test-dynamic-tokens.mjs

// Test script to verify dynamic max_tokens calculation
const { calculateSafeMaxTokens, estimateTokenCount } = require('./lib/openrouter.js');

console.log("Testing dynamic max_tokens calculation:\n");

// Mock model scenarios based on real OpenRouter models
const testScenarios = [
  {
    name: "DeepSeek V3 (High context)",
    contextLength: 131072,
    maxCompletionTokens: 8192,
    inputText: "System prompt and large HTML content with about 5000 tokens worth of text"
  },
  {
    name: "Claude 3.5 Sonnet",
    contextLength: 200000,
    maxCompletionTokens: 8192,
    inputText: "System prompt with moderate HTML content"
  },
  {
    name: "GPT-4 Turbo",
    contextLength: 128000,
    maxCompletionTokens: 4096,
    inputText: "System prompt with small context"
  }
];

testScenarios.forEach((scenario, index) => {
  const estimatedInputTokens = estimateTokenCount(scenario.inputText + "x".repeat(Math.random() * 10000));
  const safeMaxTokens = calculateSafeMaxTokens(
    scenario.contextLength,
    estimatedInputTokens,
    scenario.maxCompletionTokens
  );
  
  const totalUsage = estimatedInputTokens + safeMaxTokens;
  const usagePercentage = ((totalUsage / scenario.contextLength) * 100).toFixed(1);
  
  console.log(`${index + 1}. ${scenario.name}:`);
  console.log(`   Context Length: ${scenario.contextLength.toLocaleString()}`);
  console.log(`   Max Completion: ${scenario.maxCompletionTokens.toLocaleString()}`);
  console.log(`   Input Tokens:   ${estimatedInputTokens.toLocaleString()}`);
  console.log(`   Safe Max Out:   ${safeMaxTokens.toLocaleString()}`);
  console.log(`   Total Usage:    ${totalUsage.toLocaleString()} (${usagePercentage}%)`);
  console.log(`   Within Limit:   ${totalUsage <= scenario.contextLength ? '✅' : '❌'}`);
  console.log('');
});

console.log("✅ Dynamic max_tokens calculation test completed!");