fix: Fix Vertex AI Live API session replay on reconnect / modality switch#6218
Open
wukath wants to merge 1 commit into
Open
fix: Fix Vertex AI Live API session replay on reconnect / modality switch#6218wukath wants to merge 1 commit into
wukath wants to merge 1 commit into
Conversation
…itch Previously seeding Gemini 3.1 live history on Vertex AI collapsed turns into a single user turn and hardcoded turn_complete=True, causing the model to immediately trigger a tool call upon reconnect. Since history_config is now supported on Vertex AI, we can remove the workaround and determine turn_complete based on the last turn role (preventing model execution when history ends in a model turn) Change-Id: I624a7adc8acdd9a88f0fc17e08051ac8a5b6f9bd
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Previously seeding Gemini 3.1 live history on Vertex AI collapsed turns into a single user turn and hardcoded turn_complete=True, causing the model to immediately trigger a tool call upon reconnect. Since history_config is now supported on Vertex AI, we can remove the workaround and determine turn_complete based on the last turn role (preventing model execution when history ends in a model turn)