sandboxing agent actions on M3 Max

[phasenode]

Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher.

[oxidegrove40]

I tested this tonight. On 5090 with TensorRT-LLM, I saw basically the same behavior. The main thing that moved was latency, not quality.

[latentscope35]

Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.

[visionyard23]

My first guess would be this: If you're on SGLang, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.