Default OCR off for deploy — TrOCR OOM-kills the 512MB Render worker

Make plate OCR deploy-safe: small TrOCR model + graceful failure

Use CPU-only PyTorch on Render to avoid 2GB+ CUDA download

Pin Python to 3.11.9 for Render deploy (pydantic-core has no py3.14 wheel)

Move edge preprocessor into backend/ and add .env.example for deployment

Add violation rules, NETRA UI overhaul, MongoDB challan store, and model weights

Integrate weather-adaptive edge preprocessor into the pipeline

plate recog by TrOCR and frontend and some other things updated

basic architecture defined