@mastra/mcp-docs-server 0.13.37 → 0.13.38

package/.docs/raw/reference/scorers/run-experiment.mdx

@@ -10,23 +10,23 @@ The `runExperiment` function enables batch evaluation of agents and workflows by
 ## Usage Example
 
 ```typescript
-import { runExperiment } from '@mastra/core/scores';
-import { myAgent } from './agents/my-agent';
-import { myScorer1, myScorer2 } from './scorers';
+import { runExperiment } from "@mastra/core/scores";
+import { myAgent } from "./agents/my-agent";
+import { myScorer1, myScorer2 } from "./scorers";
 
 const result = await runExperiment({
   target: myAgent,
   data: [
     { input: "What is machine learning?" },
     { input: "Explain neural networks" },
-    { input: "How does AI work?" }
+    { input: "How does AI work?" },
   ],
   scorers: [myScorer1, myScorer2],
   concurrency: 2,
   onItemComplete: ({ item, targetResult, scorerResults }) => {
     console.log(`Completed: ${item.input}`);
     console.log(`Scores:`, scorerResults);
-  }
+  },
 });
 
 console.log(`Average scores:`, result.scores);
@@ -46,13 +46,15 @@ console.log(`Processed ${result.summary.totalItems} items`);
     {
       name: "data",
       type: "RunExperimentDataItem[]",
-      description: "Array of test cases with input data and optional ground truth.",
+      description:
+        "Array of test cases with input data and optional ground truth.",
       isOptional: false,
     },
     {
       name: "scorers",
       type: "MastraScorer[] | WorkflowScorerConfig",
-      description: "Array of scorers for agents, or configuration object for workflows specifying scorers for the workflow and individual steps.",
+      description:
+        "Array of scorers for agents, or configuration object for workflows specifying scorers for the workflow and individual steps.",
       isOptional: false,
     },
     {
@@ -65,7 +67,8 @@ console.log(`Processed ${result.summary.totalItems} items`);
     {
       name: "onItemComplete",
       type: "function",
-      description: "Callback function called after each test case completes. Receives item, target result, and scorer results.",
+      description:
+        "Callback function called after each test case completes. Receives item, target result, and scorer results.",
       isOptional: true,
     },
   ]}
@@ -78,13 +81,15 @@ console.log(`Processed ${result.summary.totalItems} items`);
     {
       name: "input",
       type: "string | string[] | CoreMessage[] | any",
-      description: "Input data for the target. For agents: messages or strings. For workflows: workflow input data.",
+      description:
+        "Input data for the target. For agents: messages or strings. For workflows: workflow input data.",
       isOptional: false,
     },
     {
       name: "groundTruth",
       type: "any",
-      description: "Expected or reference output for comparison during scoring.",
+      description:
+        "Expected or reference output for comparison during scoring.",
       isOptional: true,
     },
     {
@@ -117,7 +122,8 @@ For workflows, you can specify scorers at different levels using `WorkflowScorer
     {
       name: "steps",
       type: "Record<string, MastraScorer[]>",
-      description: "Object mapping step IDs to arrays of scorers for evaluating individual step outputs.",
+      description:
+        "Object mapping step IDs to arrays of scorers for evaluating individual step outputs.",
       isOptional: true,
     },
   ]}
@@ -130,7 +136,8 @@ For workflows, you can specify scorers at different levels using `WorkflowScorer
     {
       name: "scores",
       type: "Record<string, any>",
-      description: "Average scores across all test cases, organized by scorer name.",
+      description:
+        "Average scores across all test cases, organized by scorer name.",
     },
     {
       name: "summary",
@@ -150,33 +157,35 @@ For workflows, you can specify scorers at different levels using `WorkflowScorer
 ### Agent Evaluation
 
