now using claude opus, token is cap at 200k, and it doesnt know how to reduce the prompt size and lead to direct error. This happens very often. And restart also doesnt work. And now gemini 3.1 pro erroneous and directly return error and ask for retry.
Why still using this broken software? better go back to claude code.
how long should we wait for Antigravity to be really functional ? dont waste your time. Time is limited.
Hi @SimpleAI
Thank you for the feedback and for bringing this to our attention. We sincerely apologize for the inconvenience this has caused. We have escalated the issue to our internal teams for a thorough investigation.
Thanks for looking into this. I’ve preferred Antigravity over everything else because of the quality that Gemini has been producing. I got an AI Pro subscription specifically for Antigravity, but once Gemini 3.1 was released I get capacity hit and agent crashed errors.
Let me know if I can provide any information to help resolve the issue.
thanks BenForce, i feel like more people has similar issue to me. it is a mixed bag of issue from claude opus availability, stability to its own gemini 3.1 terminated or stopped amid generation. the product user experience is dropping to ZERO.
the only reason i am still using it is because my project is still tied to it. but i think claude has just make a move to help with its import function