fix prediction candles updates. fix for trend prediction.

ANNOTATE/core/real_training_adapter.py

@@ -1615,29 +1615,41 @@ class RealTrainingAdapter:
             # FIXED: Ensure shape is [1, 1] not [1] to match BCELoss requirements
             trade_success = torch.tensor([[1.0 if profit_loss_pct > 0 else 0.0]], dtype=torch.float32)  # [1, 1]
             
-            # NEW: Trend vector target for trend analysis optimization
-            # Calculate expected trend from entry to exit
-            direction = training_sample.get('direction', 'NONE')
+            # REAL TREND CALCULATION from actual price data (NO MORE SYNTHETIC DATA!)
+            # Use last 10 candles to calculate actual trend angle, steepness, direction
             
-            if direction == 'LONG':
-                # Upward trend: positive angle, positive direction
-                trend_angle = 0.785  # ~45 degrees in radians (pi/4)
-                trend_direction = 1.0  # Upward
-            elif direction == 'SHORT':
-                # Downward trend: negative angle, negative direction
-                trend_angle = -0.785  # ~-45 degrees
-                trend_direction = -1.0  # Downward
+            # Get price data from the batch to calculate actual trend
+            price_data = price_data_1m if price_data_1m is not None else (
+                         price_data_1s if price_data_1s is not None else price_data_1h)
+            
+            if price_data is not None and price_data.shape[1] >= 10:
+                # price_data shape: [batch=1, seq_len=200, features=5] -> OHLCV
+                recent_closes = price_data[0, -10:, 3]  # Last 10 close prices [10]
+                
+                # Calculate actual price change and time delta
+                price_start = recent_closes[0].item()
+                price_end = recent_closes[-1].item()
+                price_delta = price_end - price_start
+                time_delta = 9.0  # 10 candles = 9 intervals
+                
+                # Calculate real angle using atan2
+                import math
+                trend_angle = math.atan2(price_delta, time_delta * price_start / 100.0)  # Normalize by price scale
+                
+                # Calculate real steepness (magnitude of change)
+                if price_start > 0:
+                    price_change_pct = abs(price_delta / price_start)
+                    trend_steepness = min(price_change_pct * 100.0, 1.0)  # Scale and cap at 1.0
+                else:
+                    trend_steepness = 0.0
+                
+                # Calculate real direction
+                trend_direction = 1.0 if price_delta > 0 else (-1.0 if price_delta < 0 else 0.0)
             else:
-                # No trend
+                # Fallback if no price data available (should rarely happen)
                 trend_angle = 0.0
-                trend_direction = 0.0
-            
-            # Steepness based on profit potential
-            if exit_price and entry_price and entry_price > 0:
-                price_change_pct = abs((exit_price - entry_price) / entry_price)
-                trend_steepness = min(price_change_pct * 10, 1.0)  # Normalize to [0, 1]
-            else:
                 trend_steepness = 0.0
+                trend_direction = 0.0
             
             # Create trend target tensor [batch, 3]: [angle, steepness, direction]
             trend_target = torch.tensor([[trend_angle, trend_steepness, trend_direction]], dtype=torch.float32)  # [1, 3]