Deploy app from main@a3254bf (no paper/ binaries)

Phase E #2: scripts/recommend.py — single-genome → ranked media + phenotype CLI

Phase E modeling: per-medium classifiers + recommender training script

Fix predictions parquet type mix + plumb feature_cols through eval

Eval report enhancements: TL;DR + per-strain predictions + per-family error

Fix classification fold bug + add end-to-end integration tests

Add eval report generator + training table persistence + group-col override

Scaffold v0: BacDive + NCBI ingestion, genome feature extractor, XGBoost baseline