docs: document dynamic model fetching feature

[praneethb7]

Description

Documents the dynamic model fetching feature added in #12046.

• docs/customize/model-providers/overview.mdx — Added "Dynamic Model Fetching" section explaining per-provider behavior (auto-load vs refresh button), what data is fetched (contextLength, maxTokens, supportsTools), persistence to config.yaml, and model deduplication
• docs/customize/model-roles/chat.mdx — Added "Adding a Chat Model" section explaining how to trigger model fetching from the UI, with a link to the detailed reference

Closes #12396

AI Code Review

• Team members only: AI review runs automatically when PR is opened or marked ready for review
• Team members can also trigger a review by commenting @continue-review

Checklist

• I've read the contributing guide
• The relevant docs, if any, have been updated or created
• The relevant tests, if any, have been updated or created

Screen recording or screenshot

N/A — documentation-only change.

Tests

N/A — documentation-only change. No code logic was modified.

---

Summary by cubic

Documented dynamic model fetching across providers and how to add chat models from the UI, including per‑provider behavior (auto-load vs refresh), fetched fields (context length, max tokens, tool support), config persistence, and model deduplication. Also added guidance for multiple local config profiles via .continue/configs/, .continue/agents/, and .continue/assistants/ with auto-discovery and hot reload.

^{Written for commit 2e1ca01. Summary will update on new commits.}

[cubic-dev-ai]

No issues found across 4 files