Fix chunk loss in the long streaming response with native response field #8881
+34
−15
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Outdated suggestions cannot be applied.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.
Issue
There is an issue that some text content chunks are lost when there are more than 10 chunks for a string field, and the native response, such as Anthropic Citation, is used.
Root Cause
This was caused by the assumption that at most one streaming listener returns a chunk for the same chunk. This assumption is not true when native response, such as citation API, is used because a streaming listener buffers 10 chunks for string output fields, and sometimes the string chunk and native response chunk are produced simultaneously.
Fix
This PR fixes the issue by allowing multiple listeners to return a chunk for the same response chunk.