MUSE RADAR / EVENT BRIEF
Google Ends New Gemini Code Assist Sales as Its Coding-Agent Path Moves to Antigravity
Google stopped selling new Gemini Code Assist Standard and Enterprise subscriptions on October 9. Existing contracts continue, with separate renewal deadlines for annual and monthly plans, while future agentic coding moves to Antigravity in Gemini Enterprise. This page continues to track administrator controls and the older Agent migration rather than creating a duplicate event.
New Code Assist Standard and Enterprise subscriptions ended on October 9
Google Cloud says new Gemini Code Assist Standard and Enterprise subscriptions can no longer be purchased starting October 9, 2026. Existing subscriptions remain functional and supported through their contracts, and existing customers can add licenses until January 31, 2027.
Annual plans can auto-renew through January 31, 2027, while monthly plans can auto-renew through December 31, 2027. Google points future agentic coding to Antigravity in Gemini Enterprise editions and advises planning the transition before the final renewal or contract end.
The October 6 change lets administrators gate two agent capabilities separately
Google Cloud's release notes say Gemini Enterprise administrators can now control access to Antigravity Boost and Teamwork. Boost uses /boost and a tiered multi-agent hierarchy for algorithmic problems and deep debugging; it is generally available in Antigravity. Teamwork uses /teamwork-preview to coordinate autonomous subagents on large, long-horizon projects and remains in preview.
The administrator settings themselves are generally available and both features are enabled by default. Configuration requires the Gemini Enterprise Admin role and can apply at the organization or project level. Users also need Antigravity 2.0 version 2.18.0 or later, or Antigravity CLI 1.2.10 or later. Google warns that multi-agent work can increase token usage and cost.
The previous day's shutdown remains part of the same tracked event
Google released antigravity-preview-09-2026 on September 17 and announced that antigravity-preview-05-2026 would shut down on October 5. We record October 5 as the effective event date and preserve September 17 as the announcement date instead of presenting an older notice as a new launch.
The replacement is still a preview and Google has not announced its shutdown date. Treat this as the deadline to migrate and run regression tests, not as a promise that the interface is generally available or frozen.
Hosted output may need an ID swap; local tooling needs more
For tasks in Google's remote environment where the application reads only output_text or model_output, the official guidance says changing the agent string to antigravity-preview-09-2026 is normally enough. Run a read-only staging task first and verify output parsing, cost records and timeout handling.
Applications using local_environment or parsing function_call steps face breaking tool-contract changes. Built-in parameters move from snake_case to PascalCase; file edits move from whole-file rewrites to replacements with StartLine and EndLine; list_files becomes list_dir; and native name and grep searches are added. Keep fixtures for both the old and new contracts while migrating.
Recheck the tool boundary instead of assuming a universal browser agent
The current Antigravity Agent can execute code, manage files and search the web in a Google-hosted isolated Linux sandbox. It can also use custom functions, remote MCP servers and synchronous Hooks. Google's documented limits still exclude computer_use, file_search and Google Maps; remote MCP supports Streamable HTTP rather than SSE, and server names must be lowercase alphanumeric.
Turn those boundaries into tests: begin with read-only search, then read a file and make one small edit in a disposable sandbox, and finally inspect function calls, Hook decisions and activity logs. Keep a person in the loop for production files, credentials and external sends.
A practical migration sequence
Save three to five representative tasks and their tool calls, switch the agent ID in staging, then test hosted output, local parameters, line-range edits and failure retries separately. Move production traffic gradually only after both output and side effects match expectations. Do not use a live production directory for the first file-edit test.
Use our MCP setup guide to verify transport and permissions, the ongoing-task guide to define migration checkpoints, the activity-log guide to inspect calls and the prompt-injection guide to review untrusted web and tool output. We found no independently verifiable community test from the last 72 hours, so no forum anecdote is presented as a general result.
Source notes
Event date and our publication date are shown separately. Community reports describe individual experiences.