feat: add Qwen3.5-122B model support

[tangshixiang]

Summary

Add Qwen3.5-122B-A10B (MoE, 10B active parameters) model to the Qwen provider, served via a self-hosted vLLM endpoint at 106.75.244.215:8001.

Changes

• Add Qwen3.5-122B model definition to the Qwen provider in src/lib/ai/models.ts (context window: 40,000 tokens, matching server max_model_len)
• Add per-model base URL placeholder QWEN_QWEN3_5_122B_BASE_URL to .env.example

Related Issues

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation update
• Refactoring (no functional changes)

Checklist

• My code follows the project's coding style
• I have added tests that cover my changes (if applicable)
• All new and existing tests pass (npm test)
• Lint passes (npm run lint)
• I have updated the documentation (if applicable)
• I have checked that there are no sensitive data (API keys, tokens, etc.) in my changes