2.4
CursorSummary
This release significantly enhances agent capabilities by introducing Subagents for parallel, specialized task execution and enabling direct image generation within the agent interface. Additionally, Enterprise users gain Cursor Blame for detailed AI attribution tracking, and agents can now proactively ask clarifying questions during complex workflows.
New Features
- Introduced Subagents, specialized, independent agents that run in parallel with custom configurations for faster, more focused task execution.
- Enabled direct image generation from the agent using text descriptions or reference uploads, saving previews inline and to the assets/ folder.
- Launched Cursor Blame (Enterprise plan feature) extending git blame with AI attribution, showing which lines were AI-generated (by Tab completions or agent runs) versus human-written.
- Added the ability for agents to ask clarifying questions during Plan and Debug modes, allowing them to continue working while waiting for user input.
- Enabled building custom subagents and skills that utilize the new 'ask question tool'.
Bug Fixes
- Fixed 11 unspecified bugs (as noted in the release notes summary).
Improvements
- Improved agent harness for better context management during long-running tasks.
- Default subagents for codebase research, terminal commands, and parallel work streams are now automatically active in the editor and CLI.
- Cursor Blame provides line-level links to the conversation summary that produced the code, offering context and reasoning for changes.
- Cursor Blame tracks AI usage patterns across the team's codebase.
- Agents can now incorporate user answers to clarification questions immediately upon arrival while continuing other tasks.