fix: prebuilt CPU wheel for llama-cpp-python, skip 15min source compile on Spaces

feat: llama.cpp runtime ready for the Space (Llama Champion)

feat: switch to FLUX.2-klein-4B for image generation

feat: FLUX.1-schnell image generation after correct answers

fix: infinite spinner on question gen, 4-bit quant for low VRAM

feat: switch to Docker SDK with custom FastAPI frontend at /

feat: Off-Brand badge - custom FastAPI+HTML frontend, zero Gradio chrome

fix: pin transformers==4.57.1 for MiniCPM4-8B compatibility

feat: switch to MiniCPM4-8B, add robustness, score tracker, language selector

update

feat: initial project structure with all core modules