Skip to content
This repository was archived by the owner on May 15, 2026. It is now read-only.

Commit 807c310

Browse files
committed
docs: add changeset for vscode-lm image support feature
1 parent abc4928 commit 807c310

1 file changed

Lines changed: 13 additions & 0 deletions

File tree

Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
---
2+
"roo-cline": minor
3+
---
4+
5+
Add image support for VS Code LM API provider
6+
7+
- Upgraded @types/vscode to ^1.106.0 to support LanguageModelDataPart
8+
- Modified vscode-lm-format to convert image blocks to LanguageModelDataPart.image()
9+
- Updated VsCodeLmHandler.getModel() to detect image-capable models based on model family
10+
- Updated useSelectedModel to use model's supportsImages capability instead of always false
11+
- Added tests for image conversion functionality
12+
13+
This enables users of the VS Code LM API provider to upload images when using vision-capable models like GPT-4o, Claude 3.5 Sonnet, and Gemini models through GitHub Copilot.

0 commit comments

Comments
 (0)