fix: HF inference SDK v3 + InferenceClient + supported model IDs (Llama 3.2, Gemma, Phi-3)

fix: single-stage Dockerfile + .dockerignore + no node-llama-cpp + llama.cpp REST sidecar

v2 final: clean Dockerfile + node-llama-cpp local model + full UI (markdown+artifacts+fileupload)

v2: Full claude.ai clone — TinyLlama local model + markdown + artifacts + file upload + multi-provider

🚀 Initial Fable AI deployment — open-source models via HF Inference API