[Macbook Pro M4 Max, MacOS Sequoia 15.7.2, VS Code v1.106.3, Cline 3.40.2, LM Studio 0.3.34]
I’m running local models via LM Studio, and it’s demoralising when my LLM reasoning times out at 80+ percent with a message: ` [LM STUDIO SERVER] Client disconnected. Stopping generation… (If the model is busy processing the prompt, it will finish first.)`
So, I’m wondering if it’s possible to adjust the timeout on Requests to give it another 30 to 60 seconds or so.