feat: add MiniMax provider support for prompt refinement (M3 default)

[octo-patch]

Summary

This PR adds MiniMax as an alternative LLM provider for Open-Sora's prompt refinement step, alongside the existing OpenAI/GPT-4o integration. The default model is now MiniMax-M3, with MiniMax-M2.7 and MiniMax-M2.7-highspeed available as alternatives.

Changes

• opensora/utils/prompt_refine.py

  • Add _get_client(model) — routes to MiniMax API (OpenAI-compatible) when model starts with "MiniMax", otherwise uses OpenAI
  • Add has_minimax_key() — checks whether MINIMAX_API_KEY is set
  • Add _strip_think_tags(text) — strips <think>…</think> chain-of-thought blocks emitted by MiniMax reasoning models
  • Add _extra_tokens(model) — allocates 500 extra output tokens for MiniMax models to accommodate thinking tokens
  • Add refine_prompts_by_minimax() — convenience wrapper that defaults to MiniMax-M3
  • MINIMAX_MODELS list contains MiniMax-M3, MiniMax-M2.7, MiniMax-M2.7-highspeed (M3 first)
  • refine_prompt() and refine_prompts() now accept an optional model parameter (defaults to PROMPT_MODEL env var, falls back to "gpt-4o")

• tests/test_minimax_prompt_refine.py — 18 unit tests covering routing, API key validation, model selection (including the M3 default and M3 being first in the list), temperature constraints, think-tag stripping, and the refine_prompts_by_minimax() wrapper

Supported models

Model	Description
MiniMax-M3	Default — 512K context window, up to 128K output, supports image input
MiniMax-M2.7	Previous-generation peak-performance model
MiniMax-M2.7-highspeed	Previous-generation low-latency variant

Usage

# Use MiniMax for prompt refinement (M3 is now the default)
export MINIMAX_API_KEY=your_key_here
export PROMPT_MODEL=MiniMax-M3

Or programmatically:

from opensora.utils.prompt_refine import refine_prompts_by_minimax

# Defaults to MiniMax-M3
refined = refine_prompts_by_minimax(["a cat playing in snow"], type="t2v")

API references

• Chat (OpenAI Compatible): https://platform.minimax.io/docs/api-reference/text-openai-api