linux fixes

.aider.conf.yml

@@ -3,8 +3,9 @@
 
 # To use the custom OpenAI-compatible endpoint from hyperbolic.xyz
 # Set the model and the API base URL.
-model: Qwen/Qwen3-Coder-480B-A35B-Instruct
+# model: Qwen/Qwen3-Coder-480B-A35B-Instruct
-openai-api-base: https://api.hyperbolic.xyz/v1
+model: lm_studio/gpt-oss-120b
+openai-api-base: http://127.0.0.1:1234/v1
 openai-api-key: "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"
 model-metadata-file: .aider.model.metadata.json
 

.aider.model.metadata.json

@@ -3,5 +3,10 @@
     "context_window": 262144,
     "input_cost_per_token": 0.000002,
     "output_cost_per_token": 0.000002
+  },
+  "lm_studio/gpt-oss-120b":{
+    "context_window": 106858,
+    "input_cost_per_token": 0.00000015,
+    "output_cost_per_token": 0.00000075
   }
 } 

.env

@@ -1,4 +1,6 @@
-# MEXC API Configuration (Spot Trading)
+# export LM_STUDIO_API_KEY=dummy-api-key # Mac/Linux
+# export LM_STUDIO_API_BASE=http://localhost:1234/v1 # Mac/Linux
+# MEXC API Configuration (Spot Trading)
 MEXC_API_KEY=mx0vglhVPZeIJ32Qw1
 MEXC_SECRET_KEY=3bfe4bd99d5541e4a1bca87ab257cc7e  
 #3bfe4bd99d5541e4a1bca87ab257cc7e 45d0b3c26f2644f19bfb98b07741b2f5

.gitignore

@@ -22,7 +22,6 @@ cache/
 realtime_chart.log
 training_results.png
 training_stats.csv
-__pycache__/realtime.cpython-312.pyc
 cache/BTC_USDT_1d_candles.csv
 cache/BTC_USDT_1h_candles.csv
 cache/BTC_USDT_1m_candles.csv
@@ -47,3 +46,9 @@ chrome_user_data/*
 !.aider.model.metadata.json
 
 .env
+venv/*
+
+wandb/
+*.wandb
+*__pycache__/*
+NN/__pycache__/__init__.cpython-312.pyc

NN/models/cob_rl_model.py

@@ -20,7 +20,7 @@ import logging
 from typing import Dict, List, Optional, Tuple, Any
 from abc import ABC, abstractmethod
 
-from models import ModelInterface
+from .model_interfaces import ModelInterface
 
 logger = logging.getLogger(__name__)
 

