Changelog

v0.50

Simplified Pricing, Background Agent and Refreshed Inline Edit

Introducing unified request-based pricing, Max Mode for all top models, and Background Agent for parallel task execution.

Version 0.50

Simplified Pricing, Background Agent and Refreshed Inline Edit

Introducing unified request-based pricing, Max Mode for all top models, and Background Agent for parallel task execution. Plus, improved context management with @folders support, refreshed Inline Edit with new options, faster file edits, multi-root workspace support, and enhanced chat features including export and duplication.

Simpler, unified pricing

We’ve heard your feedback and are rolling out a unified pricing model to make it less confusing. Here’s how it works:

  • All model usage is now unified into request-based pricing
  • Max mode now uses token-based pricing (similar to how models API pricing works)
  • Premium tool calls and long context mode are removed to keep it simple

Quotas on plans Hobby, Pro and Business has not changed and slow requests are still included in the plans. All usage can be found in your dashboard to help you track and manage your spend.

Max Mode for all top models

Max Mode is now available for all state-of-the-art models in Cursor, with a simpler token-based pricing model. It’s designed to give you full control when you need it most. You can enable it from the model picker to see which models support it. When new models roll out, Max Mode will be how we deliver their full capabilities from day one.

It’s ideal for your hardest problems when you need more context, intelligence and tool use. For everything else, normal mode is still recommended with the same capabilities you’re used to.

The pricing is straightforward: you’re charged based on token usage. If you’ve used any CLI-based coding tool, Max mode will feel like that - but right in Cursor.

New Tab model

We’ve trained a new Tab model that now can suggest changes across multiple files. The model excels particularly at refactors, edit chains, multi file changes, and jumping between related code. You’ll also notice it feels more natural and snappier in day-to-day use.

With this we’ve also added syntax highlighting to the completion suggestions.

Background Agent

In early preview, rolling out gradually: Cursor agents can now run in the background! To try it, head to Settings > Beta > Background Agent.

This allows you to run many agents in parallel and have them tackle bigger tasks. The agents run in their own remote environments. At any point, you can view the status, send a follow-up, or take over.

Include your entire codebase in context

You can now use @folders to add your entire codebase into context, just make sure to enable Full folder contents from settings. If a folder (or file) is too large to be included, you’ll see a small icon on the context pill indicating this.

Refreshed Inline Edit (Cmd/Ctrl+K) with Agent integration

Inline Edit (Cmd/Ctrl+K) has gotten a UI refresh and new options for full file edits (⌘⇧⏎) and sending to agent (⌘L)

Full file makes it easy to do scope changes to a file without using agent. However, you might come across cases where you’re working with a piece of code you want to make multi-file edits to or simply just want more control you can get from agent. That’s when you want to send selected codeblock to agent and keep on editing from there.

Fast edits for long files with Agent

We’ve added a new tool to the agent that will search & replace code in files, making it much more efficient for long files. Instead of reading the complete file, Agent can now find the exact place where edits should occur and change only that part.

Work in multiple codebases with workspaces

Now you can create multi-root workspaces to make multiple codebases available to Cursor. All of them will be indexed and available to Cursor, ideal when you have projects in different folders you want to work on in the same space.

.cursor/rules are supported in all folders added

Working with Chat

Exporting Chat

You can now export chats to markdown from the chat view. Text and code blocks are included in the final export.

Duplicate Chats

Exploring different paths from a conversation while preserving the existing is now possible with chat duplication. Go to a message and start a new chat from the three dots menu.

Keybindings

  • Full file edits from Inline Edit: Cmd/Ctrl+Shift+K

Improvements

  • Agent now uses native terminal emulation instead of simulated terminals
  • @folders will now try to include all files that fit in context
  • Icons for context state in Chat to tell you if files were not included or condensed
  • Individual MCP tools can now be disabled from MCP settings
  • New C# extension available in marketplace
  • Chat font size can now be increased in settings
  • Detailed in-app changelog

MCP

  • Run stdio from remote workspace (WSL, Remote SSH)
  • Streamable HTTP support
  • Fixed leaking SSE server connections
  • More reliable refreshing when changing config

Account

  • Removed 10 free requests/day for Claude 3 Opus

Patches

0.50.1

  • Background Agent availability

0.50.2

  • Fixed keyboard navigation in Jupyter notebooks
  • Fixed Custom mode models MAX and selection issues
  • Improved indexing reliability for single-root workspaces
  • Fixed VPN reliability with ZScaler

0.50.3

  • Performance improvements

0.50.4

  • Improved apply reliability
  • Fixed Windows horizontal scrolling bug
  • MCP improvements
  • Improved multiroot workspace support

v0.49

Rules generation, improved agent terminal and MCP images

Automated rules generation, improved agent terminal, and enhanced MCP images.

Version 0.49

Rules generation, improved agent terminal and MCP images

Automated and improved rules

You can now generate rules directly from a conversation using the /Generate Cursor Rules command. This is useful when you want to capture the existing context of a conversation to reuse later.

For Auto Attached rules with path patterns defined, Agent will now automatically apply the right rules when reading or writing files.

We’ve also fixed a long-standing issue where Always attached rules now persist across longer conversations. Agent can now also edit rules reliably.

More accessible history

Chat history has moved into the command palette. You can access it from the “Show history button” in Chat as well as through the Show Chat History command.

Making reviews easier

Reviewing agent generated code is now easier with a built-in diff view at the end of each conversation. You’ll find the Review changes button at the bottom of chat after a message from the agent.

Improvements

  • Improved agent terminal performance and reliability
  • Enhanced MCP image handling and processing
  • Better error handling and recovery
  • Streamlined workflow for rule generation and management
  • Optimized chat history navigation
  • Enhanced diff view for code reviews
  • Improved rule persistence and application
  • Better context management for conversations

v0.48

New Tab model and improved completions

Introducing a new Tab model with multi-file suggestions and syntax highlighting for completions.

Version 0.48

New Tab model and improved completions

New Tab model

We’ve trained a new Tab model that now can suggest changes across multiple files. The model excels particularly at refactors, edit chains, multi file changes, and jumping between related code. You’ll also notice it feels more natural and snappier in day-to-day use.

With this we’ve also added syntax highlighting to the completion suggestions.

Improved completions

  • Enhanced syntax highlighting for all supported languages
  • Better context awareness for multi-file suggestions
  • Improved accuracy for refactoring suggestions
  • Faster response times for completion requests
  • Better handling of complex code structures
  • Enhanced support for modern JavaScript/TypeScript features
  • Improved completion quality for Python and Go
  • Better handling of imports and dependencies

Performance improvements

  • Reduced latency for completion requests
  • Optimized memory usage for large codebases
  • Improved caching for frequently used completions
  • Better handling of concurrent requests
  • Enhanced background processing for suggestions

Bug fixes

  • Fixed issues with completion suggestions in large files
  • Resolved problems with multi-file refactoring
  • Fixed syntax highlighting in certain edge cases
  • Improved handling of special characters in completions
  • Fixed issues with completion timing in certain scenarios