子图 - Docs by LangChain中文

本指南说明如何使用子图的机制。子图是一个作为另一个图中的节点使用的图。子图适用于：

构建多智能体系统
在多个图中复用一组节点
分布式开发：当你希望不同团队独立开发图的不同部分时，可以将每个部分定义为子图。只要遵守子图接口（输入和输出 schema），父图就可以在不了解子图任何实现细节的情况下构建完成

Setup

pip install -U langgraph

为 LangGraph 开发设置 LangSmith 注册 LangSmith，以便快速发现问题并提升 LangGraph 项目的性能。LangSmith 让你可以使用跟踪数据来调试、测试和监控使用 LangGraph 构建的 LLM 应用——阅读更多关于如何开始使用 LangSmith的信息。

Define subgraph communication

添加子图时，你需要定义父图和子图如何通信：

Pattern	When to use	State schemas
在节点内部调用子图	父图和子图具有不同的状态 schema（没有共享键），或者你需要在它们之间转换状态	你需要编写一个包装函数，将父状态映射为子图输入，并将子图输出映射回父状态
将子图作为节点添加	父图和子图共享状态键——子图从与父图相同的通道读取并写入	你可以将已编译的子图直接传给 `add_node`——不需要包装函数

Call a subgraph inside a node

当父图和子图具有不同的状态 schema（没有共享键）时，可以在节点函数内部调用子图。当你希望在多智能体系统中为每个智能体保留私有消息历史时，这种方式很常见。节点函数会先将父状态转换为子图状态，再调用子图；然后在返回前，将结果转换回父状态。

from typing_extensions import TypedDict
from langgraph.graph.state import StateGraph, START

class SubgraphState(TypedDict):
    bar: str

# Subgraph

def subgraph_node_1(state: SubgraphState):
    return {"bar": "hi! " + state["bar"]}

subgraph_builder = StateGraph(SubgraphState)
subgraph_builder.add_node(subgraph_node_1)
subgraph_builder.add_edge(START, "subgraph_node_1")
subgraph = subgraph_builder.compile()

# Parent graph

class State(TypedDict):
    foo: str

def call_subgraph(state: State):
    # Transform the state to the subgraph state
    subgraph_output = subgraph.invoke({"bar": state["foo"]})
    # Transform response back to the parent state
    return {"foo": subgraph_output["bar"]}

builder = StateGraph(State)
builder.add_node("node_1", call_subgraph)
builder.add_edge(START, "node_1")
graph = builder.compile()

Full example: different state schemas

from typing_extensions import TypedDict
from langgraph.graph.state import StateGraph, START

# Define subgraph
class SubgraphState(TypedDict):
    # note that none of these keys are shared with the parent graph state
    bar: str
    baz: str

def subgraph_node_1(state: SubgraphState):
    return {"baz": "baz"}

def subgraph_node_2(state: SubgraphState):
    return {"bar": state["bar"] + state["baz"]}

subgraph_builder = StateGraph(SubgraphState)
subgraph_builder.add_node(subgraph_node_1)
subgraph_builder.add_node(subgraph_node_2)
subgraph_builder.add_edge(START, "subgraph_node_1")
subgraph_builder.add_edge("subgraph_node_1", "subgraph_node_2")
subgraph = subgraph_builder.compile()

# Define parent graph
class ParentState(TypedDict):
    foo: str

def node_1(state: ParentState):
    return {"foo": "hi! " + state["foo"]}

def node_2(state: ParentState):
    # Transform the state to the subgraph state
    response = subgraph.invoke({"bar": state["foo"]})
    # Transform response back to the parent state
    return {"foo": response["bar"]}


builder = StateGraph(ParentState)
builder.add_node("node_1", node_1)
builder.add_node("node_2", node_2)
builder.add_edge(START, "node_1")
builder.add_edge("node_1", "node_2")
graph = builder.compile()

stream = graph.stream_events({"foo": "foo"}, version="v3")
for event in stream:
    if event["method"] == "updates":
        print(event["params"]["namespace"], event["params"]["data"])

[] {'node_1': {'foo': 'hi! foo'}}
['node_2:577b710b-64ae-31fb-9455-6a4d4cc2b0b9'] {'subgraph_node_1': {'baz': 'baz'}}
['node_2:577b710b-64ae-31fb-9455-6a4d4cc2b0b9'] {'subgraph_node_2': {'bar': 'hi! foobaz'}}
[] {'node_2': {'foo': 'hi! foobaz'}}

