v1.1.0: CPU-safe GPU detection, real GPU offload, hardened fallible calls, doctor command

fix(colab): GPU detection crashed every CPU runtime; guard CUDA rebuild

docs: publish the Colab notebook so it is reachable without GitHub auth

fix: default to ThoxMini-3B; 327M output is degenerate

docs: ThoxMini-3B defaults and honest free-CPU throughput

fix(space): install libgomp1 in runtime; llama.cpp links OpenMP

fix(space): bookworm base (gcc 12) and coherent ggml flags

fix(space): compile llama-cpp-python in a builder stage (no manylinux wheel exists)

THOX mesh node: OpenAI endpoint + mesh self-registration

initial commit