Skip to main content

Documentation Index

Fetch the complete documentation index at: https://nvd-54.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

单元测试在隔离环境中测试智能体的小型、确定性部分。通过用内存中的模拟(也称为 fixture)替换真实 LLM,你可以编写精确的响应(文本、工具调用和错误),使测试快速、免费且无需 API 密钥即可重复。

使用 fakeModel 模拟聊天模型

fakeModel 是一个构建器风格的模拟聊天模型,允许你编写精确的响应(文本、工具调用、错误)并断言模型接收到的内容。它扩展了 BaseChatModel,因此可以在任何期望使用真实模型的地方使用。
import { fakeModel } from "langchain";

快速开始

创建一个模型,使用 .respond() 排队响应,然后调用。每次 invoke() 按顺序消费下一个排队的响应:
import { fakeModel } from "langchain";
import { AIMessage, HumanMessage } from "@langchain/core/messages";

const model = fakeModel()
  .respond(new AIMessage("I can help with that."))
  .respond(new AIMessage("Here's what I found."))
  .respond(new AIMessage("You're welcome!"));

const r1 = await model.invoke([new HumanMessage("Can you help?")]);
// r1.content === "I can help with that."

const r2 = await model.invoke([new HumanMessage("What did you find?")]);
// r2.content === "Here's what I found."

const r3 = await model.invoke([new HumanMessage("Thanks!")]);
// r3.content === "You're welcome!"
如果模型被调用的次数超过排队响应的数量,它会抛出描述性错误:
const model = fakeModel()
  .respond(new AIMessage("only one"));

await model.invoke([new HumanMessage("first")]);  // 正常
await model.invoke([new HumanMessage("second")]); // 抛出: "no response queued for invocation 1"

工具调用响应

.respond() 通过传递带有 tool_callsAIMessage 来支持工具调用:
import { fakeModel } from "langchain";
import { AIMessage, HumanMessage } from "@langchain/core/messages";

const model = fakeModel()
  .respond(new AIMessage({
    content: "",
    tool_calls: [
      { name: "get_weather", args: { city: "San Francisco" }, id: "call_1", type: "tool_call" },
    ],
  }))
  .respond(new AIMessage("It's 72°F and sunny in San Francisco."));

const r1 = await model.invoke([new HumanMessage("What's the weather in SF?")]);
console.log(r1.tool_calls[0].name); // "get_weather"

const r2 = await model.invoke([new HumanMessage("Thanks")]);
console.log(r2.content); // "It's 72°F and sunny in San Francisco."
.respondWithTools() 是相同功能的简写。无需构造完整的 AIMessage,只需提供工具名称和参数即可:
// 这两个排队条目产生相同的响应:

model.respond(new AIMessage({
  content: "",
  tool_calls: [
    { name: "get_weather", args: { city: "SF" }, id: "call_1", type: "tool_call" },
  ],
}));

// 等效的简写:
model.respondWithTools([  
  { name: "get_weather", args: { city: "SF" }, id: "call_1" },
]);
id 字段是可选的。如果省略,将自动生成唯一 ID。
.respond().respondWithTools() 可以自由混合使用。这在测试智能体循环时特别有用,因为模型会在工具调用和文本响应之间交替。

模拟错误

特定轮次的错误

.respond() 传递一个 Error 会使模型在该特定调用时抛出异常。错误可以出现在序列中的任何位置:
import { fakeModel } from "langchain";
import { AIMessage, HumanMessage } from "@langchain/core/messages";

const model = fakeModel()
  .respond(new Error("rate limit exceeded"))  // 第1轮: 抛出异常
  .respond(new AIMessage("Recovered!"));      // 第2轮: 成功

try {
  await model.invoke([new HumanMessage("first")]);
} catch (e) {
  console.log(e.message); // "rate limit exceeded"
}

const result = await model.invoke([new HumanMessage("retry")]);
console.log(result.content); // "Recovered!"

每次调用都报错

.alwaysThrow() 使每次调用都抛出异常,无论队列如何。这对测试错误处理和重试逻辑很有用:
import { fakeModel } from "langchain";
import { HumanMessage } from "@langchain/core/messages";

const model = fakeModel().alwaysThrow(new Error("service unavailable"));

await model.invoke([new HumanMessage("a")]); // 抛出 "service unavailable"
await model.invoke([new HumanMessage("b")]); // 抛出 "service unavailable"

使用工厂函数的动态响应

.respond() 也接受一个基于输入消息计算响应的函数。该函数接收完整的消息数组,并返回 BaseMessageError
import { fakeModel } from "langchain";
import { AIMessage, HumanMessage } from "@langchain/core/messages";

const model = fakeModel()
  .respond((messages) => {
    const last = messages[messages.length - 1].text;
    return new AIMessage(`You said: ${last}`);
  });

const result = await model.invoke([new HumanMessage("hello")]);
console.log(result.content); // "You said: hello"
工厂函数也可以返回错误:
import { fakeModel } from "langchain";
import { AIMessage, HumanMessage } from "@langchain/core/messages";

const model = fakeModel()
  .respond((messages) => {
    const content = messages[messages.length - 1].text;
    if (content.includes("forbidden")) {
      return new Error("Content policy violation");
    }
    return new AIMessage("OK");
  });

await model.invoke([new HumanMessage("forbidden topic")]); // 抛出 "Content policy violation"
每个函数是单个队列条目,只消费一次。要对多个轮次重用相同的动态逻辑,需要排队多个 respond 函数调用。

