fix: Make the Space a Gradio app, which is what ZeroGPU requires

add: Hosted generation for the Space, and retire the ZeroGPU attempt

Revert "revert: Unpin the Space's torch -- the CUDA 12 theory was wrong"

revert: Unpin the Space's torch -- the CUDA 12 theory was wrong

fix: Keep CUDA calls off the dedicated inference thread -- again

fix: Run inference inside @spaces.GPU, where the weights actually exist

fix: Warm the retrieval embedder inside ZeroGPU's import window too

fix: Build the Space's agent at import scope, where ZeroGPU is watching

fix: Load the Space's model the one way ZeroGPU allows

fix: Accept the Space's existing CONTROLAI_BACKEND spelling, and stop guessing

fix: Unpin the Space's transformers -- the pin made the build unsolvable

fix: Serve the Space a pre-quantised checkpoint

add: A CUDA path for the demo Space, behind the existing engine contract

refactor: Collapse four inference backends into one MLX path