fix: avoid blocking Reactor scheduler thread during AutoContext compression#1079
Open
zhangliyuangit wants to merge 3 commits intoagentscope-ai:mainfrom
Open
Conversation
|
|
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
…ession When AutoContextMemory compression is triggered in handlePreReasoning, compressIfNeeded() internally calls .block() for LLM-based summarization. Running this on the Reactor scheduler thread causes the thread to be occupied until compression completes, preventing downstream streaming chunks from being dispatched. This results in all chunks being flushed at once after the entire Mono chain completes, breaking incremental streaming. Fix: wrap compressIfNeeded() in Mono.fromCallable(...).subscribeOn( Schedulers.boundedElastic()) so the blocking work runs on the elastic thread pool, keeping the Reactor scheduler thread free to dispatch streaming chunks incrementally. Also extract the event-building logic into a dedicated buildUpdatedEvent() method for clarity.
zhangliyuangit
force-pushed
the
fix/autocontext-compress-blocks-reactor-thread-1
branch
from
505a996 to
b199c2d
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When compression is triggered in handlePreReasoning, compressIfNeeded() internally calls .block() for LLM-based summarization. Running this on the Reactor scheduler thread stalls downstream streaming chunk dispatch, causing all chunks to be flushed at once instead of incrementally.
Fix: wrap compressIfNeeded() in Mono.fromCallable(...).subscribeOn(Schedulers.boundedElastic()) so blocking work runs on the elastic thread pool.