Testing | AI SDK 简体中文

Testing language models can be challenging, because they are non-deterministic and calling them is slow and expensive.

To enable you to unit test your code that uses the AI SDK, the AI SDK Core includes mock providers and test helpers. You can import the following helpers from ai/test:

MockEmbeddingModelV4: A mock embedding model using the embedding model v4 specification.
MockLanguageModelV4: A mock language model using the language model v4 specification.
mockId: Provides an incrementing integer ID.
mockValues: Iterates over an array of values with each call. Returns the last value when the array is exhausted.

You can also import simulateReadableStream from ai to simulate a readable stream with delays.

With mock providers and test helpers, you can control the output of the AI SDK and test your code in a repeatable and deterministic way without actually calling a language model provider.

Examples

You can use the test helpers with the AI Core functions in your unit tests:

generateText

import { generateText } from 'ai';
import { MockLanguageModelV4 } from 'ai/test';

const result = await generateText({
  model: new MockLanguageModelV4({
    doGenerate: async () => ({
      content: [{ type: 'text', text: `Hello, world!` }],
      finishReason: { unified: 'stop', raw: undefined },
      usage: {
        inputTokens: {
          total: 10,
          noCache: 10,
          cacheRead: undefined,
          cacheWrite: undefined,
        },
        outputTokens: {
          total: 20,
          text: 20,
          reasoning: undefined,
        },
      },
      warnings: [],
    }),
  }),
  prompt: 'Hello, test!',
});

streamText

import { streamText, simulateReadableStream } from 'ai';
import { MockLanguageModelV4 } from 'ai/test';

const result = streamText({
  model: new MockLanguageModelV4({
    doStream: async () => ({
      stream: simulateReadableStream({
        chunks: [
          { type: 'text-start', id: 'text-1' },
          { type: 'text-delta', id: 'text-1', delta: 'Hello' },
          { type: 'text-delta', id: 'text-1', delta: ', ' },
          { type: 'text-delta', id: 'text-1', delta: 'world!' },
          { type: 'text-end', id: 'text-1' },
          {
            type: 'finish',
            finishReason: { unified: 'stop', raw: undefined },
            logprobs: undefined,
            usage: {
              inputTokens: {
                total: 3,
                noCache: 3,
                cacheRead: undefined,
                cacheWrite: undefined,
              },
              outputTokens: {
                total: 10,
                text: 10,
                reasoning: undefined,
              },
            },
          },
        ],
      }),
    }),
  }),
  prompt: 'Hello, test!',
});

generateText with Output

import { generateText, Output } from 'ai';
import { MockLanguageModelV4 } from 'ai/test';
import { z } from 'zod';

const result = await generateText({
  model: new MockLanguageModelV4({
    doGenerate: async () => ({
      content: [{ type: 'text', text: `{"content":"Hello, world!"}` }],
      finishReason: { unified: 'stop', raw: undefined },
      usage: {
        inputTokens: {
          total: 10,
          noCache: 10,
          cacheRead: undefined,
          cacheWrite: undefined,
        },
        outputTokens: {
          total: 20,
          text: 20,
          reasoning: undefined,
        },
      },
      warnings: [],
    }),
  }),
  output: Output.object({ schema: z.object({ content: z.string() }) }),
  prompt: 'Hello, test!',
});

streamText with Output

import { streamText, Output, simulateReadableStream } from 'ai';
import { MockLanguageModelV4 } from 'ai/test';
import { z } from 'zod';

