Skip to content

feat(provider): add MiniMax regional support - #366

Open
octo-patch wants to merge 2 commits into
NVIDIA:mainfrom
octo-patch:octo/20260812-provider-add-recvs0kphjyPs8
Open

feat(provider): add MiniMax regional support#366
octo-patch wants to merge 2 commits into
NVIDIA:mainfrom
octo-patch:octo/20260812-provider-add-recvs0kphjyPs8

Conversation

@octo-patch

Copy link
Copy Markdown

Reason: Add a first-class MiniMax provider with current models and regional endpoint selection.

This change:

  • adds MiniMax-M3 and MiniMax-M2.7 with their current context windows
  • selects the global or China endpoint through MINIMAX_REGION, with an explicit URL override available
  • registers the provider in the runtime selector and documents its environment configuration
  • prevents the MiniMax credential from reaching local CLI subprocesses and recognizes it in credential-exfiltration scans
  • adds focused coverage for credentials, both regions, endpoint overrides, model metadata, chat construction, selection, and credential scrubbing

Checks:

  • uv run pytest -q tests/unit/test_providers.py tests/unit/test_minimax_provider.py
  • uv run pytest -q tests/unit/test_agent_cli.py
  • uv run ruff check src/skillspector/providers/minimax tests/unit/test_minimax_provider.py src/skillspector/providers/__init__.py src/skillspector/providers/_agent_cli.py src/skillspector/cli.py
  • uv run ruff format --check src/skillspector/providers/minimax tests/unit/test_minimax_provider.py src/skillspector/providers/__init__.py src/skillspector/providers/_agent_cli.py src/skillspector/cli.py
  • uv run mypy src/skillspector/providers/minimax
  • uv run python -m build

octo-patch and others added 2 commits August 12, 2026 21:55
class MiniMaxProvider:
"""MiniMax credentials, regional routing, and bundled model metadata."""

DEFAULT_MODEL = "MiniMax-M3"

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Official MiniMax API docs currently list MiniMax-M2.7 / MiniMax-M2.7-highspeed as the supported OpenAI-compatible model IDs, and the /v1/models example does not include MiniMax-M3; this default would make every out-of-box request fail. Use a served model with documented limits (or provide authoritative endpoint evidence plus a live contract test). Source: https://platform.minimax.io/docs/api-reference/api-overview

@rng1995 rng1995 left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[SkillSpector Review]

Requesting changes. The provider defaults to MiniMax-M3 with a 1M registry window, but current official MiniMax OpenAI-compatible docs list M2.7-family served IDs and a 204,800 combined context; the proposed default would fail out of the box. Use a documented served model/limits or provide authoritative endpoint evidence plus a live contract test. The branch also conflicts with main and DCO fails. See the inline source link.

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