在您为 LangGraph 智能体制作原型后，自然的下一步是添加测试。本指南涵盖了在编写单元测试时可以使用的一些有用模式。 请注意，本指南特定于 LangGraph，涵盖具有自定义结构的图的场景 - 如果您刚开始，请查看本节，其中使用 LangChain 的内置 create_agent。

​
先决条件

首先，确保您已安装 pytest： 
$ pip install -U pytest

​
入门

由于许多 LangGraph 智能体依赖于状态，一个有用的模式是在使用它的每个测试之前创建您的图，然后在测试中使用新的检查点器实例编译它。 下面的示例显示了这如何与一个简单的线性图一起工作，该图通过 node1 和 node2 进展。每个节点更新单个状态键 my_key： 
import pytest

from typing_extensions import TypedDict
from langgraph.graph import StateGraph, START, END
from langgraph.checkpoint.memory import MemorySaver

def create_graph() -> StateGraph:
    class MyState(TypedDict):
        my_key: str

    graph = StateGraph(MyState)
    graph.add_node("node1", lambda state: {"my_key": "hello from node1"})
    graph.add_node("node2", lambda state: {"my_key": "hello from node2"})
    graph.add_edge(START, "node1")
    graph.add_edge("node1", "node2")
    graph.add_edge("node2", END)
    return graph

def test_basic_agent_execution() -> None:
    checkpointer = MemorySaver()
    graph = create_graph()
    compiled_graph = graph.compile(checkpointer=checkpointer)
    result = compiled_graph.invoke(
        {"my_key": "initial_value"},
        config={"configurable": {"thread_id": "1"}}
    )
    assert result["my_key"] == "hello from node2"

​
测试单个节点与边

编译后的 LangGraph 智能体会通过 graph.nodes 暴露每个节点的引用。您可以利用这一点测试智能体中的单个节点。请注意，这样做会绕过编译图时传入的任何检查点： 
import pytest

from typing_extensions import TypedDict
from langgraph.graph import StateGraph, START, END
from langgraph.checkpoint.memory import MemorySaver

def create_graph() -> StateGraph:
    class MyState(TypedDict):
        my_key: str

    graph = StateGraph(MyState)
    graph.add_node("node1", lambda state: {"my_key": "hello from node1"})
    graph.add_node("node2", lambda state: {"my_key": "hello from node2"})
    graph.add_edge(START, "node1")
    graph.add_edge("node1", "node2")
    graph.add_edge("node2", END)
    return graph

def test_individual_node_execution() -> None:
    # Will be ignored in this example
    checkpointer = MemorySaver()
    graph = create_graph()
    compiled_graph = graph.compile(checkpointer=checkpointer)
    # Only invoke node 1
    result = compiled_graph.nodes["node1"].invoke(
        {"my_key": "initial_value"},
    )
    assert result["my_key"] == "hello from node1"

​
部分执行

对于由较大图组成的智能体，您可能希望测试智能体内的部分执行路径，而不是端到端的整个流程。在某些情况下，将这些部分重构为子图可能在语义上是有意义的，您可以像平常一样单独调用它们。 但是，如果您不希望更改智能体图的整体结构，可以使用 LangGraph 的持久化机制来模拟智能体在所需部分开始之前暂停的状态，并在所需部分结束时再次暂停。步骤如下：
  1. Compile your agent with a checkpointer (the in-memory checkpointer InMemorySaver will suffice for testing).
  2. Call your agent’s update_state method with an as_node parameter set to the name of the node before the one you want to start your test.
  3. Invoke your agent with the same thread_id you used to update the state and an interrupt_after parameter set to the name of the node you want to stop at.
以下是一个仅在线性图中执行第二个和第三个节点的示例： 
import pytest

from typing_extensions import TypedDict
from langgraph.graph import StateGraph, START, END
from langgraph.checkpoint.memory import MemorySaver

def create_graph() -> StateGraph:
    class MyState(TypedDict):
        my_key: str

    graph = StateGraph(MyState)
    graph.add_node("node1", lambda state: {"my_key": "hello from node1"})
    graph.add_node("node2", lambda state: {"my_key": "hello from node2"})
    graph.add_node("node3", lambda state: {"my_key": "hello from node3"})
    graph.add_node("node4", lambda state: {"my_key": "hello from node4"})
    graph.add_edge(START, "node1")
    graph.add_edge("node1", "node2")
    graph.add_edge("node2", "node3")
    graph.add_edge("node3", "node4")
    graph.add_edge("node4", END)
    return graph

def test_partial_execution_from_node2_to_node3() -> None:
    checkpointer = MemorySaver()
    graph = create_graph()
    compiled_graph = graph.compile(checkpointer=checkpointer)
    compiled_graph.update_state(
        config={
          "configurable": {
            "thread_id": "1"
          }
        },
        # The state passed into node 2 - simulating the state at
        # the end of node 1
        values={"my_key": "initial_value"},
        # Update saved state as if it came from node 1
        # Execution will resume at node 2
        as_node="node1",
    )
    result = compiled_graph.invoke(
        # Resume execution by passing None
        None,
        config={"configurable": {"thread_id": "1"}},
        # Stop after node 3 so that node 4 doesn't run
        interrupt_after="node3",
    )
    assert result["my_key"] == "hello from node3"
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.