fix(context_compressor): prevent consecutive same-role messages after compression#1186
Closed
alireza78a wants to merge 1 commit intoNousResearch:mainfrom
Closed
Conversation
teknium1
added a commit
that referenced
this pull request
Mar 17, 2026
… compression compress() checks both the head and tail neighbors when choosing the summary message role. When only the tail collides, the role is flipped. When BOTH roles would create consecutive same-role messages (e.g. head=assistant, tail=user), the summary is merged into the first tail message instead of inserting a standalone message that breaks role alternation and causes API 400 errors. The previous code handled head-side collision but left the tail-side uncovered — long conversations would crash mid-reply with no useful error, forcing the user to /reset and lose session history. Based on PR #1186 by @alireza78a, with improved double-collision handling (merge into tail instead of unconditional 'user' fallback). Co-authored-by: alireza78a <alireza78.crypto@gmail.com>
teknium1
added a commit
that referenced
this pull request
Mar 17, 2026
… compression (#1743) compress() checks both the head and tail neighbors when choosing the summary message role. When only the tail collides, the role is flipped. When BOTH roles would create consecutive same-role messages (e.g. head=assistant, tail=user), the summary is merged into the first tail message instead of inserting a standalone message that breaks role alternation and causes API 400 errors. The previous code handled head-side collision but left the tail-side uncovered — long conversations would crash mid-reply with no useful error, forcing the user to /reset and lose session history. Based on PR #1186 by @alireza78a, with improved double-collision handling (merge into tail instead of unconditional 'user' fallback). Co-authored-by: alireza78a <alireza78.crypto@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.
compress_context() picks the summary message role based only on the message before the compression window. If the first message after the window has the same role, the API returns 400 — consecutive same-role messages aren't allowed. This causes long conversations to crash mid-reply with no useful error, forcing the user to /reset and lose their session history.
Fix checks both neighbors when choosing the summary role. If flipping still collides with the head, falls back to "user" with a short prefix.