ag2-telemetry

name	ag2-telemetry
description	Add OpenTelemetry traces to an AG2 beta `Agent` via `TelemetryMiddleware` (`autogen.beta.middleware.builtin`). Emits spans for the full turn, each LLM call, each tool execution, and each human-input request, following the OpenTelemetry GenAI semantic conventions. Compatible with any OTLP backend — Jaeger, Grafana Tempo, Datadog, Honeycomb, Langfuse. Use when the user wants production-grade traces, latency analysis, token-usage attribution, or to ship telemetry into an existing observability stack.
license	Apache-2.0

Telemetry — OpenTelemetry instrumentation

When to use

The user wants to:

• See per-turn / per-call latency breakdowns
• Attribute token usage across operations
• Push traces to Jaeger, Grafana Tempo, Datadog, Honeycomb, Langfuse, etc.
• Debug a slow agent end-to-end with structured spans rather than print statements

If they just want quick stdout debugging, point them at LoggingMiddleware instead (see ag2-middleware).

Installation

pip install "ag2[openai,tracing]"

60-second recipe

from opentelemetry import trace
from opentelemetry.sdk.resources import Resource
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import SimpleSpanProcessor, ConsoleSpanExporter

 autogen.beta  Agent
 autogen.beta.config  OpenAIConfig
 autogen.beta.middleware.builtin  TelemetryMiddleware


resource = Resource.create({: })
tracer_provider = TracerProvider(resource=resource)
tracer_provider.add_span_processor(SimpleSpanProcessor(ConsoleSpanExporter()))
trace.set_tracer_provider(tracer_provider)


agent = Agent(
    ,
    prompt=,
    config=OpenAIConfig(model=),
    middleware=[
        TelemetryMiddleware(
            tracer_provider=tracer_provider,
            agent_name=,
        ),
    ],
)


 asyncio
asyncio.run(agent.ask())