fix: process InterruptionFrame synchronously through all processors #3182
Conversation
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
This fixes a race condition where the processor that initiates an interruption (e.g., LLMUserContextAggregator) would push the new context to the LLM before downstream processors (e.g., LLMAssistantContextAggregator) had a chance to save their partial response to the shared context. The root cause: `_wait_for_interruption` flag is only set on the processor that calls `push_interruption_task_frame_and_wait()`. Other processors in the pipeline have this flag as False, so they queue the InterruptionFrame instead of processing it immediately. The fix: Remove the `_wait_for_interruption` condition so InterruptionFrame is processed immediately by ALL processors. This ensures synchronous propagation through the entire pipeline, guaranteeing that when `push_interruption_task_frame_and_wait()` returns, all processors have already processed the interruption and updated their state.
Codecov Report✅ All modified and coverable lines are covered by tests.
🚀 New features to boost your workflow:
|
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Outdated suggestions cannot be applied.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.
No description provided.