Docs: Document dynamic model fetching feature

[continue]

Summary

PR #12046 added a significant new feature for dynamically fetching provider models, but there's no user-facing documentation for this capability.

Feature Overview

Users can now:

• Refresh model lists dynamically using their API keys
• Providers auto-load models (ollama scrapes library, openrouter uses public API)
• Click a refresh button after entering API key to fetch available models
• Dynamic model fetching persists context length, max tokens, and capabilities to config.yaml

Missing Documentation

• How to use the dynamic model refresh feature in the GUI
• Which providers support dynamic model fetching
• How fetched model capabilities are auto-detected and persisted
• Explanation of the refresh button behavior in Add Model flow

Supported Providers

According to PR #12046:

• Ollama: Scrapes model library with icons
• OpenRouter: Hits public API on load
• Anthropic: Calls /v1/models
• Gemini: Calls v1beta/models (chat-only)
• Others: Use listModels() with optional apiKey/apiBase

Suggested Locations

• New section in model configuration docs
• Update provider-specific pages to mention dynamic fetching
• Add to Getting Started guide

Related PR

• feat: fetch provider models dynamically and fix isOpenSource pollution #12046 - feat: fetch provider models dynamically and fix isOpenSource pollution

---

Generated with Continue

Co-Authored-By: Continue noreply@continue.dev
Co-authored-by: bekahhw rhawrot@gmail.com