Trace Anthropic SDK with BotGauge

Records Anthropic SDK LLM calls with model, input and output, and token counts. If your framework calls the Anthropic SDK underneath, this extra traces those LLM calls without the framework’s own steps.


Extra	`[anthropic]`
Verified framework versions	anthropic 1.8.0 and 1.15.0
Instrumentor installed by the extra	`openinference-instrumentation-anthropic 3.0.3`
Zero-code run	Traced

Also verified: anthropic 1.8.0 with instrumentor 2.1.6. The extra no longer installs that older instrumentor. See supported frameworks for how verification works.

In code

Call tracing.init(), attach the framework instrumentor to the provider it returns, and wrap the work in tracing.turn() and tracing.agent().

Install

terminal

pip install "botgauge[anthropic]" anthropic==1.15.0

Add the code

app.py

import os

from botgauge import tracing
from anthropic import Anthropic
from openinference.instrumentation.anthropic import AnthropicInstrumentor

provider = tracing.init()
AnthropicInstrumentor().instrument(tracer_provider=provider)

client = Anthropic()

with tracing.turn(session_id="ses_anthropic"), tracing.agent("anthropic-agent"):
    reply = client.messages.create(
        model=os.environ["ANTHROPIC_MODEL"],
        max_tokens=128,
        messages=[{"role": "user", "content": "In one sentence, what is OpenTelemetry?"}],
    )
print(reply.content[0].text)

tracing.shutdown()

Run

terminal

python app.py

Needs BOTGAUGE_API_KEY, ANTHROPIC_API_KEY, ANTHROPIC_MODEL. Set ANTHROPIC_BASE_URL too if your LLM isn’t api.anthropic.com.

Zero-code

Leave your app unchanged and start it with botgauge instrument. The sample still wraps the work in tracing.turn() and tracing.agent() so spans carry session and agent ids.

Install

terminal

pip install "botgauge[anthropic]" anthropic==1.15.0

Add the code

app.py

import os

from botgauge import tracing
from anthropic import Anthropic

client = Anthropic()

with tracing.turn(session_id="ses_anthropic"), tracing.agent("anthropic-agent"):
    reply = client.messages.create(
        model=os.environ["ANTHROPIC_MODEL"],
        max_tokens=128,
        messages=[{"role": "user", "content": "In one sentence, what is OpenTelemetry?"}],
    )
print(reply.content[0].text)

Run

terminal

botgauge instrument python app.py

Needs BOTGAUGE_API_KEY, ANTHROPIC_API_KEY, ANTHROPIC_MODEL. Set ANTHROPIC_BASE_URL too if your LLM isn’t api.anthropic.com.

View Anthropic spans live

Watch your Anthropic messages with token counts appear in BotGauge.

Try BotGauge →

See versions not verified if you run a different version, capture and redaction to control exported content, and troubleshooting if spans are missing.

Frameworks

More

Trace Anthropic SDK with BotGauge

In code

Zero-code

​In code

​Zero-code

​Related

In code

Zero-code

Related