Merge pull request #2820 from QwenLM/feat/qwen3.6-plus-support

🎉 feat: add Qwen3.6-Plus model support

Author: tanzhenxin

README.md

@@ -18,19 +18,23 @@
 
 </div>
 
-> 🎉 **News (2026-02-16)**: Qwen3.5-Plus is now live! Sign in via Qwen OAuth to use it directly, or get an API key from [Alibaba Cloud ModelStudio](https://modelstudio.console.alibabacloud.com?tab=doc#/doc/?type=model&url=2840914_2&modelId=group-qwen3.5-plus) to access it through the OpenAI-compatible API.
+## 🎉 News
 
-Qwen Code is an open-source AI agent for the terminal, optimized for [Qwen3-Coder](https://github.com/QwenLM/Qwen3-Coder). It helps you understand large codebases, automate tedious work, and ship faster.
+- **2026-04-02**: Qwen3.6-Plus is now live! Sign in via Qwen OAuth to use it directly, or get an API key from [Alibaba Cloud ModelStudio](https://modelstudio.console.alibabacloud.com/ap-southeast-1?tab=doc#/doc/?type=model&url=2840914_2&modelId=qwen3.6-plus) to access it through the OpenAI-compatible API.
 
-![](https://gw.alicdn.com/imgextra/i1/O1CN01D2DviS1wwtEtMwIzJ_!!6000000006373-2-tps-1600-900.png)
+- **2026-02-16**: Qwen3.5-Plus is now live!
 
 ## Why Qwen Code?
 
+Qwen Code is an open-source AI agent for the terminal, optimized for Qwen series models. It helps you understand large codebases, automate tedious work, and ship faster.
+
 - **Multi-protocol, OAuth free tier**: use OpenAI / Anthropic / Gemini-compatible APIs, or sign in with Qwen OAuth for 1,000 free requests/day.
 - **Open-source, co-evolving**: both the framework and the Qwen3-Coder model are open-source—and they ship and evolve together.
 - **Agentic workflow, feature-rich**: rich built-in tools (Skills, SubAgents) for a full agentic workflow and a Claude Code-like experience.
 - **Terminal-first, IDE-friendly**: built for developers who live in the command line, with optional integration for VS Code, Zed, and JetBrains IDEs.
 
+![](https://gw.alicdn.com/imgextra/i1/O1CN01D2DviS1wwtEtMwIzJ_!!6000000006373-2-tps-1600-900.png)
+
 ## Installation
 
 ### Quick Install (Recommended)
@@ -148,8 +152,8 @@ Here is a complete example:
   "modelProviders": {
     "openai": [
       {
-        "id": "qwen3-coder-plus",
-        "name": "qwen3-coder-plus",
+        "id": "qwen3.6-plus",
+        "name": "qwen3.6-plus",
         "baseUrl": "https://dashscope.aliyuncs.com/compatible-mode/v1",
         "description": "Qwen3-Coder via Dashscope",
         "envKey": "DASHSCOPE_API_KEY"
@@ -165,7 +169,7 @@ Here is a complete example:
     }
   },
   "model": {
-    "name": "qwen3-coder-plus"
+    "name": "qwen3.6-plus"
   }
 }
 ```
@@ -175,7 +179,7 @@ Here is a complete example:
 | Field                        | What it does                                                                                                                          |
 | ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------- |
 | `modelProviders`             | Declares which models are available and how to connect to them. Keys like `openai`, `anthropic`, `gemini` represent the API protocol. |
-| `modelProviders[].id`        | The model ID sent to the API (e.g. `qwen3-coder-plus`, `gpt-4o`).                                                                     |
+| `modelProviders[].id`        | The model ID sent to the API (e.g. `qwen3.6-plus`, `gpt-4o`).                                                                         |
 | `modelProviders[].envKey`    | The name of the environment variable that holds your API key.                                                                         |
 | `modelProviders[].baseUrl`   | The API endpoint URL (required for non-default endpoints).                                                                            |
 | `env`                        | A fallback place to store API keys (lowest priority; prefer `.env` files or `export` for sensitive keys).                             |
@@ -200,29 +204,17 @@ Use the `/model` command at any time to switch between all configured models.
   "modelProviders": {
     "openai": [
       {
-        "id": "qwen3.5-plus",
-        "name": "qwen3.5-plus (Coding Plan)",
+        "id": "qwen3.6-plus",
+        "name": "qwen3.6-plus (Coding Plan)",
         "baseUrl": "https://coding.dashscope.aliyuncs.com/v1",
-        "description": "qwen3.5-plus with thinking enabled from ModelStudio Coding Plan",
-        "envKey": "BAILIAN_CODING_PLAN_API_KEY",
-        "generationConfig": {
-          "extra_body": {
-            "enable_thinking": true
-          }
-        }
-      },
-      {
-        "id": "qwen3-coder-plus",
-        "name": "qwen3-coder-plus (Coding Plan)",
-        "baseUrl": "https://coding.dashscope.aliyuncs.com/v1",
-        "description": "qwen3-coder-plus from ModelStudio Coding Plan",
+        "description": "qwen3.6-plus from ModelStudio Coding Plan",
         "envKey": "BAILIAN_CODING_PLAN_API_KEY"
       },
       {
-        "id": "qwen3-coder-next",
-        "name": "qwen3-coder-next (Coding Plan)",
+        "id": "qwen3.5-plus",
+        "name": "qwen3.5-plus (Coding Plan)",
         "baseUrl": "https://coding.dashscope.aliyuncs.com/v1",
-        "description": "qwen3-coder-next with thinking enabled from ModelStudio Coding Plan",
+        "description": "qwen3.5-plus with thinking enabled from ModelStudio Coding Plan",
         "envKey": "BAILIAN_CODING_PLAN_API_KEY",
         "generationConfig": {
           "extra_body": {
@@ -265,7 +257,7 @@ Use the `/model` command at any time to switch between all configured models.
     }
   },
   "model": {
-    "name": "qwen3-coder-plus"
+    "name": "qwen3.6-plus"
   }
 }
 ```

