Live skill reloading, interactive model search, mid-session thought signature fixes, and self-correcting…

Wednesday, 16 September 2026

AI summary

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

New features include live skill reloading and improved model search capabilities, along with several bug fixes.

Added /skills reload for live skill discovery without session restart.
Introduced fuzzy search and autocomplete for /model command.
Improved OAuth error guidance with explicit instructions.
Fixed mid-conversation model switching errors with Gemini models.
Resolved issues with web search summarization failures.

Why it matters: Users who rely on AI tools for interactive sessions should care for enhanced functionality and reduced errors.

Official notes on antigravity.google

Full release notes13 changes

Adds /skills reload for live skill discovery, introduces fuzzy search and autocomplete for /model, improves OAuth scope error guidance, and resolves mid-conversation model switching errors with Gemini thinking models, search_web summarization failures, tool schema validation recovery, and daemon conversation resumption.

Added a /skills reload subcommand to asynchronously reload discovered skills and slash commands without restarting the session or blocking user input.
Added an inline argument autocomplete dropdown when typing /model and a live fuzzy search bar inside the interactive /model picker to filter models by name or ID.
Improved authentication error messages when OAuth tokens lack required scopes by including explicit instructions to run /logout and /login.
Fixed mid-conversation model switching to Gemini thinking models failing with thought_signature validation errors when prior turns were generated by non-Gemini models.
Fixed web search (search_web) failing with "no summary returned from GenerateContent" when the summarization model emits leading thought parts.
Fixed agent turns terminating prematurely with NO_TOOL_CALL when a tool call fails schema validation, allowing the agent loop to return the validation error and self-correct.
Fixed MCP tool schema augmentation mutating tool definitions in place, preventing strict argument validation failures.
Fixed hooks.json configurations being silently dropped when customization token budget truncation is active.
Fixed custom subagents losing configured exclude skill filters when runtime skill filtering is applied.
Fixed subagent status and termination tracking under pubsub batch coalescing so killed subagents are not reset to active by late step updates.
Fixed conversations with active turns or running daemon background tasks failing to auto-resume after a restart.
Fixed terminal ERROR steps (such as failed tool executions or timeouts) being omitted from transcript.jsonl conversation logs.
Fixed raw OSC 8 escape sequences rendering in Apple_Terminal over SSH connections by disabling unsupported hyperlink sequences.

Full release notes13 changes

Added a /skills reload subcommand to asynchronously reload discovered skills and slash commands without restarting the session or blocking user input.
Added an inline argument autocomplete dropdown when typing /model and a live fuzzy search bar inside the interactive /model picker to filter models by name or ID.
Improved authentication error messages when OAuth tokens lack required scopes by including explicit instructions to run /logout and /login.
Fixed mid-conversation model switching to Gemini thinking models failing with thought_signature validation errors when prior turns were generated by non-Gemini models.
Fixed web search (search_web) failing with "no summary returned from GenerateContent" when the summarization model emits leading thought parts.
Fixed agent turns terminating prematurely with NO_TOOL_CALL when a tool call fails schema validation, allowing the agent loop to return the validation error and self-correct.
Fixed MCP tool schema augmentation mutating tool definitions in place, preventing strict argument validation failures.
Fixed hooks.json configurations being silently dropped when customization token budget truncation is active.
Fixed custom subagents losing configured exclude skill filters when runtime skill filtering is applied.
Fixed subagent status and termination tracking under pubsub batch coalescing so killed subagents are not reset to active by late step updates.
Fixed conversations with active turns or running daemon background tasks failing to auto-resume after a restart.
Fixed terminal ERROR steps (such as failed tool executions or timeouts) being omitted from transcript.jsonl conversation logs.
Fixed raw OSC 8 escape sequences rendering in Apple_Terminal over SSH connections by disabling unsupported hyperlink sequences.