feat: add MiniMax as a first-class chat model provider

[octo-patch]

Summary

Add MiniMax as a first-class chat model provider with a dedicated minimax/chat kind that handles MiniMax-specific API constraints.

Changes

• Add minimax/chat kind to the chat routing in http-api-bindings
• Add MiniMax-specific request processing in ExtendedOpenAIConfig:
  • Temperature clamping to valid range (0.0, 1.0] (defaults to 1.0)
• Add 6 unit tests for temperature clamping and model fallback
• Add documentation page with configuration examples (global and China endpoints)

Supported Models

Model	Context Length	Max Output
MiniMax-M2.7	204K	192K
MiniMax-M2.7-highspeed	204K	192K

Configuration Example

[model.chat.http]
kind = "minimax/chat"
model_name = "MiniMax-M2.7"
api_endpoint = "https://api.minimax.io/v1"
api_key = "your-minimax-api-key"

API Documentation

• OpenAI Compatible: https://platform.minimax.io/docs/api-reference/text-openai-api