Switch back to InvokeModel streaming #2

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.

Sign up for GitHub

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

Jump to bottom

Open

ndurner wants to merge 5 commits into main from l6qge4-codex/revert-to-invokemodel-api-with-streaming

Owner

ndurner commented Jun 3, 2025

Summary

stream responses using invoke_model_with_response_stream
remove the obsolete document message handling
parse streaming events from InvokeModelWithResponseStream

Testing

python -m py_compile $(git ls-files '*.py')

https://chatgpt.com/codex/tasks/task_e_683f55c2446083248123944d6952732b


          use InvokeModelWithResponseStream

1ec3094

ndurner added the codex label

— with

ChatGPT Codex Connector

ndurner added 4 commits

June 3, 2025 23:56


          Fix message content format for InvokeModel


          Fix streaming parsing for InvokeModel

8c9026e


          fix streaming loop

ca50b8b


          don't turn plaintext pastes into attachments automatically

42f42d4

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels