> Discover all available pages from the documentation index: https://mastra.zisheng.pro/zh-TW/llms.txt

# 評分器工具函式

Mastra 提供工具函式，協助從評分器執行的輸入與輸出擷取及處理資料。這些工具在自訂評分器的 `preprocess` 步驟中特別實用。

## 匯入

```typescript
import {
  getAssistantMessageFromRunOutput,
  getReasoningFromRunOutput,
  getUserMessageFromRunInput,
  getSystemMessagesFromRunInput,
  getCombinedSystemPrompt,
  extractToolCalls,
  extractInputMessages,
  extractAgentResponseMessages,
  compareTrajectories,
  createTrajectoryTestRun,
} from '@mastra/evals/scorers/utils'
```

可從 `@mastra/core/evals` 使用軌跡擷取函式：

```typescript
import {
  extractTrajectory,
  extractWorkflowTrajectory,
  extractTrajectoryFromTrace,
} from '@mastra/core/evals'
```

## 訊息擷取

### `getAssistantMessageFromRunOutput`

從此次執行輸出的第一則 assistant 訊息中擷取文字內容。

```typescript
const scorer = createScorer({
  id: 'my-scorer',
  description: 'My scorer',
  type: 'agent',
})
  .preprocess(({ run }) => {
    const response = getAssistantMessageFromRunOutput(run.output)
    return { response }
  })
  .generateScore(({ results }) => {
    return results.preprocessStepResult?.response ? 1 : 0
  })
```

**output** (`ScorerRunOutputForAgent`): 評分器執行輸出（MastraDBMessage 陣列）

**傳回：** `string | undefined`——assistant 訊息文字；若找不到 assistant 訊息，則為 undefined。

### `getUserMessageFromRunInput`

從此次執行輸入的第一則使用者訊息中擷取文字內容。

```typescript
.preprocess(({ run }) => {
  const userMessage = getUserMessageFromRunInput(run.input);
  return { userMessage };
})
```

**input** (`ScorerRunInputForAgent`): 包含輸入訊息的評分器執行輸入

**傳回：** `string | undefined`——使用者訊息文字；若找不到使用者訊息，則為 undefined。

### `extractInputMessages`

以陣列形式擷取所有輸入訊息的文字內容。

```typescript
.preprocess(({ run }) => {
  const allUserMessages = extractInputMessages(run.input);
  return { conversationHistory: allUserMessages.join("\n") };
})
```

**傳回：** `string[]`——各輸入訊息文字字串的陣列。

### `extractAgentResponseMessages`

以陣列形式擷取所有 assistant 回應訊息的文字內容。

```typescript
.preprocess(({ run }) => {
  const allResponses = extractAgentResponseMessages(run.output);
  return { allResponses };
})
```

**傳回：** `string[]`——各 assistant 訊息文字字串的陣列。

## 推理擷取

### `getReasoningFromRunOutput`

從此次執行輸出擷取推理文字。評估 `deepseek-reasoner` 這類會產生思維鏈推理的推理模型回應時，此函式特別實用。

推理可儲存在兩個位置：

1. `content.reasoning`——訊息內容上的字串欄位
2. `content.parts`——含有 `details` 且 `type: 'reasoning'` 的部分

```typescript
import {
  getReasoningFromRunOutput,
  getAssistantMessageFromRunOutput,
} from '@mastra/evals/scorers/utils'

const reasoningQualityScorer = createScorer({
  id: 'reasoning-quality',
  name: 'Reasoning Quality',
  description: 'Evaluates the quality of model reasoning',
  type: 'agent',
})
  .preprocess(({ run }) => {
    const reasoning = getReasoningFromRunOutput(run.output)
    const response = getAssistantMessageFromRunOutput(run.output)
    return { reasoning, response }
  })
  .analyze(({ results }) => {
    const { reasoning } = results.preprocessStepResult || {}
    return {
      hasReasoning: !!reasoning,
      reasoningLength: reasoning?.length || 0,
      hasStepByStep: reasoning?.includes('step') || false,
    }
  })
  .generateScore(({ results }) => {
    const { hasReasoning, reasoningLength } = results.analyzeStepResult || {}
    if (!hasReasoning) return 0
    // Score based on reasoning length (normalized to 0-1)
    return Math.min(reasoningLength / 500, 1)
  })
  .generateReason(({ results, score }) => {
    const { hasReasoning, reasoningLength } = results.analyzeStepResult || {}
    if (!hasReasoning) {
      return 'No reasoning was provided by the model.'
    }
    return `Model provided ${reasoningLength} characters of reasoning. Score: ${score}`
  })
```

**output** (`ScorerRunOutputForAgent`): 評分器執行輸出（MastraDBMessage 陣列）

**傳回：** `string | undefined`——推理文字；若沒有推理，則為 undefined。

## 系統訊息擷取

### `getSystemMessagesFromRunInput`

從此次執行輸入擷取所有系統訊息，包括標準系統訊息與加上標籤的系統訊息（例如記憶體指示這類專用提示詞）。

```typescript
.preprocess(({ run }) => {
  const systemMessages = getSystemMessagesFromRunInput(run.input);
  return {
    systemPromptCount: systemMessages.length,
    systemPrompts: systemMessages
  };
})
```

**傳回：** `string[]`——系統訊息字串陣列。

### `getCombinedSystemPrompt`

將所有系統訊息合併成單一提示詞字串，並以兩個換行字元連接。

```typescript
.preprocess(({ run }) => {
  const fullSystemPrompt = getCombinedSystemPrompt(run.input);
  return { fullSystemPrompt };
})
```

**傳回：** `string`——合併後的系統提示詞字串。

## Tool 呼叫擷取

### `extractToolCalls`

從此次執行輸出擷取所有 Tool 呼叫的資訊，包括 Tool 名稱、呼叫 ID，以及它們在訊息陣列中的位置。

```typescript
const toolUsageScorer = createScorer({
  id: 'tool-usage',
  description: 'Evaluates tool usage patterns',
  type: 'agent',
})
  .preprocess(({ run }) => {
    const { tools, toolCallInfos } = extractToolCalls(run.output)
    return {
      toolsUsed: tools,
      toolCount: tools.length,
      toolDetails: toolCallInfos,
    }
  })
  .generateScore(({ results }) => {
    const { toolCount } = results.preprocessStepResult || {}
    // Score based on appropriate tool usage
    return toolCount > 0 ? 1 : 0
  })
```

**傳回：**

```typescript
{
  tools: string[];           // Array of tool names
  toolCallInfos: ToolCallInfo[];  // Detailed tool call information
}
```

其中 `ToolCallInfo` 為：

```typescript
type ToolCallInfo = {
  toolName: string // Name of the tool
  toolCallId: string // Unique call identifier
  messageIndex: number // Index in the output array
  invocationIndex: number // Index within message's tool invocations
}
```

## 測試工具

這些工具可協助建立用於評分器開發的測試資料。

### `createTestMessage`

建立用於測試的 `MastraDBMessage` 物件。

```typescript
import { createTestMessage } from '@mastra/evals/scorers/utils'

const userMessage = createTestMessage({
  content: 'What is the weather?',
  role: 'user',
})

const assistantMessage = createTestMessage({
  content: 'The weather is sunny.',
  role: 'assistant',
  toolInvocations: [
    {
      toolCallId: 'call-1',
      toolName: 'weatherTool',
      args: { location: 'London' },
      result: { temp: 20 },
      state: 'result',
    },
  ],
})
```

### `createAgentTestRun`

建立用於測試評分器的完整測試執行物件。

```typescript
import { createAgentTestRun, createTestMessage } from '@mastra/evals/scorers/utils'

const testRun = createAgentTestRun({
  inputMessages: [createTestMessage({ content: 'Hello', role: 'user' })],
  output: [createTestMessage({ content: 'Hi there!', role: 'assistant' })],
})

// Run your scorer with the test data
const result = await myScorer.run({
  input: testRun.input,
  output: testRun.output,
})
```

## 軌跡工具

### `extractTrajectory`

從 Agent 輸出訊息（`MastraDBMessage[]`）擷取 `Trajectory`。將 Tool invocation 轉換為 `ToolCallStep` 物件。`runEvals` pipeline 會為軌跡評分器自動呼叫此函式，只有直接測試時才需要自行呼叫。

可從 `@mastra/core/evals` 使用。

```typescript
import { extractTrajectory } from '@mastra/core/evals'

const trajectory = extractTrajectory(agentOutputMessages)
// trajectory.steps — ToolCallStep[] extracted from toolInvocations
// trajectory.rawOutput — the original MastraDBMessage[] array
```

**傳回：** `Trajectory`：包含 `steps: TrajectoryStep[]`、`totalDurationMs` 與 `rawOutput`。

### `extractWorkflowTrajectory`

從 Workflow 步驟結果擷取 `Trajectory`。將 `StepResult` 記錄轉換為 `WorkflowStepStep` 物件，並遵循執行路徑順序。

