    !message.tool_call_chunks?.length
  ) {
    process.stdout.write(message.text);
  }
}

process.stdout.write("\n");

View example trace

为此示例打开一个公开的 LangSmith 运行。

:::

自定义更新

:::python 在您的子智能体工具内部使用 @[get_stream_writer] 发出自定义进度事件： :::

:::js 在您的子智能体工具内部使用 config.writer 发出自定义进度事件： :::

:::python

Google

import time
from langchain.tools import tool
from langgraph.config import get_stream_writer
from deepagents import create_deep_agent


@tool
def analyze_data(topic: str) -> str:
    """Run a data analysis on a given topic.

    This tool performs the actual analysis and emits progress updates.
    You MUST call this tool for any analysis request.
    """
    writer = get_stream_writer()

    writer({"status": "starting", "topic": topic, "progress": 0})
    time.sleep(0.5)

    writer({"status": "analyzing", "progress": 50})
    time.sleep(0.5)

    writer({"status": "complete", "progress": 100})
    return (
        f'Analysis of "{topic}": Customer sentiment is 85% positive, '
        "driven by product quality and support response times."
    )


agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    system_prompt=(
        "You are a coordinator. For any analysis request, you MUST delegate "
        "to the analyst subagent using the task tool. Never try to answer directly. "
        "After receiving the result, summarize it in one sentence."
    ),
    subagents=[
        {
            "name": "analyst",
            "description": "Performs data analysis with real-time progress tracking",
            "system_prompt": (
                "You are a data analyst. You MUST call the analyze_data tool "
                "for every analysis request. Do not use any other tools. "
                "After the analysis completes, report the result."
            ),
            "tools": [analyze_data],
        },
    ],
)

custom_event_count = 0
for chunk in agent.stream(
    {"messages": [{"role": "user", "content": "Analyze customer satisfaction trends"}]},
    stream_mode="custom",
    subgraphs=True,
    version="v2",
):
    if chunk["type"] == "custom":
        custom_event_count += 1
        is_subagent = any(s.startswith("tools:") for s in chunk["ns"])
        if is_subagent:
            subagent_ns = next(s for s in chunk["ns"] if s.startswith("tools:"))
            print(f"[{subagent_ns}]", chunk["data"])
        else:
            print("[main]", chunk["data"])

Output

[tools:call_abc123] {'status': 'starting', 'topic': 'customer satisfaction trends', 'progress': 0}
[tools:call_abc123] {'status': 'analyzing', 'progress': 50}
[tools:call_abc123] {'status': 'complete', 'progress': 100}

:::

:::js

Google

import { createDeepAgent } from "deepagents";
import { tool, type ToolRuntime } from "langchain";
import { z } from "zod";

/**
 * A tool that emits custom progress events via config.writer.
 * The writer sends data to the "custom" stream mode.
 */
const analyzeData = tool(
  async ({ topic }: { topic: string }, config: ToolRuntime) => {
    const writer = config.writer;

    writer?.({ status: "starting", topic, progress: 0 });
    await new Promise((r) => setTimeout(r, 500));

    writer?.({ status: "analyzing", progress: 50 });
    await new Promise((r) => setTimeout(r, 500));

    writer?.({ status: "complete", progress: 100 });
    return `Analysis of "${topic}": Customer sentiment is 85% positive, driven by product quality and support response times.`;
  },
  {
    name: "analyze_data",
    description:
      "Run a data analysis on a given topic. " +
      "This tool performs the actual analysis and emits progress updates. " +
      "You MUST call this tool for any analysis request.",
    schema: z.object({
      topic: z.string().describe("The topic or subject to analyze"),
    }),
  },
);

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  systemPrompt:
    "You are a coordinator. For any analysis request, you MUST delegate " +
    "to the analyst subagent using the task tool. Never try to answer directly. " +
    "After receiving the result, summarize it in one sentence.",
  subagents: [
    {
      name: "analyst",
      description: "Performs data analysis with real-time progress tracking",
      systemPrompt:
        "You are a data analyst. You MUST call the analyze_data tool " +
        "for every analysis request. Do not use any other tools. " +
        "After the analysis completes, report the result.",
      tools: [analyzeData],
    },
  ],
});

for await (const [namespace, chunk] of await agent.stream(
  {
    messages: [
      {
        role: "user",
        content: "Analyze customer satisfaction trends",
      },
    ],
  },
  { streamMode: "custom", subgraphs: true },
)) {
  const isSubagent = namespace.some((s: string) => s.startsWith("tools:"));
  if (isSubagent) {
    const subagentNs = namespace.find((s: string) => s.startsWith("tools:"))!;
    console.log(`[${subagentNs}]`, chunk);
  } else {
    console.log("[main]", chunk);
  }
}

