i/next-ai-draw-io
1
0
Fork 0
mirror of https://github.com/DayuanJiang/next-ai-draw-io.git synced 2026-09-01 17:10:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: allow Qwen3.5 models to use image input (fixes #799) (#800)

Browse Source 
Qwen3.5 models deployed via vLLM natively support image input, but the
supportsImageInput() check was incorrectly blocking them. The function
only exempted qwen3.5-plus and qwen3.5-flash variants, missing the base
qwen3.5 model name.

Simplify the exception to cover all qwen3.5 variants with a single
substring check on "qwen3.5", since it is a common prefix of all three.

Co-authored-by: octo-patch <octo-patch@github.com>
This commit is contained in:
Octopus
2026-04-10 09:23:39 +08:00
committed by GitHub
parent b9fdf9538c
commit 43ddb7a999
2 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
lib/ai-providers.ts
View File

@@ -1356,12 +1356,11 @@ export function supportsImageInput(modelId: string): boolean {
}
// Qwen text models (not vision variants like qwen-vl)
// qwen3.5-plus is a vision model
// Qwen3.5 series (qwen3.5, qwen3.5-plus, qwen3.5-flash) natively support image input
if (
lowerModelId.includes("qwen") &&
!hasVisionIndicator &&
!lowerModelId.includes("qwen3.5-plus") &&
!lowerModelId.includes("qwen3.5-flash")
!lowerModelId.includes("qwen3.5")
) {
return false
}