 ```typescript
-import { runExperiment } from '@mastra/core/scores';
-import { createScorer } from '@mastra/core/scores';
+import { runExperiment } from "@mastra/core/scores";
+import { createScorer } from "@mastra/core/scores";
 
 const myScorer = createScorer({
-  name: 'My Scorer',
+  name: "My Scorer",
   description: "Check if Agent's response contains ground truth",
-  type: 'agent'
+  type: "agent",
 }).generateScore(({ run }) => {
-  const response = run.output[0]?.content || '';
-  const expectedResponse = run.groundTruth
-  return response.includes(expectedResponse) ? 1 : 0
+  const response = run.output[0]?.content || "";
+  const expectedResponse = run.groundTruth;
+  return response.includes(expectedResponse) ? 1 : 0;
 });
 
 const result = await runExperiment({
   target: chatAgent,
   data: [
-    { 
+    {
       input: "What is AI?",
-      groundTruth: "AI is a field of computer science that creates intelligent machines."
+      groundTruth:
+        "AI is a field of computer science that creates intelligent machines.",
     },
     {
       input: "How does machine learning work?",
-      groundTruth: "Machine learning uses algorithms to learn patterns from data."
-    }
+      groundTruth:
+        "Machine learning uses algorithms to learn patterns from data.",
+    },
   ],
   scorers: [relevancyScorer],
-  concurrency: 3
+  concurrency: 3,
 });
 ```
 
@@ -187,24 +196,24 @@ const workflowResult = await runExperiment({
   target: myWorkflow,
   data: [
     { input: { query: "Process this data", priority: "high" } },
-    { input: { query: "Another task", priority: "low" } }
+    { input: { query: "Another task", priority: "low" } },
   ],
   scorers: {
     workflow: [outputQualityScorer],
     steps: {
-      'validation-step': [validationScorer],
-      'processing-step': [processingScorer]
-    }
+      "validation-step": [validationScorer],
+      "processing-step": [processingScorer],
+    },
   },
   onItemComplete: ({ item, targetResult, scorerResults }) => {
     console.log(`Workflow completed for: ${item.input.query}`);
     if (scorerResults.workflow) {
-      console.log('Workflow scores:', scorerResults.workflow);
+      console.log("Workflow scores:", scorerResults.workflow);
     }
     if (scorerResults.steps) {
-      console.log('Step scores:', scorerResults.steps);
+      console.log("Step scores:", scorerResults.steps);
     }
-  }
+  },
 });
 ```
 

package/.docs/raw/reference/scorers/textual-difference.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Textual Difference | Scorers | Mastra Docs"
+title: "Reference: Textual Difference Scorer | Scorers | Mastra Docs"
 description: Documentation for the Textual Difference Scorer in Mastra, which measures textual differences between strings using sequence matching.
 ---
 
@@ -7,8 +7,6 @@ description: Documentation for the Textual Difference Scorer in Mastra, which me
 
 The `createTextualDifferenceScorer()` function uses sequence matching to measure the textual differences between two strings. It provides detailed information about changes, including the number of operations needed to transform one text into another.
 
-For a usage example, see the [Textual Difference Examples](/examples/scorers/textual-difference).
-
 ## Parameters
 
 The `createTextualDifferenceScorer()` function does not take any options.
@@ -27,7 +25,8 @@ This function returns an instance of the MastraScorer class. See the [MastraScor
     {
       name: "analyzeStepResult",
       type: "object",
-      description: "Object with difference metrics: { confidence: number, changes: number, lengthDiff: number }",
+      description:
+        "Object with difference metrics: { confidence: number, changes: number, lengthDiff: number }",
     },
     {
       name: "score",
@@ -90,21 +89,21 @@ A textual difference score between 0 and 1:
 
 In this example, the texts are exactly the same. The scorer identifies complete similarity with a perfect score and no detected changes.
 
-```typescript filename="src/example-no-differences.ts" showLineNumbers copy
+```typescript title="src/example-no-differences.ts" showLineNumbers copy
 import { createTextualDifferenceScorer } from "@mastra/evals/scorers/code";
 
 const scorer = createTextualDifferenceScorer();
 
-const input = 'The quick brown fox jumps over the lazy dog';
-const output = 'The quick brown fox jumps over the lazy dog';
+const input = "The quick brown fox jumps over the lazy dog";
+const output = "The quick brown fox jumps over the lazy dog";
 
 const result = await scorer.run({
-  input: [{ role: 'user', content: input }],
-  output: { role: 'assistant', text: output },
+  input: [{ role: "user", content: input }],
+  output: { role: "assistant", text: output },
 });
 
