Preserve recent messages during session compaction#2259
Draft
rumpl wants to merge 1 commit intodocker:mainfrom
Draft
Preserve recent messages during session compaction#2259rumpl wants to merge 1 commit intodocker:mainfrom
rumpl wants to merge 1 commit intodocker:mainfrom
Conversation
Before compaction, the last ~20k tokens of messages are now kept aside and excluded from summarization. The summary item records a FirstKeptEntry index pointing to the first preserved message, and GetMessages reconstructs the conversation as [summary, kept_messages...]. This allows the LLM to continue naturally after a compaction event by retaining recent conversational context verbatim while still compacting older history. Signed-off-by: Djordje Lukic <djordje.lukic@docker.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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Before compaction, the last ~20k tokens of messages are now kept aside and excluded from summarization. The summary item records a FirstKeptEntry index pointing to the first preserved message, and GetMessages reconstructs the conversation as [summary, kept_messages...].
This allows the LLM to continue naturally after a compaction event by retaining recent conversational context verbatim while still compacting older history.