Full example: different state schemas (two levels of subgraphs)

这是一个包含两层子图的示例：父级 -> 子级 -> 孙级。

# Grandchild graph
from typing_extensions import TypedDict
from langgraph.graph.state import StateGraph, START, END

class GrandChildState(TypedDict):
    my_grandchild_key: str

def grandchild_1(state: GrandChildState) -> GrandChildState:
    # NOTE: child or parent keys will not be accessible here
    return {"my_grandchild_key": state["my_grandchild_key"] + ", how are you"}


grandchild = StateGraph(GrandChildState)
grandchild.add_node("grandchild_1", grandchild_1)

grandchild.add_edge(START, "grandchild_1")
grandchild.add_edge("grandchild_1", END)

grandchild_graph = grandchild.compile()

# Child graph
class ChildState(TypedDict):
    my_child_key: str

def call_grandchild_graph(state: ChildState) -> ChildState:
    # NOTE: parent or grandchild keys won't be accessible here
    grandchild_graph_input = {"my_grandchild_key": state["my_child_key"]}
    grandchild_graph_output = grandchild_graph.invoke(grandchild_graph_input)
    return {"my_child_key": grandchild_graph_output["my_grandchild_key"] + " today?"}

child = StateGraph(ChildState)
# We're passing a function here instead of just compiled graph (`grandchild_graph`)
child.add_node("child_1", call_grandchild_graph)
child.add_edge(START, "child_1")
child.add_edge("child_1", END)
child_graph = child.compile()

# Parent graph
class ParentState(TypedDict):
    my_key: str

def parent_1(state: ParentState) -> ParentState:
    # NOTE: child or grandchild keys won't be accessible here
    return {"my_key": "hi " + state["my_key"]}

def parent_2(state: ParentState) -> ParentState:
    return {"my_key": state["my_key"] + " bye!"}

def call_child_graph(state: ParentState) -> ParentState:
    child_graph_input = {"my_child_key": state["my_key"]}
    child_graph_output = child_graph.invoke(child_graph_input)
    return {"my_key": child_graph_output["my_child_key"]}

parent = StateGraph(ParentState)
parent.add_node("parent_1", parent_1)
# We're passing a function here instead of just a compiled graph (`child_graph`)
parent.add_node("child", call_child_graph)
parent.add_node("parent_2", parent_2)

parent.add_edge(START, "parent_1")
parent.add_edge("parent_1", "child")
parent.add_edge("child", "parent_2")
parent.add_edge("parent_2", END)

parent_graph = parent.compile()

stream = parent_graph.stream_events({"my_key": "Bob"}, version="v3")
for event in stream:
    if event["method"] == "updates":
        print(event["params"]["namespace"], event["params"]["data"])

[] {'parent_1': {'my_key': 'hi Bob'}}
['child:2e26e9ce-602f-862c-aa66-1ea5a4655e3b', 'child_1:781bb3b1-3971-84ce-810b-acf819a03f9c'] {'grandchild_1': {'my_grandchild_key': 'hi Bob, how are you'}}
['child:2e26e9ce-602f-862c-aa66-1ea5a4655e3b'] {'child_1': {'my_child_key': 'hi Bob, how are you today?'}}
[] {'child': {'my_key': 'hi Bob, how are you today?'}}
[] {'parent_2': {'my_key': 'hi Bob, how are you today? bye!'}}

Add a subgraph as a node

当父图和子图共享状态键时，你可以将已编译的子图直接传给 add_node。不需要包装函数——子图会自动从父图的状态通道中读取并写入。例如，在多智能体系统中，智能体通常会通过共享的 messages 键进行通信。 SQL agent graph

如果你的子图与父图共享状态键，可以按照以下步骤将其添加到图中：

定义子图工作流（下面示例中的 subgraph_builder）并编译它
在定义父图工作流时，将已编译的子图传给 add_node 方法

from typing_extensions import TypedDict
from langgraph.graph.state import StateGraph, START

class State(TypedDict):
    foo: str

# Subgraph

def subgraph_node_1(state: State):
    return {"foo": "hi! " + state["foo"]}

subgraph_builder = StateGraph(State)
subgraph_builder.add_node(subgraph_node_1)
subgraph_builder.add_edge(START, "subgraph_node_1")
subgraph = subgraph_builder.compile()

