[Feature]: 240 seconds isn't enough time for my local LLM

Is your feature request related to a problem? Please describe.

For anything longer than a single sentence of optimization, the AI times out before it can make any changes.

Describe the solution you'd like

It would be helpful if we could set the timeout length in the settings, letting us extend the time the AI has to whatever we want. I would also ask that when the controller aborts due to timeout, that it actually passes through that it's a timeout failure. As it stands you first read that the "signal was aborted without reason," which is initially confusing.

Describe alternatives you've considered

I'm trying to find and change the timeout length in the code itself, but my understanding of the code is limited, which limits my progress.

Additional context

I'm running self-hosted Mistral-small over ollama. I'm well aware that timeout wouldn't be an issue otherwise.