small agent harness that stayed useful with LM Studio

[northgrid33]

That matches what I was seeing. The pattern around structured output has been pretty similar for me.

[labline]

A couple things I'd check first. If you're on PyTorch, 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.

[ggufvault]

Need a little more detail here. Are you testing this on Threadripper box or something else? I keep promising myself this is the last rebuild.