-
Notifications
You must be signed in to change notification settings - Fork 7.7k
Feat/gpt5 support #6917
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
base: main
Are you sure you want to change the base?
Feat/gpt5 support #6917
Conversation
This reverts commit b5014a0.
Codecov Report❌ Patch coverage is Additional details and impacted files@@ Coverage Diff @@
## main #6917 +/- ##
==========================================
+ Coverage 80.89% 81.05% +0.15%
==========================================
Files 237 239 +2
Lines 18349 18774 +425
==========================================
+ Hits 14844 15217 +373
- Misses 3505 3557 +52
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
python/packages/autogen-ext/src/autogen_ext/models/openai/_model_info.py
Fixed
Show fixed
Hide fixed
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It is a lot of changes, can we separate them into different PRs? Have 1 PR for the model info updates and another PR for the response client.
what is the status of this integration? I am looking forward to use gpt-5 on my project. Any other PRs that have done the changes? |
Why are these changes needed?
This PR introduces GPT-5 support across the Autogen core and extensions, enabling developers to build agents and tools that fully utilize GPT-5’s advanced reasoning and tool-use capabilities while preserving backward compatibility with existing Autogen behaviors. Updated OpenAI package to support GPT 5.
These changes unlock GPT-5’s reasoning abilities, custom tool integration, and Responses API features for more capable, context-aware agents.
Related issue number
Closes #6916
Checks