feat: add MiniMax as first-class LLM provider

[octo-patch]

Summary

• Add MiniMax as a built-in model provider alongside OpenAI and Gemini
• MiniMax models (M2.7, M2.7-highspeed, M2.5, M2.5-highspeed) accessible via OpenAI-compatible Chat Completions API with 204K context windows
• Provider extends OpenAIProvider with MiniMax-specific behavior: temperature clamping to (0.0, 1.0], think tag stripping for reasoning models, MINIMAX_API_KEY auto-detection, and forced Chat Completions protocol

Changes

File	Description
runtime/node/agent/providers/minimax_provider.py	New MiniMaxProvider class extending OpenAIProvider
runtime/node/agent/providers/builtin_providers.py	Register minimax in ProviderRegistry
tests/test_minimax_provider.py	34 unit tests + 3 integration tests
README.md	Supported providers table with MiniMax info

Usage

Set MINIMAX_API_KEY in .env and configure agent nodes:

model:
  provider: minimax
  name: MiniMax-M2.7
  api_key: ${MINIMAX_API_KEY}

Test plan

• 34 unit tests covering init defaults, temperature clamping, think-tag stripping, response deserialization, token tracking, payload construction, provider registration, regex patterns, and client creation
• 3 integration tests (skipped without MINIMAX_API_KEY) verifying real API calls with M2.7 and M2.7-highspeed models
• All 37 tests pass