From 9fce177bd8cb3629cbf2dcab8b9d7e8825b02892 Mon Sep 17 00:00:00 2001
From: Brando Magnani <brandomagnani@gmail.com>
Date: Fri, 26 Sep 2025 02:20:18 -0700
Subject: [PATCH] Fix/qwen3 vl plus highres (#721)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* feat: Add Qwen3-VL-Plus token limits (256K input, 32K output)

- Added 256K input context window limit for Qwen3-VL-Plus model
- Updated output token limit from 8K to 32K for Qwen3-VL-Plus
- Added comprehensive tests for both input and output limits

As requested by Qwen maintainers for proper model support.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* fix: enable high-res flag for qwen VL models

---------

Co-authored-by: Claude <noreply@anthropic.com>
---
 .../provider/dashscope.test.ts                | 54 +++++++++++++++++++
 .../provider/dashscope.ts                     | 24 ++++++++-
 2 files changed, 77 insertions(+), 1 deletion(-)

diff --git a/packages/core/src/core/openaiContentGenerator/provider/dashscope.test.ts b/packages/core/src/core/openaiContentGenerator/provider/dashscope.test.ts
index cc62c213..592acbae 100644
--- a/packages/core/src/core/openaiContentGenerator/provider/dashscope.test.ts
+++ b/packages/core/src/core/openaiContentGenerator/provider/dashscope.test.ts
@@ -688,6 +688,60 @@ describe('DashScopeOpenAICompatibleProvider', () => {
       ).toBe(true); // Vision-specific parameter should be preserved
     });
 
+    it('should set high resolution flag for qwen3-vl-plus', () => {
+      const request: OpenAI.Chat.ChatCompletionCreateParams = {
+        model: 'qwen3-vl-plus',
+        messages: [
+          {
+            role: 'user',
+            content: [
+              { type: 'text', text: 'Please inspect the image.' },
+              {
+                type: 'image_url',
+                image_url: { url: 'https://example.com/vl.jpg' },
+              },
+            ],
+          },
+        ],
+        max_tokens: 50000,
+      };
+
+      const result = provider.buildRequest(request, 'test-prompt-id');
+
+      expect(result.max_tokens).toBe(32768);
+      expect(
+        (result as { vl_high_resolution_images?: boolean })
+          .vl_high_resolution_images,
+      ).toBe(true);
+    });
+
+    it('should set high resolution flag for the vision-model alias', () => {
+      const request: OpenAI.Chat.ChatCompletionCreateParams = {
+        model: 'vision-model',
+        messages: [
+          {
+            role: 'user',
+            content: [
+              { type: 'text', text: 'Alias payload' },
+              {
+                type: 'image_url',
+                image_url: { url: 'https://example.com/alias.png' },
+              },
+            ],
+          },
+        ],
+        max_tokens: 9000,
+      };
+
+      const result = provider.buildRequest(request, 'test-prompt-id');
+
+      expect(result.max_tokens).toBe(8192);
+      expect(
+        (result as { vl_high_resolution_images?: boolean })
+          .vl_high_resolution_images,
+      ).toBe(true);
+    });
+
     it('should handle streaming requests with output token limits', () => {
       const request: OpenAI.Chat.ChatCompletionCreateParams = {
         model: 'qwen3-coder-plus',
diff --git a/packages/core/src/core/openaiContentGenerator/provider/dashscope.ts b/packages/core/src/core/openaiContentGenerator/provider/dashscope.ts
index fda3d3e5..756572c1 100644
--- a/packages/core/src/core/openaiContentGenerator/provider/dashscope.ts
+++ b/packages/core/src/core/openaiContentGenerator/provider/dashscope.ts
@@ -100,7 +100,7 @@ export class DashScopeOpenAICompatibleProvider
       request.model,
     );
 
-    if (request.model.startsWith('qwen-vl')) {
+    if (this.isVisionModel(request.model)) {
       return {
         ...requestWithTokenLimits,
         messages,
@@ -267,6 +267,28 @@ export class DashScopeOpenAICompatibleProvider
     return contentArray;
   }
 
+  private isVisionModel(model: string | undefined): boolean {
+    if (!model) {
+      return false;
+    }
+
+    const normalized = model.toLowerCase();
+
+    if (normalized === 'vision-model') {
+      return true;
+    }
+
+    if (normalized.startsWith('qwen-vl')) {
+      return true;
+    }
+
+    if (normalized.startsWith('qwen3-vl-plus')) {
+      return true;
+    }
+
+    return false;
+  }
+
   /**
    * Apply output token limit to a request's max_tokens parameter.
    *