在运行时重建图

my-app/
|-- langgraph.json
|-- my_project/
|   |-- __init__.py
|   |-- agents.py     # 你的图代码
|-- pyproject.toml

# my_project/agents.py
from langgraph.graph import StateGraph, MessagesState, START

async def model(state: MessagesState):
    return {"messages": [{"role": "assistant", "content": "Hi, there!"}]}

graph_workflow = StateGraph(MessagesState)
graph_workflow.add_node("model", model)
graph_workflow.add_edge(START, "model")
agent = graph_workflow.compile()

{
    "$schema": "https://langgra.ph/schema.json",
    "dependencies": ["."],
    "graphs": {
        "chat_agent": "my_project.agents:agent",
    }
}

from langchain_openai import ChatOpenAI
from langgraph.graph import START, StateGraph
from langchain_core.runnables import RunnableConfig
from langgraph_sdk.runtime import ServerRuntime

from my_agent.utils.state import AgentState

model = ChatOpenAI(model="gpt-5.4")


def make_graph_for_user(user_id: str):
    """为每个用户构建一个定制的图。"""
    graph_workflow = StateGraph(AgentState)

    async def call_model(state):
        return {"messages": [await model.ainvoke(state["messages"])]}

    graph_workflow.add_node("agent", call_model)
    graph_workflow.add_edge(START, "agent")
    return graph_workflow.compile()


async def make_graph(config: RunnableConfig, runtime: ServerRuntime):
    user = runtime.ensure_user()
    return make_graph_for_user(user.identity)

import contextlib

from langchain_openai import ChatOpenAI
from langgraph.graph import START, StateGraph
from langchain_core.runnables import RunnableConfig
from langgraph_sdk.runtime import ServerRuntime

from my_agent.utils.state import AgentState

model = ChatOpenAI(model="gpt-5.4")


def make_agent_graph(tools: list):
    """制作一个简单的 LLM 代理。"""
    graph_workflow = StateGraph(AgentState)
    bound = model.bind_tools(tools)

    async def call_model(state):
        return {"messages": [await bound.ainvoke(state["messages"])]}

    graph_workflow.add_node("agent", call_model)
    graph_workflow.add_edge(START, "agent")
    return graph_workflow.compile()


@contextlib.asynccontextmanager
async def make_graph(runtime: ServerRuntime):
    if ert := runtime.execution_runtime:
        # 仅在实际执行期间设置昂贵的资源。
        # 内省调用（get_schema, get_graph, ...）会跳过此步骤。
        mcp_tools = await connect_mcp(ert.ensure_user())  # 你的设置逻辑
        yield make_agent_graph(tools=mcp_tools)
        await disconnect_mcp()  # 你的清理逻辑
    else:
        # 对于模式/状态读取，返回一个具有相同拓扑结构
        # 但不设置昂贵资源的图。
        yield make_agent_graph(tools=[])

{
    "$schema": "https://langgra.ph/schema.json",
    "dependencies": ["."],
    "graphs": {
        "chat_agent": "my_project.agents:make_graph",
    }
}