-console.log('Score:', result.score);
-console.log('AnalyzeStepResult:', result.analyzeStepResult);
+console.log("Score:", result.score);
+console.log("AnalyzeStepResult:", result.analyzeStepResult);
 ```
 
 #### No differences output
@@ -127,21 +126,21 @@ The scorer returns a high score, indicating the texts are identical. The detaile
 
 In this example, the texts have small variations. The scorer detects these minor differences and returns a moderate similarity score.
 
-```typescript filename="src/example-minor-differences.ts" showLineNumbers copy
+```typescript title="src/example-minor-differences.ts" showLineNumbers copy
 import { createTextualDifferenceScorer } from "@mastra/evals/scorers/code";
 
 const scorer = createTextualDifferenceScorer();
 
-const input = 'Hello world! How are you?';
-const output = 'Hello there! How is it going?';
+const input = "Hello world! How are you?";
+const output = "Hello there! How is it going?";
 
 const result = await scorer.run({
-  input: [{ role: 'user', content: input }],
-  output: { role: 'assistant', text: output },
+  input: [{ role: "user", content: input }],
+  output: { role: "assistant", text: output },
 });
 
-console.log('Score:', result.score);
-console.log('AnalyzeStepResult:', result.analyzeStepResult);
+console.log("Score:", result.score);
+console.log("AnalyzeStepResult:", result.analyzeStepResult);
 ```
 
 #### Minor differences output
@@ -164,21 +163,21 @@ The scorer returns a moderate score reflecting the small variations between the
 
 In this example, the texts differ significantly. The scorer detects extensive changes and returns a low similarity score.
 
-```typescript filename="src/example-major-differences.ts" showLineNumbers copy
+```typescript title="src/example-major-differences.ts" showLineNumbers copy
 import { createTextualDifferenceScorer } from "@mastra/evals/scorers/code";
 
 const scorer = createTextualDifferenceScorer();
 
-const input = 'Python is a high-level programming language';
-const output = 'JavaScript is used for web development';
+const input = "Python is a high-level programming language";
+const output = "JavaScript is used for web development";
 
 const result = await scorer.run({
-  input: [{ role: 'user', content: input }],
-  output: { role: 'assistant', text: output },
+  input: [{ role: "user", content: input }],
+  output: { role: "assistant", text: output },
 });
 
-console.log('Score:', result.score);
-console.log('AnalyzeStepResult:', result.analyzeStepResult);
+console.log("Score:", result.score);
+console.log("AnalyzeStepResult:", result.analyzeStepResult);
 ```
 
 #### Major differences output
@@ -201,4 +200,4 @@ The scorer returns a low score due to significant differences between the texts.
 
 - [Content Similarity Scorer](./content-similarity)
 - [Completeness Scorer](./completeness)
-- [Keyword Coverage Scorer](./keyword-coverage)
+- [Keyword Coverage Scorer](./keyword-coverage)

package/.docs/raw/reference/scorers/tone-consistency.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Tone Consistency | Scorers | Mastra Docs"
+title: "Reference: Tone Consistency Scorer | Scorers | Mastra Docs"
 description: Documentation for the Tone Consistency Scorer in Mastra, which evaluates emotional tone and sentiment consistency in text.
 ---
 
@@ -7,8 +7,6 @@ description: Documentation for the Tone Consistency Scorer in Mastra, which eval
 
 The `createToneScorer()` function evaluates the text's emotional tone and sentiment consistency. It can operate in two modes: comparing tone between input/output pairs or analyzing tone stability within a single text.
 
-For a usage example, see the [Tone Consistency Examples](/examples/scorers/tone-consistency).
-
 ## Parameters
 
 The `createToneScorer()` function does not take any options.
@@ -27,7 +25,8 @@ This function returns an instance of the MastraScorer class. See the [MastraScor
     {
       name: "analyzeStepResult",
       type: "object",
-      description: "Object with tone metrics: { responseSentiment: number, referenceSentiment: number, difference: number } (for comparison mode) OR { avgSentiment: number, sentimentVariance: number } (for stability mode)",
+      description:
+        "Object with tone metrics: { responseSentiment: number, referenceSentiment: number, difference: number } (for comparison mode) OR { avgSentiment: number, sentimentVariance: number } (for stability mode)",
     },
     {
       name: "score",
@@ -68,7 +67,7 @@ The scorer evaluates sentiment consistency through tone pattern analysis and mod
    - Compares sentiment between texts
    - Calculates sentiment difference
    - Score = 1 - (sentiment_difference / max_difference)
-   **Tone Stability** (single input):
+     **Tone Stability** (single input):
    - Analyzes sentiment across sentences
    - Calculates sentiment variance
    - Score = 1 - (sentiment_variance / max_variance)
@@ -86,7 +85,9 @@ Final score: `mode_specific_score * scale`
 - 0.0: No consistency - completely different tones
 
 ### analyzeStepResult
+
 Object with tone metrics:
+
 - **responseSentiment**: Sentiment score for the response (comparison mode).
 - **referenceSentiment**: Sentiment score for the input/reference (comparison mode).
 - **difference**: Absolute difference between sentiment scores (comparison mode).
@@ -99,21 +100,21 @@ Object with tone metrics:
 
 In this example, the texts exhibit a similar positive sentiment. The scorer measures the consistency between the tones, resulting in a high score.
 
-```typescript filename="src/example-positive-tone.ts" showLineNumbers copy
+```typescript title="src/example-positive-tone.ts" showLineNumbers copy
 import { createToneScorer } from "@mastra/evals/scorers/code";
 
 const scorer = createToneScorer();
 
-const input = 'This product is fantastic and amazing!';
-const output = 'The product is excellent and wonderful!';
+const input = "This product is fantastic and amazing!";
+const output = "The product is excellent and wonderful!";
 
 const result = await scorer.run({
-  input: [{ role: 'user', content: input }],
-  output: { role: 'assistant', text: output },
+  input: [{ role: "user", content: input }],
+  output: { role: "assistant", text: output },
 });
 
-console.log('Score:', result.score);
-console.log('AnalyzeStepResult:', result.analyzeStepResult);
+console.log("Score:", result.score);
+console.log("AnalyzeStepResult:", result.analyzeStepResult);
 ```
 
