Changelog

0.16.0

Copilot++ improvements and VS Code 1.84.2

Copilot++ improvements:

  1. Caching — add and delete a letter and the suggestion will still be there for you!
  2. Do not interfere with intellisense and cmd-k.
  3. Fixes bugs with lag on large files and with the blue highlight staying around.
  4. Copilot++ sees your lint errors and will use this to improve its suggestions

Cursor is now based on VS Code 1.84.2. Notably, this fixes a few notebook bugs, and ensures that all of the most recent extensions work.

0.15.6-nightly

New upstream

Now based on VS Code 1.84.2. Notably, this fixes a few notebook bugs, and ensures that all of the most recent extensions work.

0.15.2

0.15.5 - Copilot++ improvements, Bug fixes

  • Copilot++ improvements: Includes green highlights to see what Copilot++ has added, the ability to accept multiple Copilot++ suggestions immediately one after another, support for Copilot++ on SSH, and fixes to how Copilot++ UI interacts with autocomplete plugins.
  • Bug fixes: Fixed a bug where Cmd-k could get into a bad state when removing at the top of a file. And another that was causing some files to not be indexed.

0.15.0

0.15.1 - New models, Copilot++ beta

  • Command-dot: you can now use the Command-dot menu to have Command-K fix lint errors inline.
  • New models: you can plug in your API key to try out the newest gpt-4 and gpt-3 turbo models. We're evaluating the coding skills of these models before rolling out to pro users.
  • Apply chat suggestions: click on the play button on any code block to have the AI apply in-chat suggestions to your current file.
  • Copilot++ (beta): this is an "add-on" to Copilot that suggests diffs around your cursor, using your recent edits as context. To enable it, go to the "More" tab in the right chat bar. Note: to cover the costs of the AI, this is only available for pro users.
    • This is very experimental, so don't expect too much yet! Your feedback will decide which direction we take this.

0.14.1

Indexing fixes

Fixes a problem where indexing got stuck. Indexing capacity is now also allocated by-user, so it should be more fair and faster for most users.