Advanced Features

const costlens = new CostLens({ 
  apiKey: process.env.COSTLENS_API_KEY,
  enableCache: true  // Enable caching globally
});

const tracked = costlens.wrapOpenAI(openai);

// Cache this specific request for 1 hour
const result = await tracked.chat.completions.create(
  { model: 'gpt-4', messages: [...] },
  { cacheTTL: 3600000 }  // 1 hour in milliseconds
);

// Second identical call returns cached result instantly
const cached = await tracked.chat.completions.create(
  { model: 'gpt-4', messages: [...] },
  { cacheTTL: 3600000 }
);

// Clear cache when needed
costlens.clearCache();

const costlens = new CostLens({ 
  apiKey: process.env.COSTLENS_API_KEY,
  maxRetries: 3  // Retry up to 3 times
});

// Automatically retries on 5xx errors with backoff: 1s, 2s, 4s
const tracked = costlens.wrapOpenAI(openai);
const result = await tracked.chat.completions.create({
  model: 'gpt-4',
  messages: [...]
});
// ✅ Handles transient failures automatically

const costlens = new CostLens({
  apiKey: process.env.COSTLENS_API_KEY,
  middleware: [
    {
      // Run before API call
      before: async (params) => {
        console.log('Making API call with model:', params.model);
        // Modify params if needed
        params.temperature = params.temperature || 0.7;
        return params;
      },
      
      // Run after successful API call
      after: async (result) => {
        console.log('Tokens used:', result.usage?.total_tokens);
        // Transform result if needed
        return result;
      },
      
      // Run on error
      onError: async (error) => {
        console.error('API call failed:', error.message);
        // Send to error tracking service
      }
    }
  ]
});

const tracked = costlens.wrapOpenAI(openai);

const stream = await tracked.chat.completions.stream({
  model: 'gpt-4',
  messages: [{ role: 'user', content: 'Tell me a long story' }]
});

// Stream chunks to user
for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content || '';
  process.stdout.write(content);
}

// ✅ Automatically tracked after stream completes
// Includes full content and estimated token count

// Track multiple calls in one request
await costlens.trackBatch([
  { provider: 'openai', model: 'gpt-4', tokens: 100, latency: 500 },
  { provider: 'openai', model: 'gpt-3.5-turbo', tokens: 50, latency: 200 },
  { provider: 'anthropic', model: 'claude-3-opus', tokens: 150, latency: 600 }
]);

// Useful for background jobs or bulk processing

const tracked = costlens.wrapOpenAI(openai);

// Tag with promptId for analytics
const result = await tracked.chat.completions.create(
  { model: 'gpt-4', messages: [...] },
  { promptId: 'customer-support-v2' }
);

// View analytics grouped by promptId in dashboard
// Compare performance across different prompt versions

interface CostLensConfig {
  apiKey: string;           // Required: Your API key
  baseUrl?: string;         // Optional: Custom endpoint
  enableCache?: boolean;    // Optional: Enable caching (default: false)
  maxRetries?: number;      // Optional: Max retry attempts (default: 3)
  middleware?: Middleware[]; // Optional: Custom middleware
}

interface Middleware {
  before?: (params: any) => Promise<any>;
  after?: (result: any) => Promise<any>;
  onError?: (error: Error) => Promise<void>;
}