fix(hindsight): clear _session_turns after retain to stop transcript duplication - #29555
Closed
AndyZHENG0715 wants to merge 1 commit into
Closed
Conversation
…duplication The sync_turn() method appends each turn to _session_turns and, when the retain interval fires, constructs content from all accumulated turns before enqueueing the async retain. However _session_turns was never cleared after enqueue, so every subsequent retain re-sent every prior turn — causing quadratic transcript duplication over the session lifetime. Fix: clear self._session_turns = [] immediately after enqueueing. The async writer thread uses frozen snapshot variables (content, metadata_snapshot, num_turns) captured in the _do_retain closure, so clearing the source list has no effect on the in-flight retain. Closes: NousResearch#23724 (transcript duplication)
alt-glitch
added
type/bug
Collaborator
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The sync_turn() method appends each turn to _session_turns and, when the retain interval fires, constructs content from all accumulated turns before enqueueing the async retain. However _session_turns was never cleared after enqueue, so every subsequent retain re-sent every prior turn - causing quadratic transcript duplication over the session lifetime.
Fix: clear self._session_turns = [] immediately after enqueueing. The async writer thread uses frozen snapshot variables captured in the _do_retain closure, so clearing the source list has no effect on the in-flight retain.
Closes #23724