Vercel AI

Import name: Sentry.vercelAIIntegration

The vercelAIIntegration adds instrumentation for the ai SDK by Vercel to capture spans using the AI SDK's built-in telemetry.

Setup

Sentry.init({
  dsn: "___PUBLIC_DSN___",
  tracesSampleRate: 1.0,
});

Sentry.init({
  dsn: "___PUBLIC_DSN___",
  tracesSampleRate: 1.0,
});

Record Inputs and Outputs

Prompts and completions are not captured by default, because they usually contain user data. Turn recording on with recordInputs and recordOutputs.

Sentry resolves both settings in this order, and stops at the first one that is set:

1. The integration option — applies to every call.
2. The call's experimental_telemetry — applies to that call.
3. dataCollection.genAI — applies to every call.

The integration option wins over the call, not the other way around. If you set recordInputs: false on the integration, no call site can turn it back on.

Sentry.init({
  dsn: "___PUBLIC_DSN___",
  tracesSampleRate: 1.0,
  integrations: [
    Sentry.vercelAIIntegration({
      recordInputs: true,
      recordOutputs: true,
    }),
  ],
});

Sentry.init({
  dsn: "___PUBLIC_DSN___",
  tracesSampleRate: 1.0,
  integrations: [
    Sentry.vercelAIIntegration({
      recordInputs: true,
      recordOutputs: true,
    }),
  ],
});

const result = await generateText({
  model: openai("gpt-4o"),
  experimental_telemetry: {
    recordInputs: true,
    recordOutputs: true,
  },
});

const result = await generateText({
  model: openai("gpt-4o"),
  experimental_telemetry: {
    recordInputs: true,
    recordOutputs: true,
  },
});

Configure individual calls

Every instrumented ai function takes an experimental_telemetry object. Use it to control one call instead of all of them. For the full list of fields, see the AI SDK telemetry metadata docs.

Skip a Call

To capture no span for one call, set isEnabled to false:

const result = await generateText({
  model: openai("gpt-4o"),
  experimental_telemetry: { isEnabled: false },
});

const result = await generateText({
  model: openai("gpt-4o"),
  experimental_telemetry: { isEnabled: false },
});

Identify Your Call Sites

Spans carry the AI SDK function name, not yours, so a trace with several generateText calls is hard to read. Set functionId to label the call site. It appears on the span as gen_ai.function_id:

const result = await generateText({
  model: openai("gpt-4o"),
  experimental_telemetry: {
    functionId: "summarize-ticket",
  },
});

const result = await generateText({
  model: openai("gpt-4o"),
  experimental_telemetry: {
    functionId: "summarize-ticket",
  },
});

ToolLoopAgent

The integration captures spans for the ToolLoopAgent class. Each call to generate() or stream() creates an agent span, with the individual LLM requests and tool executions as child spans.

ToolLoopAgent takes its telemetry settings on the constructor, not on generate() or stream():

const agent = new ToolLoopAgent({
  model: openai("gpt-4o"),
  tools: {
    /* ... */
  },
  experimental_telemetry: {
    functionId: "weather-agent",
  },
});

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

const agent = new ToolLoopAgent({
  model: openai("gpt-4o"),
  tools: {
    /* ... */
  },
  experimental_telemetry: {
    functionId: "weather-agent",
  },
});

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

Options

enableTruncation

Type: boolean

Truncates recorded input messages so large payloads stay within span size limits. Affects inputs only, not outputs.

Defaults to true.

Sentry.init({
  integrations: [Sentry.vercelAIIntegration({ enableTruncation: false })],
});

Sentry.init({
  integrations: [Sentry.vercelAIIntegration({ enableTruncation: false })],
});

Sentry.init({
  integrations: [Sentry.vercelAIIntegration({ force: true })],
});

Sentry.init({
  integrations: [Sentry.vercelAIIntegration({ force: true })],
});

recordInputs

Type: boolean

Records inputs to the ai function call. See Record inputs and outputs for the full resolution order and the per-call alternative.

recordOutputs

Type: boolean

Records outputs from the ai function call. See Record inputs and outputs for the full resolution order and the per-call alternative.

Supported Operations

• generateText()
• streamText()
• generateObject()
• streamObject()
• embed()
• embedMany()
• rerank()

Plus generate() and stream() on ToolLoopAgent.

Supported Versions

• ai: >=3.0.0 <=7

Troubleshooting