# Enhanced Multi-Modal Trading System Configuration

# System Settings
system:
  timezone: "Europe/Sofia"     # Configurable timezone for all timestamps
  log_level: "INFO"            # DEBUG, INFO, WARNING, ERROR
  session_timeout: 3600        # Session timeout in seconds

# LLM Proxy Configuration
llm_proxy:
  base_url: "http://localhost:1234"     # LLM server base URL
  model: "openai/gpt-oss-20b"           # Model name
  temperature: 0.7                      # Response creativity (0.0-1.0)
  max_tokens: -1                        # Max response tokens (-1 for unlimited)
  timeout: 30                           # Request timeout in seconds
  api_key: null                         # API key if required

# Cold Start Mode Configuration
cold_start:
  enabled: true                # Enable cold start mode logic
  inference_interval: 0.5      # Inference interval (seconds) during cold start
  training_interval: 2         # Training interval (seconds) during cold start
  heavy_adjustments: true      # Allow more aggressive parameter/training adjustments
  log_cold_start: true         # Log when in cold start mode

# Exchange Configuration
exchanges:
  primary: "bybit"  # Primary exchange: mexc, deribit, binance, bybit
  
  # Deribit Configuration
  deribit:
    enabled: true
    test_mode: true  # Use testnet for testing
    trading_mode: "live"  # simulation, testnet, live
    supported_symbols: ["BTC-PERPETUAL", "ETH-PERPETUAL"]
    base_position_percent: 5.0
    max_position_percent: 20.0
    leverage: 10.0  # Lower leverage for safer testing
    trading_fees:
      maker_fee: 0.0000    # 0.00% maker fee
      taker_fee: 0.0005    # 0.05% taker fee
      default_fee: 0.0005
  
  # MEXC Configuration (secondary/backup)
  mexc:
    enabled: false  # Disabled as secondary
    test_mode: true
    trading_mode: "simulation"
    supported_symbols: ["ETH/USDT"]  # MEXC-specific symbol format
    base_position_percent: 5.0
    max_position_percent: 20.0
    leverage: 50.0
    trading_fees:
      maker_fee: 0.0002
      taker_fee: 0.0006
      default_fee: 0.0006
  
  # Bybit Configuration
  bybit:
    enabled: true
    test_mode: false  # Use mainnet (your credentials are for live trading)
    trading_mode: "simulation"  # simulation, testnet, live 
    supported_symbols: ["BTCUSDT", "ETHUSDT"]  # Bybit perpetual format
    base_position_percent: 5.0
    max_position_percent: 20.0
    leverage: 10.0  # Conservative leverage for safety
    leverage_applied_by_exchange: true  # Broker already applies leverage to P&L
    trading_fees:
      maker_fee: 0.0001    # 0.01% maker fee
      taker_fee: 0.0006    # 0.06% taker fee
      default_fee: 0.0006

# Trading Symbols Configuration
# Primary trading pair: ETH/USDT (main signals generation)
# Reference pair: BTC/USDT (correlation analysis only, no trading signals)
symbols:
  - "ETH/USDT"  # MAIN TRADING PAIR - Generate signals and execute trades
  - "BTC/USDT"  # REFERENCE ONLY - For correlation analysis, no direct trading

# Timeframes for ultra-fast scalping (500x leverage)
timeframes:  
  - "1s"  # Primary scalping timeframe  
  - "1m"  # Short-term confirmation  
  - "1h"  # Medium-term trend 
  - "1d"  # Long-term direction

# Data Provider Settings
data:
  provider: "binance"
  cache_enabled: true
  cache_dir: "cache"
  historical_limit: 1000
  real_time_enabled: true
  websocket_reconnect: true
  feature_engineering:
    technical_indicators: true
    market_regime_detection: true
    volatility_analysis: true

# Model configurations have been moved to models.yml for better organization
# See models.yml for all model-specific settings including:
# - CNN configuration
# - RL/DQN configuration  
# - Orchestrator settings
# - Training configuration
# - Enhanced training system
# - Real-time RL COB trader

# Enhanced RL Agent Configuration
rl:
  state_size: 100  # Will be calculated dynamically based on features
  action_space: 3  # BUY, HOLD, SELL
  hidden_size: 256
  epsilon: 1.0
  epsilon_decay: 0.995
  epsilon_min: 0.01
  learning_rate: 0.0001
  gamma: 0.99
  memory_size: 10000
  batch_size: 64
  target_update_freq: 1000
  buffer_size: 10000
  model_dir: "models/enhanced_rl"
  # Market regime adaptation
  market_regime_weights:
    trending: 1.2    # Higher confidence in trending markets
    ranging: 0.8     # Lower confidence in ranging markets
    volatile: 0.6    # Much lower confidence in volatile markets
  # Prioritized experience replay
  replay_alpha: 0.6  # Priority exponent
  replay_beta: 0.4   # Importance sampling exponent