packages/cli/src/i18n/locales/de.js

@@ -1336,8 +1336,8 @@ export default {
   unknown: 'unbekannt',
   "Failed to switch model to '{{modelId}}'.\n\n{{error}}":
     "Modell konnte nicht auf '{{modelId}}' umgestellt werden.\n\n{{error}}",
-  'Qwen 3.5 Plus — efficient hybrid model with leading coding performance':
-    'Qwen 3.5 Plus — effizientes Hybridmodell mit führender Programmierleistung',
+  'Qwen 3.6 Plus — efficient hybrid model with leading coding performance':
+    'Qwen 3.6 Plus — effizientes Hybridmodell mit führender Programmierleistung',
   'The latest Qwen Vision model from Alibaba Cloud ModelStudio (version: qwen3-vl-plus-2025-09-23)':
     'Das neueste Qwen Vision Modell von Alibaba Cloud ModelStudio (Version: qwen3-vl-plus-2025-09-23)',
 

packages/cli/src/i18n/locales/en.js

@@ -1385,8 +1385,8 @@ export default {
   unknown: 'unknown',
   "Failed to switch model to '{{modelId}}'.\n\n{{error}}":
     "Failed to switch model to '{{modelId}}'.\n\n{{error}}",
-  'Qwen 3.5 Plus — efficient hybrid model with leading coding performance':
-    'Qwen 3.5 Plus — efficient hybrid model with leading coding performance',
+  'Qwen 3.6 Plus — efficient hybrid model with leading coding performance':
+    'Qwen 3.6 Plus — efficient hybrid model with leading coding performance',
   'The latest Qwen Vision model from Alibaba Cloud ModelStudio (version: qwen3-vl-plus-2025-09-23)':
     'The latest Qwen Vision model from Alibaba Cloud ModelStudio (version: qwen3-vl-plus-2025-09-23)',
 

packages/cli/src/i18n/locales/ja.js

@@ -1026,8 +1026,8 @@ export default {
   'not set': '未設定',
   none: 'なし',
   unknown: '不明',
-  'Qwen 3.5 Plus — efficient hybrid model with leading coding performance':
-    'Qwen 3.5 Plus — 効率的なハイブリッドモデル、業界トップクラスのコーディング性能',
+  'Qwen 3.6 Plus — efficient hybrid model with leading coding performance':
+    'Qwen 3.6 Plus — 効率的なハイブリッドモデル、業界トップクラスのコーディング性能',
   'The latest Qwen Vision model from Alibaba Cloud ModelStudio (version: qwen3-vl-plus-2025-09-23)':
     'Alibaba Cloud ModelStudioの最新Qwen Visionモデル(バージョン: qwen3-vl-plus-2025-09-23)',
   // Dialogs - Permissions

packages/cli/src/i18n/locales/pt.js

@@ -1339,8 +1339,8 @@ export default {
   unknown: 'desconhecido',
   "Failed to switch model to '{{modelId}}'.\n\n{{error}}":
     "Falha ao trocar o modelo para '{{modelId}}'.\n\n{{error}}",
-  'Qwen 3.5 Plus — efficient hybrid model with leading coding performance':
-    'Qwen 3.5 Plus — modelo híbrido eficiente com desempenho líder em programação',
+  'Qwen 3.6 Plus — efficient hybrid model with leading coding performance':
+    'Qwen 3.6 Plus — modelo híbrido eficiente com desempenho líder em programação',
   'The latest Qwen Vision model from Alibaba Cloud ModelStudio (version: qwen3-vl-plus-2025-09-23)':
     'O modelo Qwen Vision mais recente do Alibaba Cloud ModelStudio (versão: qwen3-vl-plus-2025-09-23)',
 

packages/cli/src/i18n/locales/ru.js

@@ -1262,8 +1262,8 @@ export default {
   unknown: 'неизвестно',
   "Failed to switch model to '{{modelId}}'.\n\n{{error}}":
     "Не удалось переключиться на модель '{{modelId}}'.\n\n{{error}}",
-  'Qwen 3.5 Plus — efficient hybrid model with leading coding performance':
-    'Qwen 3.5 Plus — эффективная гибридная модель с лидирующей производительностью в программировании',
+  'Qwen 3.6 Plus — efficient hybrid model with leading coding performance':
+    'Qwen 3.6 Plus — эффективная гибридная модель с лидирующей производительностью в программировании',
   'The latest Qwen Vision model from Alibaba Cloud ModelStudio (version: qwen3-vl-plus-2025-09-23)':
     'Последняя модель Qwen Vision от Alibaba Cloud ModelStudio (версия: qwen3-vl-plus-2025-09-23)',
 

packages/cli/src/i18n/locales/zh.js

@@ -1309,8 +1309,8 @@ export default {
   unknown: '未知',
   "Failed to switch model to '{{modelId}}'.\n\n{{error}}":
     "无法切换到模型 '{{modelId}}'.\n\n{{error}}",
-  'Qwen 3.5 Plus — efficient hybrid model with leading coding performance':
-    'Qwen 3.5 Plus — 高效混合架构，编程性能业界领先',
+  'Qwen 3.6 Plus — efficient hybrid model with leading coding performance':
+    'Qwen 3.6 Plus — 高效混合架构，编程性能业界领先',
   'The latest Qwen Vision model from Alibaba Cloud ModelStudio (version: qwen3-vl-plus-2025-09-23)':
     '来自阿里云 ModelStudio 的最新 Qwen Vision 模型（版本：qwen3-vl-plus-2025-09-23）',
 

packages/core/src/core/openaiContentGenerator/provider/dashscope.test.ts

@@ -762,19 +762,7 @@ describe('DashScopeOpenAICompatibleProvider', () => {
 
       const result = provider.buildRequest(request, 'test-prompt-id');
 
-      expect(result.max_tokens).toBe(65536); // Should be limited to model's output limit (64K)
-    });
-
-    it('should limit max_tokens when it exceeds model limit for qwen-vl-max-latest', () => {
-      const request: OpenAI.Chat.ChatCompletionCreateParams = {
-        model: 'qwen-vl-max-latest',
-        messages: [{ role: 'user', content: 'Hello' }],
-        max_tokens: 20000, // Exceeds the 8192 limit
-      };
-
-      const result = provider.buildRequest(request, 'test-prompt-id');
-
-      expect(result.max_tokens).toBe(8192); // Should be limited to model's output limit
+      expect(result.max_tokens).toBe(32768); // Should be limited to model's output limit (32K)
     });
 
     it('should not modify max_tokens when it is within model limit', () => {
@@ -799,7 +787,7 @@ describe('DashScopeOpenAICompatibleProvider', () => {
       const result = provider.buildRequest(request, 'test-prompt-id');
 
       // Should set conservative default (min of model limit and DEFAULT_OUTPUT_TOKEN_LIMIT)
-      // qwen3-max has 64K output limit, so min(64K, 32K) = 32K
+      // qwen3-max has 32K output limit, so min(32K, 32K) = 32K
       expect(result.max_tokens).toBe(32000);
     });
 
@@ -845,7 +833,7 @@ describe('DashScopeOpenAICompatibleProvider', () => {
       const result = provider.buildRequest(request, 'test-prompt-id');
 
       // max_tokens should be limited
-      expect(result.max_tokens).toBe(65536); // Limited to model's output limit (64K)
+      expect(result.max_tokens).toBe(32768); // Limited to model's output limit (32K)
 
       // Other parameters should be preserved
       expect(result.temperature).toBe(0.8);
@@ -856,58 +844,6 @@ describe('DashScopeOpenAICompatibleProvider', () => {
       expect(result.user).toBe('test-user');
     });
 
-    it('should work with vision models and output token limits', () => {
-      const request: OpenAI.Chat.ChatCompletionCreateParams = {
-        model: 'qwen-vl-max-latest',
-        messages: [
-          {
-            role: 'user',
-            content: [
-              { type: 'text', text: 'Look at this image:' },
-              {
-                type: 'image_url',
-                image_url: { url: 'https://example.com/image.jpg' },
-              },
-            ],
-          },
-        ],
-        max_tokens: 20000, // Exceeds the model's output limit
-      };
-
-      const result = provider.buildRequest(request, 'test-prompt-id');
-
-      expect(result.max_tokens).toBe(8192); // Should be limited to model's output limit (8K)
-      expect(
-        (result as { vl_high_resolution_images?: boolean })
-          .vl_high_resolution_images,
-      ).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' },
-              },
-            ],
-          },
-        ],
-      };
-
-      const result = provider.buildRequest(request, 'test-prompt-id');
-
-      expect(
-        (result as { vl_high_resolution_images?: boolean })
-          .vl_high_resolution_images,
-      ).toBe(true);
-    });
-
     it('should set high resolution flag for the coder-model model', () => {
       const request: OpenAI.Chat.ChatCompletionCreateParams = {
         model: 'coder-model',
@@ -945,7 +881,7 @@ describe('DashScopeOpenAICompatibleProvider', () => {
 
       const result = provider.buildRequest(request, 'test-prompt-id');
 
-      expect(result.max_tokens).toBe(65536); // Should be limited to model's output limit (64K)
+      expect(result.max_tokens).toBe(32768); // Should be limited to model's output limit (32K)
       expect(result.stream).toBe(true); // Streaming should be preserved
     });
 

packages/core/src/core/openaiContentGenerator/provider/dashscope.ts

@@ -150,9 +150,7 @@ export class DashScopeOpenAICompatibleProvider extends DefaultOpenAICompatiblePr
   }
 
   override getDefaultGenerationConfig(): GenerateContentConfig {
-    return {
-      temperature: 0.3,
-    };
+    return {};
   }
 
   /**

packages/core/src/core/tokenLimits.test.ts

@@ -270,14 +270,11 @@ describe('tokenLimit with output type', () => {
   describe('Qwen output limits', () => {
     it('should return correct output limits for Qwen models', () => {
       expect(tokenLimit('qwen3.5-plus', 'output')).toBe(65536);
-      expect(tokenLimit('qwen3-max', 'output')).toBe(65536);
-      expect(tokenLimit('qwen3-max-2026-01-23', 'output')).toBe(65536);
+      expect(tokenLimit('qwen3.6-plus', 'output')).toBe(65536);
       expect(tokenLimit('coder-model', 'output')).toBe(65536);
-      // Models without specific output limits fall back to default
-      expect(tokenLimit('qwen3-coder-plus', 'output')).toBe(8192);
-      expect(tokenLimit('qwen3-coder-next', 'output')).toBe(8192);
-      expect(tokenLimit('qwen3-vl-plus', 'output')).toBe(8192);
-      expect(tokenLimit('qwen-vl-max-latest', 'output')).toBe(8192);
+      // Models without specific output limits fall back to Qwen default (32K)
+      expect(tokenLimit('qwen3-max', 'output')).toBe(32768);
+      expect(tokenLimit('qwen3-max-2026-01-23', 'output')).toBe(32768);
     });
   });
 
@@ -314,7 +311,7 @@ describe('tokenLimit with output type', () => {
   describe('input vs output comparison', () => {
     it('should return different limits for input vs output', () => {
       expect(tokenLimit('qwen3-max', 'input')).toBe(262144);
-      expect(tokenLimit('qwen3-max', 'output')).toBe(65536);
+      expect(tokenLimit('qwen3-max', 'output')).toBe(32768);
     });
 
     it('should default to input type when no type is specified', () => {
@@ -325,9 +322,8 @@ describe('tokenLimit with output type', () => {
 
   describe('normalization with output limits', () => {
     it('should handle normalized model names for output limits', () => {
-      expect(tokenLimit('QWEN3-MAX', 'output')).toBe(65536);
-      expect(tokenLimit('qwen3-max-20250601', 'output')).toBe(65536);
-      expect(tokenLimit('QWEN-VL-MAX-LATEST', 'output')).toBe(8192);
+      expect(tokenLimit('QWEN3-MAX', 'output')).toBe(32768);
+      expect(tokenLimit('qwen3-max-20250601', 'output')).toBe(32768);
     });
   });
 });