feat(bot-detector): add parallel Autoencoder scorer (#9)

- TrafficAutoEncoder class: symmetric AE (n→64→32→16→32→64→n) with BatchNorm+ReLU
- Trained alongside EIF on human_baseline, saved/loaded with model versioning
- Score = per-sample MSE reconstruction error, combined with EIF via AE_WEIGHT (α=0.30)
- AE latent space (16-dim) used for HDBSCAN clustering instead of raw features
- Configurable: AE_WEIGHT, AE_EPOCHS, AE_LATENT_DIM, AE_LEARNING_RATE
- Graceful fallback: if torch unavailable or AE fails, EIF-only scoring continues
- ClickHouse: ae_recon_error column added to ml_all_scores
- Tests: 5 new tests (AE train/score, encode latent, state dict save/load, weight combination)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

services/bot-detector/bot_detector/requirements.txt

@@ -5,5 +5,6 @@ shap==0.47.2
 scipy>=1.14
 hdbscan>=0.8.38
 isotree>=0.6.1
+torch>=2.0
 pyyaml>=6.0
 ja4-common @ file:///app/shared/ja4_common