TODO.md

@@ -1,60 +1,7 @@
-# 🚀 GOGO2 Enhanced Trading System - TODO
+- [ ] Load MCP documentation
-
+- [ ] Read existing cline_mcp_settings.json
-## 📈 **PRIORITY TASKS** (Real Market Data Only)
+- [ ] Create directory for new MCP server (e.g., .clie_mcp_servers/filesystem)
-
+- [ ] Add server config to cline_mcp_settings.json with name "github.com/modelcontextprotocol/servers/tree/main/src/filesystem"
-### **1. Real Market Data Enhancement**
+- [x] Install the server (use npx or docker, choose appropriate method for Linux)
-- [ ] Optimize live data refresh rates for 1s timeframes
+- [x] Verify server is running
-- [ ] Implement data quality validation checks
+- [x] Demonstrate server capability using one tool (e.g., list_allowed_directories)
-- [ ] Add redundant data sources for reliability
-- [ ] Enhance WebSocket connection stability
-
-### **2. Model Architecture Improvements**
-- [ ] Optimize 504M parameter model for faster inference
-- [ ] Implement dynamic model scaling based on market volatility
-- [ ] Add attention mechanisms for price prediction
-- [ ] Enhance multi-timeframe fusion architecture
-
-### **3. Training Pipeline Optimization**
-- [ ] Implement progressive training on expanding real datasets
-- [ ] Add real-time model validation against live market data
-- [ ] Optimize GPU memory usage for larger batch sizes
-- [ ] Implement automated hyperparameter tuning
-
-### **4. Risk Management & Real Trading**
-- [ ] Implement position sizing based on market volatility
-- [ ] Add dynamic leverage adjustment
-- [ ] Implement stop-loss and take-profit automation
-- [ ] Add real-time portfolio risk monitoring
-
-### **5. Performance & Monitoring**
-- [ ] Add real-time performance benchmarking
-- [ ] Implement comprehensive logging for all trading decisions
-- [ ] Add real-time PnL tracking and reporting
-- [ ] Optimize dashboard update frequencies
-
-### **6. Model Interpretability**
-- [ ] Add visualization for model decision making
-- [ ] Implement feature importance analysis
-- [ ] Add attention visualization for CNN layers
-- [ ] Create real-time decision explanation system
-
-## Implemented Enhancements1. **Enhanced CNN Architecture**   - [x] Implemented deeper CNN with residual connections for better feature extraction   - [x] Added self-attention mechanisms to capture temporal patterns   - [x] Implemented dueling architecture for more stable Q-value estimation   - [x] Added more capacity to prediction heads for better confidence estimation2. **Improved Training Pipeline**   - [x] Created example sifting dataset to prioritize high-quality training examples   - [x] Implemented price prediction pre-training to bootstrap learning   - [x] Lowered confidence threshold to allow more trades (0.4 instead of 0.5)   - [x] Added better normalization of state inputs3. **Visualization and Monitoring**   - [x] Added detailed confidence metrics tracking   - [x] Implemented TensorBoard logging for pre-training and RL phases   - [x] Added more comprehensive trading statistics4. **GPU Optimization & Performance**   - [x] Fixed GPU detection and utilization during training   - [x] Added GPU memory monitoring during training   - [x] Implemented mixed precision training for faster GPU-based training   - [x] Optimized batch sizes for GPU training5. **Trading Metrics & Monitoring**   - [x] Added trade signal rate display and tracking   - [x] Implemented counter for actions per second/minute/hour   - [x] Added visualization of trading frequency over time   - [x] Created moving average of trade signals to show trends6. **Reward Function Optimization**   - [x] Revised reward function to better balance profit and risk   - [x] Implemented progressive rewards based on holding time   - [x] Added penalty for frequent trading (to reduce noise)   - [x] Implemented risk-adjusted returns (Sharpe ratio) in reward calculation
-
-## Future Enhancements1. **Multi-timeframe Price Direction Prediction**   - [ ] Extend CNN model to predict price direction for multiple timeframes   - [ ] Modify CNN output to predict short, mid, and long-term price directions   - [ ] Create data generation method for back-propagation using historical data   - [ ] Implement real-time example generation for training   - [ ] Feed direction predictions to RL agent as additional state information2. **Model Architecture Improvements**   - [ ] Experiment with different residual block configurations   - [ ] Implement Transformer-based models for better sequence handling   - [ ] Try LSTM/GRU layers to combine with CNN for temporal data   - [ ] Implement ensemble methods to combine multiple models3. **Training Process Improvements**   - [ ] Implement curriculum learning (start with simple patterns, move to complex)   - [ ] Add adversarial training to make model more robust   - [ ] Implement Meta-Learning approaches for faster adaptation   - [ ] Expand pre-training to include extrema detection4. **Trading Strategy Enhancements**   - [ ] Add position sizing based on confidence levels (dynamic sizing based on prediction confidence)   - [ ] Implement risk management constraints   - [ ] Add support for stop-loss and take-profit mechanisms   - [ ] Develop adaptive confidence thresholds based on market volatility   - [ ] Implement Kelly criterion for optimal position sizing5. **Training Data & Model Improvements**   - [ ] Implement data augmentation for more robust training   - [ ] Simulate different market conditions   - [ ] Add noise to training data   - [ ] Generate synthetic data for rare market events6. **Model Interpretability**   - [ ] Add visualization for model decision making   - [ ] Implement feature importance analysis   - [ ] Add attention visualization for key price patterns   - [ ] Create explainable AI components7. **Performance Optimizations**   - [ ] Optimize data loading pipeline for faster training   - [ ] Implement distributed training for larger models   - [ ] Profile and optimize inference speed for real-time trading   - [ ] Optimize memory usage for longer training sessions8. **Research Directions**   - [ ] Explore reinforcement learning algorithms beyond DQN (PPO, SAC, A3C)   - [ ] Research ways to incorporate fundamental data   - [ ] Investigate transfer learning from pre-trained models   - [ ] Study methods to interpret model decisions for better trust
-
-## Implementation Timeline
-
-### Short-term (1-2 weeks)
-- Run extended training with enhanced CNN model
-- Analyze performance and confidence metrics
-- Implement the most promising architectural improvements
-
-### Medium-term (1-2 months)
-- Implement position sizing and risk management features
-- Add meta-learning capabilities
-- Optimize training pipeline
-
-### Long-term (3+ months)
-- Research and implement advanced RL algorithms
-- Create ensemble of specialized models
-- Integrate fundamental data analysis 

