Anthropic

Installation

pip
uv
npm
yarn
pnpm

pip install "pandaprobe[anthropic]"

uv add "pandaprobe[anthropic]"

npm install pandaprobe @anthropic-ai/sdk

yarn add pandaprobe @anthropic-ai/sdk

pnpm add pandaprobe @anthropic-ai/sdk

Setup

Python
TypeScript

Python

from pandaprobe.wrappers import wrap_anthropic
from anthropic import Anthropic

client = wrap_anthropic(Anthropic())

TypeScript

import Anthropic from "@anthropic-ai/sdk";
import { wrapAnthropic } from "pandaprobe/wrappers/anthropic";

const client = wrapAnthropic(new Anthropic());

PandaProbe traces both synchronous and asynchronous Python clients, plus the Promise-based TypeScript client.

Messages API

Span name: "anthropic-messages", SpanKind: LLM

Python

response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    system="You are a helpful assistant.",
    messages=[{"role": "user", "content": "Explain quantum computing."}],
)

TypeScript

const response = await client.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  system: "You are a helpful assistant.",
  messages: [{ role: "user", content: "Explain quantum computing." }],
});

What gets traced

Input: system prompt (from top-level system kwarg) plus messages, normalized to a standard format
Output: text content blocks
Model name
Token usage
Model parameters: temperature, top_p, top_k, max_tokens, stop_sequences, thinking configuration
Extended thinking or reasoning blocks stored in metadata as reasoning_summary

Streaming

response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
)
for event in response:
    if hasattr(event, "delta") and hasattr(event.delta, "text"):
        print(event.delta.text, end="")

with client.messages.stream(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
) as stream:
    for text in stream.text_stream:
        print(text, end="")

Both streaming patterns are fully supported with time-to-first-token tracking. In TypeScript, both messages.create({stream: true, ...}) and messages.stream(...) are instrumented:

TypeScript

const stream = await client.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello!" }],
  stream: true,
});
for await (const event of stream) {
  if (event.type === "content_block_delta" && event.delta.type === "text_delta") {
    process.stdout.write(event.delta.text);
  }
}

Extended thinking

When using Anthropic’s extended thinking feature, thinking blocks are automatically extracted and stored in the span metadata under the reasoning_summary key. Thinking content is stripped from the visible output.

Token usage mapping

Anthropic Field	PandaProbe Field
`input_tokens`	`prompt_tokens`
`output_tokens`	`completion_tokens`
`cache_read_input_tokens`	`cache_read_tokens`
`cache_creation_input_tokens`	`cache_creation_tokens`

Get Started

Tracing

Installation

Setup

Messages API

Streaming

Extended thinking

Token usage mapping

​Installation

​Setup

​Messages API

​Streaming

​Extended thinking

​Token usage mapping

Installation

Setup

Messages API

Streaming

Extended thinking

Token usage mapping