View example trace

为此示例打开一个公开的 LangSmith 运行。

Output

[tools:call_abc123] { status: 'fetching', progress: 0 }
[tools:call_abc123] { status: 'analyzing', progress: 50 }
[tools:call_abc123] { status: 'complete', progress: 100 }

:::

流式传输多种模式

组合多种流式传输模式以获取智能体执行的完整视图：

:::python

# Skip internal middleware steps - only show meaningful node names
INTERESTING_NODES = {"model", "tools"}

last_source = ""
mid_line = False  # True when we've written tokens without a trailing newline

for chunk in agent.stream(
    {"messages": [{"role": "user", "content": "Analyze the impact of remote work on team productivity"}]},
    stream_mode=["updates", "messages", "custom"],
    subgraphs=True,
    version="v2",
):
    is_subagent = any(s.startswith("tools:") for s in chunk["ns"])
    source = "subagent" if is_subagent else "main"

    if chunk["type"] == "updates":
        for node_name in chunk["data"]:
            if node_name not in INTERESTING_NODES:
                continue
            if mid_line:
                print()
                mid_line = False
            print(f"[{source}] step: {node_name}")

    elif chunk["type"] == "messages":
        token, metadata = chunk["data"]
        if token.content:
            # Print a header when the source changes
            if source != last_source:
                if mid_line:
                    print()
                    mid_line = False
                print(f"\n[{source}] ", end="")
                last_source = source
            print(token.content, end="", flush=True)
            mid_line = True

    elif chunk["type"] == "custom":
        if mid_line:
            print()
            mid_line = False
        print(f"[{source}] custom event:", chunk["data"])

print()

:::

:::js

// Skip internal middleware steps - only show meaningful node names
const INTERESTING_NODES = new Set(["model", "tools"]);

let lastSource = "";
let midLine = false; // true when we've written tokens without a trailing newline

for await (const [namespace, mode, data] of await agent.stream(
  {
    messages: [
      {
        role: "user",
        content: "Analyze the impact of remote work on team productivity",
      },
    ],
  },
  { streamMode: ["updates", "messages", "custom"], subgraphs: true },
)) {
  const isSubagent = namespace.some((s: string) => s.startsWith("tools:"));
  const source = isSubagent ? "subagent" : "main";

  if (mode === "updates") {
    for (const nodeName of Object.keys(data)) {
      if (!INTERESTING_NODES.has(nodeName)) continue;
      if (midLine) {
        process.stdout.write("\n");
        midLine = false;
      }
      console.log(`[${source}] step: ${nodeName}`);
    }
  } else if (mode === "messages") {
    const [message] = data;
    if (message.text) {
      // Print a header when the source changes
      if (source !== lastSource) {
        if (midLine) {
          process.stdout.write("\n");
          midLine = false;
        }
        process.stdout.write(`\n[${source}] `);
        lastSource = source;
      }
      process.stdout.write(message.text);
      midLine = true;
    }
  } else if (mode === "custom") {
    if (midLine) {
      process.stdout.write("\n");
      midLine = false;
    }
    console.log(`[${source}] custom event:`, data);
  }
}

process.stdout.write("\n");

View example trace

为此示例打开一个公开的 LangSmith 运行。

:::

常见模式

跟踪子智能体生命周期

监控子智能体启动、运行和完成的时间：

:::python

active_subagents = {}

for chunk in agent.stream(
    {"messages": [{"role": "user", "content": "Research the latest AI safety developments"}]},
    stream_mode="updates",
    subgraphs=True,
    version="v2",
):
    if chunk["type"] == "updates":
        for node_name, data in chunk["data"].items():
            # ─── Phase 1: Detect subagent starting ────────────────────────
            # When the main agent's model node contains task tool calls,
            # a subagent has been spawned.
            if not chunk["ns"] and node_name == "model":
                for msg in data.get("messages", []):
                    for tc in getattr(msg, "tool_calls", []):
                        if tc["name"] == "task":
                            active_subagents[tc["id"]] = {
                                "type": tc["args"].get("subagent_type"),
                                "description": tc["args"].get("description", "")[:80],
                                "status": "pending",
                            }
                            print(
                                f'[lifecycle] PENDING  → subagent "{tc["args"].get("subagent_type")}" '
                                f'({tc["id"]})'
                            )

