Back
AI summary
Written by AI from the official notes. Check them for exact details.New features include path auto-completion, optimistic prompt rendering, and improved fuzzy matching for commands.
- Added shell-style path auto-completion for
/openand/add-dir - Introduced optimistic rendering for chat prompts to reduce lag
- Enabled fuzzy matching for slash commands
- Skipped subagent conversations in
/resumefor clarity - Fixed bugs related to suggestion triggers and prompt interruptions.
Why it matters: Users who rely on command inputs and chat interactions will benefit from these enhancements.
Full release notes8 changes
Path autocompletion for /open and /add-dir, optimistic chat prompt rendering, and fuzzy slash command matching.
- Added shell-style path auto-completion for
/openand/add-dir. - Added optimistic rendering for user chat prompt submissions, injecting messages immediately into the viewport to eliminate perceived input lag.
- Added fuzzy and partial substring matching across slash commands. E.g.
/el-> shows/helpand/modelwhile previous no suggested completions. - Skipped subagent conversations from
/resume, keeping the standalone conversation picker focused purely on direct user initiated conversations. - Added a
stack_with_defaultflag to thestatusLineconfiguration to render both the default Antigravity status line and custom status line output vertically stacked. - Fixed a bug when suggestion was not triggered when
@is typed after(. Enabled unconditional typeahead suggestions whenever@is typed without preceding whitespace, streamlining mention workflows. - Fixed a bug where entering a prompt immediately after pressing
Esc(to interrupt an active agent stream) caused the newly typed input to be swallowed or rejected. - Fixed
--sandboxflag propagation in headless print mode (-p/--print), ensuring sandbox isolation is correctly enforced during non-interactive execution.