fix: missing tool call chunks for openai logging

.vscode/launch.json

@@ -101,13 +101,6 @@
       "env": {
         "GEMINI_SANDBOX": "false"
       }
-    },
-    {
-      "name": "Attach by Process ID",
-      "processId": "${command:PickProcess}",
-      "request": "attach",
-      "skipFiles": ["<node_internals>/**"],
-      "type": "node"
     }
   ],
   "inputs": [
@@ -122,12 +115,6 @@
       "type": "promptString",
       "description": "Enter your prompt for non-interactive mode",
       "default": "Explain this code"
-    },
-    {
-      "id": "debugPort",
-      "type": "promptString",
-      "description": "Enter the debug port number (default: 9229)",
-      "default": "9229"
     }
   ]
 }

CHANGELOG.md

@@ -1,25 +1,5 @@
 # Changelog
 
-## 0.0.12
-
-- Added vision model support for Qwen-OAuth authentication.
-- Synced upstream `gemini-cli` to v0.3.4 with numerous improvements and bug fixes.
-- Enhanced subagent functionality with system reminders and improved user experience.
-- Added tool call type coercion for better compatibility.
-- Fixed arrow key navigation issues on Windows.
-- Fixed missing tool call chunks for OpenAI logging.
-- Fixed system prompt issues to avoid malformed tool calls.
-- Fixed terminal flicker when subagent is executing.
-- Fixed duplicate subagents configuration when running in home directory.
-- Fixed Esc key unable to cancel subagent dialog.
-- Added confirmation prompt for `/init` command when context file exists.
-- Added `skipLoopDetection` configuration option.
-- Fixed `is_background` parameter reset issues.
-- Enhanced Windows compatibility with multi-line paste handling.
-- Improved subagent documentation and branding consistency.
-- Fixed various linting errors and improved code quality.
-- Miscellaneous improvements and bug fixes.
-
 ## 0.0.11
 
 - Added subagents feature with file-based configuration system for specialized AI assistants.

README.md

@@ -54,7 +54,6 @@ For detailed setup instructions, see [Authorization](#authorization).
 - **Code Understanding & Editing** - Query and edit large codebases beyond traditional context window limits
 - **Workflow Automation** - Automate operational tasks like handling pull requests and complex rebases
 - **Enhanced Parser** - Adapted parser specifically optimized for Qwen-Coder models
-- **Vision Model Support** - Automatically detect images in your input and seamlessly switch to vision-capable models for multimodal analysis
 
 ## Installation
 
@@ -122,58 +121,6 @@ Create or edit `.qwen/settings.json` in your home directory:
 
 > 📝 **Note**: Session token limit applies to a single conversation, not cumulative API calls.
 
-### Vision Model Configuration
-
-Qwen Code includes intelligent vision model auto-switching that detects images in your input and can automatically switch to vision-capable models for multimodal analysis. **This feature is enabled by default** - when you include images in your queries, you'll see a dialog asking how you'd like to handle the vision model switch.
-
-#### Skip the Switch Dialog (Optional)
-
-If you don't want to see the interactive dialog each time, configure the default behavior in your `.qwen/settings.json`:
-
-```json
-{
-  "experimental": {
-    "vlmSwitchMode": "once"
-  }
-}
-```
-
-**Available modes:**
-
-- **`"once"`** - Switch to vision model for this query only, then revert
-- **`"session"`** - Switch to vision model for the entire session
-- **`"persist"`** - Continue with current model (no switching)
-- **Not set** - Show interactive dialog each time (default)
-
-#### Command Line Override
-
-You can also set the behavior via command line:
-
-```bash
-# Switch once per query
-qwen --vlm-switch-mode once
-
-# Switch for entire session
-qwen --vlm-switch-mode session
-
-# Never switch automatically
-qwen --vlm-switch-mode persist
-```
-
-#### Disable Vision Models (Optional)
-
-To completely disable vision model support, add to your `.qwen/settings.json`:
-
-```json
-{
-  "experimental": {
-    "visionModelPreview": false
-  }
-}
-```
-
-> 💡 **Tip**: In YOLO mode (`--yolo`), vision switching happens automatically without prompts when images are detected.
-
 ### Authorization
 
 Choose your preferred authentication method based on your needs:

