feat(vscode): add compaction model setting - #13533
Merged
Merged
Conversation
Contributor
Code Review SummaryStatus: No Issues Found | Recommendation: Merge Files Reviewed (24 files)
Reviewed by grok-4.6 · Input: 315.4K · Output: 18.6K · Cached: 1.4M Review guidance: REVIEW.md from base branch |
marius-kilocode
enabled auto-merge
August 28, 2026 07:52
WebReflection
approved these changes
Aug 28, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What Problem This Solves
Choosing a separate model for conversation compaction required editing CLI configuration. Kilo settings did not expose this choice.
Why This Change Was Made
Expose the existing
agent.compaction.modelsetting in Context settings. The selector uses the current SDK configuration path, so no backend, SDK, or schema change is needed.User Impact
Choose a model for automatic and manual compaction, or clear the selection to use the chat model. Changing the compaction model does not change the chat model. Cost, speed, and summary quality depend on the selected model.
The code diff contains the selector, required translations, one focused set/reset test, and a changeset. No benchmark artifacts or generated files are included.
Evidence
Typecheck, lint, compile, Knip, and the change-marker check passed. The extension unit suite passed all 4,321 tests.
The isolated VS Code self-test verified model selection, Save, Reload, Discard, clearing an unavailable model, and keyboard reset with auto-compaction disabled. The chat model and other compaction settings stayed unchanged.
Two live compaction attempts used identical synthetic histories. The saved override selected the configured compaction model; clearing it selected the chat model. Both requests returned HTTP 401 before generation, so these attempts do not establish timing, cost, or summary-quality differences.