结构化输出

对于使用 .withStructuredOutput() 的代码,使用 .structuredResponse() 配置模拟返回值:
import { fakeModel } from "langchain";
import { HumanMessage } from "@langchain/core/messages";
import { z } from "zod";

const model = fakeModel()
  .structuredResponse({ temperature: 72, unit: "fahrenheit" });

const structured = model.withStructuredOutput(
  z.object({
    temperature: z.number(),
    unit: z.string(),
  })
);

const result = await structured.invoke([new HumanMessage("Weather?")]);
console.log(result);
// { temperature: 72, unit: "fahrenheit" }
传递给 .withStructuredOutput() 的 schema 会被忽略。模型始终返回 .structuredResponse() 配置的值。这使测试专注于应用逻辑而非解析。

断言模型接收到的内容

fakeModel 记录每次调用,包括传递给模型的消息和选项。这类似于传统测试框架中的 spy 或 mock:
import { fakeModel } from "langchain";
import { AIMessage, HumanMessage } from "@langchain/core/messages";

const model = fakeModel()
  .respond(new AIMessage("first"))
  .respond(new AIMessage("second"));

await model.invoke([new HumanMessage("question 1")]);
await model.invoke([new HumanMessage("question 2")]);

console.log(model.callCount); // 2

console.log(model.calls[0].messages[0].content); // "question 1"
console.log(model.calls[1].messages[0].content); // "question 2"
即使模型抛出异常,调用也会被记录:
import { fakeModel } from "langchain";
import { HumanMessage } from "@langchain/core/messages";

const model = fakeModel().respond(new Error("boom"));

try {
  await model.invoke([new HumanMessage("will fail")]);
} catch {
  // 处理错误
}

console.log(model.callCount); // 1
console.log(model.calls[0].messages[0].content); // "will fail"

bindTools 配合使用

智能体框架如 LangChain 智能体和 LangGraph 会在内部调用 model.bindTools(tools)fakeModel 自动处理这一点。绑定后的模型与原始模型共享相同的响应队列和调用记录,因此无需特殊设置:
import { fakeModel } from "langchain";
import { AIMessage, HumanMessage } from "@langchain/core/messages";
import { tool } from "@langchain/core/tools";
import { z } from "zod";

const searchTool = tool(async ({ query }) => `Results for: ${query}`, {
  name: "search",
  description: "Search the web",
  schema: z.object({ query: z.string() }),
});

const model = fakeModel()
  .respondWithTools([{ name: "search", args: { query: "weather" }, id: "1" }])
  .respond(new AIMessage("The weather is sunny."));

const bound = model.bindTools([searchTool]);

const r1 = await bound.invoke([new HumanMessage("weather?")]);
console.log(r1.tool_calls[0].name); // "search"

const r2 = await bound.invoke([new HumanMessage("thanks")]);
console.log(r2.content); // "The weather is sunny."

// 调用记录是共享的。通过原始模型检查。
console.log(model.callCount); // 2
import { describe, test, expect } from "vitest";
import { fakeModel } from "langchain";
import { AIMessage, HumanMessage, ToolMessage } from "@langchain/core/messages";
import { tool } from "@langchain/core/tools";
import { z } from "zod";

const getWeather = tool(
  async ({ city }) => `72°F and sunny in ${city}`,
  {
    name: "get_weather",
    description: "Get weather for a city",
    schema: z.object({ city: z.string() }),
  }
);

async function runAgent(
  model: ReturnType<typeof fakeModel>,
  input: string
) {
  const messages: any[] = [new HumanMessage(input)];
  const bound = model.bindTools([getWeather]);

  while (true) {
    const response = await bound.invoke(messages);
    messages.push(response);

    if (!response.tool_calls?.length) {
      return { messages, finalResponse: response };
    }

    for (const tc of response.tool_calls) {
      const result = await getWeather.invoke(tc.args);
      messages.push(new ToolMessage({
        content: result as string,
        tool_call_id: tc.id!,
      }));
    }
  }
}

describe("weather agent", () => {
  test("calls get_weather and returns a final answer", async () => {
    const model = fakeModel()
      .respondWithTools([
        { name: "get_weather", args: { city: "SF" }, id: "call_1" },
      ])
      .respond(new AIMessage("It's 72°F and sunny in SF!"));

    const { finalResponse } = await runAgent(model, "Weather in SF?");

    expect(finalResponse.content).toBe("It's 72°F and sunny in SF!");
    expect(model.callCount).toBe(2);

    const secondCall = model.calls[1].messages;
    const toolMsg = secondCall.find((m: any) => m._getType() === "tool");
    expect(toolMsg?.content).toContain("72°F and sunny in SF");
  });

  test("handles model errors gracefully", async () => {
    const model = fakeModel()
      .respond(new Error("rate limit"));

    await expect(
      runAgent(model, "Weather?")
    ).rejects.toThrow("rate limit");

    expect(model.callCount).toBe(1);
  });
});

后续步骤

了解如何使用真实模型提供商 API 测试你的智能体,请参阅集成测试