models.py

@@ -0,0 +1,98 @@
+"""
+Models Module
+
+Provides model registry and interfaces for the trading system.
+This module acts as a bridge between the core system and the NN models.
+"""
+
+import logging
+from typing import Dict, Any, Optional, List
+from NN.models.model_interfaces import ModelInterface, CNNModelInterface, RLAgentInterface, ExtremaTrainerInterface
+
+logger = logging.getLogger(__name__)
+
+class ModelRegistry:
+    """Registry for managing trading models"""
+    
+    def __init__(self):
+        self.models: Dict[str, ModelInterface] = {}
+        self.model_performance: Dict[str, Dict[str, Any]] = {}
+    
+    def register_model(self, name: str, model: ModelInterface):
+        """Register a model in the registry"""
+        self.models[name] = model
+        self.model_performance[name] = {
+            'correct': 0,
+            'total': 0,
+            'accuracy': 0.0,
+            'last_used': None
+        }
+        logger.info(f"Registered model: {name}")
+    
+    def get_model(self, name: str) -> Optional[ModelInterface]:
+        """Get a model by name"""
+        return self.models.get(name)
+    
+    def get_all_models(self) -> Dict[str, ModelInterface]:
+        """Get all registered models"""
+        return self.models.copy()
+    
+    def update_performance(self, name: str, correct: bool):
+        """Update model performance metrics"""
+        if name in self.model_performance:
+            self.model_performance[name]['total'] += 1
+            if correct:
+                self.model_performance[name]['correct'] += 1
+            self.model_performance[name]['accuracy'] = (
+                self.model_performance[name]['correct'] / 
+                self.model_performance[name]['total']
+            )
+    
+    def get_best_model(self, model_type: str = None) -> Optional[str]:
+        """Get the best performing model"""
+        if not self.model_performance:
+            return None
+        
+        best_model = None
+        best_accuracy = -1.0
+        
+        for name, perf in self.model_performance.items():
+            if model_type and not name.lower().startswith(model_type.lower()):
+                continue
+            if perf['accuracy'] > best_accuracy:
+                best_accuracy = perf['accuracy']
+                best_model = name
+        
+        return best_model
+
+# Global model registry instance
+_model_registry = ModelRegistry()
+
+def get_model_registry() -> ModelRegistry:
+    """Get the global model registry instance"""
+    return _model_registry
+
+def register_model(name: str, model: ModelInterface):
+    """Register a model in the global registry"""
+    _model_registry.register_model(name, model)
+
+def get_model(name: str) -> Optional[ModelInterface]:
+    """Get a model from the global registry"""
+    return _model_registry.get_model(name)
+
+def get_all_models() -> Dict[str, ModelInterface]:
+    """Get all models from the global registry"""
+    return _model_registry.get_all_models()
+
+# Export the interfaces
+__all__ = [
+    'ModelRegistry',
+    'get_model_registry',
+    'register_model',
+    'get_model',
+    'get_all_models',
+    'ModelInterface',
+    'CNNModelInterface',
+    'RLAgentInterface',
+    'ExtremaTrainerInterface'
+]

requirements.txt

@@ -9,9 +9,8 @@ psutil>=5.9.0
 tensorboard>=2.15.0
 torch>=2.0.0
 torchvision>=0.15.0
-torchaudio>=2.0.0
+torchaudio>=2.0.0n
 scikit-learn>=1.3.0
 matplotlib>=3.7.0
 seaborn>=0.12.0
-asyncio-compat>=0.1.2
 wandb>=0.16.0