feat(chat_v2): add MiniMax AI as LLM provider (default MiniMax-M3)

[octo-patch]

Summary

• Add MiniMax AI as a third model provider in the chat demo alongside Local (vLLM) and HeyWhale API
• Users can now select "MiniMax AI" from the Model Provider dropdown and use cloud-hosted MiniMax models without running a local model service
• Default model is MiniMax-M3 (512K context window, up to 128K output, image-input capable). MiniMax-M2.7 and MiniMax-M2.7-highspeed are still selectable via the model field
• Includes MiniMax-specific temperature clamping (0.01-1.0) and API key management in both backend and frontend

Changes

Backend (demo/chat_v2/backend_app/services/chat.py):

• _iter_minimax_stream(): new streaming function using OpenAI-compatible SDK with MiniMax base URL
• _normalize_minimax_temperature(): clamps temperature to MiniMax-accepted range [0.01, 1.0]
• Extended build_chat_runtime_config() with minimax provider routing, auto-defaults for API base and model (MiniMax-M3)
• Updated bot_stream() dispatch to route minimax provider to the new stream iterator

Frontend (demo/chat_v2/frontend/components/three-panel-interface.tsx):

• Added MiniMax AI option in Model Provider Select dropdown
• Added MiniMax API Key input with sessionStorage persistence
• Validation: blocks send if MiniMax is selected without API key
• Sends correct model name (MiniMax-M3) when MiniMax provider is active

Documentation (demo/chat_v2/README.md, demo/chat_v2/README_ZH.md):

• Listed MiniMax AI as a supported provider in features
• Default model documented as MiniMax-M3; alternatives MiniMax-M2.7 / MiniMax-M2.7-highspeed noted

Tests (demo/chat_v2/tests/test_minimax_provider.py):

• Replaced removed MiniMax-M2.5-highspeed example with MiniMax-M2.7-highspeed
• Default-model assertion updated to MiniMax-M3

Why MiniMax-M3 as the new default

MiniMax-M3 is the latest MiniMax model: 512K context window, up to 128K output, and image-input support — better suited to long data-analysis transcripts than M2.7 (192K context, 32K output).

Test plan

• Unit tests in demo/chat_v2/tests/test_minimax_provider.py updated to reflect new default model
• Integration tests in demo/chat_v2/tests/test_minimax_integration.py use MINIMAX_DEFAULT_MODEL (= MiniMax-M3) and continue to pass
• Manual: select MiniMax AI in UI, enter API key, send a data-analysis prompt — verifies MiniMax-M3 end-to-end
• Verify Local and HeyWhale providers still work unchanged

[LIUyizheSDU]

Is the API base https://api.minimaxi.com/v1? I’ve registered a MiniMax account, but my API key doesn’t work with https://api.minimaxi.io/v1.

[octo-patch]

Thanks for trying it out @LIUyizheSDU!

The correct API base URL for MiniMax is:

https://api.minimax.io/v1

Note: It's minimax.io, not minimaxi.com. The URL in the code should already be set correctly. If you're seeing issues, please double-check:

1. Your API key is valid (you can get one from the MiniMax platform)
2. The base URL in the configuration is https://api.minimax.io/v1

Let me know if you run into any other issues!