feat(ml): replace Autoencoder with RealNVP Normalizing Flow and add SessionTransformer embeddings

Replace TrafficAutoEncoder (MSE reconstruction scoring) with TrafficNormalizingFlow
(RealNVP via FrEIA, 4 affine coupling blocks, anomaly score = -log p(x)) for
mathematically rigorous density estimation. Add SessionTransformer module producing
32-dimensional sequence embeddings from raw HTTP request sequences (path, method,
timing) via a lightweight TransformerEncoder, replacing path_transition_entropy and
cadence_cv features. Update thesis documentation sections 2.4.2b and 3.8 accordingly.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

services/bot-detector/bot_detector/requirements.txt

@@ -6,6 +6,7 @@ scipy>=1.14
 hdbscan>=0.8.38
 isotree>=0.6.1
 torch>=2.0
+FrEIA>=0.2
 xgboost>=2.0
 cleanlab>=2.6
 pyyaml>=6.0