Optimistic slash commands, strict permission matching, and multiline undo

Saturday, 27 June 2026

AI summary

Written by AI from the official notes. Check them for exact details.

Google's Gemini and Antigravity updates include improved command permissions and a unified undo/redo system.

Why it matters: Users who rely on command execution and UI interactions should be aware of these enhancements for improved functionality.

Optimistic slash command rendering, strict non-regex permission matching, and unified undo/redo prompt history.

Improved command permission security by making "Always Approve" rule matching strict (non-regex) by default, while allowing users to explicitly opt-in to regex matching by prepending rules with regex:.
Improved command permission usability by relaxing redirection checks, allowing safe commands with output redirection (e.g., tool > file) to match without requiring strict full-command approval.
Fixed a bug where the CLI would temporarily render skill commands without their slash prefix during optimistic updates by deferring prefix stripping to the serialization boundary, ensuring the UI always displays exactly what the user typed.
Fixed a redundant CLI exit message by removing the "Resume in the same project" hint line, leaving only the standard resume command to simplify exit output.
Resolved bugs during UI transitions (such as opening subagent details or logging out) by introducing a unified synchronization mechanism that prevents key lockups and ensures overlay panels like the /help view are properly reset.
Fixed a bug in the CLI prompt editor where undo and redo history stacks could become desynchronized during rapid mutations by decoupling the history state into a unified, pointer-backed structure.
Fixed a bug where browser-related prompt sections were missing from the agent's prompt registry, ensuring browser-based tasks execute reliably.

Full release notes7 changes

Optimistic slash command rendering, strict non-regex permission matching, and unified undo/redo prompt history.

Improved command permission security by making "Always Approve" rule matching strict (non-regex) by default, while allowing users to explicitly opt-in to regex matching by prepending rules with regex:.
Improved command permission usability by relaxing redirection checks, allowing safe commands with output redirection (e.g., tool > file) to match without requiring strict full-command approval.
Fixed a bug where the CLI would temporarily render skill commands without their slash prefix during optimistic updates by deferring prefix stripping to the serialization boundary, ensuring the UI always displays exactly what the user typed.
Fixed a redundant CLI exit message by removing the "Resume in the same project" hint line, leaving only the standard resume command to simplify exit output.
Resolved bugs during UI transitions (such as opening subagent details or logging out) by introducing a unified synchronization mechanism that prevents key lockups and ensures overlay panels like the /help view are properly reset.
Fixed a bug in the CLI prompt editor where undo and redo history stacks could become desynchronized during rapid mutations by decoupling the history state into a unified, pointer-backed structure.
Fixed a bug where browser-related prompt sections were missing from the agent's prompt registry, ensuring browser-based tasks execute reliably.