fix: model weights setup — export scripts, ORT compat, bootstrap

- Add export_models.py for OpenCLIP ViT-B/32 and YOLOv8n ONNX export
- Fix ArgMax(13) ORT ARM64 incompatibility by passing eot_indices as a
  separate ONNX input (computed outside the graph in embed.py)
- Use legacy TorchScript exporter (dynamo=False) for IR version 9 compat
- Upgrade onnxruntime to 1.18.1
- Rewrite bootstrap_models.py with clear separation of auto-downloadable
  models (YuNet, SFace) vs manually-exported ones (OpenCLIP, YOLOv8n)
- Wire bootstrap into worker CMD (runs before Celery)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

backend/requirements.txt

@@ -35,7 +35,7 @@ pyexiftool==0.5.6
 watchfiles==0.21.0
 
 # Vision pipeline (ONNX Runtime CPU inference)
-onnxruntime==1.17.1
+onnxruntime==1.18.1
 open-clip-torch==2.24.0     # tokenizer + export helper; inference via ONNX
 rapidocr-onnxruntime==1.3.22
 scikit-learn==1.4.0          # DBSCAN for face clustering