Add image paste and drag-drop support to replace default "R" box#12
Draft
Add image paste and drag-drop support to replace default "R" box#12
Conversation
Co-authored-by: bschlenk <1390303+bschlenk@users.noreply.github.com>
Co-authored-by: bschlenk <1390303+bschlenk@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Add functionality to paste SVGS or images
Add image paste and drag-drop support to replace default "R" box
Nov 17, 2025
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The default "R" box visualization is now replaceable. Users can paste images from clipboard (Ctrl/Cmd+V) or drag-drop image files onto the canvas. Images respond to affine transformations identically to the original box.
Changes
Canvas state management:
customImage: HTMLImageElement | nullto store loaded imagessetCustomImage(dataUrl: string)method handles image loading with error fallbackEvent handling:
ClipboardEventfor image itemsloadImageFromFile()converts File objects to data URLs via FileReaderRendering logic:
drawRect()to check for custom image before rendering default "R" textctx.drawImage()into the same 100×100 rectangleScreenshots
Default state:

After pasting SVG:

Multiple pastes replace (blue square replaces red circle):

Transforms apply correctly (2x horizontal scale):

PNG support:

Original prompt
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.