Hmmm I haven't used for Cline for several months but in Roo I have made some (fairly minor) changes to my Roo Code code modes and have not experienced this at all. Especially that frequently, I use GPT 4.1 via my Copilot Pro plan and Gemini 2.5 Pro via OpenRouter as my daily drivers. That being said I have had found using Gemini through the AI Studio API much less reliable in Roo/Cline and I'm not sure how you are accessing it.

I have auto approve turned on for most routine tasks and run Gemini for relatively long (by Cline/Roo standards) tasks unsupervised without issue, with the normal caveats of any LLM going off the deep end every now and then but haven't seen that more frequently with Gemini except in the first couple months 2.5 Pro was released.