cim_summary/backend/debug-llm-service.js

const { OpenAI } = require('openai');
require('dotenv').config();

const openai = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});

function extractJsonFromResponse(content) {
  try {
    console.log('🔍 Extracting JSON from content...');
    console.log('📄 Content preview:', content.substring(0, 200) + '...');
    
    // First, try to find JSON within ```json ... ```
    const jsonMatch = content.match(/```json\n([\s\S]*?)\n```/);
    if (jsonMatch && jsonMatch[1]) {
      console.log('✅ Found JSON in ```json block');
      const parsed = JSON.parse(jsonMatch[1]);
      console.log('✅ JSON parsed successfully');
      return parsed;
    }

    // Try to find JSON within ``` ... ```
    const codeBlockMatch = content.match(/```\n([\s\S]*?)\n```/);
    if (codeBlockMatch && codeBlockMatch[1]) {
      console.log('✅ Found JSON in ``` block');
      const parsed = JSON.parse(codeBlockMatch[1]);
      console.log('✅ JSON parsed successfully');
      return parsed;
    }

    // If that fails, fall back to finding the first and last curly braces
    const startIndex = content.indexOf('{');
    const endIndex = content.lastIndexOf('}');
    if (startIndex === -1 || endIndex === -1) {
      throw new Error('No JSON object found in response');
    }

    console.log('✅ Found JSON using brace matching');
    const jsonString = content.substring(startIndex, endIndex + 1);
    const parsed = JSON.parse(jsonString);
    console.log('✅ JSON parsed successfully');
    return parsed;
  } catch (error) {
    console.error('❌ JSON extraction failed:', error.message);
    console.error('📄 Full content:', content);
    throw new Error(`JSON extraction failed: ${error instanceof Error ? error.message : 'Unknown error'}`);
  }
}

async function testLLMService() {
  try {
    console.log('🤖 Testing LLM service logic...');
    
    // Simulate the exact prompt from the service
    const systemPrompt = `You are a financial analyst tasked with analyzing CIM (Confidential Information Memorandum) documents. You must respond with ONLY a valid JSON object that follows the exact structure provided. Do not include any other text, explanations, or markdown formatting.`;
    
    const prompt = `Please analyze the following CIM document and generate a JSON object based on the provided structure.

CIM Document Text:
This is a test CIM document for STAX, a technology company focused on digital transformation solutions. The company operates in the software-as-a-service sector with headquarters in San Francisco, CA. STAX provides cloud-based enterprise software solutions to Fortune 500 companies.

