🤖 fix: use correct model for post-compaction continue messages #723
Conversation
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
ammar-agent
force-pushed
the
compact-followup-regression
branch
2 times, most recently
from
478e3ed to
83ccea6
Compare
Introduced in a31a2e0, the auto-continue message queueing logic was inheriting the compaction model (e.g. haiku) for the follow-up task. This fix: 1. Preserves the original workspace model as `resumeModel` in compaction metadata 2. Sanitizes the queued continue message options to strip compaction-specific flags 3. Restores the correct model for the follow-up turn
ammar-agent
force-pushed
the
compact-followup-regression
branch
from
83ccea6 to
97a783d
Compare
ammario
approved these changes
Nov 24, 2025
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Outdated suggestions cannot be applied.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.
Summary
Fixes a regression where the
/compactmodel (often a cheaper/faster model) was incorrectly used for the follow-up continue message instead of the user's selected workspace model.Regression
Introduced in a31a2e0 which moved continue message logic to the backend message queue but failed to sanitize the options.
Changes
CompactionRequestDatato carryresumeModelbuildContinueMessageOptionshelper in backend to:mode: 'compact',maxOutputTokens)resumeModelGenerated with
mux