Skip to content

feat: add MiniMax provider support#7

Open
octo-patch wants to merge 1 commit intokevinrgu:mainfrom
octo-patch:feature/add-minimax-provider
Open

feat: add MiniMax provider support#7
octo-patch wants to merge 1 commit intokevinrgu:mainfrom
octo-patch:feature/add-minimax-provider

Conversation

@octo-patch
Copy link
Copy Markdown

Summary

  • Add MiniMax chat model provider support to agent.py via OpenAI-compatible API
  • Auto-configure AsyncOpenAI client when MODEL starts with "MiniMax" (case-insensitive)
  • Support MINIMAX_API_KEY and optional MINIMAX_BASE_URL environment variables

How to use

Set MODEL = "MiniMax-M2.7" (or "MiniMax-M2.7-highspeed") in agent.py and add your key to .env:

MINIMAX_API_KEY=your-key-here

MiniMax uses an OpenAI-compatible API at https://api.minimax.io/v1, so no additional dependencies are required.

API Reference

Test plan

  • Unit tests: provider instantiation, default/custom base URL, missing API key error
  • Integration test: live call to MiniMax-M2.7 chat completions endpoint
  • Non-MiniMax models (gpt-5, gpt-4o) unaffected

- Add MiniMax chat model provider via OpenAI-compatible API
- Auto-configure AsyncOpenAI client when MODEL starts with "MiniMax"
- Support MINIMAX_API_KEY and MINIMAX_BASE_URL environment variables
- Add unit tests and integration test for MiniMax-M2.7
- Add pytest as optional dev dependency
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant