Sentry Setup AI Monitoring

All Skills > Feature Setup > AI Monitoring

Setup Sentry AI Agent Monitoring

Configure Sentry to track LLM calls, agent executions, tool usage, and token consumption.

Invoke This Skill When

• User asks to "monitor AI/LLM calls" or "track OpenAI/Anthropic usage"
• User wants "AI observability" or "agent monitoring"
• User asks about token usage, model latency, or AI costs

Important: The SDK versions, API names, and code samples below are examples. Always verify against docs.sentry.io before implementing, as APIs and minimum versions may have changed.

Prerequisites

AI monitoring requires tracing enabled (tracesSampleRate > 0).

If the app has multi-turn chats, set a conversation ID by default anywhere it makes sense to identify a chat session. Sentry uses gen_ai.conversation.id to group related AI spans into Conversations. Some integrations infer it automatically, but many setups need to set it explicitly.

Data Capture Warning

Prompt and output recording captures user content that is likely PII. In JavaScript, genAI input/output capture is on by default (governed by dataCollection.genAI); in Python it is enabled via send_default_pii=True; in Laravel it is enabled via SENTRY_SEND_DEFAULT_PII=true. Before relying on this capture (or per-integration overrides — recordInputs/recordOutputs in JS, include_prompts in Python), confirm:

• The application's privacy policy permits capturing user prompts and model responses
• Captured data complies with applicable regulations (GDPR, CCPA, etc.)
• Sentry data retention settings are appropriate for the sensitivity of the data

Ask the user whether they want prompt/output capture enabled. Do not enable prompt/output capture without explicit confirmation. Use tracesSampleRate: 1.0 only in development; in production, use a lower value or a tracesSampler function.

Detection First

Always detect installed AI SDKs before configuring:

# JavaScript
grep -E '"(openai|@anthropic-ai/sdk|ai|@langchain|@google/genai)"' package.json

# Python
grep -E '(openai|anthropic|langchain|huggingface)' requirements.txt pyproject.toml 2>/dev/null

# PHP / Laravel
grep -E '"(laravel/ai|openai-php|openai/|anthropic|llm)' composer.json 2>/dev/null
ls artisan 2>/dev/null && echo "Laravel detected"

Sampling Check

After detecting AI SDKs, check the current sampling configuration:

# JavaScript
grep -E 'tracesSampleRate|tracesSampler' sentry.*.config.* instrument.* src/instrument.* app/instrument.* 2>/dev/null

# Python
grep -E 'traces_sample_rate|traces_sampler' *.py **/*.py 2>/dev/null

# PHP / Laravel
grep -E 'SENTRY_TRACES_SAMPLE_RATE|traces_sample_rate|traces_sampler' .env config/sentry.php 2>/dev/null

If tracesSampleRate / traces_sample_rate is below 1.0 AND no tracesSampler / traces_sampler is configured:

Ask the user:

"Your current sample rate is {rate}. Agent runs are sampled as complete span trees — if the root span is dropped, all child gen_ai spans are lost. For full AI visibility, gen_ai-related transactions should be sampled at 100%. Would you like me to set up a tracesSampler that keeps AI traces at 100% while sampling other traffic at your current rate?"

If user confirms, read ${SKILL_ROOT}/references/sampling.md for implementation patterns.

Supported SDKs

JavaScript

*Vercel AI: 10.53.0+ required. Requires experimental_telemetry per-call.

Python

Integrations auto-enable when the AI package is installed — no explicit registration needed:

PHP / Laravel

Laravel AI support requires Laravel 12.x or later, sentry/sentry-laravel 4.27.0 or later, and tracing enabled.

JavaScript Configuration

Node.js — auto-enabled integrations

Just ensure tracing is enabled. Integrations auto-enable when the AI package is installed:

Sentry.init({
  dsn: "YOUR_DSN",
  tracesSampleRate: 1.0, // Lower in production (e.g., 0.1)
  // OpenAI, Anthropic, Google GenAI, LangChain integrations auto-enable in Node.js
});

To customize (e.g., enable prompt capture after user confirmation — see Data Capture Warning):

Sentry.init({
  dsn: "YOUR_DSN",
  tracesSampleRate: 1.0,
  dataCollection: {
    // To disable sending user data and HTTP bodies, uncomment the lines below. For more info visit:
    // https://docs.sentry.io/platforms/javascript/configuration/options/#dataCollection
    // userInfo: false,
    // httpBodies: [],
  },
  integrations: [
    Sentry.openAIIntegration({
      // recordInputs/recordOutputs default to true (governed by dataCollection.genAI)
    }),
  ],
});

Cloudflare Workers (no runtime patching)

The Workers runtime (workerd) does not support monkey-patching, so Node.js-style auto-instrumentation does not apply. Workers AI (env.AI) is auto-instrumented by withSentry (v10.67.0+); openai, @anthropic-ai/sdk, @google/genai, and ai need either the build-time Sentry Cloudflare Vite plugin (v10.68.0+, experimental) or manual client wrapping; LangChain/LangGraph are manual-only. Read ${SKILL_ROOT}/../../references/sdks/cloudflare/ai-monitoring.md for the full setup.

