feat: add MiniMax as first-class LLM provider#123
Open
octo-patch wants to merge 1 commit intoEladlev:mainfrom
Open
feat: add MiniMax as first-class LLM provider#123octo-patch wants to merge 1 commit intoEladlev:mainfrom
octo-patch wants to merge 1 commit intoEladlev:mainfrom
Conversation
Add MiniMax (M2.7 / M2.7-highspeed / M2.5 / M2.5-highspeed) as a supported LLM provider via OpenAI-compatible API. MiniMax models offer 1M context windows and can be used for both meta-prompt refinement and prediction. Changes: - utils/config.py: Add MiniMax branch in get_llm() with temperature clamping (0,1] and configurable API key/base URL - utils/llm_chain.py: Enable structured output and OpenAI cost tracking callback for MiniMax provider - config/llm_env.yml: Add minimax credentials section - config/config_default.yml: Document MiniMax in provider comment - docs/installation.md: Add MiniMax configuration instructions - README.md: Mention MiniMax in supported providers - tests/: 16 unit tests + 3 integration tests
Eladlev
approved these changes
Mar 26, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 first-class LLM provider for AutoPrompt, enabling users to leverage MiniMax M2.7 and M2.5 series models for both prompt optimization (meta-prompt LLM) and prediction tasks.
Changes
utils/config.py: Addminimaxbranch inget_llm()factory usingChatOpenAIwith OpenAI-compatible API endpoint (https://api.minimax.io/v1). Temperature is clamped to (0.0, 1.0] per MiniMax API requirements.utils/llm_chain.py: Enable structured output support (with_structured_output) and OpenAI cost tracking callback for MiniMax provider.config/llm_env.yml: Addminimaxcredentials section withMINIMAX_API_KEYandMINIMAX_API_BASE.config/config_default.yml: Add MiniMax to the supported provider list comment.docs/installation.md: Add MiniMax configuration instructions with example YAML snippets.README.md: Mention MiniMax in the supported LLM providers list.Supported Models
Usage
Test plan