feat(tagger): smart ensemble — WD14 EVA02-Large v3 + JoyTag fusion, YOLO pose tags, optional VLM captions

feat(tagger): NL captioning via Qwen3-VL, pose detection UI fixes, memory-safe for HF Spaces (16GB CPU)

fix(tagger): CPU-only safety, memory budget, pose toggle, fold single-model modes into slide-panel

feat(prod): rewrite pipeline + NoobAI + ensemble tagger (3xWD14+DeepDanbooru-ready) + 1000 artists + negative templates + history ext + scoring config