Skip to main content
Deep Agents 基于 LangGraph 的流式处理基础设施构建，并提供对子代理流的一流支持。当深度代理将工作委托给子代理时，您可以独立地从每个子代理流式传输更新——实时跟踪进度、LLM 令牌和工具调用。 深度代理流式处理能实现什么：

​
启用子图流式处理

Deep Agents 使用 LangGraph 的子图流式处理来呈现来自子代理执行的事件。要接收子代理事件，请在流式处理时启用 stream_subgraphs。 
from deepagents import create_deep_agent

agent = create_deep_agent(
    model="google_genai:gemini-3.1-pro-preview",
    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"]:
            # 子代理事件 - 命名空间标识来源
            print(f"[subagent: {chunk['ns']}]")
        else:
            # 主代理事件
            print("[main agent]")
        print(chunk["data"])

​
命名空间

当启用 subgraphs 时，每个流式处理事件都包含一个命名空间，用于标识产生该事件的代理。命名空间是节点名称和任务 ID 的路径，表示代理层次结构。
命名空间来源
() (空)主代理
("tools:abc123",)由主代理的 task 工具调用 abc123 生成的子代理
("tools:abc123", "model_request:def456")子代理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： 
for chunk in agent.stream(
    {"messages": [{"role": "user", "content": "Plan my vacation"}]},
    stream_mode="updates",
    subgraphs=True,
    version="v2",
):
    if chunk["type"] == "updates":
        # 检查此事件是否来自子代理
        is_subagent = any(
            segment.startswith("tools:") for segment in chunk["ns"]
        )

        if is_subagent:
            # 从命名空间中提取工具调用 ID
            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']}")

​
子代理进度

使用 stream_mode="updates" 在每个步骤完成时跟踪子代理进度。这对于显示哪些子代理处于活动状态以及它们完成了哪些工作非常有用。 
from deepagents import create_deep_agent

agent = create_deep_agent(
    model="google_genai:gemini-3.1-pro-preview",
    system_prompt=(
        "You are a project coordinator. Always delegate research tasks "
        "to your researcher subagent using the task tool. 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":
        # 主代理更新（空命名空间）
        if not chunk["ns"]:
            for node_name, data in chunk["data"].items():
                if node_name == "tools":
                    # 返回给主代理的子代理结果
                    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}")

        # 子代理更新（非空命名空间）
        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

​
LLM 令牌

使用 stream_mode="messages" 从主代理和子代理流式传输单个令牌。每个消息事件都包含标识来源代理的元数据。 
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"]

        # 检查此事件是否来自子代理（命名空间包含 "tools:"）
        is_subagent = any(s.startswith("tools:") for s in chunk["ns"])

        if is_subagent:
            # 来自子代理的令牌
            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:
            # 来自主代理的令牌
            if "main" != current_source:
                print("\n\n--- [main agent] ---")
                current_source = "main"
            if token.content:
                print(token.content, end="", flush=True)

print()

​
工具调用

当子代理使用工具时，您可以流式传输工具调用事件以显示每个子代理正在做什么。工具调用块出现在 messages 流模式中。 
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"]

        # 识别来源："main" 或子代理命名空间段
        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"

        # 工具调用块（流式工具调用）
        if token.tool_call_chunks:
            for tc in token.tool_call_chunks:
                if tc.get("name"):
                    print(f"\n[{source}] Tool call: {tc['name']}")
                # 参数以块形式流式传输 - 增量写入
                if tc.get("args"):
                    print(tc["args"], end="", flush=True)

        # 工具结果
        if token.type == "tool":
            print(f"\n[{source}] Tool result [{token.name}]: {str(token.content)[:150]}")

        # 常规 AI 内容（跳过工具调用消息）
        if token.type == "ai" and token.content and not token.tool_call_chunks:
            print(token.content, end="", flush=True)

print()

​
自定义更新

在子代理工具内使用 get_stream_writer 发出自定义进度事件： 
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-3.1-pro-preview",
    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],
        },
    ],
)

for chunk in agent.stream(
    {"messages": [{"role": "user", "content": "Analyze customer satisfaction trends"}]},
    stream_mode="custom",
    subgraphs=True,
    version="v2",
):
    if chunk["type"] == "custom":
        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}

​
流式传输多种模式

组合多种流模式以获取代理执行的完整视图： 
# 跳过内部中间件步骤 - 仅显示有意义的节点名称
INTERESTING_NODES = {"model_request", "tools"}

last_source = ""
mid_line = False  # 当我们写入令牌而没有尾随换行符时为 True

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:
            # 当来源更改时打印标题
            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()

​
常见模式

​
跟踪子代理生命周期

监控子代理何时启动、运行和完成： 
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():
            # ─── 阶段 1：检测子代理启动 ────────────────────────
            # 当主代理的 model_request 包含 task 工具调用时，
            # 子代理已被生成。
            if not chunk["ns"] and node_name == "model_request":
                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"]})'
                            )

            # ─── 阶段 2：检测子代理运行 ─────────────────────────
            # 当我们从 tools:UUID 命名空间接收到事件时，
            # 该子代理正在主动执行。
            if chunk["ns"] and chunk["ns"][0].startswith("tools:"):
                pregel_id = chunk["ns"][0].split(":")[1]
                # 检查是否有待处理的子代理需要标记为运行中。
                # 注意：pregel 任务 ID 与 tool_call_id 不同，
                # 因此我们在第一个子代理事件时将任何待处理的子代理标记为运行中。
                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

            # ─── 阶段 3：检测子代理完成 ──────────────────────
            # 当主代理的 tools 节点返回工具消息时，
            # 子代理已完成并返回了其结果。
            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]}...")

# 打印最终状态
print("\n--- Final subagent states ---")
for sub_id, sub in active_subagents.items():
    print(f"  {sub['type']}: {sub['status']}")

​
v2 流式处理格式

需要 LangGraph >= 1.1。
本页上的所有示例都使用 v2 流式处理格式（version="v2"），这是推荐的方法。每个块都是一个 StreamPart 字典，包含 type、ns 和 data 键——无论流模式、模式数量或子图设置如何，其结构都相同。 v2 格式消除了嵌套元组解包，使得在 Deep Agents 中处理子图流式处理变得简单直接。比较两种格式： 
# 统一格式 - 无嵌套元组解包
for chunk in agent.stream(
    {"messages": [{"role": "user", "content": "Research quantum computing"}]},
    stream_mode=["updates", "messages", "custom"],
    subgraphs=True,
    version="v2",
):
    print(chunk["type"])  # "updates"、"messages" 或 "custom"
    print(chunk["ns"])    # 主代理为 ()，子代理为 ("tools:<id>",)
    print(chunk["data"])  # 有效负载
有关 v2 格式的更多详细信息，包括类型收窄和 Pydantic/dataclass 强制转换，请参阅 LangGraph 流式处理文档。

​
相关内容

将这些文档连接到 Claude、VSCode 等，通过 MCP 获取实时答案。
在 GitHub 上编辑此页面 或 提交问题。