Fix scheduler for calling chat models streaming - #6814
Open
EgbertW wants to merge 1 commit into
Open
Conversation
EgbertW
force-pushed
the
fix-model-scheduler
branch
2 times, most recently
from
August 18, 2026 13:37
31df7c8 to
b6091c5
Compare
Signed-off-by: Egbert van der Wal <ewal@pointpro.nl>
EgbertW
force-pushed
the
fix-model-scheduler
branch
from
August 18, 2026 13:45
b6091c5 to
f87fcb9
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Replace
publishOnwithsubscribeOnfor calling a chat model in the streaming flow.publishOnaffects the flow downstream of where it is defined, which doesn't make that much sense in this context because it's forwarding from I/O call, not producing an I/O call.At least for the Google GenAI chat models, OkHttp is used in a blocking call. With
publishOnthis ends up blocking the original thread (e.g. a Spring Boot worker thread) and only AFTER the I/O call switching to the boundedElastic pool. It makes a lot more sense to run the OkHttp blocking call on the boundedElastic scheduler instead to free up the worker thread.If needed, you could release that afterwards but there's not a lot of value in that.