Back to Ai

hasToolCall

content/docs/07-reference/01-ai-sdk-core/71-has-tool-call.mdx

2.1.102.6 KB
Original Source

hasToolCall()

Creates a stop condition that stops when a specific tool is called.

This function is used with stopWhen in generateText and streamText to control when a tool-calling loop should stop based on whether a particular tool has been invoked.

ts
import { generateText, hasToolCall } from 'ai';
__PROVIDER_IMPORT__;

const result = await generateText({
  model: __MODEL__,
  tools: {
    weather: weatherTool,
    finalAnswer: finalAnswerTool,
  },
  // Stop when the finalAnswer tool is called
  stopWhen: hasToolCall('finalAnswer'),
});

Import

<Snippet text={import { hasToolCall } from "ai"} prompt={false} />

API Signature

Parameters

<PropertiesTable content={[ { name: 'toolName', type: 'string', description: 'The name of the tool that should trigger the stop condition when called.', }, ]} />

Returns

A StopCondition function that returns true when the specified tool is called in the current step. The function can be used with the stopWhen parameter in generateText and streamText.

Examples

Basic Usage

Stop when a specific tool is called:

ts
import { generateText, hasToolCall } from 'ai';

const result = await generateText({
  model: yourModel,
  tools: {
    submitAnswer: submitAnswerTool,
    search: searchTool,
  },
  stopWhen: hasToolCall('submitAnswer'),
});

Combining with Other Conditions

You can combine multiple stop conditions in an array:

ts
import { generateText, hasToolCall, stepCountIs } from 'ai';

const result = await generateText({
  model: yourModel,
  tools: {
    weather: weatherTool,
    search: searchTool,
    finalAnswer: finalAnswerTool,
  },
  // Stop when weather tool is called OR finalAnswer is called OR after 5 steps
  stopWhen: [
    hasToolCall('weather'),
    hasToolCall('finalAnswer'),
    stepCountIs(5),
  ],
});

Agent Pattern

Common pattern for agents that run until they provide a final answer:

ts
import { generateText, hasToolCall } from 'ai';

const result = await generateText({
  model: yourModel,
  tools: {
    search: searchTool,
    calculate: calculateTool,
    finalAnswer: {
      description: 'Provide the final answer to the user',
      parameters: z.object({
        answer: z.string(),
      }),
      execute: async ({ answer }) => answer,
    },
  },
  stopWhen: hasToolCall('finalAnswer'),
});

See also