Browser / Next.js OpenAI (manual wrapping required)

In browser-side code or Next.js meta-framework apps, auto-instrumentation is not available. Wrap the client manually:

import OpenAI from "openai";
import * as Sentry from "@sentry/nextjs"; // or @sentry/react, @sentry/browser

const openai = Sentry.instrumentOpenAiClient(new OpenAI());
// Use 'openai' client as normal

LangChain / LangGraph (auto-enabled)

Sentry.init({
  dsn: "YOUR_DSN",
  tracesSampleRate: 1.0,
  dataCollection: {
    // To disable sending user data and HTTP bodies, uncomment the lines below. For more info visit:
    // https://docs.sentry.io/platforms/javascript/configuration/options/#dataCollection
    // userInfo: false,
    // httpBodies: [],
  },
  integrations: [
    Sentry.langChainIntegration(),
    Sentry.langGraphIntegration(),
  ],
});

Vercel AI SDK

Add to sentry.edge.config.ts for Edge runtime:

Sentry.init({
  dsn: "YOUR_DSN",
  tracesSampleRate: 1.0,
  dataCollection: {
    // To disable sending user data and HTTP bodies, uncomment the lines below. For more info visit:
    // https://docs.sentry.io/platforms/javascript/configuration/options/#dataCollection
    // userInfo: false,
    // httpBodies: [],
  },
  integrations: [Sentry.vercelAIIntegration()],
});

Enable telemetry per-call:

await generateText({
  model: openai("gpt-4o"),
  prompt: "Hello",
  experimental_telemetry: {
    isEnabled: true,
    recordInputs: true,
    recordOutputs: true,
  },
});

Python Configuration

Integrations auto-enable — just init with tracing. Only add explicit imports to customize options:

import sentry_sdk

sentry_sdk.init(
    dsn="YOUR_DSN",
    traces_sample_rate=1.0,  # Lower in production (e.g., 0.1)
    send_default_pii=True,
    # Integrations auto-enable when the AI package is installed.
    # Only specify explicitly to customize (e.g., include_prompts):
    # integrations=[OpenAIIntegration(include_prompts=True)],
)

PHP / Laravel AI Configuration

Laravel AI instrumentation auto-enables when both sentry/sentry-laravel and laravel/ai are installed and tracing is active.

composer require sentry/sentry-laravel "^4.27.0"
composer require laravel/ai
php artisan vendor:publish --provider="Laravel\Ai\AiServiceProvider"
php artisan migrate

Enable tracing in .env:

SENTRY_TRACES_SAMPLE_RATE=1.0

To include LLM prompts, tool arguments, and responses after explicit user confirmation, enable PII capture:

SENTRY_SEND_DEFAULT_PII=true

Sentry treats LLM and tool inputs/outputs as PII and does not capture them by default. Do not enable SENTRY_SEND_DEFAULT_PII=true without confirming the Data Capture Warning above.

The Laravel integration captures these span types automatically:

For detailed Laravel setup, verification, Conversations behavior, and feature flags, read ${SKILL_ROOT}/../../references/sdks/php/ai-monitoring.md.

Manual Instrumentation

Use when no supported SDK is detected. Follow the canonical Sentry Conventions for gen_ai.* attributes — the JS docs may lag behind; do not set attributes marked deprecated in the conventions.

Span Types

For LLM-call spans, the op follows the pattern gen_ai.{gen_ai.operation.name} — use gen_ai.chat, gen_ai.embeddings, gen_ai.generate_content, or gen_ai.text_completion where the operation is known. Span attributes only accept primitives; arrays/objects must be JSON-stringified.

Example (JavaScript)

const inputMessages = [
  { role: "user", parts: [{ type: "text", content: "Tell me a joke" }] },
];

await Sentry.startSpan({
  op: "gen_ai.chat",
  name: "chat gpt-4o",
  attributes: {
    "gen_ai.request.model": "gpt-4o",
    "gen_ai.operation.name": "chat",
    "gen_ai.input.messages": JSON.stringify(inputMessages),
  },
}, async (span) => {
  const result = await llmClient.complete(inputMessages);

  const outputMessages = [
    {
      role: "assistant",
      parts: [
        // Thinking/reasoning content goes in a `reasoning` part, NOT a `text` part.
        // Sentry surfaces it separately and filters it out of the Conversations view.
        { type: "reasoning", content: result.reasoning },
        { type: "text", content: result.text },
      ],
      finish_reason: result.finishReason,
    },
  ];
  span.setAttribute("gen_ai.output.messages", JSON.stringify(outputMessages));
  span.setAttribute("gen_ai.usage.input_tokens", result.inputTokens);
  span.setAttribute("gen_ai.usage.output_tokens", result.outputTokens);
  return result;
});

Key Attributes

Common (all AI spans):

Model config (LLM call spans):

Request / response content (PII — enable only after confirming; see Data Capture Warning above):

Thinking / reasoning messages: Models with extended thinking (Anthropic thinking blocks, Gemini thought, DeepSeek reasoning_content) produce internal reasoning that isn't part of the user-visible reply. Represent it as a reasoning part inside the assistant message — {"type": "reasoning", "content": "..."} — alongside the user-facing text part. Sentry surfaces reasoning parts separately and filters them out of the user-facing Conversations view, so do not fold thinking into a text part. When previous thinking is fed back into a multi-turn request, include the same reasoning parts in the assistant messages within gen_ai.input.messages. Record reasoning token counts via gen_ai.usage.output_tokens.reasoning (a subset of gen_ai.usage.output_tokens). | gen_ai.system_instructions | System prompt passed to the model | | gen_ai.tool.definitions | JSON-stringified list of tools available to the model |

Token usage:

Tool spans (gen_ai.execute_tool):