LLM Tracekit - Anthropic

OpenTelemetry instrumentation for the Anthropic Python SDK (Messages API), designed to simplify LLM application development and production tracing and debugging.

Installation

Anthropic

pip install "llm-tracekit-anthropic"

Usage

This section describes how to set up instrumentation for the Anthropic SDK.

Setting up tracing

You can use the setup_export_to_coralogix function to setup tracing and export traces to Coralogix

from llm_tracekit.anthropic import setup_export_to_coralogix

setup_export_to_coralogix(
    service_name="ai-service",
    application_name="ai-application",
    subsystem_name="ai-subsystem",
    capture_content=True,
)

Alternatively, you can set up tracing manually:

from opentelemetry import trace
from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk.resources import SERVICE_NAME, Resource
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import SimpleSpanProcessor

tracer_provider = TracerProvider(
    resource=Resource.create({SERVICE_NAME: "ai-service"}),
)
exporter = OTLPSpanExporter()
span_processor = SimpleSpanProcessor(exporter)
tracer_provider.add_span_processor(span_processor)
trace.set_tracer_provider(tracer_provider)

Activation

To instrument all clients, call the instrument method

from llm_tracekit.anthropic import AnthropicInstrumentor

AnthropicInstrumentor().instrument()

Enabling message content

Message content such as the contents of the prompt, completion, function arguments and return values are not captured by default. To capture message content as span attributes, do one of the following:

• Pass capture_content=True when calling setup_export_to_coralogix
• Set the environment variable OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT to true

Most Coralogix AI evaluations will not work without message contents, so it is highly recommended to enable capturing.

Uninstrument

To uninstrument clients, call the uninstrument method:

AnthropicInstrumentor().uninstrument()

Full Example

from llm_tracekit.anthropic import AnthropicInstrumentor, setup_export_to_coralogix
from anthropic import Anthropic

# Optional: Configure sending spans to Coralogix
# Reads Coralogix connection details from the following environment variables:
# - CX_TOKEN
# - CX_ENDPOINT
setup_export_to_coralogix(
    service_name="ai-service",
    application_name="ai-application",
    subsystem_name="ai-subsystem",
    capture_content=True,
)

# Activate instrumentation
AnthropicInstrumentor().instrument()

# Example Anthropic Usage
client = Anthropic()
response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Write a short poem on open telemetry."},
    ],
)

Changes from OpenTelemetry

General

• Instruments sync and async messages.create (including stream=True) and messages.stream / AsyncMessages.stream.
• The metadata.user_id request field is recorded as the gen_ai.request.user attribute.
• User prompts and model responses are captured as span attributes instead of log events (see Semantic Conventions below).

Semantic Conventions