· Changelog

CLI Improvements and Mermaid ASCII Diagrams

This release introduces the ability to hand off plans from the CLI to the cloud, in-line rendering of ASCII diagrams, and many quality-of-life improvements.

Plan mode improvements in CLI

When a plan is generated, the CLI now shows a persistent decision menu. You can choose to build in the cloud or build locally to execute the plan.

Typing /plan takes you back to your current plan and its action menu. We've also added keyboard shortcuts in the prompt bar so you can use arrow keys to navigate options, Enter to execute the selected option, and Shift+Enter as a shortcut for "Build in cloud."

Mermaid ASCII diagrams in CLI

Mermaid code blocks now render inline as ASCII diagrams in your CLI conversation. Flowcharts, sequence diagrams, state machines, class diagrams, and ER diagrams can all be displayed directly in the terminal.

Ctrl+O allows you to switch between the rendered diagram and the original mermaid source to see both representations.

Other improvements

We've also made lots of improvements to the CLI focused on tooling, quality of life, and reliability.

  • AI code and conversations in CLI are now tracked by Cursor Blame.
  • AI code attribution is now preserved by Cursor Blame when formatters like Prettier, Biome, or pre-commit hooks rewrite code.
  • File deletions are tracked by Cursor Blame to reflect the full lifecycle of code.
  • Clipboard operations on Linux now work with Wayland (wl-copy) and X11 (xclip) for better compatibility across desktop environments.
  • Agent sessions are now saved as JSONL transcripts. Headless mode also writes transcripts, making it easier to review and debug non-interactive runs.
  • CLI now stores conversation transcripts that the agent can use as context.

  • Unified domain allowlisting for WebSearch and WebFetch.
  • Known-safe URLs (e.g. Cursor docs) are auto-approved without permission prompts.
  • When an MCP server's credentials expire mid-session, the agent can now re-authenticate on demand instead of failing silently.
  • If you skip approving an MCP server, it stays disabled for the rest of the session rather than prompting you repeatedly.
  • The sandbox in the CLI now supports granular network access controls: user config only, user config with defaults, or allow all.

  • /resume now sorts by last interaction time, not creation time, so your most recent conversations appear first.
  • Model reasoning and thinking blocks are now rendered inline as they stream in.
  • Markdown tables now wrap text within cells, use box-drawing borders, and correctly handle escaped pipes.
  • Your message appears right after sending, and the "Generating..." indicator clears as soon as the model finishes rather than waiting for the full stream to close.
  • /auto-run, /max-mode, /vim, and similar commands now toggle with a single invocation. Current status is shown in the command description.
  • Slash commands are ranked by how closely they match what you've typed, with recency as a tie-breaker.
  • Added Emacs-style navigation: Ctrl+N/Ctrl+P for up/down and Ctrl+G for cancel/dismiss, alongside the existing arrow keys and Esc.
  • Added keybindings: Alt+Delete deletes the previous word; Ctrl+D exits questionnaire prompts.
  • Use --yolo and --force flags to approve workspace trust, skip MCP confirmation prompts, enable auto-run, and activate web tools.
  • Tool output now distinguishes "Cancelled" (you stopped it) from "Interrupted" (stopped externally).
  • When the sandbox isn't available, the message now explains why for your specific OS.
  • Reduced padding, removed the sandbox lock icon from shell prompts, and tightened up visual spacing throughout the CLI interface.
  • CLI output now detects your terminal's dark or light background and adjusts colors to match.
  • Shell and task durations now display in minutes and seconds.

  • Auto-updates now run in the background for faster time-to-interactive.
  • Reduced boot time.
  • Automatically retries connection on transport errors and stalls, with checkpoint-aware state recovery.
  • Background subagent resumes are now queued instead of interrupting running subagents.
  • 403 errors no longer trigger logout.
  • Fixed hanging headless mode when workspace trust is required; -force now implicitly trusts the workspace.
  • approvalMode: "unrestricted" is now respected without requiring -force.
  • Fixed abort restore so when no checkpoint exists, state rolls back cleanly and user text is preserved.
  • Fixed resume in non-git workspaces.
  • Fixed stale model lookup after model renames.
  • Fixed auto-run not applying to delete and MCP tools when toggling with Shift+Tab.
  • Fixed iTerm2 Ctrl+J for newlines.
  • Hardened sudo askpass helper and fixed sudo prompts on macOS.
  • Fixed Windows Delete key sending forward-delete instead of backspace.
  • Fixed duplicate rendering artifacts during state transitions.
  • Fixed a readability issue with user message colors on light backgrounds.
  • Relative paths in sandbox.json now resolve correctly against their config file location.