feat: add MiniMax provider support#28
Open
octo-patch wants to merge 1 commit into
Open
Conversation
Add MiniMax as a new OpenAI-compatible LLM provider, alongside the existing OpenAI / Gemini / DeepSeek / DashScope providers. - Add MiniMax client (models/llm_minimax.py) on the OpenAI-compatible Chat Completions API (base_url https://api.minimax.io/v1) - Register minimax provider config in backend config + config.yaml.example - Route minimax-* models to the MiniMax client in llm_client.py - Register MiniMax-M3 (flagship) and MiniMax-M2.7 in the model registry - Expose MiniMax provider in the frontend settings page and model groups - Document the provider in README / README_EN / SKILL.md - Add unit tests for provider config, registry, and model routing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Add MiniMax as a new LLM provider, compatible with the existing multi-provider architecture (OpenAI / Gemini / DeepSeek / DashScope). MiniMax uses an OpenAI-compatible Chat Completions API, so it slots in next to the existing
DeepSeek/GPTclients.Changes
backend/models/llm_minimax.py(OpenAI-compatible, base URLhttps://api.minimax.io/v1)minimaxprovider inbackend/config.pyandconfig.yaml.exampleminimax-*model names to the MiniMax client inbackend/models/llm_client.pyMiniMax-M3(flagship) andMiniMax-M2.7in the central model registry (backend/models/config_model.py), so they show up in the/api/modelsendpoint and the frontend selectorREADME.md/README_EN.md/SKILL.mdWhy
MiniMax-M3is the latest flagship model with a 1M context window, 128K max output, and image input, exposed through an OpenAI-compatible interface — a good fit for the script / storyboard LLM stages.Testing
pytest backend/tests/— 8 passed (provider config, model registry, routing)MiniMax-M3,MiniMax-M2.7) againsthttps://api.minimax.io/v1