Speed up CPU inference: halve token limits, pre-download models, fix OMP threads

Use bfloat16 on CPU to halve memory (8GB vs 16GB float32)

Fix MCP subprocess deadlock: use stderr=None instead of PIPE

Add timeout and stderr logging to MCP subprocess to debug tool hangs

Remove unused files: old Gradio frontend, dead model code, test artifacts

Force MCP tool models to CPU to avoid GPU VRAM contention with MedGemma

Add missing deps: sentence-transformers, pdfplumber, scipy for MCP tools

Add RAG Phase 4 management guidance, rebuild guidelines index (286 chunks), post-analysis hint UI

Use dtype instead of deprecated torch_dtype in model_kwargs

Redesign chat UI and fix MedGemma generation config issues

Fix requirements: opencv-headless (no libGL needed), remove unused gradio, add faiss-cpu and huggingface_hub

Copy mcp_server/ into Docker image

Include mcp_server/ in Docker image — required at runtime for tool calls

Pass HF_TOKEN explicitly to pipeline() for gated model auth

Use HF_TOKEN env var to authenticate for gated MedGemma model

Fix Dockerfile: install curl before using it for NodeSource setup

Migrate FAISS index to Git LFS

Track FAISS index via Git LFS

Add HF Spaces Dockerfile, Git LFS for model weights

Initial commit — SkinProAI dermoscopic analysis platform