use enhanced orchestrator

_dev/notes.md

@@ -33,6 +33,11 @@ how effective is our training? show current loss and accuracy on the chart. also
 what are our rewards and penalties in the RL training pipeline? reprt them so we can evaluate them and make sure they are working as expected and do improvements
 
 
+allow models to be dynamically loaded and unloaded from the webui (orchestrator)
+
+show cob data in the dashboard over ws
+
+report and audit rewards and penalties in the RL training pipeline
 
 
 >> clean dashboard
@@ -68,4 +73,7 @@ use existing checkpoint manager if it;s not too bloated as well. otherwise re-im
 - [ ] Chart updates every second
 - [ ] No flickering or data loss
 - [ ] WebSocket connection stable
-- [ ] Memory usage reasonable
+- [ ] Memory usage reasonable
+
+
+

core/realtime_rl_cob_trader.py

@@ -93,7 +93,6 @@ class TradeSignal:
 
 # MassiveRLNetwork is now imported from NN.models.cob_rl_model
 
-
 class RealtimeRLCOBTrader:
     """
     Real-time RL trader using COB data with comprehensive subscriber system

core/shared_cob_service.py

@@ -332,7 +332,6 @@ class SharedCOBService:
         
         return base_stats
 
-
 # Global service instance access functions
 
 def get_shared_cob_service(symbols: List[str] = None, data_provider: DataProvider = None) -> SharedCOBService:

training/williams_market_structure.py

@@ -36,7 +36,6 @@ from typing import Dict, List, Optional, Tuple, Any
 from dataclasses import dataclass
 from enum import Enum
 
-
 # Setup logger immediately after logging import
 logger = logging.getLogger(__name__)
 
@@ -167,7 +166,6 @@ except ImportError:
     TrainingDataPacket = None
     print("Warning: TrainingDataPacket could not be imported. Using fallback interface.")
 
-
 class TrendDirection(Enum):
     UP = "up"
     DOWN = "down"
@@ -964,7 +962,6 @@ class WilliamsMarketStructure:
                     else:
                         y_train_batch = y_train
 
-
                     logger.info(f"CNN Training with X_shape: {X_train_batch.shape}, y_shape: {y_train_batch.shape}")
                     # Perform a single step of training (online learning)
                     # Use the wrapper's fit method, not the model's directly
@@ -1340,7 +1337,6 @@ class WilliamsMarketStructure:
             # Emergency fallback: return features as-is but scaled to [0,1] roughly
             return np.clip(features / (np.max(np.abs(features)) + 1e-8), -1.0, 1.0)
 
-
     def _get_cnn_ground_truth(self, 
                               previous_pivot_info: Dict[str, Any], # Contains 'pivot': SwingPoint obj of N-1
                               actual_current_pivot: SwingPoint     # This is pivot N

utils/reward_calculator.py

@@ -194,7 +194,6 @@ class ImprovedRewardCalculator:
         
         return reward
 
-
 # Example usage:
 if __name__ == "__main__":
     # Create calculator instance

web/clean_dashboard.py

@@ -31,7 +31,7 @@ logger = logging.getLogger(__name__)
 # Import core components
 from core.config import get_config
 from core.data_provider import DataProvider
-from core.orchestrator import TradingOrchestrator
+from core.enhanced_orchestrator import EnhancedTradingOrchestrator
 from core.trading_executor import TradingExecutor
 
 # Import layout and component managers
@@ -60,13 +60,22 @@ from core.realtime_rl_cob_trader import RealtimeRLCOBTrader, PredictionResult
 class CleanTradingDashboard:
     """Clean, modular trading dashboard implementation"""
     
-    def __init__(self, data_provider: DataProvider = None, orchestrator: TradingOrchestrator = None, trading_executor: TradingExecutor = None):
+    def __init__(self, data_provider: DataProvider = None, orchestrator: EnhancedTradingOrchestrator = None, trading_executor: TradingExecutor = None):
         self.config = get_config()
         
         # Initialize components
         self.data_provider = data_provider or DataProvider()
-        self.orchestrator = orchestrator
+        self.trading_executor = trading_executor or TradingExecutor()
-        self.trading_executor = trading_executor
+        
+        # Initialize orchestrator with enhanced capabilities
+        if orchestrator is None:
+            self.orchestrator = EnhancedTradingOrchestrator(
+                data_provider=self.data_provider,
+                symbols=['ETH/USDT', 'BTC/USDT'],
+                enhanced_rl_training=True
+            )
+        else:
+            self.orchestrator = orchestrator
         
         # Initialize layout and component managers
         self.layout_manager = DashboardLayoutManager(
@@ -126,6 +135,42 @@ class CleanTradingDashboard:
         
         logger.info("Clean Trading Dashboard initialized with COB RL integration")
     
+    def load_model_dynamically(self, model_name: str, model_type: str, model_path: str = None) -> bool:
+        """Dynamically load a model at runtime"""
+        try:
+            if hasattr(self.orchestrator, 'load_model'):
+                success = self.orchestrator.load_model(model_name, model_type, model_path)
+                if success:
+                    logger.info(f"Successfully loaded model: {model_name}")
+                    return True
+            return False
+        except Exception as e:
+            logger.error(f"Error loading model {model_name}: {e}")
+            return False
+    
+    def unload_model_dynamically(self, model_name: str) -> bool:
+        """Dynamically unload a model at runtime"""
+        try:
+            if hasattr(self.orchestrator, 'unload_model'):
+                success = self.orchestrator.unload_model(model_name)
+                if success:
+                    logger.info(f"Successfully unloaded model: {model_name}")
+                    return True
+            return False
+        except Exception as e:
+            logger.error(f"Error unloading model {model_name}: {e}")
+            return False
+    
+    def get_loaded_models_status(self) -> Dict[str, Any]:
+        """Get status of all loaded models"""
+        try:
+            if hasattr(self.orchestrator, 'list_loaded_models'):
+                return self.orchestrator.list_loaded_models()
+            return {'loaded_models': {}, 'total_models': 0, 'system_status': 'NO_ORCHESTRATOR'}
+        except Exception as e:
+            logger.error(f"Error getting model status: {e}")
+            return {'loaded_models': {}, 'total_models': 0, 'system_status': 'ERROR'}
+    
     def _get_initial_balance(self) -> float:
         """Get initial balance from trading executor or default"""
         try:

web/cob_realtime_dashboard.py

@@ -537,7 +537,6 @@ class COBDashboardServer:
                 logger.error(f"Error in cleanup: {e}")
                 await asyncio.sleep(300)
 
-
 async def main():
     """Main entry point"""
     # Set up logging
@@ -565,6 +564,5 @@ async def main():
         if 'server' in locals():
             await server.stop()
 
-
 if __name__ == "__main__":
     asyncio.run(main())