docs(usage): list qwen-max/qwen-plus in the model alias table

[kayodeo1]

Summary

The "Tested models and aliases" table in USAGE.md omitted the qwen-max and qwen-plus DashScope models, even though:

• both have first-class token limits in rust/crates/api/src/providers/mod.rs (model_token_limit: 8192 max output / 131072 context), and
• both are already documented as working aliases in the Alibaba DashScope (Qwen) section of the same guide.

This adds their rows so the alias table matches the code and the rest of USAGE.md. Rows are placed next to kimi to keep the DashScope models grouped, and use the same space-separated number style as the existing rows.

Changes

• USAGE.md: add qwen-max and qwen-plus rows to the model alias table.

Verification

• Docs-only change; no code or behavior touched.
• Token limits cross-checked against model_token_limit in crates/api/src/providers/mod.rs.
• .github/scripts/check_doc_source_of_truth.py only forbids stale links/assets — this change introduces none.

Test plan

• Visual diff review of the rendered table
• Values match model_token_limit in the api crate

[Copilot]

Pull request overview

Note

Copilot was unable to run its full agentic suite in this review.

Adds two new DashScope Qwen model aliases (qwen-max and qwen-plus) to the documented built-in alias table in USAGE.md.

Changes:

• Documents qwen-max alias with 8,192 output / 131,072 context token limits.
• Documents qwen-plus alias with 8,192 output / 131,072 context token limits.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.