[ENHANCEMENT] Add support for qwen3-vl-plus for qwencode cli #8993
Description
Problem (one or two sentences)
Qwen Code CLI has support for Vision Model as well, which is using qwen3-vl-plus. But its not available for usage via Roo Code.
Context (who is affected and when)
Users using Qwen3 Models via Qwen Code CLI authentication will face this issue.
Desired behavior (conceptual, not technical)
User should be able to use vision model right from Roo Code only
Constraints / preferences (optional)
No response
Request checklist
- I've searched existing Issues and Discussions for duplicates
- This describes a specific problem with clear context and impact
Roo Code Task Links (optional)
No response
Acceptance criteria (optional)
No response
Proposed approach (optional)
I can update packages/types/src/providers/qwen-code.ts to add qwen3-vl-plus as well.
export type QwenCodeModelId = "qwen3-coder-plus" | "qwen3-coder-flash" | "qwen3-vl-plus"
...
"qwen3-vl-plus": {
maxTokens: 32_768,
contextWindow: 262_144,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
cacheWritesPrice: 0,
cacheReadsPrice: 0,
description: "Qwen3 VL Plus - Vision-language model with image understanding capabilities",
},Trade-offs / risks (optional)
No response