- Add MiniMax-M3 to model list and set as default
- Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed
- Remove older models (M2.5/M2.5-highspeed)
- Update related tests
- Add MiniMax-M2.7 and MiniMax-M2.7-highspeed to model list
- Set MiniMax-M2.7 as default model
- Keep all previous models as alternatives
- Update related tests
- Add MiniMax model detection and compatibility handling in LLMClient
- Handle response_format incompatibility: MiniMax does not support
response_format parameter, use prompt engineering for JSON output
- Add temperature clamping for MiniMax (must be > 0)
- Add robust JSON parsing from LLM responses (parse_json_from_response)
- Update simulation_config_generator and oasis_profile_generator for
MiniMax compatibility
- Add MiniMax configuration examples in .env.example
- Add MiniMax documentation in README.md and README-EN.md
- Add unit tests for MiniMax compatibility functions
Supported models: MiniMax-M2.5, MiniMax-M2.5-highspeed
API docs: https://platform.minimax.io/docs/api-reference/text-openai-api
octo-patch
Octopus
PR Bot