fix: Fix ADK Runner race condition for sequential tool execution#1234
Open
copybara-service[bot] wants to merge 1 commit into
Open
fix: Fix ADK Runner race condition for sequential tool execution#1234copybara-service[bot] wants to merge 1 commit into
copybara-service[bot] wants to merge 1 commit into
Conversation
Persist agent events to the session synchronously within each LLM step in BaseLlmFlow.run(), so the next step does not start before the previous step's events have been appended. Both BaseLlmFlow.run() and Runner skip the duplicate appendEvent for events already present in the session (by id), so events emitted by a transferred sub-agent are appended exactly once. PiperOrigin-RevId: 921989444
bfaf0eb to
baa21a0
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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: Fix ADK Runner race condition for sequential tool execution
Persist agent events to the session synchronously within each LLM step in
BaseLlmFlow.run(), so the next step does not start before the previous
step's events have been appended. Both BaseLlmFlow.run() and Runner skip
the duplicate appendEvent for events already present in the session (by
id), so events emitted by a transferred sub-agent are appended exactly
once.