            # ─── Phase 2: Detect subagent running ─────────────────────────
            # When we receive events from a tools:UUID namespace, that
            # subagent is actively executing.
            if chunk["ns"] and chunk["ns"][0].startswith("tools:"):
                pregel_id = chunk["ns"][0].split(":")[1]
                # Check if any pending subagent needs to be marked running.
                # Note: the pregel task ID differs from the tool_call_id,
                # so we mark any pending subagent as running on first subagent event.
                for sub_id, sub in active_subagents.items():
                    if sub["status"] == "pending":
                        sub["status"] = "running"
                        print(
                            f'[lifecycle] RUNNING  → subagent "{sub["type"]}" '
                            f"(pregel: {pregel_id})"
                        )
                        break

            # ─── Phase 3: Detect subagent completing ──────────────────────
            # When the main agent's tools node returns a tool message,
            # the subagent has completed and returned its result.
            if not chunk["ns"] and node_name == "tools":
                for msg in data.get("messages", []):
                    if msg.type == "tool":
                        sub = active_subagents.get(msg.tool_call_id)
                        if sub:
                            sub["status"] = "complete"
                            print(
                                f'[lifecycle] COMPLETE → subagent "{sub["type"]}" '
                                f"({msg.tool_call_id})"
                            )
                            print(f"  Result preview: {str(msg.content)[:120]}...")

# Print final state
print("\n--- Final subagent states ---")
for sub_id, sub in active_subagents.items():
    print(f"  {sub['type']}: {sub['status']}")

:::

:::js

function getToolCalls(message: unknown): Array<{
  id?: string;
  name?: string;
  args?: Record<string, unknown>;
}> {
  if (!message || typeof message !== "object") {
    return [];
  }
  const record = message as Record<string, unknown>;
  const toolCalls = record.tool_calls ?? record.toolCalls;
  return Array.isArray(toolCalls)
    ? (toolCalls as Array<{
        id?: string;
        name?: string;
        args?: Record<string, unknown>;
      }>)
    : [];
}

const activeSubagents = new Map<
  string,
  { type?: string; description?: string; status: string }
>();

for await (const [namespace, chunk] of await agent.stream(
  {
    messages: [
      { role: "user", content: "Research the latest AI safety developments" },
    ],
  },
  { streamMode: "updates", subgraphs: true },
)) {
  for (const [nodeName, data] of Object.entries(chunk)) {
    // ─── Phase 1: Detect subagent starting ────────────────────────
    // When the main agent emits a task tool call, a subagent has been spawned.
    if (namespace.length === 0) {
      for (const msg of (data as { messages?: unknown[] }).messages ?? []) {
        for (const tc of getToolCalls(msg)) {
          if (tc.name === "task" && tc.id) {
            activeSubagents.set(tc.id, {
              type: tc.args?.subagent_type as string | undefined,
              description: String(tc.args?.description ?? "").slice(0, 80),
              status: "pending",
            });
            console.log(
              `[lifecycle] PENDING  → subagent "${tc.args?.subagent_type}" (${tc.id})`,
            );
          }
        }
      }
    }

    // ─── Phase 2: Detect subagent running ─────────────────────────
    // When we receive events from a tools:UUID namespace, that
    // subagent is actively executing.
    if (namespace.length > 0 && namespace[0].startsWith("tools:")) {
      const pregelId = namespace[0].split(":")[1];
      // Check if any pending subagent needs to be marked running.
      // Note: the pregel task ID differs from the tool_call_id,
      // so we mark any pending subagent as running on first subagent event.
      let markedRunning = false;
      for (const [, sub] of activeSubagents) {
        if (sub.status === "pending") {
          sub.status = "running";
          markedRunning = true;
          console.log(
            `[lifecycle] RUNNING  → subagent "${sub.type}" (pregel: ${pregelId})`,
          );
          break;
        }
      }
      if (!markedRunning && activeSubagents.size === 0) {
        activeSubagents.set(pregelId, {
          type: "researcher",
          status: "running",
        });
        console.log(
          `[lifecycle] RUNNING  → subagent "researcher" (pregel: ${pregelId})`,
        );
      }
    }

