feat: upgrade MiniMax provider to OpenAI-compatible API with M2.7 models

[octo-patch]

Summary

Upgrade the existing MiniMax model worker from the legacy api.minimax.chat endpoint to the new OpenAI-compatible Chat Completions API at api.minimax.io/v1, with support for the latest MiniMax-M2.7 models.

Changes

• Upgrade MiniMaxWorker to use OpenAI-compatible /v1/chat/completions endpoint
• Update model: from legacy abab5.5-chat to MiniMax-M2.7 (204K context) and MiniMax-M2.7-highspeed
• Standard message format: Use OpenAI-style role/content instead of legacy sender_type/text
• Temperature clamping: Enforce MiniMax's valid range (0.0, 1.0]
• Environment variable: Support MINIMAX_API_KEY for API authentication
• Remove legacy dependencies: No more GroupId, no more chatcompletion_pro URL patterns
• Config examples: Add MiniMax entry in model_config.py.example and server_config.py.example
• README: Add MiniMax-M2.7 to the supported models table
• Tests: 29 unit tests + 3 integration tests

Files Changed

File	Description
examples/model_workers/minimax.py	Upgraded worker implementation
configs/model_config.py.example	Added minimax-api config entry
configs/server_config.py.example	Added minimax-api worker port
README.md / README_en.md	Added MiniMax-M2.7 to models table
tests/test_minimax_worker.py	Unit + integration tests

API Reference

• Chat (OpenAI Compatible): https://platform.minimax.io/docs/api-reference/text-openai-api
• Pricing: https://platform.minimax.io/docs/guides/pricing-paygo

MiniMax Models

Model	Context	Description
MiniMax-M2.7	204K	Peak Performance. Ultimate Value. Master the Complex
MiniMax-M2.7-highspeed	204K	Same performance, faster and more agile

Configuration Example

ONLINE_LLM_MODEL = {
    "minimax-api": {
        "version": "MiniMax-M2.7",
        "api_base_url": "https://api.minimax.io/v1",
        "api_key": os.environ.get("MINIMAX_API_KEY", ""),
        "provider": "MiniMaxWorker",
    },
}