Added MAX_TOKENS and MAX_RESPONSE_SEGMENTS to .env.example and documentation. Updated constants to read from environment variables, allowing configuration of token and response segment limits.
Introduces new provider modules for DouBao, Ernie, Kimi, Qwen, and ZhiPu, and registers them in the LLM registry. Updates documentation and .env.example to include configuration instructions for these providers. Refactors OpenAI provider to support OpenAI-compatible endpoints. Adds @ai-sdk/openai-compatible and node-fetch dependencies.
