Persistent HTTP 500 errors and agent execution failures on Google Antigravity causing all models to stop responding to prompts.

Multiple users across different regions are experiencing consistent failures when using Google Antigravity. The issue typically appears as an HTTP 500 Internal Server Error or messages such as “Agent execution terminated due to error.”

The problem seems to affect all available models, where prompts fail to generate responses. In some cases, clicking continue loads previous prompts but still results in failure.

Reported symptoms include:

  • HTTP 500 Internal Server Error on every prompt

  • Agent execution terminated unexpectedly

  • Conversations failing across all models

  • Prompts loading but failing to generate responses

  • Intermittent service outages reported by multiple users globally

The issue has been reported by users in several countries and appears intermittently over the last 24 hours, with several incidents detected but not officially acknowledged.

This discussion is intended to collect reports, confirm whether the issue is widespread, and identify any temporary workarounds while the service stabilizes.

Hi @Abdullah_Ziauddin
Welcome to the Google AI Forum!!!

Thank you for bringing this to our attention. We have escalated the issue to our internal teams for a thorough investigation.

To ensure our engineering team can investigate and resolve these issues effectively, we highly recommend filing bug reports directly through the Antigravity in-app feedback tool. You can do this by navigating to the top-right corner of the interface, clicking the Feedback icon, and selecting Report Issue.