- Updated console log messages in cost.ts and proxy.ts for clarity and consistency.
- Added important SSRF warning in README.md regarding localhost access issues with certain clients, along with solutions using external proxy services.
- Created a new .env.example file with default environment variables for PORT, OPENAI_UPSTREAM_URL, ANTHROPIC_UPSTREAM_URL, and DATABASE_URL.
- Updated .npmignore to exclude all .env files except .env.example.
- Revised CONTRIBUTING.md to simplify the contribution process and provide clearer setup instructions.
- Enhanced cost.ts with detailed type definitions and improved cost calculation logic.
- Updated proxy.ts to include new environment variables and improved logging functionality.
- Modified README.md to reflect new configuration instructions and usage examples.
- Removed unnecessary dashboard files and streamlined the project structure.
Add a lightweight Next.js dashboard to visualize OpenProxy metrics in real-time. The dashboard provides comprehensive insights into LLM API usage, costs, and performance.
Features:
- Real-time metrics overview (requests, tokens, costs, response times)
- Model breakdown with usage statistics
- Hourly trends visualization with charts
- Recent requests table with detailed information
- Auto-refresh every 30 seconds
- Configurable time ranges (1h, 6h, 24h, 7d)
Technical details:
- Built with Next.js 14 and React 18
- Uses Recharts for data visualization
- Connects directly to PostgreSQL database
- Runs on port 3008 by default
- TypeScript for type safety
- Minimal dependencies for lightweight deployment
The dashboard complements the proxy server by providing a user-friendly interface for monitoring and analyzing LLM API usage patterns.
