feat: add MiniMax as first-class LLM provider

[octo-patch]

Summary

• Add MiniMax as a first-class LLM provider alongside OpenAI and LMStudio
• Support MiniMax-M2.7 and MiniMax-M2.7-highspeed models (1M context window, OpenAI-compatible API)
• Auto-detect MiniMax via MINIMAX_API_KEY / CC_MINIMAX_API_KEY environment variables
• Return static model list for MiniMax (no /v1/models endpoint available)
• Verify MiniMax API key via chat completions endpoint

Changes (9 files, 631 additions)

• backend/utils/globals.py: is_minimax_url(), MINIMAX_MODELS, env var support, auto-detect in apply_llm_env_defaults()
• backend/agent_factory.py: Default to MiniMax-M2.7 when base_url points to MiniMax API
• backend/controller/llm_api.py: Static MiniMax model list, key verification via chat completions
• README.md, README_CN.md: MiniMax configuration documentation (env vars + UI)
• tests/: 27 unit tests + 5 integration tests with ComfyUI runtime stubs

Test plan

• 27 unit tests pass (URL detection, constants, env defaults, agent factory)
• 5 integration tests pass (real MiniMax API: M2.7, M2.7-highspeed, temp=0, key verification)
• Manual test in ComfyUI with MiniMax API key

[CLAassistant]

All committers have signed the CLA.

[Jefsky]

Hi @octo-patch! Just a heads-up: the base_url https://api.minimax.io/v1 was tested in a related Pixelle-Video project and couldn't fetch the model list. The working URL is https://api.minimax.chat/v1 — that one successfully returns the model list (e.g. MiniMax-M2.7). You may want to update this PR to use the correct URL. Thanks!