feat: add new DeepSeek and GLM models with detailed descriptions to the Chutes provider

[mohammad154]

…configurations

Related GitHub Issue

Closes: #8157

Roo Code Task Context (Optional)

Description

This PR adds five new Chutes models to Roo Code’s model registry so they appear in the provider picker and can be used across tasks: deepseek-ai/DeepSeek-V3.1-Terminus, deepseek-ai/DeepSeek-V3.1-turbo, deepseek-ai/DeepSeek-V3.2-Exp, zai-org/GLM-4.6-FP8, and Qwen/Qwen3-VL-235B-A22B-Thinking. It addresses the gap where the Chutes list was missing popular, up-to-date models by extending the existing, hardcoded registry without altering provider behavior.

Test Procedure

Successfully added to the Chutes ai models list

Pre-Submission Checklist

• Issue Linked: This PR is linked to an approved GitHub Issue (see "Related GitHub Issue" above).
• Scope: My changes are focused on the linked issue (one major feature/fix per PR).
• Self-Review: I have performed a thorough self-review of my code.
• Testing: New and/or updated tests have been added to cover my changes (if applicable).
• Documentation Impact: I have considered if my changes require documentation updates (see "Documentation Updates" section below).
• Contribution Guidelines: I have read and agree to the Contributor Guidelines.

Screenshots / Videos

Documentation Updates

Additional Notes

Get in Touch

---

Important

Add new DeepSeek and GLM models to chutes.ts with detailed configurations and descriptions.

• Models Added:
  • Added deepseek-ai/DeepSeek-V3.1-Terminus, deepseek-ai/DeepSeek-V3.1-turbo, deepseek-ai/DeepSeek-V3.2-Exp to ChutesModelId and chutesModels.
  • Added zai-org/GLM-4.6-FP8 and Qwen/Qwen3-VL-235B-A22B-Thinking to ChutesModelId and chutesModels.
• Model Details:
  • DeepSeek-V3.1-Terminus: Improved language consistency, better agent performance.
  • DeepSeek-V3.1-turbo: Optimized for fast queries, speculative-decoding.
  • DeepSeek-V3.2-Exp: Experimental LLM with Sparse Attention.
  • GLM-4.6-FP8: Longer context window, improved coding and reasoning.
  • Qwen3-VL-235B-A22B-Thinking: Vision-language model with multi-step reasoning.

^{This description was created by for 0257fea. You can customize this summary. It will automatically update as commits are pushed.}

[roomote]

I found some issues that need attention in the changes.