Skip to content

feat: add MiniMax provider support#278

Closed
octo-patch wants to merge 3 commits into
KeygraphHQ:mainfrom
octo-patch:feature/add-minimax-provider
Closed

feat: add MiniMax provider support#278
octo-patch wants to merge 3 commits into
KeygraphHQ:mainfrom
octo-patch:feature/add-minimax-provider

Conversation

@octo-patch
Copy link
Copy Markdown

Summary

Adds MiniMax as a provider option in Shannon's router mode, enabling users to use MiniMax models as an alternative to Anthropic Claude.

Changes

  • apps/cli/infra/router-config.json: Add minimax provider entry with OpenAI-compatible API endpoint (https://api.minimax.io/v1/chat/completions) and models MiniMax-M2.7 and MiniMax-M2.7-highspeed
  • apps/cli/infra/compose.yml: Pass MINIMAX_API_KEY environment variable to the router container
  • .env.example: Document MiniMax configuration option and available models

Usage

To use MiniMax with Shannon router mode:

# In your .env file:
MINIMAX_API_KEY=your-minimax-api-key
ROUTER_DEFAULT=minimax,MiniMax-M2.7

# Start with router mode:
./shannon start ... ROUTER=true

MiniMax Models

Model Description
MiniMax-M2.7 Peak Performance. Ultimate Value. Master the Complex
MiniMax-M2.7-highspeed Same performance, faster and more agile

API reference:

@ezl-keygraph
Copy link
Copy Markdown
Collaborator

Thanks for the PR. This builds on router mode (router-config.json, ROUTER_DEFAULT), which has since been removed from Shannon.

Note that only Claude models are officially supported; non-Claude models such as MiniMax may not reliably follow Shannon's instructions or tool-use constraints, so results may be unstable.

Closing this PR, thanks again.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants