feat: add hybrid bot implementation and enhance NNUE training pipeline with tactical data extraction

modules/bot/python/src/export.py

@@ -13,8 +13,9 @@ def export_weights_to_binary(weights_file, output_file):
         print(f"Error: Weights file not found at {weights_file}")
         sys.exit(1)
 
-    # Load weights
-    state_dict = torch.load(weights_file, map_location='cpu')
+    # Load weights — handle both raw state dicts and full training checkpoints
+    loaded = torch.load(weights_file, map_location='cpu')
+    state_dict = loaded["model_state_dict"] if isinstance(loaded, dict) and "model_state_dict" in loaded else loaded
 
     # Debug: print available layers
     print(f"Available layers in {weights_file}:")
@@ -31,7 +32,7 @@ def export_weights_to_binary(weights_file, output_file):
         f.write(struct.pack('<I', 1))  # version 1
 
         # Write each weight tensor in order
-        for layer_name in ['l1.weight', 'l1.bias', 'l2.weight', 'l2.bias', 'l3.weight', 'l3.bias']:
+        for layer_name in ['l1.weight', 'l1.bias', 'l2.weight', 'l2.bias', 'l3.weight', 'l3.bias', 'l4.weight', 'l4.bias', 'l5.weight', 'l5.bias']:
             if layer_name not in state_dict:
                 print(f"Error: Missing layer {layer_name}")
                 sys.exit(1)