const result = streamText({
  model: new MockLanguageModelV4({
    doStream: async () => ({
      stream: simulateReadableStream({
        chunks: [
          { type: 'text-start', id: 'text-1' },
          { type: 'text-delta', id: 'text-1', delta: '{ ' },
          { type: 'text-delta', id: 'text-1', delta: '"content": ' },
          { type: 'text-delta', id: 'text-1', delta: `"Hello, ` },
          { type: 'text-delta', id: 'text-1', delta: `world` },
          { type: 'text-delta', id: 'text-1', delta: `!"` },
          { type: 'text-delta', id: 'text-1', delta: ' }' },
          { type: 'text-end', id: 'text-1' },
          {
            type: 'finish',
            finishReason: { unified: 'stop', raw: undefined },
            logprobs: undefined,
            usage: {
              inputTokens: {
                total: 3,
                noCache: 3,
                cacheRead: undefined,
                cacheWrite: undefined,
              },
              outputTokens: {
                total: 10,
                text: 10,
                reasoning: undefined,
              },
            },
          },
        ],
      }),
    }),
  }),
  output: Output.object({ schema: z.object({ content: z.string() }) }),
  prompt: 'Hello, test!',
});

ToolLoopAgent

You can provide a sequence of mock responses to test an agent that calls a tool and continues to a final response:

import { ToolLoopAgent, tool } from 'ai';
import { MockLanguageModelV4 } from 'ai/test';
import { expect, it } from 'vitest';
import { z } from 'zod';

it('executes a tool and continues the loop', async () => {
  const weatherRequests: string[] = [];
  const usage = {
    inputTokens: {
      total: 10,
      noCache: 10,
      cacheRead: undefined,
      cacheWrite: undefined,
    },
    outputTokens: {
      total: 5,
      text: 5,
      reasoning: undefined,
    },
  };

  const model = new MockLanguageModelV4({
    doGenerate: [
      {
        content: [
          {
            type: 'tool-call',
            toolCallId: 'call-1',
            toolName: 'weather',
            input: '{"city":"San Francisco"}',
          },
        ],
        finishReason: { unified: 'tool-calls', raw: undefined },
        usage,
        warnings: [],
      },
      {
        content: [{ type: 'text', text: 'It is 72°F in San Francisco.' }],
        finishReason: { unified: 'stop', raw: undefined },
        usage,
        warnings: [],
      },
    ],
  });

  const agent = new ToolLoopAgent({
    model,
    tools: {
      weather: tool({
        description: 'Get the weather for a city.',
        inputSchema: z.object({ city: z.string() }),
        execute: async ({ city }) => {
          weatherRequests.push(city);
          return { temperature: 72 };
        },
      }),
    },
  });

  const result = await agent.generate({
    prompt: 'What is the weather in San Francisco?',
  });

  expect(weatherRequests).toEqual(['San Francisco']);
  expect(result.text).toBe('It is 72°F in San Francisco.');
  expect(model.doGenerateCalls).toHaveLength(2);
});

Simulate UI Message Stream Responses

You can also simulate UI Message Stream responses for testing, debugging, or demonstration purposes.

Here is a Next example:

import { simulateReadableStream } from 'ai';

export async function POST(req: Request) {
  return new Response(
    simulateReadableStream({
      initialDelayInMs: 1000, // Delay before the first chunk
      chunkDelayInMs: 300, // Delay between chunks
      chunks: [
        `data: {"type":"start","messageId":"msg-123"}\n\n`,
        `data: {"type":"text-start","id":"text-1"}\n\n`,
        `data: {"type":"text-delta","id":"text-1","delta":"This"}\n\n`,
        `data: {"type":"text-delta","id":"text-1","delta":" is an"}\n\n`,
        `data: {"type":"text-delta","id":"text-1","delta":" example."}\n\n`,
        `data: {"type":"text-end","id":"text-1"}\n\n`,
        `data: {"type":"finish"}\n\n`,
        `data: [DONE]\n\n`,
      ],
    }).pipeThrough(new TextEncoderStream()),
    {
      status: 200,
      headers: {
        'Content-Type': 'text/event-stream',
        'Cache-Control': 'no-cache',
        Connection: 'keep-alive',
        'x-vercel-ai-ui-message-stream': 'v1',
      },
    },
  );
}