Gemini model is stuck in a loop where it keeps replying to its own previous messages without any new user input.
It basically talks to itself continuously, causing unnecessary token usage and rapidly increasing costs.
This should not happen — the model should stop after one response and wait for the next user message.
Model Claude not error like this, browsersubagent use Gemini Flash it error too
same problem on browsersubagent！
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.
