feat: add MiniMax M3 provider

[octo-patch]

Summary

Add MiniMax as a new LLM provider, compatible with the existing provider architecture.

Changes

• Add MiniMax provider implementation (providers/minimax.go) using the OpenAI-compatible chat completions API shape
• Add MiniMax provider configuration (API key, base URL) via environment variables (MINIMAX_API_KEY, MINIMAX_BASE_URL)
• Register MiniMax in the provider routing (body field, host-based detection, intercept domains)
• Add MiniMax to the frontend provider selector with MiniMax-M3 as the default model
• Add unit tests for the MiniMax provider
• Update env.example with MINIMAX_API_KEY placeholder

Testing

• go build and go vet passing for providers and config packages
• Unit tests added (minimax_test.go)
• Integration tests require CGO dependencies (ltokenizers) not available in this environment; relies on CI

[github-actions]

Thank you for your submission, we really appreciate it. Like many open-source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution. You can sign the CLA by just posting a Pull Request Comment same as the below format.

---

I have read the CLA Document and I hereby sign the CLA

---

_{You can retrigger this bot by commenting recheck in this Pull Request. Posted by the CLA Assistant Lite bot.}