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@qwen-code/qwen-code",
-  "version": "0.0.13",
+  "version": "0.0.11",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@qwen-code/qwen-code",
-      "version": "0.0.13",
+      "version": "0.0.11",
       "workspaces": [
         "packages/*"
       ],
@@ -13454,7 +13454,7 @@
     },
     "packages/cli": {
       "name": "@qwen-code/qwen-code",
-      "version": "0.0.13",
+      "version": "0.0.11",
       "dependencies": {
         "@google/genai": "1.9.0",
         "@iarna/toml": "^2.2.5",
@@ -13662,7 +13662,7 @@
     },
     "packages/core": {
       "name": "@qwen-code/qwen-code-core",
-      "version": "0.0.13",
+      "version": "0.0.11",
       "dependencies": {
         "@google/genai": "1.13.0",
         "@lvce-editor/ripgrep": "^1.6.0",
@@ -13788,7 +13788,7 @@
     },
     "packages/test-utils": {
       "name": "@qwen-code/qwen-code-test-utils",
-      "version": "0.0.13",
+      "version": "0.0.11",
       "dev": true,
       "license": "Apache-2.0",
       "devDependencies": {
@@ -13800,7 +13800,7 @@
     },
     "packages/vscode-ide-companion": {
       "name": "qwen-code-vscode-ide-companion",
-      "version": "0.0.13",
+      "version": "0.0.11",
       "license": "LICENSE",
       "dependencies": {
         "@modelcontextprotocol/sdk": "^1.15.1",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qwen-code/qwen-code",
-  "version": "0.0.13",
+  "version": "0.0.11",
   "engines": {
     "node": ">=20.0.0"
   },
@@ -13,7 +13,7 @@
     "url": "git+https://github.com/QwenLM/qwen-code.git"
   },
   "config": {
-    "sandboxImageUri": "ghcr.io/qwenlm/qwen-code:0.0.13"
+    "sandboxImageUri": "ghcr.io/qwenlm/qwen-code:0.0.11"
   },
   "scripts": {
     "start": "node scripts/start.js",

packages/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qwen-code/qwen-code",
-  "version": "0.0.13",
+  "version": "0.0.11",
   "description": "Qwen Code",
   "repository": {
     "type": "git",
@@ -25,7 +25,7 @@
     "dist"
   ],
   "config": {
-    "sandboxImageUri": "ghcr.io/qwenlm/qwen-code:0.0.13"
+    "sandboxImageUri": "ghcr.io/qwenlm/qwen-code:0.0.11"
   },
   "dependencies": {
     "@google/genai": "1.9.0",

packages/cli/src/config/config.test.ts

@@ -1514,7 +1514,7 @@ describe('loadCliConfig model selection', () => {
       argv,
     );
 
-    expect(config.getModel()).toBe('coder-model');
+    expect(config.getModel()).toBe('qwen3-coder-plus');
   });
 
   it('always prefers model from argvs', async () => {

packages/cli/src/config/config.ts

@@ -82,7 +82,6 @@ export interface CliArgs {
   includeDirectories: string[] | undefined;
   tavilyApiKey: string | undefined;
   screenReader: boolean | undefined;
-  vlmSwitchMode: string | undefined;
 }
 
 export async function parseArguments(settings: Settings): Promise<CliArgs> {
@@ -250,13 +249,6 @@ export async function parseArguments(settings: Settings): Promise<CliArgs> {
           description: 'Enable screen reader mode for accessibility.',
           default: false,
         })
-        .option('vlm-switch-mode', {
-          type: 'string',
-          choices: ['once', 'session', 'persist'],
-          description:
-            'Default behavior when images are detected in input. Values: once (one-time switch), session (switch for entire session), persist (continue with current model). Overrides settings files.',
-          default: process.env['VLM_SWITCH_MODE'],
-        })
         .check((argv) => {
           if (argv.prompt && argv['promptInteractive']) {
             throw new Error(
@@ -532,9 +524,6 @@ export async function loadCliConfig(
     argv.screenReader !== undefined
       ? argv.screenReader
       : (settings.ui?.accessibility?.screenReader ?? false);
-
-  const vlmSwitchMode =
-    argv.vlmSwitchMode || settings.experimental?.vlmSwitchMode;
   return new Config({
     sessionId,
     embeddingModel: DEFAULT_GEMINI_EMBEDDING_MODEL,
@@ -641,7 +630,6 @@ export async function loadCliConfig(
     skipNextSpeakerCheck: settings.model?.skipNextSpeakerCheck,
     enablePromptCompletion: settings.general?.enablePromptCompletion ?? false,
     skipLoopDetection: settings.skipLoopDetection ?? false,
-    vlmSwitchMode,
   });
 }
 

packages/cli/src/config/settings.test.ts

@@ -69,11 +69,7 @@ const MOCK_WORKSPACE_SETTINGS_PATH = pathActual.join(
 );
 
 // A more flexible type for test data that allows arbitrary properties.
-type TestSettings = Settings & {
-  [key: string]: unknown;
-  nested?: { [key: string]: unknown };
-  nestedObj?: { [key: string]: unknown };
-};
+type TestSettings = Settings & { [key: string]: unknown };
 