# Enhanced Orchestrator Settings
orchestrator:
  # Model weights for decision combination
  cnn_weight: 0.7      # Weight for CNN predictions
  rl_weight: 0.3       # Weight for RL decisions
  confidence_threshold: 0.45
  confidence_threshold_close: 0.30
  decision_frequency: 30
  
  # Multi-symbol coordination
  symbol_correlation_matrix:
    "ETH/USDT-BTC/USDT": 0.85  # ETH-BTC correlation
    
  # Perfect move marking
  perfect_move_threshold: 0.02  # 2% price change to mark as significant
  perfect_move_buffer_size: 10000
  
  # RL evaluation settings
  evaluation_delay: 3600  # Evaluate actions after 1 hour
  reward_calculation:
    success_multiplier: 10    # Reward for correct predictions
    failure_penalty: 5        # Penalty for wrong predictions
    confidence_scaling: true   # Scale rewards by confidence

  # Entry aggressiveness: 0.0 = very conservative (fewer, higher quality trades), 1.0 = very aggressive (more trades)
  entry_aggressiveness: 0.5
  # Exit aggressiveness: 0.0 = very conservative (let profits run), 1.0 = very aggressive (quick exits)
  exit_aggressiveness: 0.5

# Training Configuration
training:
  learning_rate: 0.001
  batch_size: 32
  epochs: 100
  validation_split: 0.2
  early_stopping_patience: 10
  
  # CNN specific training
  cnn_training_interval: 3600    # Train CNN every hour (was 6 hours)
  min_perfect_moves: 50          # Reduced from 200 for faster learning
  
  # RL specific training  
  rl_training_interval: 300      # Train RL every 5 minutes (was 1 hour)
  min_experiences: 50            # Reduced from 100 for faster learning
  training_steps_per_cycle: 20   # Increased from 10 for more learning

  model_type: "optimized_short_term"
  use_realtime: true
  use_ticks: true
  checkpoint_dir: "NN/models/saved/realtime_ticks_checkpoints"
  save_best_model: true
  save_final_model: false  # We only want to keep the best performing model
  
  # Continuous learning settings
  continuous_learning: true
  learning_from_trades: true
  pattern_recognition: true
  retrospective_learning: true

# Universal Trading Configuration (applies to all exchanges)
trading:
  enabled: true
  
  # Position sizing as percentage of account balance
  base_position_percent: 5.0     # 5% base position of account
  max_position_percent: 20.0     # 20% max position of account
  min_position_percent: 2.0      # 2% min position of account
  simulation_account_usd: 100.0  # $100 simulation account balance
  
  # Risk management
  max_daily_loss_usd: 200.0
  max_concurrent_positions: 3
  min_trade_interval_seconds: 5  # Minimum time between trades
  consecutive_loss_reduction_factor: 0.8 # Reduce position size by 20% after each consecutive loss
  
  # Order configuration (can be overridden by exchange-specific settings)
  order_type: market  # market or limit

# Memory Management
memory:
  total_limit_gb: 28.0       # Total system memory limit
  model_limit_gb: 4.0       # Per-model memory limit
  cleanup_interval: 1800    # Memory cleanup every 30 minutes
  
# Enhanced training and real-time RL configurations moved to models.yml

# Web Dashboard
web:
  host: "127.0.0.1"
  port: 8050
  debug: false
  update_interval: 500  # Milliseconds
  chart_history: 200     # Number of candles to show
  
  # Enhanced dashboard features
  show_timeframe_analysis: true
  show_confidence_scores: true
  show_perfect_moves: true
  show_rl_metrics: true

# Logging
logging:
  level: "INFO"
  format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
  file: "logs/enhanced_trading.log"
  max_size: 10485760  # 10MB
  backup_count: 5
  
  # Component-specific logging
  orchestrator_level: "INFO"
  cnn_level: "INFO"
  rl_level: "INFO"
  training_level: "INFO"

# Model Directories
model_dir: "models"
data_dir: "data"
cache_dir: "cache"
logs_dir: "logs"

# GPU/Performance
gpu:
  enabled: true  
  memory_fraction: 0.8  # Use 80% of GPU memory
  allow_growth: true    # Allow dynamic memory allocation
  
# Monitoring and Alerting
monitoring:
  tensorboard_enabled: true
  tensorboard_log_dir: "logs/tensorboard"
  metrics_interval: 300     # Log metrics every 5 minutes
  performance_alerts: true
  
  # Performance thresholds
  min_confidence_threshold: 0.3
  max_memory_usage: 0.9     # 90% of available memory
  max_decision_latency: 10  # 10 seconds max per decision

# Backtesting (for future implementation)
backtesting:
  start_date: "2024-01-01"
  end_date: "2024-12-31"
  initial_balance: 10000
  commission: 0.0002
  slippage: 0.0001

model_paths:
  realtime_model: "NN/models/saved/optimized_short_term_model_realtime_best.pt"
  ticks_model: "NN/models/saved/optimized_short_term_model_ticks_best.pt"
  backup_model: "NN/models/saved/realtime_ticks_checkpoints/checkpoint_epoch_50449_backup/model.pt"