You can now use an early preview of
/edit in the chat! It's significantly faster at editing entire files than just using cmd-k. The
/edit feature is currently only supported if you do not use your own API key, since it relies on non-public models.
You can now alternate between diffs and texts responses in Cmd-K. This can be helpful for clarifying the models thinking behind a diff or for getting quick inline answers to questions about a file.
The main addition in this update is better docs support. This means you can add and remove docs and inspect the urls that are actually being used for each doc you have uploaded. You'll also be able to see what webpages end up being shown to GPT-4 to provide you an answer.
You can also paste a url into the chat and the model will automatically include it in the context being used. Teams can also share private docs.
Following this update, future updates should come as staged rollouts. This will mean greater guarantees of stability and more frequent updates.
Long files in chat
We continued to improve the experience of chatting with large files. If you @ multiple files that are too large to fit in GPT-4's context window, we'll intelligently pick the most relevant chunks of code to show to show the model.
- Copy Paste chat text form Jupyter
- Some chat focus issues
- UI tweaks
- Better state management - prevents crashes from editor using too much memory
- You can now switch to the VSCode sidebar orientation
- For "with codebase" chats, you can now see the codebase context that Cursor shows GPT-4. We hope this will make it easier to prompt codebase answers.
- API Key input box is now a password type
- Fixed a bug where code was being indexed right after turning off the indexing option
- A new icon! Thank you so much to the amazing Atanas Mahony who made it.
- You can now reply to Cmd-K outputs, making it much easier to have the model revise its work.
- If you @ reference a long file that will be cutoff by the context limit, you'll be given the option to automatically chunk the file and scan it with many GPTs.
- Codeblocks and code symbols in "with codebase" responses will now often be clickable.
- Follow-up chat messages to "with codebase" will keep the codebase context.
- Nicer error messages in the chat! Fewer annoying popups.
- Activity bar elements can now be reordered with drag-and-drop.
- SSH support is now more robust! Please continue to let us know if you are experiencing any SSH problems.
- Fix https://github.com/getcursor/cursor/issues/711.
- Fix cmd-k connection error.
- Fix cmd-k fast mode bug with empty lines.
- Fix bm25 search infinite loading.
- Fix @Codebase in followups.
Long AI completions
If you press ⌘/^+↩️ on any line, you will now get gpt-4 powering fast-completions for you! We know that sometimes all of us want copilot to write an entire function or a big chunk of code. But copilot can be slow and sometimes just not smart enough :(. So we're trying to solve this with a new completion experience powered by gpt-4. Just press ⌘/^+↩️ and you'll get a long completion from gpt-4.
Better support for remote-ssh
Remote-ssh is now built-in to cursor. You do not need to edit the behavior, it should just work :) We know this has been a big blocker for many users that rely on remote machines for development. If you are still running into issues, please let us know and we will fix it ASAP.
The AI linter is now enabled for everyone in pro! The AI will highlight suspicious parts of your code in blue. You can also add your own lint rules that you want that are easy to express in natural language but aren't covered by traditional linters.
- Enterprise support!
- C# and F# now properly render in the chat
- Qmd support has been restored
- Experimental @Codebase support in the chat (and coming to the cmd-k soon!)
- Linter is back!
- Some fixes to codebase indexing.
This build includes:
- More control of context building abilities for codebase-wide chat
- A better flow for getting CMD-k to produce code with no linter errors (you should see a "Try lint-fix" button when relevant)
- Some UI/UX tweaks to CMD-K
- Bug fixes
- Improved the "@Add new doc" experience
- Python/Pylance support has been restored
- Better @ symbol keyboard ergonomics
- Makes it clearer which docs are being looked at by the AI
- AI will respond with citations when you refernce docs
- Fixes Cmd-K for Jupyter
- Chat/Edit tooltip blocks less code
- Improves Cursor's appearance when custom themes are on
- Importing VSCode extensions now takes into account enabled/disabled
- Cmd-k should work better for long diffs (greater than 100 lines of code)
Cmd+K's UI has been changed: it's in-editor, "sticky," and @-symbol-compatible. We hope it helps you stay in flow and more quickly iterate on your prompts. (Also, you can now use up/down arrows for history in chat.)
Also, Cursor's AI will now use popular documentation to improve the answers to your questions. For example, if you ask it "how do I grab all s3 buckets with boto3?" it will search over the boto3 docs to find the answer. To add your own documentation or explicitly reference existing docs, type '@library_name' in chat.
- Long code selections no longer brick the editor
- Auto-fixing errors no longer brings up the problems view (in particular, this fixes an annoying bug if you have auto-fix on save turned on)
- Chat works if you don't have a folder open again
- Cmd-shift-E to fix an error in chat works again
cursor://deep linking works now, so you should be able to log in to extensions
- Autoscrolling works again
- A few cmd-Z bugs for inline diffs have been squashed
- You can now use Run & debug in Cursor again (the toolbar is back)
- Early support for slash commands
- If you're not logged in, we show the popup to log in again
- Cursor is now based on version 1.79.2 of VSCodium, which comes with security updates and minor features
The chat has been revamped! You can now use @ symbols to show files/code/docs to the AI. The chat history is improved, it's easier to see what the AI can see, and codeblocks auto-format on paste.
You can now have the AI read documentation on your behalf! This will improve it's ability to answer questions about your favorite libraries. To use this feature, simply press the "Docs" button in the top right of the chat pane.