# Parent graph

builder = StateGraph(State)
builder.add_node("node_1", subgraph)
builder.add_edge(START, "node_1")
graph = builder.compile()

Full example: shared state schemas

from typing_extensions import TypedDict
from langgraph.graph.state import StateGraph, START

# Define subgraph
class SubgraphState(TypedDict):
    foo: str  # shared with parent graph state
    bar: str  # private to SubgraphState

def subgraph_node_1(state: SubgraphState):
    return {"bar": "bar"}

def subgraph_node_2(state: SubgraphState):
    # note that this node is using a state key ('bar') that is only available in the subgraph
    # and is sending update on the shared state key ('foo')
    return {"foo": state["foo"] + state["bar"]}

subgraph_builder = StateGraph(SubgraphState)
subgraph_builder.add_node(subgraph_node_1)
subgraph_builder.add_node(subgraph_node_2)
subgraph_builder.add_edge(START, "subgraph_node_1")
subgraph_builder.add_edge("subgraph_node_1", "subgraph_node_2")
subgraph = subgraph_builder.compile()

# Define parent graph
class ParentState(TypedDict):
    foo: str

def node_1(state: ParentState):
    return {"foo": "hi! " + state["foo"]}

builder = StateGraph(ParentState)
builder.add_node("node_1", node_1)
builder.add_node("node_2", subgraph)
builder.add_edge(START, "node_1")
builder.add_edge("node_1", "node_2")
graph = builder.compile()

stream = graph.stream_events({"foo": "foo"}, version="v3")
for event in stream:
    if event["method"] == "updates" and not event["params"]["namespace"]:
        print(event["params"]["data"])

{'node_1': {'foo': 'hi! foo'}}
{'node_2': {'foo': 'hi! foobar'}}

Subgraph persistence

使用子图时，你需要决定在两次调用之间如何处理它的内部数据。想象一个客服机器人会委派任务给专业子智能体：这个“账单专家”子智能体应该记住客户之前的问题，还是每次被调用时都重新开始？ .compile() 上的 checkpointer 参数控制子图持久化：

Mode	`checkpointer=`	Behavior
按调用	`None`（默认）	每次调用都重新开始，并继承父图的 checkpointer，以支持单次调用内的中断和持久执行。
按线程	`True`	状态会在同一线程的多次调用之间累积。每次调用都会从上一次结束的位置继续。
无状态	`False`	完全不进行 checkpoint——像普通函数调用一样运行。不支持中断或持久执行。

对于大多数应用来说，按调用是正确选择，包括子智能体处理独立请求的多智能体系统。当子智能体需要多轮对话记忆时（例如，一个会在多次交流中逐步建立上下文的研究助手），请使用按线程模式。

父图必须使用 checkpointer 编译，子图持久化功能（中断、状态检查、按线程记忆）才能工作。参见持久化。

下面的示例使用 LangChain 的 create_agent，这是构建智能体的常见方式。create_agent 底层会生成一个 LangGraph 图，因此所有子图持久化概念都可以直接应用。如果你使用原始的 LangGraph StateGraph 构建，同样的模式和配置选项也适用——详情参见 Graph API。

Stateful

有状态子图会继承父图的 checkpointer，从而启用中断、持久化和状态检查。这两种有状态模式的区别在于状态保留多久。

Per-invocation (default)

这是大多数应用推荐使用的模式，包括子智能体作为工具被调用的多智能体系统。它支持中断、持久化和并行调用，同时保持每次调用相互隔离。

当每次对子图的调用都是独立的，并且子智能体不需要记住之前调用中的任何内容时，请使用按调用持久化。这是最常见的模式，尤其适用于多智能体系统：子智能体处理一次性请求，比如“查询这个客户的订单”或“总结这份文档”。省略 checkpointer 或将其设置为 None。每次调用都会重新开始，但在单次调用内部，子图会继承父图的 checkpointer，并且可以使用 interrupt() 暂停和恢复。下面的示例使用两个子智能体（水果专家、蔬菜专家），并将它们包装为外层智能体的工具：

from langchain.agents import create_agent
from langchain.tools import tool
from langgraph.checkpoint.memory import MemorySaver
from langgraph.types import Command, interrupt

@tool
def fruit_info(fruit_name: str) -> str:
    """Look up fruit info."""
    return f"Info about {fruit_name}"

@tool
def veggie_info(veggie_name: str) -> str:
    """Look up veggie info."""
    return f"Info about {veggie_name}"

# Subagents - no checkpointer setting (inherits parent)
fruit_agent = create_agent(
    model="gpt-5.4-mini",
    tools=[fruit_info],
    prompt="You are a fruit expert. Use the fruit_info tool. Respond in one sentence.",
)

veggie_agent = create_agent(
    model="gpt-5.4-mini",
    tools=[veggie_info],
    prompt="You are a veggie expert. Use the veggie_info tool. Respond in one sentence.",
)

# Wrap subagents as tools for the outer agent
@tool
def ask_fruit_expert(question: str) -> str:
    """Ask the fruit expert. Use for ALL fruit questions."""
    response = fruit_agent.invoke(
        {"messages": [{"role": "user", "content": question}]},
    )
    return response["messages"][-1].content

@tool
def ask_veggie_expert(question: str) -> str:
    """Ask the veggie expert. Use for ALL veggie questions."""
    response = veggie_agent.invoke(
        {"messages": [{"role": "user", "content": question}]},
    )
    return response["messages"][-1].content

# Outer agent with checkpointer
agent = create_agent(
    model="gpt-5.4-mini",
    tools=[ask_fruit_expert, ask_veggie_expert],
    prompt=(
        "You have two experts: ask_fruit_expert and ask_veggie_expert. "
        "ALWAYS delegate questions to the appropriate expert."
    ),
    checkpointer=MemorySaver(),
)

Interrupts
Multi-turn
Multiple subgraph calls

每次调用都可以使用 interrupt() 暂停和恢复。在工具函数中添加 interrupt()，即可在继续执行前要求用户批准：

@tool
def fruit_info(fruit_name: str) -> str:
    """Look up fruit info."""
    interrupt("continue?")
    return f"Info about {fruit_name}"

from langgraph.types import Command

config = {"configurable": {"thread_id": "1"}}

# Stream events - the subagent's tool calls interrupt()
stream = agent.stream_events(
    {"messages": [{"role": "user", "content": "Tell me about apples"}]},
    config=config,
    version="v3",
)
output = stream.output  # drive the stream to completion
# stream.interrupts contains pending interrupts (and stream.interrupted is True)

# Resume - approve the interrupt
resumed = agent.stream_events(Command(resume=True), config=config, version="v3")
final = resumed.output

每次调用都会从全新的子智能体状态开始。子智能体不会记住之前的调用：

config = {"configurable": {"thread_id": "1"}}

# First call
response = agent.invoke(
    {"messages": [{"role": "user", "content": "Tell me about apples"}]},
    config=config,
)
# Subagent message count: 4

# Second call - subagent starts fresh, no memory of apples
response = agent.invoke(
    {"messages": [{"role": "user", "content": "Now tell me about bananas"}]},
    config=config,
)
# Subagent message count: 4 (still fresh!)

对同一个子图的多次调用不会产生冲突，因为每次调用都会获得自己的 checkpoint 命名空间：

config = {"configurable": {"thread_id": "1"}}

# LLM calls ask_fruit_expert for both apples and bananas
response = agent.invoke(
    {"messages": [{"role": "user", "content": "Tell me about apples and bananas"}]},
    config=config,
)
# Subagent message count: 4 (apples - fresh)
# Subagent message count: 4 (bananas - fresh)

Per-thread

当子智能体需要记住之前的交互时，请使用按线程持久化。例如，一个会在多次交流中逐步积累上下文的研究助手，或者一个会跟踪已经编辑过哪些文件的编码助手。子智能体的对话历史和数据会在同一线程的多次调用之间累积。每次调用都会从上一次结束的位置继续。使用 checkpointer=True 编译即可启用这种行为。

