|
| 1 | +Version: 2.4.27 |
| 2 | +Installer: |
| 3 | +- Architecture: x64 |
| 4 | + Scope: user |
| 5 | + InstallerUrl: https://downloads.cursor.com/production/4f2b772756b8f609e1354b3063de282ccbe7a69b/win32/x64/user-setup/CursorUserSetup-x64-2.4.27.exe |
| 6 | +- Architecture: x64 |
| 7 | + Scope: machine |
| 8 | + InstallerUrl: https://downloads.cursor.com/production/4f2b772756b8f609e1354b3063de282ccbe7a69b/win32/x64/system-setup/CursorSetup-x64-2.4.27.exe |
| 9 | +- Architecture: arm64 |
| 10 | + Scope: user |
| 11 | + InstallerUrl: https://downloads.cursor.com/production/4f2b772756b8f609e1354b3063de282ccbe7a69b/win32/arm64/user-setup/CursorUserSetup-arm64-2.4.27.exe |
| 12 | +- Architecture: arm64 |
| 13 | + Scope: machine |
| 14 | + InstallerUrl: https://downloads.cursor.com/production/4f2b772756b8f609e1354b3063de282ccbe7a69b/win32/arm64/system-setup/CursorSetup-arm64-2.4.27.exe |
| 15 | +Locale: |
| 16 | +- Locale: en-US |
| 17 | + Key: ReleaseNotes |
| 18 | + Value: |- |
| 19 | + Agents are solving increasingly complex, long-running tasks across your codebase. This release introduces new agent harness improvements for better context management, as well as many quality-of-life fixes in the editor and CLI. |
| 20 | +
|
| 21 | + Subagents |
| 22 | + Subagents are independent agents specialized to handle discrete parts of a parent agent's task. They run in parallel, use their own context, and can be configured with custom prompts, tool access, and models. |
| 23 | +
|
| 24 | + The result is faster overall execution, more focused context in your main conversation, and specialized expertise for each subtask. |
| 25 | + Cursor includes default subagents for researching your codebase, running terminal commands, and executing parallel work streams. These will automatically start improving the quality of your agent conversations in the editor and the Cursor CLI. |
| 26 | + Optionally, you can define custom subagents. Learn more in our docs. |
| 27 | +
|
| 28 | + Skills |
| 29 | + Cursor now supports Agent Skills in the editor and CLI. Agents can discover and apply skills when domain-specific knowledge and workflows are relevant. You can also invoke a skill using the slash command menu. |
| 30 | +
|
| 31 | + Define skills in SKILL.md files, which can include custom commands, scripts, and instructions for specializing the agent’s capabilities based on the task at hand. |
| 32 | + Compared to always-on, declarative rules, skills are better for dynamic context discovery and procedural “how-to” instructions. This gives agents more flexibility while keeping context focused. |
| 33 | +
|
| 34 | + Image generation |
| 35 | + Generate images directly from Cursor's agent. Describe the image in text or upload a reference to guide the underlying image generation model (Google Nano Banana Pro). |
| 36 | +
|
| 37 | + Images are returned as an inline preview and saved to your project's assets/ folder by default. This is useful for creating UI mockups, product assets, and visualizing architecture diagrams. |
| 38 | +
|
| 39 | + Cursor Blame |
| 40 | + On the Enterprise plan, Cursor Blame extends traditional git blame with AI attribution, so you can see exactly what was AI-generated versus human-written. |
| 41 | +
|
| 42 | + When reviewing or revisiting code, each line links to a summary of the conversation that produced it, giving you the context and reasoning behind the change. |
| 43 | + Cursor Blame distinguishes between code from Tab completions, agent runs (broken down by model), and human edits. It also lets you track AI usage patterns across your team's codebase. |
| 44 | +
|
| 45 | + Clarification questions from the agent |
| 46 | + The interactive Q&A tool used by agents in Plan and Debug mode now lets agents ask clarifying questions in any conversation. |
| 47 | +
|
| 48 | + While waiting for your response, the agent can continue reading files, making edits, or running commands, then incorporate your answer as soon as it arrives. |
| 49 | + You can also build custom subagents and skills that use this tool by instructing them to "use the ask question tool." |
| 50 | + Improvements (29) |
| 51 | +
|
| 52 | + - Use agent to start working with the upgraded Cursor CLI in your terminal. |
