Fix async runner to respect --disable-streaming flag#20
Open
Fix async runner to respect --disable-streaming flag#20
Conversation
The async runner was hardcoding stream=True in the payload, ignoring the --disable-streaming CLI flag. This fix: 1. Adds disable_streaming parameter to BaseAsyncRunner and factory 2. Updates payload to use stream=not self.disable_streaming 3. Adds conditional stream_options only when streaming is enabled 4. Adds non-streaming response parsing logic 5. Passes disable_streaming from CLI through to the runner factory
added 3 commits
January 5, 2026 18:57
- BasetenUser: Catch additional exception types (ValueError, TypeError) in parse_chat_response and handle plain text parsing failures gracefully - Async runner: Detect non-SSE error responses (plain text errors, exceptions, tracebacks) in streaming responses and return proper error responses - Errors are now reported with status codes in metrics instead of crashing - Removed test_streaming.py with async test configuration issues
- Remove sys.exit(1) from logging error handlers that was crashing the benchmark - BasetenUser: Catch additional exception types in parse methods - Async runner: Detect non-SSE error responses in streaming - Skip test_streaming.py tests with pytest-asyncio configuration issues
- Remove automatic flush_buffer() call on ERROR-level logs in DelayedRichHandler - Live dashboard now continues running when API errors (500) occur - flush_buffer() still called only for uncaught exceptions/KeyboardInterrupt
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The async runner was hardcoding stream=True in the payload, ignoring the --disable-streaming CLI flag. This fix:
Description
Related Issue
Changes
Correctness Tests
Checklist
git pull origin main)make checkto ensure code is properly formatted and passes all lint checksmake testormake test_changedto verify test coverage (~90% required)Additional Information
Add any other context, screenshots, or information about the PR here.