按线程子图不支持并行工具调用。当 LLM 可以将按线程子智能体作为工具使用时，它可能会尝试并行多次调用该工具（例如，同时询问水果专家关于苹果和香蕉的问题）。这会导致 checkpoint 冲突，因为两次调用都会写入同一个命名空间。下面的示例使用 LangChain 的 ToolCallLimitMiddleware 来避免这种情况。如果你使用纯 LangGraph StateGraph 构建，则需要自行阻止并行工具调用——例如，通过配置模型禁用并行工具调用，或者添加逻辑确保同一个子图不会被并行调用多次。

下面的示例使用一个通过 checkpointer=True 编译的水果专家子智能体：

from langchain.agents import create_agent
from langchain.agents.middleware import ToolCallLimitMiddleware
from langchain.tools import tool
from langgraph.checkpoint.memory import MemorySaver
from langgraph.types import Command, interrupt

@tool
def fruit_info(fruit_name: str) -> str:
    """Look up fruit info."""
    return f"Info about {fruit_name}"

# Subagent with checkpointer=True for persistent state
fruit_agent = create_agent(
    model="gpt-5.4-mini",
    tools=[fruit_info],
    prompt="You are a fruit expert. Use the fruit_info tool. Respond in one sentence.",
    checkpointer=True,
)

# Wrap subagent as a tool for the outer agent
@tool
def ask_fruit_expert(question: str) -> str:
    """Ask the fruit expert. Use for ALL fruit questions."""
    response = fruit_agent.invoke(
        {"messages": [{"role": "user", "content": question}]},
    )
    return response["messages"][-1].content

# Outer agent with checkpointer
# Use ToolCallLimitMiddleware to prevent parallel calls to per-thread subagents,
# which would cause checkpoint conflicts.
agent = create_agent(
    model="gpt-5.4-mini",
    tools=[ask_fruit_expert],
    prompt="You have a fruit expert. ALWAYS delegate fruit questions to ask_fruit_expert.",
    middleware=[
        ToolCallLimitMiddleware(tool_name="ask_fruit_expert", run_limit=1),
    ],
    checkpointer=MemorySaver(),
)

Interrupts
Multi-turn
Multiple subgraph calls

按线程子智能体像按调用模式一样支持 interrupt()。在工具函数中添加 interrupt()，即可要求用户批准：

@tool
def fruit_info(fruit_name: str) -> str:
    """Look up fruit info."""
    interrupt("continue?")
    return f"Info about {fruit_name}"

from langgraph.types import Command

config = {"configurable": {"thread_id": "1"}}

# Stream events - the subagent's tool calls interrupt()
stream = agent.stream_events(
    {"messages": [{"role": "user", "content": "Tell me about apples"}]},
    config=config,
    version="v3",
)
output = stream.output  # drive the stream to completion
# stream.interrupts contains pending interrupts (and stream.interrupted is True)

# Resume - approve the interrupt
resumed = agent.stream_events(Command(resume=True), config=config, version="v3")
final = resumed.output

状态会在多次调用之间累积——子智能体会记住过去的对话：

config = {"configurable": {"thread_id": "1"}}

# First call
response = agent.invoke(
    {"messages": [{"role": "user", "content": "Tell me about apples"}]},
    config=config,
)
# Subagent message count: 4

# Second call - subagent REMEMBERS apples conversation
response = agent.invoke(
    {"messages": [{"role": "user", "content": "Now tell me about bananas"}]},
    config=config,
)
# Subagent message count: 8 (accumulated!)

当你有多个不同的按线程子图时（例如，一个水果专家和一个蔬菜专家），每个子图都需要自己的存储空间，这样它们的 checkpoint 才不会互相覆盖。这称为命名空间隔离。如果你在节点内部调用子图，LangGraph 会根据调用顺序分配命名空间（第一次调用、第二次调用，等等）。这意味着如果你重新排序调用，可能会混淆哪个子图加载哪个状态。为避免这种情况，请将每个子智能体包装到自己的 StateGraph 中，并使用唯一的节点名称——这会为每个子图提供稳定且唯一的命名空间：

from langgraph.graph import MessagesState, StateGraph

def create_sub_agent(model, *, name, **kwargs):
    """Wrap an agent with a unique node name for namespace isolation."""
    agent = create_agent(model=model, name=name, **kwargs)
    return (
        StateGraph(MessagesState)
        .add_node(name, agent)  # unique name → stable namespace  #
        .add_edge("__start__", name)
        .compile()
    )

fruit_agent = create_sub_agent(
    "gpt-5.4-mini", name="fruit_agent",
    tools=[fruit_info], prompt="...", checkpointer=True,
)
veggie_agent = create_sub_agent(
    "gpt-5.4-mini", name="veggie_agent",
    tools=[veggie_info], prompt="...", checkpointer=True,
)

config = {"configurable": {"thread_id": "1"}}

# First call - LLM calls both fruit and veggie experts
response = agent.invoke(
    {"messages": [{"role": "user", "content": "Tell me about cherries and broccoli"}]},
    config=config,
)
# Fruit subagent message count: 4
# Veggie subagent message count: 4

# Second call - both agents accumulate independently
response = agent.invoke(
    {"messages": [{"role": "user", "content": "Now tell me about oranges and carrots"}]},
    config=config,
)
# Fruit subagent message count: 8 (remembers cherries!)
# Veggie subagent message count: 8 (remembers broccoli!)

作为节点添加的子图已经会自动获得基于名称的命名空间，因此不需要这个包装器。

Stateless

当你希望像普通函数调用一样运行子智能体、且不想承担 checkpoint 开销时，请使用此模式。子图不能暂停/恢复，也无法受益于持久执行。使用 checkpointer=False 编译。

如果没有 checkpoint，子图就没有持久执行能力。如果进程在运行中崩溃，子图无法恢复，必须从头重新运行。

subgraph_builder = StateGraph(...)
subgraph = subgraph_builder.compile(checkpointer=False)

Checkpointer reference

通过 .compile() 上的 checkpointer 参数控制子图持久化：

subgraph = builder.compile(checkpointer=False)  # or True / None

Feature	Per-invocation (default)	Per-thread	Stateless
`checkpointer=`	`None`	`True`	`False`
Interrupts (HITL)	✅	✅	❌
Multi-turn memory	❌	✅	❌
Multiple calls (different subgraphs)	✅		✅
Multiple calls (same subgraph)	✅	❌	✅
State inspection		✅	❌

Interrupts (HITL)：子图可以使用 interrupt() 暂停执行并等待用户输入，然后从暂停处继续。
Multi-turn memory：子图会在同一线程内的多次调用之间保留其状态。每次调用都会从上一次结束的位置继续，而不是重新开始。
Multiple calls (different subgraphs)：可以在单个节点中调用多个不同的子图实例，而不会产生 checkpoint 命名空间冲突。
Multiple calls (same subgraph)：同一个子图实例可以在单个节点中被调用多次。使用有状态持久化时，这些调用会写入同一个 checkpoint 命名空间并产生冲突——请改用按调用持久化。
State inspection：可通过 get_state(config, subgraphs=True) 获取子图状态，用于调试和监控。

View subgraph state

启用持久化后，你可以使用 subgraphs 选项检查子图状态。使用无状态 checkpoint（checkpointer=False）时，不会保存任何子图 checkpoint，因此无法获取子图状态。

查看子图状态要求 LangGraph 能够静态发现该子图——也就是说，它是作为节点添加的，或是在节点内部调用的。当子图在工具函数内部或其他间接方式中被调用时（例如，subagents 模式），该功能不起作用。无论嵌套层级如何，中断仍会传播到顶层图。

Per-invocation
Per-thread

仅返回当前调用的子图状态。每次调用都会重新开始。

from langgraph.graph import START, StateGraph
from langgraph.checkpoint.memory import MemorySaver
from langgraph.types import interrupt, Command
from typing_extensions import TypedDict

class State(TypedDict):
    foo: str

# Subgraph
def subgraph_node_1(state: State):
    value = interrupt("Provide value:")
    return {"foo": state["foo"] + value}

subgraph_builder = StateGraph(State)
subgraph_builder.add_node(subgraph_node_1)
subgraph_builder.add_edge(START, "subgraph_node_1")
subgraph = subgraph_builder.compile()  # inherits parent checkpointer

# Parent graph
builder = StateGraph(State)
builder.add_node("node_1", subgraph)
builder.add_edge(START, "node_1")

checkpointer = MemorySaver()
graph = builder.compile(checkpointer=checkpointer)

config = {"configurable": {"thread_id": "1"}}

graph.invoke({"foo": ""}, config)

