fix: No context vars for async agents replies #4640
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Why are these changes needed?
The Autogen currently utilizes the
asyncio.get_event_loop().run_in_executor()
method for generating async agent replies. However, this approach presents a challenge if the application decorates OpenAI calls (such asopenai.resources.chat.completions.AsyncCompletions.create
) for purposes like call tracing or statistics measurement. The problem is that context variables cannot be accessed in this setup.To address this issue, suggested to use
contextvars.copy_context().run()
method. This change will allow context variables to be properly propagated and accessed.Related issue number
Checks