fix: allow QvQ (Qwen Visual QA) models to use image input (#808)

QvQ models (e.g. qvq-72b-preview, qvq-max) are visual reasoning models
from the Qwen family that support image input. When accessed via providers
that prefix model names with 'qwen/' (e.g., OpenRouter), these models
contain 'qwen' in their ID but lack the 'vl' or 'vision' indicator.

This caused supportsImageInput() to incorrectly return false for model
IDs like 'qwen/qvq-72b-preview', blocking image uploads for vision-capable
models.

Add 'qvq' as an explicit exception in the Qwen text-model check so that
QvQ models are correctly allowed to receive image input regardless of the
provider prefix.

Co-authored-by: octo-patch <octo-patch@github.com>

lib/ai-providers.ts

@@ -1357,10 +1357,12 @@ export function supportsImageInput(modelId: string): boolean {
 
     // Qwen text models (not vision variants like qwen-vl)
     // Qwen3.5 series (qwen3.5, qwen3.5-plus, qwen3.5-flash) natively support image input
+    // QvQ (Qwen Visual QA) models are vision models — exclude them even when prefixed with "qwen/"
     if (
         lowerModelId.includes("qwen") &&
         !hasVisionIndicator &&
-        !lowerModelId.includes("qwen3.5")
+        !lowerModelId.includes("qwen3.5") &&
+        !lowerModelId.includes("qvq")
     ) {
         return false
     }