- Added
/thinking(/thinking [on|off], saved as"showThinking"insettings.jsonand off by default) to stream the model's full thinking live in the transcript while it thinks and keep finished thoughts expanded without pressingCtrl+O. - Added a live
Overviewsection to/swarm boardon terminals at least 28 rows tall, showing the swarm's goal, overall task progress (Overview · N of M tasks doneand any blocked count), and up to six workstream threads with status indicators for which workers are working, in review, waiting on a peer, failed, or done. - Added
planmode to--remote-agentsessions, so a remote agent can research and write a plan for your review before editing files or running commands: switch to it withShift+Tab, start in it with--mode plan, or chooseplanunderAgent Modeon theRemote Agenttab of/config. - Added an
Agent Modesetting (default,accept-edits, andplan) to theRemote Agenttab of/configin--remote-agentsessions: choosing a mode saves it as your default for new remote sessions and updates the current conversation, whileShift+Tabswitches modes for the session without changing your saved default and--modeoverrides a resumed conversation's saved mode. - Added a
Switch to RTL text directionbutton to the header of Markdown (.md,.markdown) and.txtfile tabs in the side panel of the Remote Control browser view, so right-to-left prose renders cleanly without paragraphs that start with English words snapping left, while code blocks and line numbers stay left-to-right. - Improved the
Orchestratorrow in/modelon consumer plans in local sessions so you can pick both itsPlannerandExecutormodels and each one's thinkingEffort(saved under"orchestrator"insettings.jsonand--settings): pressTaborShift+Tabto move betweenPlanner,Executor, and theirEffortsliders, use←and→to change the focused choice, and see the active planner next toOrchestratorin the status line. - Improved expanded tool groups in
mediumverbosity: expanding a group withCtrl+Oor by clicking now keeps the summary header's colors, including red status markers on failed runs, instead of dimming it to gray, and indents the expanded tool calls behind a│gutter. - Improved permission prompts for creating or editing a file outside the workspace in the Remote Control browser view: the "always allow" options now suggest the enclosing repository or project folder (or the parent folder when there is none) instead of only that single file, while sensitive files such as
.envor SSH keys and broad folders such as your home directory or/tmpstay limited to the exact file, and editing the target path in the prompt overrides the suggestion. - Improved turns that launch several subagents in a row in the Remote Control browser view: consecutive subagent launches now collapse into a single
Started N subagentsrow (Starting N subagentswhile launching) that you can expand to see and open each subagent. - Changed Auto mode (the default
Agent Mode) to allow reading files outside the workspace without asking for approval; previously Auto mode prompted before reading outside the workspace unlessNon-Workspace Accesswas turned on in/config. Writing or editing files outside the workspace still asks for approval, and youraskanddenypermission rules, protected configuration files such asmcp_config.json, other projects' conversations, and organization policies requiring outside-workspace file review still apply. - Fixed a security issue on Windows where network (UNC), device, and NT object paths in workspace permission rules,
@file mentions, plugins,sidecars.json, and custom agents could trigger a lookup that sent Windows credentials to a remote host; those paths are now rejected without being accessed. - Fixed model responses that error out, are canceled, or are cut off partway through running partial tool calls from the incomplete response or resending that broken attempt on retry, which could make later turns fail with thinking-signature validation errors.
- Fixed wide Markdown tables in agent responses cutting off column headers with
…and squeezing text columns until words broke mid-word on narrow terminals; headers now wrap and columns are sized to keep words intact while breaking long paths and URLs. - Fixed
/plugin,agy plugin list,agy plugin enable, andagy plugin installlisting the wrong skills, subagents, MCP servers, and hooks for plugins whoseplugin.jsondeclares an Agent Plugins$schema(such as readingmcp_config.jsoninstead ofmcp.jsonor reportinghooks.jsonas hooks named$schemaandhooks), and fixed theagy plugin installsummary cutting off subagent names at a.. - Fixed
agy plugin install <plugin>@<marketplace>failing withunknown marketplacewhen you connect with aGEMINI_API_KEYinstead of a saved sign-in. - Fixed plugin suggestions in agent responses telling you
The <id> plugin needs you to sign in. Open /plugin to sign in.with a raw marketplace catalog ID even when the plugin was not installed; they now sayOpen /plugin to install or sign in to this plugin. - Fixed the status line permanently showing a red
AI: Out of creditswarning when AI credits are enabled and your credit balance is0, even while normal model quota is still available; the status line now shows AI credits only when you have a positive balance. - Fixed
--remote-agentsessions offering local-only and custom models that remote agents cannot run, and showing an unexplained error when a model is unavailable remotely:/modelnow marks models that remote agents don't support asnot available for remote agentsand omits local custom models, and requests with an unsupported model report<model> isn't available for remote conversations yet. Choose another model and try again.
Google Antigravity 1.5.14
Released · Google
Security fix