Skip to content

introduce AutoGen instrumentation. #1157

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 11 commits into
base: main
Choose a base branch
from
Open

Conversation

fenilfaldu
Copy link
Contributor

📥 Pull Request

📘 Description

  • Added AutoGen instrumentation modules to support agent interactions, including agent-specific instrumentors and utilities.
  • Implemented new agent types and team structures for enhanced collaboration in AutoGen examples.
  • Updated documentation and examples to reflect the new features and usage scenarios, including a GroupChat and Swarm team example.

🧪 Testing
Tested Examples

Copy link

codecov bot commented Jul 17, 2025

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

@Dwij1704
Copy link
Member

What happened to LangGraph? lol

@Dwij1704
Copy link
Member

I re ran it and it works

@fenilfaldu fenilfaldu requested review from dot-agi and Dwij1704 July 17, 2025 23:20
@fenilfaldu
Copy link
Contributor Author

So our integration tests are randomly failing on push, different ones each time.

What I suspect:
The validate_trace_spans() function (which I believe validates presence of LLM spans) is synchronous, while some of our examples involve async logic and await agent calls. There are chances the spans haven’t fully flushed/exported by the time validation kicks in.This might just be a race condition between span export and validation but this just all in theory for now.

@Dwij1704
Copy link
Member

So our integration tests are randomly failing on push, different ones each time.

What I suspect: The validate_trace_spans() function (which I believe validates presence of LLM spans) is synchronous, while some of our examples involve async logic and await agent calls. There are chances the spans haven’t fully flushed/exported by the time validation kicks in.This might just be a race condition between span export and validation but this just all in theory for now.

Few examples are failing due to backend failure, o3 example is busted, @areibman pushed it yesterday as it was working on his machine, will need to check what the actual reason is behind its failure. ag2, web_search and mem0 were already busted, needs fixing as discussed yesterday.

Copy link
Member

@dot-agi dot-agi left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Left some comments for improvements.

AutoGen example notebooks are not clean at all. They are copypasta from the Python scripts. I cannot stress the importance enoughof having clean and structured notebooks as they provide the users with running examples out of the box.

Please look at the other notebooks and structure the content properly.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants