feat: add MiniMax as LLM text completion provider

- Add MiniMax chat model provider using OpenAI-compatible API
- Support MiniMax-M2.7 and MiniMax-M2.7-highspeed models
- Temperature clamping to MiniMax valid range (0.0, 1.0]
- Streaming support with token usage tracking
- MINIMAX_API_KEY environment variable support
- Add text-completion-minimax entry point
- Add 15 unit tests and 3 integration tests
- Update README with MiniMax in LLM APIs list
This commit is contained in:
PR Bot 2026-03-24 18:19:00 +08:00
parent d30857b5c3
commit 50f24b8e2a
8 changed files with 960 additions and 4 deletions

View file

@ -108,6 +108,7 @@ text-completion-claude = "trustgraph.model.text_completion.claude:run"
text-completion-cohere = "trustgraph.model.text_completion.cohere:run"
text-completion-llamafile = "trustgraph.model.text_completion.llamafile:run"
text-completion-lmstudio = "trustgraph.model.text_completion.lmstudio:run"
text-completion-minimax = "trustgraph.model.text_completion.minimax:run"
text-completion-mistral = "trustgraph.model.text_completion.mistral:run"
text-completion-ollama = "trustgraph.model.text_completion.ollama:run"
text-completion-openai = "trustgraph.model.text_completion.openai:run"