Your response MUST be a single, valid JSON object that follows this exact structure. Do not include any other text.
JSON Structure to Follow:
\`\`\`json
{
  "dealOverview": {
    "targetCompanyName": "Target Company Name",
    "industrySector": "Industry/Sector",
    "geography": "Geography (HQ & Key Operations)",
    "dealSource": "Deal Source",
    "transactionType": "Transaction Type",
    "dateCIMReceived": "Date CIM Received",
    "dateReviewed": "Date Reviewed",
    "reviewers": "Reviewer(s)",
    "cimPageCount": "CIM Page Count",
    "statedReasonForSale": "Stated Reason for Sale (if provided)"
  },
  "businessDescription": {
    "coreOperationsSummary": "Core Operations Summary (3-5 sentences)",
    "keyProductsServices": "Key Products/Services & Revenue Mix (Est. % if available)",
    "uniqueValueProposition": "Unique Value Proposition (UVP) / Why Customers Buy",
    "customerBaseOverview": {
      "keyCustomerSegments": "Key Customer Segments/Types",
      "customerConcentrationRisk": "Customer Concentration Risk (Top 5 and/or Top 10 Customers as % Revenue - if stated/inferable)",
      "typicalContractLength": "Typical Contract Length / Recurring Revenue % (if applicable)"
    },
    "keySupplierOverview": {
      "dependenceConcentrationRisk": "Dependence/Concentration Risk"
    }
  },
  "marketIndustryAnalysis": {
    "estimatedMarketSize": "Estimated Market Size (TAM/SAM - if provided)",
    "estimatedMarketGrowthRate": "Estimated Market Growth Rate (% CAGR - Historical & Projected)",
    "keyIndustryTrends": "Key Industry Trends & Drivers (Tailwinds/Headwinds)",
    "competitiveLandscape": {
      "keyCompetitors": "Key Competitors Identified",
      "targetMarketPosition": "Target's Stated Market Position/Rank",
      "basisOfCompetition": "Basis of Competition"
    },
    "barriersToEntry": "Barriers to Entry / Competitive Moat (Stated/Inferred)"
  },
  "financialSummary": {
    "financials": {
      "fy3": {
        "revenue": "Revenue amount for FY-3",
        "revenueGrowth": "N/A (baseline year)",
        "grossProfit": "Gross profit amount for FY-3",
        "grossMargin": "Gross margin % for FY-3",
        "ebitda": "EBITDA amount for FY-3",
        "ebitdaMargin": "EBITDA margin % for FY-3"
      },
      "fy2": {
        "revenue": "Revenue amount for FY-2",
        "revenueGrowth": "Revenue growth % for FY-2",
        "grossProfit": "Gross profit amount for FY-2",
        "grossMargin": "Gross margin % for FY-2",
        "ebitda": "EBITDA amount for FY-2",
        "ebitdaMargin": "EBITDA margin % for FY-2"
      },
      "fy1": {
        "revenue": "Revenue amount for FY-1",
        "revenueGrowth": "Revenue growth % for FY-1",
        "grossProfit": "Gross profit amount for FY-1",
        "grossMargin": "Gross margin % for FY-1",
        "ebitda": "EBITDA amount for FY-1",
        "ebitdaMargin": "EBITDA margin % for FY-1"
      },
      "ltm": {
        "revenue": "Revenue amount for LTM",
        "revenueGrowth": "Revenue growth % for LTM",
        "grossProfit": "Gross profit amount for LTM",
        "grossMargin": "Gross margin % for LTM",
        "ebitda": "EBITDA amount for LTM",
        "ebitdaMargin": "EBITDA margin % for LTM"
      }
    },
    "qualityOfEarnings": "Quality of earnings/adjustments impression",
    "revenueGrowthDrivers": "Revenue growth drivers (stated)",
    "marginStabilityAnalysis": "Margin stability/trend analysis",
    "capitalExpenditures": "Capital expenditures (LTM % of revenue)",
    "workingCapitalIntensity": "Working capital intensity impression",
    "freeCashFlowQuality": "Free cash flow quality impression"
  },
  "managementTeamOverview": {
    "keyLeaders": "Key Leaders Identified (CEO, CFO, COO, Head of Sales, etc.)",
    "managementQualityAssessment": "Initial Assessment of Quality/Experience (Based on Bios)",
    "postTransactionIntentions": "Management's Stated Post-Transaction Role/Intentions (if mentioned)",
    "organizationalStructure": "Organizational Structure Overview (Impression)"
  },
  "preliminaryInvestmentThesis": {
    "keyAttractions": "Key Attractions / Strengths (Why Invest?)",
    "potentialRisks": "Potential Risks / Concerns (Why Not Invest?)",
    "valueCreationLevers": "Initial Value Creation Levers (How PE Adds Value)",
    "alignmentWithFundStrategy": "Alignment with Fund Strategy (BPCP is focused on companies in 5+MM EBITDA range in consumer and industrial end markets. M&A, increased technology & data usage, supply chain and human capital optimization are key value-levers. Also a preference companies which are founder / family-owned and within driving distance of Cleveland and Charlotte.)"
  },
  "keyQuestionsNextSteps": {
    "criticalQuestions": "Critical Questions Arising from CIM Review",
    "missingInformation": "Key Missing Information / Areas for Diligence Focus",
    "preliminaryRecommendation": "Preliminary Recommendation",
    "rationaleForRecommendation": "Rationale for Recommendation (Brief)",
    "proposedNextSteps": "Proposed Next Steps"
  }
}
\`\`\`

IMPORTANT: Replace all placeholder text with actual information from the CIM document. If information is not available, use "Not specified in CIM". Ensure all financial metrics are properly formatted as strings.`;

    const messages = [];
    if (systemPrompt) {
      messages.push({ role: 'system', content: systemPrompt });
    }
    messages.push({ role: 'user', content: prompt });

    console.log('📤 Sending request to OpenAI...');
    const response = await openai.chat.completions.create({
      model: 'gpt-4o',
      messages,
      max_tokens: 4000,
      temperature: 0.1,
    });

    console.log('📥 Received response from OpenAI');
    const content = response.choices[0].message.content;
    
    console.log('📄 Raw response content:');
    console.log(content);
    
    // Extract JSON
    const jsonOutput = extractJsonFromResponse(content);
    
    console.log('✅ JSON extraction successful');
    console.log('📊 Extracted JSON structure:');
    console.log('- dealOverview:', jsonOutput.dealOverview ? 'Present' : 'Missing');
    console.log('- businessDescription:', jsonOutput.businessDescription ? 'Present' : 'Missing');
    console.log('- marketIndustryAnalysis:', jsonOutput.marketIndustryAnalysis ? 'Present' : 'Missing');
    console.log('- financialSummary:', jsonOutput.financialSummary ? 'Present' : 'Missing');
    console.log('- managementTeamOverview:', jsonOutput.managementTeamOverview ? 'Present' : 'Missing');
    console.log('- preliminaryInvestmentThesis:', jsonOutput.preliminaryInvestmentThesis ? 'Present' : 'Missing');
    console.log('- keyQuestionsNextSteps:', jsonOutput.keyQuestionsNextSteps ? 'Present' : 'Missing');
    
    // Test validation (simplified)
    const requiredFields = [
      'dealOverview', 'businessDescription', 'marketIndustryAnalysis', 
      'financialSummary', 'managementTeamOverview', 'preliminaryInvestmentThesis', 
      'keyQuestionsNextSteps'
    ];
    
    const missingFields = requiredFields.filter(field => !jsonOutput[field]);
    if (missingFields.length > 0) {
      console.log('❌ Missing required fields:', missingFields);
    } else {
      console.log('✅ All required fields present');
    }
    
  } catch (error) {
    console.error('❌ Error:', error.message);
  }
}

testLLMService();