import { NextResponse } from 'next/server'
import { PrismaClient } from '@prisma/client'

const prisma = new PrismaClient()

// Generate enhanced recommendations based on automation insights
function generateEnhancedRecommendation(automationContext) {
  if (!automationContext) return null

  const { multiTimeframeSignals, topPatterns, marketContext } = automationContext
  
  // Multi-timeframe consensus
  const signals = multiTimeframeSignals.filter(s => s.decision)
  const bullishSignals = signals.filter(s => s.decision === 'BUY').length
  const bearishSignals = signals.filter(s => s.decision === 'SELL').length
  
  // Pattern strength
  const avgWinRate = signals.length > 0 ? 
    signals.reduce((sum, s) => sum + (s.winRate || 0), 0) / signals.length : 0
  
  // Profitability insights
  const avgProfit = topPatterns.length > 0 ?
    topPatterns.reduce((sum, p) => sum + Number(p.profitPercent || 0), 0) / topPatterns.length : 0

  let recommendation = '🤖 AUTOMATION-ENHANCED: '
  
  if (bullishSignals > bearishSignals) {
    recommendation += `BULLISH CONSENSUS (${bullishSignals}/${signals.length} timeframes)`
    if (avgWinRate > 60) recommendation += ` ✅ Strong pattern (${avgWinRate.toFixed(1)}% win rate)`
    if (avgProfit > 3) recommendation += ` 💰 High profit potential (~${avgProfit.toFixed(1)}%)`
  } else if (bearishSignals > bullishSignals) {
    recommendation += `BEARISH CONSENSUS (${bearishSignals}/${signals.length} timeframes)`
  } else {
    recommendation += 'NEUTRAL - Mixed signals across timeframes'
  }

  return recommendation
}

export async function GET(request) {
  try {
    const { searchParams } = new URL(request.url)
    const symbol = searchParams.get('symbol') || 'SOLUSD'

    console.log('🧠 Getting automation insights for manual analysis:', symbol)

    // Get recent automation sessions for context
    const sessions = await prisma.automationSession.findMany({
      where: {
        userId: 'default-user',
        symbol: symbol,
        lastAnalysisData: { not: null }
      },
      orderBy: { createdAt: 'desc' },
      take: 3
    })

    // Get top performing trades for pattern recognition
    const successfulTrades = await prisma.trade.findMany({
      where: {
        userId: 'default-user',
        symbol: symbol,
        status: 'COMPLETED',
        profit: { gt: 0 }
      },
      orderBy: { profit: 'desc' },
      take: 5
    })

    // Get recent market context
    const allTrades = await prisma.trade.findMany({
      where: {
        userId: 'default-user',
        symbol: symbol,
        status: 'COMPLETED'
      },
      orderBy: { createdAt: 'desc' },
      take: 10
    })

    const recentPnL = allTrades.reduce((sum, t) => sum + (t.profit || 0), 0)
    const winningTrades = allTrades.filter(t => (t.profit || 0) > 0)
    const winRate = allTrades.length > 0 ? (winningTrades.length / allTrades.length * 100) : 0

    const automationContext = {
      multiTimeframeSignals: sessions.map(s => ({
        timeframe: s.timeframe,
        decision: s.lastAnalysisData?.decision,
        confidence: s.lastAnalysisData?.confidence,
        sentiment: s.lastAnalysisData?.sentiment,
        winRate: s.winRate,
        totalPnL: s.totalPnL,
        totalTrades: s.totalTrades
      })),
      topPatterns: successfulTrades.map(t => ({
        side: t.side,
        profit: t.profit,
        confidence: t.confidence,
        entryPrice: t.price,
        exitPrice: t.exitPrice,
        profitPercent: t.exitPrice ? ((t.exitPrice - t.price) / t.price * 100).toFixed(2) : null
      })),
      marketContext: {
        recentPnL,
        winRate: winRate.toFixed(1),
        totalTrades: allTrades.length,
        avgProfit: allTrades.length > 0 ? (recentPnL / allTrades.length).toFixed(2) : 0,
        trend: sessions.length > 0 ? sessions[0].lastAnalysisData?.sentiment : 'NEUTRAL'
      }
    }

    const insights = {
      multiTimeframeConsensus: automationContext.multiTimeframeSignals.length > 0 ? 
        automationContext.multiTimeframeSignals[0].decision : null,
      avgConfidence: automationContext.multiTimeframeSignals.length > 0 ?
        (automationContext.multiTimeframeSignals.reduce((sum, s) => sum + (s.confidence || 0), 0) / automationContext.multiTimeframeSignals.length).toFixed(1) : null,
      marketTrend: automationContext.marketContext.trend,
      winRate: automationContext.marketContext.winRate + '%',
      profitablePattern: automationContext.topPatterns.length > 0 ? 
        `${automationContext.topPatterns[0].side} signals with avg ${automationContext.topPatterns.reduce((sum, p) => sum + Number(p.profitPercent || 0), 0) / automationContext.topPatterns.length}% profit` : null,
      recommendation: generateEnhancedRecommendation(automationContext),
      timeframeAnalysis: automationContext.multiTimeframeSignals,
      topPerformingPatterns: automationContext.topPatterns.slice(0, 3),
      marketMetrics: automationContext.marketContext
    }

    return NextResponse.json({
      success: true,
      symbol: symbol,
      automationInsights: insights,
      enhancementSummary: {
        timeframesAnalyzed: automationContext.multiTimeframeSignals.length,
        patternsFound: automationContext.topPatterns.length,
        totalTradesAnalyzed: automationContext.marketContext.totalTrades,
        overallConfidence: insights.avgConfidence ? insights.avgConfidence + '%' : 'N/A'
      },
      message: `🧠 Automation insights gathered for ${symbol} manual analysis enhancement`
    })

  } catch (error) {
    console.error('Error getting automation insights:', error)
    return NextResponse.json({
      success: false,
      error: 'Failed to get automation insights',
      message: error.message
    }, { status: 500 })
  }
}