Back
AI summary
Written by AI from the official notes. Check them for exact details.A new model quota screen was introduced along with agent security fixes and MCP stability improvements.
- Redesigned quota screen for clearer credit usage view.
- Fixed bug in agent security mode persistence.
- Improved MCP server stability and troubleshooting.
- MCP schema now accepts 'url' field.
- New sensitive paths require user confirmation.
Why it matters: Users managing agent permissions and monitoring model usage should pay attention to these updates for improved security and usability.
Full release notes5 changes
New model quota screen, agent permission and security fixes, and MCP stability improvements
- Quota screen redesign: clearer, unambiguous view into “used” versus “remaining” credits in the Models tab of the Settings screen.
- Fixed Agent Permission Issue: Fixed the bug where changes to the agent security mode were not persisted.
- Improved MCP server stability: increased resilience to unresponsive MCP servers and improved browser agent self-troubleshooting abilities when using the Chrome DevTools MCP server.
- MCP server schema compatibility: the mcp_config.json schema now accepts url in addition to serverUrl as a field.
- New entries in the sensitive paths list:.vscode and.cache are now recognized as sensitive paths that require explicit user confirmation before the agent can access them in strict mode.