 #### Positive tone output
@@ -135,21 +136,21 @@ The scorer returns a high score reflecting strong sentiment alignment. The `anal
 
 In this example, the text’s internal tone consistency is analyzed by passing an empty response. This signals the scorer to evaluate sentiment stability within the single input text, resulting in a score reflecting how uniform the tone is throughout.
 
-```typescript filename="src/example-stable-tone.ts" showLineNumbers copy
+```typescript title="src/example-stable-tone.ts" showLineNumbers copy
 import { createToneScorer } from "@mastra/evals/scorers/code";
 
 const scorer = createToneScorer();
 
-const input = 'Great service! Friendly staff. Perfect atmosphere.';
-const output = '';
+const input = "Great service! Friendly staff. Perfect atmosphere.";
+const output = "";
 
 const result = await scorer.run({
-  input: [{ role: 'user', content: input }],
-  output: { role: 'assistant', text: output },
+  input: [{ role: "user", content: input }],
+  output: { role: "assistant", text: output },
 });
 
-console.log('Score:', result.score);
-console.log('AnalyzeStepResult:', result.analyzeStepResult);
+console.log("Score:", result.score);
+console.log("AnalyzeStepResult:", result.analyzeStepResult);
 ```
 
 #### Stable tone output
@@ -170,21 +171,23 @@ The scorer returns a high score indicating consistent sentiment throughout the i
 
 In this example, the input and response have different emotional tones. The scorer picks up on these variations and gives a lower consistency score.
 
-```typescript filename="src/example-mixed-tone.ts" showLineNumbers copy
+```typescript title="src/example-mixed-tone.ts" showLineNumbers copy
 import { createToneScorer } from "@mastra/evals/scorers/code";
 
 const scorer = createToneScorer();
 
-const input = 'The interface is frustrating and confusing, though it has potential.';
-const output = 'The design shows promise but needs significant improvements to be usable.';
+const input =
+  "The interface is frustrating and confusing, though it has potential.";
+const output =
+  "The design shows promise but needs significant improvements to be usable.";
 
 const result = await scorer.run({
-  input: [{ role: 'user', content: input }],
-  output: { role: 'assistant', text: output },
+  input: [{ role: "user", content: input }],
+  output: { role: "assistant", text: output },
 });
 
-console.log('Score:', result.score);
-console.log('AnalyzeStepResult:', result.analyzeStepResult);
+console.log("Score:", result.score);
+console.log("AnalyzeStepResult:", result.analyzeStepResult);
 ```
 
 #### Mixed tone output