Reduce uvicorn workers from 8 to 1 to prevent OOM on HF Spaces

feat: cache reranker snapshot at build time via huggingface_hub

perf: 8 workers, 10 concurrent uploads, Qdrant wait=False + batch 2000

fix: free memory between model downloads, graceful fallback if reranker OOMs

perf: upgrade embedding to all-mpnet-base-v2, add cross-encoder reranker, LRU cache, enable PII by default

fix: COPY alembic directory correctly so migrations run

production hardening: circuit breakers, graceful degradation, health checks, parallel uploads, HF Spaces deploy config

fix upload pipeline: await add_document, pre-load model eagerly, add verbose UPLOAD/VectorStore logging; remove unused deployment configs

fix models.py: match Neon schema varchar sizes, add email unique constraint