| 53 | + - MCP server definitions and tools now live as JSON files in .cursor. Agents discover and load MCPs only when needed, reducing token usage and keeping the context focused. |
| 54 | + - Agents can now proactively request switching modes mid-conversation when it detects a different mode would be more effective for the task. You can also auto-approve and auto-reject specific transitions. |
| 55 | + - Fast read-only diff viewer improved performance of the review changes pane. |
| 56 | + - It's now faster to open and resize any chats which used inline code blocks. |
| 57 | + - Agents can now read PDFs, which you can attach in chats as context. |
| 58 | + - CLI can be linked to run as a service account. |
| 59 | + - Improved capabilities & coverage for hooks: stop hook; modify prompts beforeSubmitPrompt ; PreToolUse and PostToolUse hooks. |
| 60 | + - Hook commands now start 40x faster. |
| 61 | + - The in-editor browser is now 10× faster at navigation, with more reliable click actions, drag-and-drop support, and improved text input handling. Agents can also lock the browser while working to prevent accidental interference. |
| 62 | + - Light mode is now supported in the Cursor web dashboard. |
| 63 | + - We've removed the peek sidebar based on your feedback. |
| 64 | + - Windows notifications now have accept/reject buttons like MacOS. |
| 65 | + - Users who choose to "Run Everything" will never have their agents blocked. |
| 66 | + - Editing skills and rules files no longer requires approval in sandboxes. |
| 67 | + - Git writes are now allowed in sandboxes. |
| 68 | + - File edit approvals persist for the entire agent session in sandboxes. |
| 69 | + - Out-of-workspace folder edits can be allowed for the session in sandboxes. |
| 70 | + - Added team and MDM hooks support to CLI with more efficient execution. |
| 71 | + - Added more hooks to CLI already supported in the editor. See the full list of hooks in our docs. |
| 72 | + - Added compatibility with Claude Code hooks in CLI. |
| 73 | + - Faster startup on warm starts in CLI. |
| 74 | + - Unified CLI permissions with the editor, including Run Everything, Auto-Run in Sandbox (if available), and Ask Every Time (allowlist). |
| 75 | + - Improved Ctrl+C detection prevents accidental exits when canceling agent runsin CLI. |
| 76 | + - Ctrl+D now exits immediately on empty chat, matching common shell behavior in CLI. |
| 77 | + - Added -continue to quickly resume your last chat session (shorthand for --resume=-1) in CLI. |
| 78 | + - /mcp enable and /mcp disable now only show relevant MCP servers in autocomplete in CLI. |
| 79 | + - Added /max-mode [on|off] to toggle max mode on models that support it in CLI. |
| 80 | + - Better vim mode support in CLI. |
| 81 | + Bug Fixes (14) |
| 82 | +
|
| 83 | + - Fixed performance issue with adding more MCP server connections. |
| 84 | + - Fixed text being truncated in Windows UI elements including chat tab titles, code block headers, and @-mentions. |
| 85 | + - Fixed the Browser panel rendering on top of other UI components. |
| 86 | + - Browser can now request local network permissions, fixing authentication flows with identity providers like Okta. |
| 87 | + - Fixed issues with splitting and joining browser tabs. |
| 88 | + - Improved message queueing with better handling, and added drag-and-drop reordering for queued items. |
| 89 | + - Fixed chat tabs persistence after reloading or restarting the app. |
| 90 | + - Fixed syntax highlighting issues in git worktrees. |
| 91 | + - Fixed stale diff views from previous sessions remaining visible after app restart. |
| 92 | + - Fixed tabs disappearing when the titlebar is hidden. |
| 93 | + - Fixed the accept/reject diff UI sometimes not appearing when edits were made to dotfiles. |
| 94 | + - Fixed some cases of input lag when handling rapid text changes in CLI. |
| 95 | + - Fixed text wrapping in queued follow-ups in CLI. |
| 96 | + - Fixed an issue allowing edit tool usage during plan mode execution in CLI. |
| 97 | +ReleaseTime: 2026-01-22T00:00:00.0000000Z |
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?v=4&size=40){kind=avatar}
0 commit comments