fix: EURLEXEmbedder.encode() must return numpy array, not list

fix: EURLEXEmbedder.encode() must accept normalize_embeddings kwarg that SentenceTransformer uses

fix: pass HF_TOKEN to onnx model download

fix: use suffix variables in download_index instead of hardcoded filenames

fix: add onnxruntime+transformers deps and fix model download repo_type

phase-2: EURLEX-BERT ONNX INT8 quantization, matrix sharding workflow, EURLEXEmbedder

phase-1: CI workflow, ruff linting, keepalive alerting, VITE_API_URL, pre-commit hooks

checkpoint: create app/ directory with consolidated backend (9-stage pipeline)