feat: upgrade MiniMax default model to M3

[octo-patch]

Summary

Upgrade MiniMax model configuration to use M3 as the default model.

Changes

• Add MiniMax-M3 to the model selection list and set as default
• Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives
• Remove older models (M2.5/M2.1/M2/M1)
• Update CLI default for --model flag (minimax/minimax-m3)
• Update related unit tests (wiki-llm-client.test.ts, wiki-flags.test.ts)
• Update i18n / locale strings (en + zh-CN, web + CLI)
• Update eval configs: replace minimax-2.5.yaml (M1 2.5) with minimax-m3.yaml; rename minimax-m2.1.yaml to minimax-m2.7.yaml (model ID also updated to m2.7)

Why

MiniMax-M3 is the latest model, with a 512K context window, up to 128K output, and image input support.

Testing

• Unit tests updated to reference minimax/minimax-m3
• Default model resolution path and CLI help text verified by grep — no stale M2.5 / m2.5 references remain in code

[vercel]

Someone is attempting to deploy a commit to the NexusCore Team on Vercel.

A member of the Team first needs to authorize it.