Fixed local Qwen GGUF vision handler initialization with recent JamePeng llama-cpp-python builds
Added runtime compatibility for MTMD handlers that expect mmproj_path
Preserved compatibility with older builds that still require clip_model_path
Prevented Qwen3-VL and Qwen3.5/3.6 local vision runs from falling back to text-only mode because of the handler keyword mismatch
Improved mmproj logging for local Qwen vision models
Reports the selected mmproj after manual selection or auto-detection
Avoids printing Using mmproj: None for text-only paths