在 CI 中运行 Scorer

在 CI Pipeline 中运行 Scorer，可以提供可量化的指标来衡量 Agent 质量随时间的变化。runEvals 函数会将多个测试用例交给 Agent 或 Workflow 处理，并返回聚合分数。

基础设置

可以使用任何支持 ESM 模块的测试框架，例如 Vitest、Jest 或 Mocha。

创建测试用例

使用 runEvals 针对多个测试用例评估 Agent。该函数接受数据项目数组，每个项目均包含 input，还可包含供 Scorer 验证使用的 groundTruth。

src/mastra/agents/weather-agent.test.ts

import { describe, it, expect } from 'vitest'
import { createScorer, runEvals } from '@mastra/core/evals'
import { weatherAgent } from './weather-agent'
import { locationScorer } from '../scorers/location-scorer'

describe('Weather Agent Tests', () => {
  it('should correctly extract locations from queries', async () => {
    const result = await runEvals({
      data: [
        {
          input: 'weather in Berlin',
          groundTruth: { expectedLocation: 'Berlin', expectedCountry: 'DE' },
        },
        {
          input: 'weather in Berlin, Maryland',
          groundTruth: { expectedLocation: 'Berlin', expectedCountry: 'US' },
        },
        {
          input: 'weather in Berlin, Russia',
          groundTruth: { expectedLocation: 'Berlin', expectedCountry: 'RU' },
        },
      ],
      target: weatherAgent,
      scorers: [locationScorer],
    })

    // Assert aggregate score meets threshold
    expect(result.scores['location-accuracy']).toBe(1)
    expect(result.summary.totalItems).toBe(3)
  })
})

理解结果

runEvals 函数返回一个包含以下内容的对象：

• scores：每个 Scorer 在所有测试用例上的平均分数
• summary.totalItems：已处理的测试用例总数

{
  scores: {
    'location-accuracy': 1.0,  // Average score across all items
    'another-scorer': 0.85
  },
  summary: {
    totalItems: 3
  }
}

多种测试场景

为不同评估场景创建单独的测试用例：

src/mastra/agents/weather-agent.test.ts

describe('Weather Agent Tests', () => {
  const locationScorer = createScorer({/* ... */})

  it('should handle location disambiguation', async () => {
    const result = await runEvals({
      data: [
        {
          input: 'weather in Berlin',
          groundTruth: {/* ... */},
        },
        {
          input: 'weather in Berlin, Maryland',
          groundTruth: {/* ... */},
        },
      ],
      target: weatherAgent,
      scorers: [locationScorer],
    })

    expect(result.scores['location-accuracy']).toBe(1)
  })

  it('should handle typos and misspellings', async () => {
    const result = await runEvals({
      data: [
        {
          input: 'weather in Berln',
          groundTruth: { expectedLocation: 'Berlin', expectedCountry: 'DE' },
        },
        {
          input: 'weather in Parris',
          groundTruth: { expectedLocation: 'Paris', expectedCountry: 'FR' },
        },
      ],
      target: weatherAgent,
      scorers: [locationScorer],
    })

    expect(result.scores['location-accuracy']).toBe(1)
  })
})

后续步骤

• 了解如何创建自定义 Scorer
• 探索内置 Scorer
• 针对启用了 Memory 的 Agent运行 Scorer
• 阅读 runEvals API Reference