This is a Deno notebook

Trace Claude Agent SDK JS/TS with Langfuse

The Claude Agent SDK is Anthropic’s open-source framework for building AI agents in TypeScript. By combining the Claude Agent SDK with Langfuse, you can trace, monitor, and analyze every agent step, tool call, and model response in development and production.

This notebook demonstrates how to use the ClaudeAgentSDKInstrumentation library from OpenInference to automatically instrument Claude Agent SDK calls and send OpenTelemetry spans to Langfuse.

What is Claude Agent SDK?
The Claude Agent SDK is Anthropic’s open-source framework for building AI agents. It provides a clean API for creating tool-using agents with the query() function, including native support for MCP servers and custom tools.

What is Langfuse?
Langfuse is an open source platform for LLM observability and monitoring. It helps you trace and monitor your AI applications by capturing metadata, prompt details, token usage, latency, and more.

Step 1: Install Dependencies

Install the necessary packages:

npm install @anthropic-ai/claude-agent-sdk @arizeai/openinference-instrumentation-claude-agent-sdk @langfuse/otel @opentelemetry/sdk-node

Note: This cookbook uses Deno.js for execution, which requires different syntax for importing packages and setting environment variables. For Node.js applications, the setup process is similar but uses standard npm packages and process.env.

Step 2: Configure Environment

Set up your Langfuse and Anthropic API keys. You can get Langfuse keys by signing up for a free Langfuse Cloud account or by self-hosting Langfuse. Get your Anthropic API key from the Anthropic Console.

Deno.env.set("ANTHROPIC_API_KEY", "sk-ant-...");
 
Deno.env.set("LANGFUSE_PUBLIC_KEY", "pk-lf-...");
Deno.env.set("LANGFUSE_SECRET_KEY", "sk-lf-...");
 
Deno.env.set("LANGFUSE_BASE_URL", "https://cloud.langfuse.com"); // 🇪🇺 EU region
// Deno.env.set("LANGFUSE_BASE_URL", "https://us.cloud.langfuse.com"); // 🇺🇸 US region

Step 3: Initialize OpenTelemetry with Langfuse

Set up the OpenTelemetry SDK with the LangfuseSpanProcessor and the ClaudeAgentSDKInstrumentation from OpenInference. The instrumentation automatically captures agent runs and tool calls, sending them as OpenTelemetry spans to Langfuse.

We also provide a custom shouldExportSpan filter to include spans from the @arizeai/openinference-instrumentation-claude-agent-sdk instrumentation scope alongside the default Langfuse filter.

import { NodeSDK } from "npm:@opentelemetry/sdk-node";
import { LangfuseSpanProcessor, isDefaultExportSpan } from "npm:@langfuse/otel";
import { ClaudeAgentSDKInstrumentation } from "npm:@arizeai/openinference-instrumentation-claude-agent-sdk";
 
import * as ClaudeAgentSDKModule from "npm:@anthropic-ai/claude-agent-sdk";
 
// Create mutable copy — Deno's ESM namespace objects are read-only
const ClaudeAgentSDK = { ...ClaudeAgentSDKModule };
 
const instrumentation = new ClaudeAgentSDKInstrumentation();
instrumentation.manuallyInstrument(ClaudeAgentSDK);
 
const sdk = new NodeSDK({
  spanProcessors: [
    new LangfuseSpanProcessor({
      shouldExportSpan: ({ otelSpan }) =>
        isDefaultExportSpan(otelSpan) ||
        otelSpan.instrumentationScope.name ===
          "@arizeai/openinference-instrumentation-claude-agent-sdk",
    }),
  ],
  instrumentations: [instrumentation],
});
 
sdk.start();

Step 4: Run the Agent

Use the Claude Agent SDK’s query() function to run an agent. All agent steps, tool calls, and model completions are automatically traced and sent to Langfuse.

const { query } = ClaudeAgentSDK;
 
for await (const message of query({
  prompt: "What is the capital of France? Answer in a single sentence.",
  options: {
    model: "claude-sonnet-4-5",
  },
})) {
  if (message.type === "assistant") {
    console.log(message.message.content);
  }
}
 
await sdk.shutdown();

View Traces in Langfuse

After running the agent, navigate to your Langfuse Trace Table. You will find detailed traces of the agent’s execution, providing insights into every agent step, tool call, input, output, and performance metric.

Claude Agent SDK JS/TS example trace in Langfuse

Interoperability with the JS/TS SDK

You can use this integration together with the Langfuse SDKs to add additional attributes or group observations into a single trace.

The Context Manager allows you to wrap your instrumented code using context managers (with with statements), which allows you to add additional attributes to the trace. Any observation created inside the callback will automatically be nested under the active observation, and the observation will be ended when the callback finishes.

import { startActiveObservation, propagateAttributes } from "npm:@langfuse/tracing";
 
await startActiveObservation("context-manager", async (span) => {
  span.update({
    input: { query: "What is the capital of France?" },
  });
 
  // Propagate userId to all child observations
  await propagateAttributes(
    {
      userId: "user-123",
      sessionId: "session-123",
      metadata: {
        source: "api",
        region: "us-east-1",
      },
      tags: ["api", "user"],
      version: "1.0.0",
    },
    async () => {
        
      // YOUR CODE HERE
      const { text } = await generateText({
        model: openai("gpt-5"),
        prompt: "What is the capital of France?",
        experimental_telemetry: { isEnabled: true },
      });
    }
  );
  span.update({ output: "Paris" });
});

Learn more about using the Context Manager in the Langfuse SDK instrumentation docs.

Troubleshooting

No traces appearing

First, enable debug mode in the JS/TS SDK:

export LANGFUSE_LOG_LEVEL="DEBUG"

Then run your application and check the debug logs:

OTel spans appear in the logs: Your application is instrumented correctly but traces are not reaching Langfuse. To resolve this:
1. Call forceFlush() at the end of your application to ensure all traces are exported. This is especially important in short-lived environments like serverless functions.
2. Verify that you are using the correct API keys and base URL.
No OTel spans in the logs: Your application is not instrumented correctly. Make sure the instrumentation runs before your application code.

Unwanted observations in Langfuse

The Langfuse SDK is based on OpenTelemetry. Other libraries in your application may emit OTel spans that are not relevant to you. These still count toward your billable units, so you should filter them out. See Unwanted spans in Langfuse for details.

Missing attributes

Some attributes may be stored in the metadata object of the observation rather than being mapped to the Langfuse data model. If a mapping or integration does not work as expected, please raise an issue on GitHub.

Next Steps

Once you have instrumented your code, you can manage, evaluate and debug your application:

Manage prompts in Langfuse Add evaluation scores Run LLM-as-a-judge Evaluators Create datasets Create custom dashboards Test queries in the Playground

Claude Agent SDK CrewAI

Was this page helpful?

Support