feat: add MiniMax as a first-class LLM provider (M3 default)#88
Open
octo-patch wants to merge 2 commits into
Open
feat: add MiniMax as a first-class LLM provider (M3 default)#88octo-patch wants to merge 2 commits into
octo-patch wants to merge 2 commits into
Conversation
Add MiniMax AI (M2.7, M2.7-highspeed) as a third provider option alongside OpenAI and Azure OpenAI. MiniMax uses an OpenAI-compatible API, so it integrates cleanly with the existing openai library. Changes: - Provider detection via OPENAI_API_TYPE=minimax or auto-detection when MINIMAX_API_KEY is set without OPENAI_API_KEY - Temperature clamping to MiniMax's (0, 1] range - Default model list: MiniMax-M2.7 and MiniMax-M2.7-highspeed - .env.minimax-example configuration template - README section with MiniMax setup instructions - 14 unit tests + 3 integration tests
- Add MiniMax-M3 to model list and set as default (first entry) - Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives - Update README to describe M3 (512K context, 128K output, image input) - Update tests to cover M3 in defaults and integration
octo-patch
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 AI as a third LLM provider alongside OpenAI and Azure OpenAI. MiniMax models (M3, M2.7, M2.7-highspeed) are supported via the OpenAI-compatible API, integrating cleanly with the existing
openailibrary.Changes
OPENAI_API_TYPE=minimaxor auto-detection whenMINIMAX_API_KEYis set withoutOPENAI_API_KEYhttps://api.minimax.io/v1) configured as the default base URL; uses standardmodelparameter(0, 1]MiniMax-M3(default),MiniMax-M2.7, andMiniMax-M2.7-highspeed, customizable viaMINIMAX_MODELSenv var.env.minimax-examplewith all MiniMax configuration optionsAbout MiniMax-M3
MiniMax-M3is the latest MiniMax model: 512K context window, up to 128K output, and image input support. It is now the default;MiniMax-M2.7andMiniMax-M2.7-highspeedremain available for users who want to pin to the previous generation.Files Changed
gpt_code_ui/webapp/main.py.env.minimax-exampleREADME.mdtests/__init__.pytests/test_minimax_provider.pytests/test_minimax_integration.pyMINIMAX_API_KEY); covers M3, M2.7, M2.7-highspeedTest Plan
python -m unittest tests.test_minimax_provider)OPENAI_API_TYPE=minimaxand rungptcode; verify M3 is the default model in the UI