Update llm-info model catalog and backfill descriptions

[github-actions]

This pull request was authored by a coding agent.

📝 Summary

• Syncs packages/llm-info/data/models.yml with the latest models from models.dev, adding recent entries for Azure (Claude Opus 4.8, DeepSeek V4 Flash/Pro), Ollama (GLM-5.2, Kimi K2.7 Code, MiniMax M3, Nemotron 3 Ultra), and OpenCode Go (GLM-5.2, Kimi K2.7 Code, MiniMax M3, Qwen3.7 Plus).
• Backfills every empty model description using OpenRouter and provider documentation so the model picker shows concise capability summaries instead of blanks.
• Removes unverified placeholder entries from the initial sync that were not ready for the catalog — Claude Fable 5 regional Bedrock stubs, duplicate Google/Azure Claude entries, gpt-image-2, and superseded Ollama/OpenCode Go listings (e.g. MiMo V2 Omni/Pro, GLM 5, MiniMax M2.5).
• Reorders provider sections by release date so newer models surface first in the picker.

📋 Pre-Review Checklist

• For large changes, or changes that affect the public API: this change was discussed or approved through an issue, on Discord, or the community discussions (Please provide a link if applicable).
• Any AI generated code has been reviewed line-by-line by the human PR author, who stands by it.
• Video or media evidence is provided for any visual changes (optional).

✅ Merge Checklist

• I have read the contributor guidelines.
• Documentation has been updated where applicable, including docstrings for API changes.
• Tests have been added for the changes made.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
marimo-docs	Ready	Preview, Comment	Jun 26, 2026 3:15pm