可從 `@mastra/core/evals` 使用。

```typescript
import { extractWorkflowTrajectory } from '@mastra/core/evals'

const trajectory = extractWorkflowTrajectory(
  workflowResult.steps, // Record<string, StepResult>
  workflowResult.stepExecutionPath, // string[] (optional)
)
// trajectory.steps — WorkflowStepStep[] in execution order
```

**傳回：** `Trajectory`：包含 `steps: TrajectoryStep[]`、`totalDurationMs` 與 `rawWorkflowResult`。

### `extractTrajectoryFromTrace`

從可觀測性 Trace span（`SpanRecord[]`）建立階層式 `Trajectory`。它會重建父子 span 樹狀結構，並將每個 span 對應至適當的 `TrajectoryStep` 可辨識聯集型別，且包含巢狀 `children`。

若儲存空間可用，這是首選的擷取方法。target 的 `Mastra` 執行個體已設定儲存後端時，`runEvals` pipeline 會自動呼叫此函式。相較於 `extractTrajectory` 或 `extractWorkflowTrajectory`，它能擷取完整執行樹，包括巢狀 Agent 執行、Tool 呼叫與模型產生作業，因此會產生更豐富的軌跡。

可從 `@mastra/core/evals` 使用。

```typescript
import { extractTrajectoryFromTrace } from '@mastra/core/evals'

// After fetching a trace from the observability store
const traceData = await observabilityStore.getTrace({ traceId })
const trajectory = extractTrajectoryFromTrace(traceData.spans, rootSpanId)
// trajectory.steps — hierarchical TrajectoryStep[] with children
```

**參數：**

- `spans`（`SpanRecord[]`）：Trace 查詢傳回的 span 記錄陣列。
- `rootSpanId`（`string`，選填）：作為起點的 span ID。省略時，使用沒有 parent 的 span。

**傳回：** `Trajectory`：包含具遞迴 `children` 的 `steps: TrajectoryStep[]`，以及 `totalDurationMs`。

#### Span 型別對應

| Span 型別                | 軌跡步驟型別                 | 擷取的主要欄位                                                    |
| ---------------------- | ---------------------- | ---------------------------------------------------------- |
| `TOOL_CALL`            | `tool_call`            | `toolArgs`、`toolResult`、`success`                          |
| `MCP_TOOL_CALL`        | `mcp_tool_call`        | `toolArgs`、`toolResult`、`mcpServer`、`success`              |
| `MODEL_GENERATION`     | `model_generation`     | `modelId`、`promptTokens`、`completionTokens`、`finishReason` |
| `AGENT_RUN`            | `agent_run`            | `agentId`（來自 entity ID）                                    |
| `WORKFLOW_RUN`         | `workflow_run`         | `workflowId`（來自 entity ID）                                 |
| `WORKFLOW_STEP`        | `workflow_step`        | `output`                                                   |
| `WORKFLOW_CONDITIONAL` | `workflow_conditional` | `conditionCount`、`selectedSteps`                           |
| `WORKFLOW_PARALLEL`    | `workflow_parallel`    | `branchCount`、`parallelSteps`                              |
| `WORKFLOW_LOOP`        | `workflow_loop`        | `loopType`、`totalIterations`                               |
| `WORKFLOW_SLEEP`       | `workflow_sleep`       | `sleepDurationMs`、`sleepType`                              |
| `WORKFLOW_WAIT_EVENT`  | `workflow_wait_event`  | `eventName`、`eventReceived`                                |
| `PROCESSOR_RUN`        | `processor_run`        | `processorId`                                              |

`GENERIC`、`MODEL_STEP`、`MODEL_CHUNK` 與 `WORKFLOW_CONDITIONAL_EVAL` 型別的 span 會視為雜訊而略過。

### `compareTrajectories`

將實際軌跡與預期軌跡進行比較，並傳回詳細的比較結果。`createTrajectoryAccuracyScorerCode` 會在內部使用此函式。

`expected` 參數接受 `Trajectory`（實際軌跡）或 `{ steps: ExpectedStep[] }`。使用 `ExpectedStep[]` 時，可以只依名稱比對，也可依名稱 + stepType 比對。你也能加入要比較的資料。詳情請參閱[預期步驟](https://mastra.zisheng.pro/zh-TW/reference/evals/trajectory-accuracy)。

```typescript
import { compareTrajectories } from '@mastra/evals/scorers/utils'

// Using ExpectedStep[] (recommended for expectations)
// Data fields (e.g. toolArgs) are auto-compared when present on expected steps
const result = compareTrajectories(
  actualTrajectory,
  { steps: [{ name: 'search' }, { name: 'summarize', stepType: 'tool_call' }] },
  { allowRepeatedSteps: true },
)
// result.score — 0.0 to 1.0
// result.missingSteps — step names not found
// result.extraSteps — unexpected step names
// result.outOfOrderSteps — steps found but in wrong order
```

