AutoGen | Respan Docs

AutoGen is Microsoft’s framework for building multi-agent conversational AI systems. It enables the creation of agents that can converse with each other to solve tasks, with support for human-in-the-loop patterns. Respan gives you full observability over every conversation, agent message, and LLM call — and gateway routing through the OpenAI-compatible Respan endpoint.

Set up Respan

Create an account at platform.respan.ai and grab an API key. For gateway, also add credits or a provider key.

Run npx @respan/cli setup to set up with your coding agent.

Example projects

Python examples

Tracing

Gateway

Setup

Install packages

$ pip install respan-ai openinference-instrumentation-autogen-agentchat pyautogen

Set environment variables

$ export OPENAI_API_KEY="YOUR_OPENAI_API_KEY"
$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

OPENAI_API_KEY is used for LLM requests. RESPAN_API_KEY is used to export traces to Respan.

Initialize and run

1 import os
2 import autogen
3 from respan import Respan
4 from openinference.instrumentation.autogen_agentchat import AutoGenInstrumentor
5 
6 respan = Respan(instrumentations=[AutoGenInstrumentor()])
7 
8 config_list = [{"model": "gpt-4.1-nano", "api_key": os.environ["OPENAI_API_KEY"]}]
9 
10 assistant = autogen.AssistantAgent(
11     name="assistant",
12     llm_config={"config_list": config_list},
13     system_message="You are a helpful AI assistant.",
14 )
15 
16 user_proxy = autogen.UserProxyAgent(
17     name="user_proxy",
18     human_input_mode="NEVER",
19     max_consecutive_auto_reply=3,
20     code_execution_config={"work_dir": "coding", "use_docker": False},
21 )
22 
23 user_proxy.initiate_chat(
24     assistant,
25     message="Write a Python function to calculate the fibonacci sequence.",
26 )
27 
28 respan.flush()

View your trace

Open the Traces page to see your AutoGen conversation with agent messages, LLM calls, and code execution.

Configuration

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Falls back to `RESPAN_API_KEY` env var.
`base_url`	`str \| None`	`None`	Falls back to `RESPAN_BASE_URL` env var.
`instrumentations`	`list`	`[]`	Plugin instrumentations to activate (e.g. `AutoGenInstrumentor()`).
`customer_identifier`	`str \| None`	`None`	Default customer identifier for all spans.
`metadata`	`dict \| None`	`None`	Default metadata attached to all spans.
`environment`	`str \| None`	`None`	Environment tag (e.g. `"production"`).

Attributes

In Respan()

Set defaults at initialization — these apply to all spans.

1 from respan import Respan
2 from openinference.instrumentation.autogen_agentchat import AutoGenInstrumentor
3 
4 respan = Respan(
5     instrumentations=[AutoGenInstrumentor()],
6     customer_identifier="user_123",
7     metadata={"service": "autogen-api", "version": "1.0.0"},
8 )

With propagate_attributes

Override per-request using a context scope.

1 from respan import Respan, propagate_attributes
2 from openinference.instrumentation.autogen_agentchat import AutoGenInstrumentor
3 
4 respan = Respan(instrumentations=[AutoGenInstrumentor()])
5 
6 def handle_request(user_id: str, message: str):
7     with propagate_attributes(
8         customer_identifier=user_id,
9         thread_identifier="conv_abc_123",
10         metadata={"plan": "pro"},
11     ):
12         user_proxy.initiate_chat(assistant, message=message)

Attribute	Type	Description
`customer_identifier`	`str`	Identifies the end user in Respan analytics.
`thread_identifier`	`str`	Groups related messages into a conversation.
`metadata`	`dict`	Custom key-value pairs. Merged with default metadata.