fix: preserve non-text output in streaming responses#1325
Merged
Conversation
copybara-service
Bot
force-pushed
the
test_942010840
branch
7 times, most recently
from
07bfbdf to
8767b1c
Compare
The streaming response aggregator only accumulated text and function-call parts, so any other part (an image returned as inline data, server-side tool calls/responses, etc.) was dropped from the final aggregated response when text accompanied it. Mirror ADK Python and preserve any part that is not text or a function call, keeping the existing exclusion of standalone thought-signature parts. PiperOrigin-RevId: 942147787
copybara-service
Bot
force-pushed
the
test_942010840
branch
from
8767b1c to
b8be90d
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
fix: preserve non-text output in streaming responses
The streaming response aggregator only accumulated text and function-call
parts, so any other part (an image returned as inline data, server-side tool
calls/responses, etc.) was dropped from the final aggregated response when text
accompanied it. Mirror ADK Python and preserve any part that is not text or a
function call, keeping the existing exclusion of standalone thought-signature
parts.