# View subgraph state for the current invocation
subgraph_state = graph.get_state(config, subgraphs=True).tasks[0].state  

# Resume the subgraph
graph.invoke(Command(resume="bar"), config)

返回该线程上所有调用累积得到的子图状态。

from langgraph.graph import START, StateGraph, MessagesState
from langgraph.checkpoint.memory import MemorySaver

# Subgraph with its own persistent state
subgraph_builder = StateGraph(MessagesState)
# ... add nodes and edges
subgraph = subgraph_builder.compile(checkpointer=True)

# Parent graph
builder = StateGraph(MessagesState)
builder.add_node("agent", subgraph)
builder.add_edge(START, "agent")

checkpointer = MemorySaver()
graph = builder.compile(checkpointer=checkpointer)

config = {"configurable": {"thread_id": "1"}}

graph.invoke({"messages": [{"role": "user", "content": "hi"}]}, config)
graph.invoke({"messages": [{"role": "user", "content": "what did I say?"}]}, config)

# View accumulated subgraph state (includes messages from both invocations)
subgraph_state = graph.get_state(config, subgraphs=True).tasks[0].state  

Stream subgraph outputs

若要观察嵌套图的执行，我们推荐使用事件流：stream.subgraphs 投影会发现每个嵌套运行，并暴露其 path、messages 和 values，无需解析命名空间字符串。

stream = graph.stream_events({"foo": "foo"}, version="v3")

for subgraph in stream.subgraphs:
    print(subgraph.graph_name, subgraph.path)

    for snapshot in subgraph.values:
        print(subgraph.path, snapshot)

如果你需要原始协议事件，请直接迭代 stream，并根据 event["method"] 和 event["params"]["namespace"] 进行过滤：

stream = graph.stream_events({"foo": "foo"}, version="v3")
for event in stream:
    if event["method"] == "updates":
        print(event["params"]["namespace"], event["params"]["data"])

Stream from subgraphs

from typing_extensions import TypedDict
from langgraph.graph.state import StateGraph, START

# Define subgraph
class SubgraphState(TypedDict):
    foo: str
    bar: str

def subgraph_node_1(state: SubgraphState):
    return {"bar": "bar"}

def subgraph_node_2(state: SubgraphState):
    # note that this node is using a state key ('bar') that is only available in the subgraph
    # and is sending update on the shared state key ('foo')
    return {"foo": state["foo"] + state["bar"]}

subgraph_builder = StateGraph(SubgraphState)
subgraph_builder.add_node(subgraph_node_1)
subgraph_builder.add_node(subgraph_node_2)
subgraph_builder.add_edge(START, "subgraph_node_1")
subgraph_builder.add_edge("subgraph_node_1", "subgraph_node_2")
subgraph = subgraph_builder.compile()

# Define parent graph
class ParentState(TypedDict):
    foo: str

def node_1(state: ParentState):
    return {"foo": "hi! " + state["foo"]}

builder = StateGraph(ParentState)
builder.add_node("node_1", node_1)
builder.add_node("node_2", subgraph)
builder.add_edge(START, "node_1")
builder.add_edge("node_1", "node_2")
graph = builder.compile()

stream = graph.stream_events({"foo": "foo"}, version="v3")
for event in stream:
    if event["method"] == "updates":
        print(event["params"]["namespace"], event["params"]["data"])

[] {'node_1': {'foo': 'hi! foo'}}
['node_2:e58e5673-a661-ebb0-70d4-e298a7fc28b7'] {'subgraph_node_1': {'bar': 'bar'}}
['node_2:e58e5673-a661-ebb0-70d4-e298a7fc28b7'] {'subgraph_node_2': {'foo': 'hi! foobar'}}
[] {'node_2': {'foo': 'hi! foobar'}}

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

Edit this page on GitHub or file an issue.

​Setup

​Define subgraph communication

​Call a subgraph inside a node

​Add a subgraph as a node

​Subgraph persistence

​Stateful

​Per-invocation (default)

​Per-thread

​Stateless

​Checkpointer reference

​View subgraph state

​Stream subgraph outputs

Setup

Define subgraph communication

Call a subgraph inside a node

Add a subgraph as a node

Subgraph persistence

Stateful

Per-invocation (default)

Per-thread

Stateless

Checkpointer reference

View subgraph state

Stream subgraph outputs