**傳回：** `TrajectoryComparisonResult`

### `createTrajectoryTestRun`

為軌跡評分器建立測試執行物件。將 `Trajectory` 包裝成預期的 `ScorerRun` 格式。

```typescript
import { createTrajectoryTestRun } from '@mastra/evals/scorers/utils'

const run = createTrajectoryTestRun({
  steps: [
    { stepType: 'tool_call', name: 'search', toolArgs: { q: 'test' } },
    { stepType: 'tool_call', name: 'summarize' },
  ],
})

const result = await trajectoryScorer.run(run)
```

### `checkTrajectoryEfficiency`

依據步驟、token 與持續時間預算評估軌跡效率，也會偵測重複呼叫（以相同引數呼叫相同 Tool）。

```typescript
import { checkTrajectoryEfficiency } from '@mastra/evals/scorers/utils'

const result = checkTrajectoryEfficiency(trajectory, {
  maxSteps: 5,
  maxTotalTokens: 2000,
  maxTotalDurationMs: 5000,
  noRedundantCalls: true,
})
// result.score — 1.0 if within all budgets, lower with penalties
// result.redundantCalls — duplicate tool+args combos
// result.overStepBudget — true if maxSteps exceeded
// result.overTokenBudget — true if maxTotalTokens exceeded
// result.overDurationBudget — true if maxTotalDurationMs exceeded
```

**傳回：** `TrajectoryEfficiencyResult`

### `checkTrajectoryBlacklist`

檢查軌跡是否包含禁止的 Tool 或 Tool 呼叫序列。

```typescript
import { checkTrajectoryBlacklist } from '@mastra/evals/scorers/utils'

const result = checkTrajectoryBlacklist(trajectory, {
  blacklistedTools: ['deleteAll', 'admin-override'],
  blacklistedSequences: [['escalate', 'admin-override']],
})
// result.score — 1.0 if no violations, 0.0 if any found
// result.violatedTools — blacklisted tools that were called
// result.violatedSequences — blacklisted sequences that were detected
```

**傳回：** `TrajectoryBlacklistResult`

### `analyzeToolFailures`

偵測 Tool 失敗模式，包括重試、後援與引數修正。

```typescript
import { analyzeToolFailures } from '@mastra/evals/scorers/utils'

const result = analyzeToolFailures(trajectory, {
  maxRetriesPerTool: 2,
})
// result.score — 1.0 if no failure patterns, lower if patterns detected
// result.patterns — detected patterns (retry, fallback, arg_correction)
```

**傳回：** `ToolFailureAnalysisResult`

## 完整範例

以下完整範例示範如何搭配使用多個工具函式：

```typescript
import { createScorer } from '@mastra/core/evals'
import {
  getAssistantMessageFromRunOutput,
  getReasoningFromRunOutput,
  getUserMessageFromRunInput,
  getCombinedSystemPrompt,
  extractToolCalls,
} from '@mastra/evals/scorers/utils'

const comprehensiveScorer = createScorer({
  id: 'comprehensive-analysis',
  name: 'Comprehensive Analysis',
  description: 'Analyzes all aspects of an agent response',
  type: 'agent',
})
  .preprocess(({ run }) => {
    // Extract all relevant data
    const userMessage = getUserMessageFromRunInput(run.input)
    const response = getAssistantMessageFromRunOutput(run.output)
    const reasoning = getReasoningFromRunOutput(run.output)
    const systemPrompt = getCombinedSystemPrompt(run.input)
    const { tools, toolCallInfos } = extractToolCalls(run.output)

    return {
      userMessage,
      response,
      reasoning,
      systemPrompt,
      toolsUsed: tools,
      toolCount: tools.length,
    }
  })
  .generateScore(({ results }) => {
    const { response, reasoning, toolCount } = results.preprocessStepResult || {}

    let score = 0
    if (response && response.length > 0) score += 0.4
    if (reasoning) score += 0.3
    if (toolCount > 0) score += 0.3

    return score
  })
  .generateReason(({ results, score }) => {
    const { response, reasoning, toolCount } = results.preprocessStepResult || {}

    const parts = []
    if (response) parts.push('provided a response')
    if (reasoning) parts.push('included reasoning')
    if (toolCount > 0) parts.push(`used ${toolCount} tool(s)`)

    return `Score: ${score}. The agent ${parts.join(', ')}.`
  })
```