Sentry for Flue

Install

Choose the features you want to configure, and this guide will show you how:

Install the Sentry Node SDK:

npm install @sentry/node@^11.0.0

npm install @sentry/node@^11.0.0

yarn add @sentry/node@^11.0.0

pnpm add @sentry/node@^11.0.0

npm install @sentry/node@^11.0.0 @sentry/profiling-node@^11.0.0

npm install @sentry/node@^11.0.0 @sentry/profiling-node@^11.0.0

yarn add @sentry/node@^11.0.0 @sentry/profiling-node@^11.0.0

pnpm add @sentry/node@^11.0.0 @sentry/profiling-node@^11.0.0

Configure

Create a file that calls Sentry.init() and registers the Flue instrumentation. Flue is instrumented by registering with it rather than by patching, so this instrument() call is what connects the two:

import { instrument } from "@flue/runtime";
import * as Sentry from "@sentry/node";
// ___PRODUCT_OPTION_START___ profiling
import { nodeProfilingIntegration } from "@sentry/profiling-node";
// ___PRODUCT_OPTION_END___ profiling

Sentry.init({
  dsn: "___PUBLIC_DSN___",
  // ___PRODUCT_OPTION_START___ profiling

  integrations: [
    // Add our Profiling integration
    nodeProfilingIntegration(),
  ],
  // ___PRODUCT_OPTION_END___ profiling
  // ___PRODUCT_OPTION_START___ performance

  // Set tracesSampleRate to 1.0 to capture 100%
  // of spans for tracing.
  // We recommend adjusting this value in production.
  tracesSampleRate: 1.0,
  // ___PRODUCT_OPTION_END___ performance
  // ___PRODUCT_OPTION_START___ profiling

  // Set profileSessionSampleRate to 1.0 to profile every session.
  // Learn more at
  // https://docs.sentry.io/platforms/javascript/configuration/options/#profileSessionSampleRate
  profileSessionSampleRate: 1.0,
  // ___PRODUCT_OPTION_END___ profiling
});

instrument(Sentry.createFlueInstrumentation());

import { instrument } from "@flue/runtime";
import * as Sentry from "@sentry/node";
// ___PRODUCT_OPTION_START___ profiling
import { nodeProfilingIntegration } from "@sentry/profiling-node";
// ___PRODUCT_OPTION_END___ profiling

Sentry.init({
  dsn: "___PUBLIC_DSN___",
  // ___PRODUCT_OPTION_START___ profiling

  integrations: [
    // Add our Profiling integration
    nodeProfilingIntegration(),
  ],
  // ___PRODUCT_OPTION_END___ profiling
  // ___PRODUCT_OPTION_START___ performance

  // Set tracesSampleRate to 1.0 to capture 100%
  // of spans for tracing.
  // We recommend adjusting this value in production.
  tracesSampleRate: 1.0,
  // ___PRODUCT_OPTION_END___ performance
  // ___PRODUCT_OPTION_START___ profiling

  // Set profileSessionSampleRate to 1.0 to profile every session.
  // Learn more at
  // https://docs.sentry.io/platforms/javascript/configuration/options/#profileSessionSampleRate
  profileSessionSampleRate: 1.0,
  // ___PRODUCT_OPTION_END___ profiling
});

instrument(Sentry.createFlueInstrumentation());

Import it at the top of your app entry, so it runs before your agents take a turn:

import "./instrument.ts";

import "./instrument.ts";

Call instrument() once, at module scope. On Cloudflare the Vite plugin registers the instrumentation at build time instead; on Node there's no equivalent, so this call is what installs it.

Run With the Sentry Loader

Libraries like database drivers, caches, and dataloader are instrumented by a module transform that has to be installed before your app loads them. A Flue build imports your dependencies before src/instrument.ts runs, so start the server with the Sentry loader to catch them:

{
  "scripts": {
    "dev": "NODE_OPTIONS='--import=@sentry/node/import' vite dev",
    "start": "NODE_OPTIONS='--import=@sentry/node/import' node dist/server.mjs"
  }
}

{
  "scripts": {
    "dev": "NODE_OPTIONS='--import=@sentry/node/import' vite dev",
    "start": "NODE_OPTIONS='--import=@sentry/node/import' node dist/server.mjs"
  }
}

Agent, model, and tool spans arrive without this, as do outgoing HTTP requests. Everything instrumented through the module transform needs it.

With this setup, Sentry captures errors thrown by your agents and tools, and AI spans for every run (agent turns, model calls, tool executions, token usage, and latency). Manual spans you start inside a tool nest under that tool's span.

To review what's captured and turn recording of prompts and responses off, see Privacy Controls below.

Privacy Controls

The SDK will record generative AI inputs and outputs (the prompts your agent sends and the model responses it receives) by default. To turn recording off, set genAI.inputs and genAI.outputs to false in dataCollection:

Sentry.init({
  dsn: "___PUBLIC_DSN___",
  dataCollection: {
    genAI: { inputs: false, outputs: false },
  },
});

Sentry.init({
  dsn: "___PUBLIC_DSN___",
  dataCollection: {
    genAI: { inputs: false, outputs: false },
  },
});

See dataCollection documentation for details on privacy control options.

Link Conversations

Sentry groups a multi-turn chat into a single Conversation automatically — there's no Sentry-specific setup. Flue already tracks a conversation id per conversation, and the SDK maps it to gen_ai.conversation.id on the agent, model, and tool spans of every turn.

The agent span also carries gen_ai.agent.name, so you can tell a lead agent's runs from its subagents'.

Verify

Send a message to one of your agents, then open Explore → Agents in Sentry. Select the conversation to open its detail. The timeline shows the agent turn, model calls, tool executions, token usage, latency, and any errors your tools threw.

If no data appears, confirm that:

• The dsn belongs to the Sentry project you're viewing.
• tracesSampleRate is greater than 0.
• Your agent completed at least one turn after you added the setup.