    // ─── Phase 3: Detect subagent completing ──────────────────────
    // When the main agent's tools node returns a tool message,
    // the subagent has completed and returned its result.
    if (namespace.length === 0 && nodeName === "tools") {
      for (const msg of (data as { messages?: Array<Record<string, unknown>> })
        .messages ?? []) {
        if (msg.type === "tool") {
          const toolCallId = String(msg.tool_call_id ?? msg.toolCallId ?? "");
          const subagent = activeSubagents.get(toolCallId);
          if (subagent) {
            subagent.status = "complete";
            console.log(
              `[lifecycle] COMPLETE → subagent "${subagent.type}" (${toolCallId})`,
            );
            console.log(
              `  Result preview: ${String(msg.content).slice(0, 120)}...`,
            );
          }
        }
      }
    }
  }
}

// Print final state
console.log("\n--- Final subagent states ---");
for (const [id, sub] of activeSubagents) {
  console.log(`  ${sub.type}: ${sub.status}`);
}

View example trace

为此示例打开一个公开的 LangSmith 运行。

:::

处理人机交互中断

当 interrupt_on 配置时，updates 流中可能包含 __interrupt__ 条目，用于暂停执行以供人工批准。通过检查更新块中的 __interrupt__ 键来检测它们。使用与 .invoke() 相同的扁平 {"decisions": [...]} 负载继续：

:::python

from langchain_core.utils.uuid import uuid7

config = {"configurable": {"thread_id": str(uuid7())}}

for mode, data in agent.stream(
    {"messages": [{"role": "user", "content": "Delete temp.txt"}]},
    stream_mode=["messages", "updates"],
    config=config,
):
    if mode == "updates" and isinstance(data, dict):
        if "__interrupt__" in data:  
            for interrupt_obj in data["__interrupt__"]:
                print(f"Approval needed: {interrupt_obj.value}")

:::

:::js

import { v7 as uuid7 } from "uuid";

const config = { configurable: { thread_id: uuid7() } };

for await (const [mode, data] of await agent.stream(
  { messages: [{ role: "user", content: "Delete temp.txt" }] },
  { streamMode: ["messages", "updates"], ...config }
)) {
  if (mode === "updates" && data?.__interrupt__) {  
    for (const interruptObj of data.__interrupt__) {
      console.log("Approval needed:", interruptObj.value);
    }
  }
}

:::

参见 人机交互：使用流式传输处理中断，了解完整的流式恢复循环模式。

流式传输块形状

使用 subgraphs=True 时，块形状取决于您是否传递了一个流式传输模式或多个：

stream_mode	块形状
单一模式（例如 "updates"）	(namespace, data)
多种模式（例如 ["messages", "updates"]）	(namespace, mode, data)

没有 subgraphs，单一模式直接生成 data，多种模式生成 (mode, data)。

# Single mode + subgraphs
for namespace, data in agent.stream(
    {"messages": [{"role": "user", "content": "Research quantum computing"}]},
    stream_mode="updates",
    subgraphs=True,
):
    print(namespace)  # () for main agent, ("tools:<id>",) for subagent
    print(data)

# Multiple modes + subgraphs
for namespace, mode, data in agent.stream(
    {"messages": [{"role": "user", "content": "Research quantum computing"}]},
    stream_mode=["updates", "messages", "custom"],
    subgraphs=True,
):
    print(mode)       # "updates", "messages", or "custom"
    print(namespace)  # () for main agent, ("tools:<id>",) for subagent
    print(data)

:::python LangGraph 1.1 及更高版本还支持统一的 version="v2" StreamPart 字典格式。参见 流式输出格式 (v2)。本页上的深度智能体示例使用元组格式，该格式与深度智能体当前依赖的 LangGraph 版本匹配。 :::

相关

• 人机交互—为敏感工具操作配置审批工作流
• 子智能体—使用 Deep Agents 配置和使用子智能体
• 前端流式传输—使用 @[useStream] 为 Deep Agents 构建 React UI
• LangChain 事件流式传输—LangChain 智能体的通用流式传输概念

---

官方原文：src/oss/deepagents/streaming.mdx · 非官方翻译，译文由 AI 生成，以英文原文为准。