Skip to content

feat: upgrade MiniMax default model to M3#328

Open
octo-patch wants to merge 1 commit into
vxcontrol:mainfrom
octo-patch:feature/upgrade-minimax-m3
Open

feat: upgrade MiniMax default model to M3#328
octo-patch wants to merge 1 commit into
vxcontrol:mainfrom
octo-patch:feature/upgrade-minimax-m3

Conversation

@octo-patch
Copy link
Copy Markdown
Contributor

Summary

Add MiniMax provider to PentAGI with MiniMax-M3 as the default model, keeping MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives.

Changes

  • Add new MiniMax provider package (backend/pkg/providers/minimax/) implementing the provider.Provider interface via the OpenAI-compatible https://api.minimax.io/v1 endpoint.
  • Set MiniMax-M3 as the default model for all agent types (simple, primary_agent, assistant, generator, refiner, adviser, reflector, searcher, enricher, coder, installer, pentester).
  • Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed in the model list as alternatives.
  • Register ProviderMiniMax type, DefaultProviderNameMiniMax name, and wire the provider into NewProviderController / NewProvider / buildProviderFromConfig / buildProviderFromConfig / GetProvider paths.
  • Add env vars MINIMAX_API_KEY, MINIMAX_SERVER_URL (default https://api.minimax.io/v1), MINIMAX_PROVIDER and the matching secret pattern.
  • Add provider.ProviderMiniMax to the Valid() whitelist in pkg/server/models/providers.go (required for REST API acceptance).
  • Unit tests covering config loading, default-model sanity, models list (M3 first, no legacy M1/M2/M2.1/M2.5), model prefix behaviour, and missing-API-key error.

Why

MiniMax-M3 is MiniMax's latest flagship model (512K context, 128K max output, image input support) and is the right default for a security-testing workload that benefits from large context and multimodal input. MiniMax-M2.7 and its high-speed variant are retained for users who want to pin to the previous generation.

Model list

  • MiniMax-M3 (default) — 512K context, 128K output, image input, input $0.60 / output $2.40 per 1M tokens
  • MiniMax-M2.7 — input $0.40 / output $1.10
  • MiniMax-M2.7-highspeed — input $0.40 / output $1.10

No legacy models (MiniMax-M1 / MiniMax-M2 / MiniMax-M2.1 / MiniMax-M2.5) are included.

API docs

Testing

  • go test ./pkg/providers/minimax/... — 7/7 passing (config loading, provider type, models list with M3 as first entry, prefix behaviour, missing key, usage extraction).
  • go build ./pkg/providers/minimax/... — clean.

- Add MiniMax provider with M3 as the default model (512K context, 128K max output, image input support)
- Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives
- Configure agent defaults (simple, primary_agent, assistant, generator, etc.) on M3
- Register MiniMax provider type, env vars (MINIMAX_API_KEY, MINIMAX_SERVER_URL, MINIMAX_PROVIDER)
- Add unit tests covering config loading, models list, prefix behavior, and missing API key
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.

1 participant