feat: add MiniMax as LLM provider with M2.7 default

[octo-patch]

Summary

• Add MiniMax as a first-class LLM provider in the provider chain (between Groq and OpenRouter)
• Default model: MiniMax-M2.7 (latest flagship with enhanced reasoning and coding capabilities)
• Support MINIMAX_MODEL env var override (e.g. MiniMax-M2.7-highspeed for low-latency scenarios)
• API endpoint: https://api.minimax.io/v1 (OpenAI-compatible)

Changes

• server/_shared/llm.ts: Add minimax provider with API key auth, model env var override, and provider chain integration
• .env.example: Add MINIMAX_API_KEY and MINIMAX_MODEL configuration docs
• tests/shared-llm.test.mts: Add 2 unit tests for default model and model override

Testing

• All 5 unit tests passing (3 existing + 2 new MiniMax tests)
• Default model verified as MiniMax-M2.7
• MINIMAX_MODEL env var override verified with MiniMax-M2.7-highspeed

[vercel]

@octo-patch is attempting to deploy a commit to the Elie Team on Vercel.

A member of the Team first needs to authorize it.