feat: add Qwen3-Next-80B-A3B-Instruct and Qwen3-Next-80B-A3B-Thinking models to Chutes provider

[unixsysdev]

This PR adds two new models to the Chutes provider:

Qwen/Qwen3-Next-80B-A3B-Instruct - A Qwen3 Next model with 262K context window
Qwen/Qwen3-Next-80B-A3B-Thinking - A Qwen3 Next Thinking model with 262K context window

Changes Made:

• Added new model IDs to the ChutesModelId type in packages/types/src/providers/chutes.ts
• Added model configurations with appropriate context windows and descriptions to the chutesModels object
• Fixed alphabetical ordering of all Qwen models
• Added comprehensive tests for both new models in src/api/providers/__tests__/chutes.spec.ts

Testing:

• All existing tests pass ✅
• New tests added for both models ✅
• TypeScript compilation successful ✅
• Linting checks passed ✅

---

Important

Add Qwen3-Next-80B-A3B-Instruct and Qwen3-Next-80B-A3B-Thinking models to Chutes provider with tests and configuration updates.

• Models:
  • Add Qwen/Qwen3-Next-80B-A3B-Instruct and Qwen/Qwen3-Next-80B-A3B-Thinking to ChutesModelId in chutes.ts.
  • Configure new models in chutesModels with 262K context window.
  • Fix alphabetical ordering of Qwen models.
• Testing:
  • Add tests for new models in chutes.spec.ts to verify correct configuration and behavior.
• Misc:
  • Ensure all existing tests pass and update TypeScript and linting checks.

^{This description was created by for e3ee87d01b248b06f67a2fdebd5ec94e78236578. You can customize this summary. It will automatically update as commits are pushed.}

[roomote]

Thank you for your contribution! I've reviewed the changes and have some suggestions for improvement.

[roomote]

I noticed the alphabetical ordering isn't quite right here. The Qwen models should be ordered alphabetically by their full names. Currently, the order mixes different model families.

Could we reorder them as:

• Qwen/Qwen3-14B
• Qwen/Qwen3-235B-A22B
• Qwen/Qwen3-235B-A22B-Instruct-2507
• Qwen/Qwen3-235B-A22B-Thinking-2507
• Qwen/Qwen3-30B-A3B
• Qwen/Qwen3-32B
• Qwen/Qwen3-8B
• Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8
• Qwen/Qwen3-Next-80B-A3B-Instruct
• Qwen/Qwen3-Next-80B-A3B-Thinking

[roomote]

Is it intentional that both new models have inputPrice: 0 and outputPrice: 0? I noticed that Qwen3-235B-A22B-Thinking-2507 has actual pricing values. Should we add pricing information for these models when it becomes available?

[roomote]

One additional observation: I noticed that Qwen3-Next-80B-A3B-Thinking is a "Thinking" model similar to Qwen3-235B-A22B-Thinking-2507. Currently in src/api/providers/chutes.ts, only DeepSeek-R1 models have special handling for reasoning output (lines 50-89).

Should we consider adding similar handling for Qwen Thinking models to properly parse their chain-of-thought output? Or do Qwen Thinking models use a different format that doesn't require special parsing?