trading_bot_v3/.github/copilot-instructions.md

AI-Powered Trading Bot Dashboard

This is a Next.js 15 App Router application with TypeScript, Tailwind CSS, and API routes. It's a production-ready trading bot with AI analysis, automated screenshot capture, and real-time trading execution via Drift Protocol and Jupiter DEX.

Core Architecture

Dual-Session Screenshot Automation

• AI Layout: Z1TzpUrf - RSI (top), EMAs, MACD (bottom)
• DIY Layout: vWVvjLhP - Stochastic RSI (top), VWAP, OBV (bottom)
• Parallel browser sessions for multi-layout capture in lib/enhanced-screenshot.ts
• TradingView automation with session persistence in lib/tradingview-automation.ts

AI Analysis Pipeline

• OpenAI GPT-4o mini for cost-effective chart analysis (~$0.006 per analysis)
• Multi-layout comparison and consensus detection
• Professional trading setups with exact entry/exit levels and risk management
• Layout-specific indicator analysis (RSI vs Stochastic RSI, MACD vs OBV)

Trading Integration

• Drift Protocol: Perpetual futures trading via @drift-labs/sdk
• Jupiter DEX: Spot trading on Solana
• Position management and P&L tracking
• Real-time account balance and collateral monitoring

Critical Development Patterns

Docker Environment

Use Docker for consistency: npm run docker:dev (port 9001) or npm run docker:up (port 9000)

• Multi-stage builds with browser automation optimizations
• Session persistence via volume mounts
• Chromium path: /usr/bin/chromium

API Route Structure

// Enhanced screenshot with progress tracking
POST /api/enhanced-screenshot
{
  symbol: "SOLUSD", 
  timeframe: "240", 
  layouts: ["ai", "diy"],
  analyze: true
}

// Returns: { screenshots, analysis, sessionId }

Progress Tracking System

• lib/progress-tracker.ts manages real-time analysis progress
• SessionId-based tracking for multi-step operations
• Steps: init → auth → navigation → loading → capture → analysis

Timeframe Mapping

Critical: Always use minute values first to avoid TradingView confusion

'4h': ['240', '240m', '4h', '4H'] // 240 minutes FIRST, not "4h"
'1h': ['60', '60m', '1h', '1H']   // 60 minutes FIRST

Component Architecture

• components/AIAnalysisPanel.tsx - Multi-timeframe analysis interface
• components/Dashboard.tsx - Main trading dashboard with real Drift positions
• components/AdvancedTradingPanel.tsx - Drift Protocol trading interface
• Layout: app/layout.js with gradient styling and navigation

Environment Variables

OPENAI_API_KEY=        # Required for AI analysis
TRADINGVIEW_EMAIL=     # Required for automation
TRADINGVIEW_PASSWORD=  # Required for automation
SOLANA_RPC_URL=        # Drift trading
DRIFT_PRIVATE_KEY=     # Drift trading (base58 encoded)

Build & Development Commands

# Development (recommended)
npm run docker:dev         # Port 9001, hot reload
npm run docker:logs        # View container logs
npm run docker:exec        # Shell access

# Production deployment  
npm run docker:prod:up     # Port 9000, optimized build

# Testing automation
node test-enhanced-screenshot.js  # Test dual-session capture
./test-docker-comprehensive.sh    # Full system test

Code Style Guidelines

• Use "use client" for client components with state/effects
• Tailwind with gradient backgrounds and glassmorphism effects
• TypeScript interfaces for all trading parameters and API responses
• Error handling with detailed logging for browser automation
• Session persistence to avoid TradingView captchas

Key Integration Points

• Session data: .tradingview-session/ (volume mounted)
• Screenshots: screenshots/ directory
• Progress tracking: EventEmitter-based real-time updates
• Database: Prisma with SQLite (file:./prisma/dev.db)

Generate code that follows these patterns and integrates seamlessly with the existing trading infrastructure.