fix: cancel in-flight generation when starting a new session#289
Merged
Conversation
Signed-off-by: Logan Nguyen <lg.131.dev@gmail.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Starting a new session now stops the in-flight backend generation instead of only clearing the frontend view. Previously the old stream kept running and held the engine's single decode slot, so a message sent in the new session queued behind the old one until it finished.
Key changes
reset()(new chat via+, summon) andloadMessages()(loading a conversation from history) now signalcancel_generationwhen a generation is active, routed through the samependingCancelRefplumbing the pause button uses so the nextask()awaits the cancel round-trip before starting a new turn.requestBackendCancel()helper used bycancel(),reset(), andloadMessages().search_pipelineshares the sameGenerationState, so an in-flight/searchturn is stopped on a new session as well.Testing
reset()andloadMessages()cancel the backend when a generation is mid-stream, and do not fire a cancel when idle.useModel.tsstays at 100% coverage; full frontend suite green.