fix: pool-stashed transformer swap + MPS-safe vram + corrected model-zoo anchor

fix(deploy): switch model lookups to HF + fix ZeroGPU build

ci: ruff + pytest on push/pr (l1+l2, no gpu deps)

feat(models): hf cache mirror (hardlink blobs, preserve snapshot symlinks, copy refs)

feat(models): device autodetect, vram-limit helpers, model config registry