fix(vscode-lm): reliable auto context condensing + 3.53.1#11
Merged
Conversation
added 2 commits
June 22, 2026 11:02
Treat maxTokens:-1 (unlimited) as the default output reserve instead of a hard cap, and measure contextPercent against available input space so the condense gate fires reliably on the VS Code LM provider. Add a getCondenseContextWindow() seam that drives the condense gate from the curated model maxInputTokens rather than the inflated live context window. Refresh the VS Code LM model catalog and update the default model. Bump the extension to 3.53.1 and add the vscode-lm-condense-fix changeset.
Restores the upstream v3.54.0 changeset that was removed in 8ed3455; that file originated upstream (Release v3.54.0 RooCodeInc#12369) and should not have been deleted.
9 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes unreliable automatic context condensing on the VS Code LM (vscode-lm) provider.