feat: add ML-based adaptive timeout prediction using LinearRegressor

Train a linear regression model on actual message delivery times to
predict tighter timeouts, replacing worst-case physics estimates.
Features: path length, message bytes, seconds since last RX, flood mode.
Global model with per-contact blending after 10+ observations per contact.
Falls back to existing physics formula when model has insufficient data.

pubspec.yaml

@@ -69,6 +69,8 @@ dependencies:
   material_symbols_icons: ^4.2906.0
   web: ^1.1.1
   flutter_svg: ^2.0.10+1
+  ml_algo: ^16.0.0
+  ml_dataframe: ^1.0.0
 
 dev_dependencies:
   flutter_test: