LangChain

Import name: Sentry.langChainIntegration

The langChainIntegration adds instrumentation for LangChain to capture spans by automatically wrapping LangChain operations and recording AI agent interactions with configurable input/output recording.

import * as Sentry from "@sentry/cloudflare";
import { ChatAnthropic } from "@langchain/anthropic";

// Create a LangChain callback handler
const callbackHandler = Sentry.createLangChainCallbackHandler({
  recordInputs: true, // Optional: record input prompts/messages
  recordOutputs: true, // Optional: record output responses
});

// Use with chat models
const model = new ChatAnthropic({
  model: "claude-3-5-sonnet-20241022",
  apiKey: process.env.ANTHROPIC_API_KEY,
});

await model.invoke("Tell me a joke", {
  callbacks: [callbackHandler],
});

Options

recordInputs

Type: boolean

Records inputs to LangChain operations (such as prompts and messages).

Defaults to true if sendDefaultPii is true.

Sentry.init({
  integrations: [Sentry.langChainIntegration({ recordInputs: true })],
});

recordOutputs

Type: boolean

Records outputs from LangChain operations (such as generated text and responses).

Defaults to true if sendDefaultPii is true.

Sentry.init({
  integrations: [Sentry.langChainIntegration({ recordOutputs: true })],
});

Configuration

By default this integration adds tracing support for LangChain operations including:

• Chat model invocations (gen_ai.request) - Captures spans for chat model calls
• LLM invocations (gen_ai.pipeline) - Captures spans for LLM pipeline executions
• Chain executions (gen_ai.invoke_agent) - Captures spans for chain invocations
• Tool executions (gen_ai.execute_tool) - Captures spans for tool calls

Supported Runnables

The integration automatically instruments the following LangChain runnable methods:

• invoke() - Single execution
• stream() - Streaming execution
• batch() - Batch execution

Supported Versions

• langchain: >=0.1.0 <1.0.0