feat: add configurable image downscaling before LLM upload#11913
Draft
roomote-v0[bot] wants to merge 1 commit intomainfrom
Draft
feat: add configurable image downscaling before LLM upload#11913roomote-v0[bot] wants to merge 1 commit intomainfrom
roomote-v0[bot] wants to merge 1 commit intomainfrom
Conversation
Adds a new image downscaling feature that resizes images before sending them to the LLM, reducing token usage for high-resolution screenshots. Changes: - Add sharp dependency for image processing - New settings: maxImageDimension (0=disabled) and imageDownscaleQuality (1-100) - New resize-image.ts utility using sharp for proportional downscaling - Integrate resizing into all image entry points: selectImages, readImageAsDataUrlWithBuffer, processImageFile, resolveImageMentions - Add settings UI controls in Context Management settings tab - Add English translation strings for the new settings - Downscaling disabled by default (opt-in) Closes #11912
Open
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR attempts to address Issue #11912. It adds configurable image downscaling before images are sent to the LLM, reducing token usage for high-resolution screenshots.
Changes
sharpfor high-performance image processingmaxImageDimension(0 = disabled, default) andimageDownscaleQuality(1-100, default 85)src/integrations/misc/resize-image.ts-- uses sharp for proportional downscaling preserving aspect ratioselectImages()(file picker)readImageAsDataUrlWithBuffer()/processImageFile()(read_file tool)resolveImageMentions()(@-mention image references)Design decisions
sharpas recommended by the issue authorFeedback and guidance are welcome.
Interactively review PR in Roo Code Cloud