We've improved codebase context!
In order to take full advantage, navigate to Settings (top right button), then "Sync the current codebase"
Login via github, then add the repo you wish to sync!
Following this, you'll be able to see an improved version of codebase context in the search pane, and in chat (by pressing cmd+enter).
Codebase Context v1
Introducing v1 of codebase-wide context! We'll be shipping major improvements to this in the next few days, but we'd love to hear your feedback.
Go to the "Search" pane in order to see the new context.
Or, on chat, press Cmd+Enter in order to get a response that uses context from the full codebase.
🧠 Upgrades to GPT-4
- All users get 10 free gpt-4 requests !!!
- Switching between models is a lot more easy, and the transition to gpt-4 is a lot smoother
📝 Please give us feedback!!
Please keep the bug reports rolling! We really are listening!
- We've added a new feedback button at the top right of the app. - We really do listen to your feedback, and your bug reports! We've fixed a lot of bugs in the last few weeks, and we're excited to keep improving the product. - We made this modal to make it easier to report feedback. Please keep the feedback coming!
💻 In-terminal Debugging
- Press Cmd+D to auto-debug a terminal error
- Press Cmd+Shift+L, and the model will add the terminal context to chat
⚙️ Activity Bar pinning
- You can Pin custom extensions to your activity bar in the top left
Here I've pinned File Explorer, Source Control, and Testing
📔 Better Jupyter Support
- Context ingestion across a full notebook
- Small bug fixes
➕➖ Diff/Generate improvements
- Partial diff accent/reject
Pressing Cmd+Y/Cmd+N lets you accept/reject subdiffs!
- Generates work when you click elsewhere!
- Fixed diff bug where it edits outside selected region
🛠️ Quality of Life Improvements
- Press ESC to exit the chat
- Fixed the bug that shrinks code blocks in the chat!
- Remote SSH is easier to use!
- A better Cursor Tutor onboarding!
- Better prompting for Toolformer
- One-Click Extension Import from VSCode (beta). As a highly requested feature, we're excited to present the beta version of one-click extension imports!
- Alpha feature: 🧠 Alpha feature: Ask questions about your entire repo 🛠️. We are experimenting with ⌥+enter in the chat! The feature allows the model to think deeply about your response, search through files, and deliver a well-crafted answer. While it's in alpha, we're working hard to enhance this feature in the coming weeks. We'd love to hear your feedback!
- Improved prompting for edits and generates
- Fixed login bugs
- Added the ability to hide the tooltip (Cursor config > Advanced > Chat/Edit Tooltip)
- Extended prompt length for project generation
- GPT-4 support now available for project generation
🧠 Pro users can now use GPT-4 (switch between models in settings). Pro users are being granted 150k tokens of GPT-4 usage and can now use GPT-4 to power the AI suggestions in Cursor. This should improve the quality of all of your generations, edits, and chats – GPT-4 is an absolutely amazing code model. Switching between GPT-3.5 and GPT-4 is easy - just click on the settings gear in the top right corner of Cursor
🤖 Generate entire projects with the AI (experimental). We’re releasing experimental support for a new feature that creates entire repos for you, from just one prompt.
- Fixes to scrolling in chat
- 👻 Ghost mode for opting out of storing any kind of data on our servers
- 🛠️ Nicer edits, now work with cmd-Z
- Various bugs squashed in the streaming diffs
- Hover over an error to have the AI explain it/fix it
- Settings icon on Linux
- Don't install "cursor" command on startup
- GPT-4 support
- Fixes the Mac autoupdating experience
- "Undefined uri" issue fixed
- Turns off the auto-install of the "cursor ." command (and fixes its install altogether)
🚀🌟 Introducing Cursor 0.2.0! 🌟🚀
To focus on delivering the most advanced AI features at lightning speed, we’ve transitioned to building Cursor on top of a fork of VSCodium, moving away from our previous Codemirror-based approach. ⚡
With Cursor, our vision is to create an IDE specifically designed for pair-programming with AI 🤖 In the short term, it will resemble a typical code editor, but with cutting-edge AI capabilities. However, before long, we think programming with Cursor look be entirely different than coding today.
In order to achieve this transformation as quickly as possible, we’re focusing our efforts on enhancing the AI, rather than reinventing the wheel for standard text editing features. Building on the phenomenal foundation of VSCode/VSCodium will help us achieve this goal at a rapid pace! 🚀
- Transitioned to building Cursor on top of a fork of VSCodium
- Focus on enhancing the AI for pair-programming
- Opens the terminal in your current folder
- Adds an optional paid plan if you'd like to avoid the server capacity rate limits
- Changes autoupdate to notify you when there's a new version
- Other fixes
- Automatically apply chat suggestion
- Ask AI to "fix" language errors
- Chat history saved between sessions
- Easy to select and copy from chat
- Resizable sidebar
- Terminal no longer interferes with chat
- Fixes to all the language servers/copilot
- Built-in terminal
- Diffs automatically continue
- More diff fixes
- Up and down arrow in prompt bar have been mapped to less annoying keybindings
- Can open chat history from the prompt bar
- Have chat auto-insert suggested changes into editor
- Windows and Linux support 🥳
- Edits can be as long as you'd like
- Diffs shouldn't disappear anymore
- Editing works for same file on multiple tabs
- Instant fix all lint errors with AI 😎