feature about responses api

[caozhiyuan]

This pull request introduces a new configuration system, structured logging, and support for the /v1/responses endpoint, along with improvements to model selection and request handling. The most important changes are grouped below:
Responses API Integration

• Added full support for the /v1/responses endpoint, including a new handler (src/routes/responses/handler.ts) that validates model support, streams or returns results, and logs all activity.
• Enhanced src/routes/messages/handler.ts to route requests to the Responses API when supported by the selected model, including translation logic for payloads and results. [1] [2]

Configuration System

• Added src/lib/config.ts to provide persistent configuration management, including default prompts, small model selection, and reasoning effort levels for models. This enables dynamic model selection and custom prompt injection.
• Updated src/lib/paths.ts to include a path for the configuration file and ensure its existence at startup.

Structured Logging

• Implemented a robust logging system in src/lib/logger.ts that supports per-handler log files, log rotation, and verbosity control, replacing direct consola usage in request handlers.
• Refactored request handlers in src/routes/chat-completions/handler.ts and src/routes/messages/handler.ts to use the new logger, improving log clarity and manageability. [1] [2] [3] [4] [5] [6] [7] [8] [9]

Model Selection and Request Handling

• Improved model selection logic to force the use of a "small" model for certain requests (e.g., warmup requests without tools) to optimize resource usage. [1] [2]
• Added a verbose flag to the global state object to control logging verbosity across the application.

Documentation

• Updated the API documentation in README.md to include the new /v1/responses endpoint and clarify its purpose.