feat: RapidOCR default OCR engine, office-only ocr_engine, drop operator toggle

requirements.txt

@@ -10,7 +10,8 @@ python-dotenv
 pyyaml  # also pulled by ultralytics; used directly by src/config_loader.py
 openpyxl
 paramiko  # deploy_to_jetson.py only
-pytesseract  # DO OCR (Phase 2); system tesseract-ocr package also required on Jetson
+pytesseract  # DO OCR backup; system tesseract-ocr package also required on Jetson
+rapidocr_onnxruntime  # DO OCR default engine (RapidOCR/PP-OCR, models bundled)
 
 # Test-only (dev/CI):
 # pytest