 vi.mock('fs', async (importOriginal) => {
   // Get all the functions from the real 'fs' module
@@ -141,9 +137,6 @@ describe('Settings Loading and Merging', () => {
         advanced: {
           excludedEnvVars: [],
         },
-        experimental: {},
-        contentGenerator: {},
-        systemPromptMappings: {},
         extensions: {
           disabled: [],
           workspacesWithMigrationNudge: [],
@@ -204,9 +197,6 @@ describe('Settings Loading and Merging', () => {
         advanced: {
           excludedEnvVars: [],
         },
-        experimental: {},
-        contentGenerator: {},
-        systemPromptMappings: {},
         extensions: {
           disabled: [],
           workspacesWithMigrationNudge: [],
@@ -270,9 +260,6 @@ describe('Settings Loading and Merging', () => {
         advanced: {
           excludedEnvVars: [],
         },
-        experimental: {},
-        contentGenerator: {},
-        systemPromptMappings: {},
         extensions: {
           disabled: [],
           workspacesWithMigrationNudge: [],
@@ -333,9 +320,6 @@ describe('Settings Loading and Merging', () => {
         advanced: {
           excludedEnvVars: [],
         },
-        experimental: {},
-        contentGenerator: {},
-        systemPromptMappings: {},
         extensions: {
           disabled: [],
           workspacesWithMigrationNudge: [],
@@ -401,9 +385,6 @@ describe('Settings Loading and Merging', () => {
         advanced: {
           excludedEnvVars: [],
         },
-        experimental: {},
-        contentGenerator: {},
-        systemPromptMappings: {},
         extensions: {
           disabled: [],
           workspacesWithMigrationNudge: [],
@@ -496,9 +477,6 @@ describe('Settings Loading and Merging', () => {
         advanced: {
           excludedEnvVars: [],
         },
-        experimental: {},
-        contentGenerator: {},
-        systemPromptMappings: {},
         extensions: {
           disabled: [],
           workspacesWithMigrationNudge: [],
@@ -584,9 +562,6 @@ describe('Settings Loading and Merging', () => {
         advanced: {
           excludedEnvVars: [],
         },
-        experimental: {},
-        contentGenerator: {},
-        systemPromptMappings: {},
         extensions: {
           disabled: [],
           workspacesWithMigrationNudge: [],
@@ -716,9 +691,6 @@ describe('Settings Loading and Merging', () => {
             '/system/dir',
           ],
         },
-        experimental: {},
-        contentGenerator: {},
-        systemPromptMappings: {},
         extensions: {
           disabled: [],
           workspacesWithMigrationNudge: [],
@@ -1459,9 +1431,6 @@ describe('Settings Loading and Merging', () => {
         advanced: {
           excludedEnvVars: [],
         },
-        experimental: {},
-        contentGenerator: {},
-        systemPromptMappings: {},
         extensions: {
           disabled: [],
           workspacesWithMigrationNudge: [],
@@ -1547,11 +1516,7 @@ describe('Settings Loading and Merging', () => {
         'workspace_endpoint_from_env/api',
       );
       expect(
-        (
-          (settings.workspace.settings as TestSettings).nested as {
-            [key: string]: unknown;
-          }
-        )['value'],
+        (settings.workspace.settings as TestSettings)['nested']['value'],
       ).toBe('workspace_endpoint_from_env');
       expect((settings.merged as TestSettings)['endpoint']).toBe(
         'workspace_endpoint_from_env/api',
@@ -1801,39 +1766,19 @@ describe('Settings Loading and Merging', () => {
       ).toBeUndefined();
 
       expect(
-        (
-          (settings.user.settings as TestSettings).nestedObj as {
-            [key: string]: unknown;
-          }
-        )['nestedNull'],
+        (settings.user.settings as TestSettings)['nestedObj']['nestedNull'],
       ).toBeNull();
       expect(
-        (
-          (settings.user.settings as TestSettings).nestedObj as {
-            [key: string]: unknown;
-          }
-        )['nestedBool'],
+        (settings.user.settings as TestSettings)['nestedObj']['nestedBool'],
       ).toBe(true);
       expect(
-        (
-          (settings.user.settings as TestSettings).nestedObj as {
-            [key: string]: unknown;
-          }
-        )['nestedNum'],
+        (settings.user.settings as TestSettings)['nestedObj']['nestedNum'],
       ).toBe(0);
       expect(
-        (
-          (settings.user.settings as TestSettings).nestedObj as {
-            [key: string]: unknown;
-          }
-        )['nestedString'],
+        (settings.user.settings as TestSettings)['nestedObj']['nestedString'],
       ).toBe('literal');
       expect(
-        (
-          (settings.user.settings as TestSettings).nestedObj as {
-            [key: string]: unknown;
-          }
-        )['anotherEnv'],
+        (settings.user.settings as TestSettings)['nestedObj']['anotherEnv'],
       ).toBe('env_string_nested_value');
 
       delete process.env['MY_ENV_STRING'];
@@ -1919,9 +1864,6 @@ describe('Settings Loading and Merging', () => {
           advanced: {
             excludedEnvVars: [],
           },
-          experimental: {},
-          contentGenerator: {},
-          systemPromptMappings: {},
           extensions: {
             disabled: [],
             workspacesWithMigrationNudge: [],
@@ -2394,14 +2336,14 @@ describe('Settings Loading and Merging', () => {
           vimMode: false,
         },
         model: {
-          maxSessionTurns: -1,
+          maxSessionTurns: 0,
         },
         context: {
           includeDirectories: [],
         },
         security: {
           folderTrust: {
-            enabled: false,
+            enabled: null,
           },
         },
       };
@@ -2410,9 +2352,9 @@ describe('Settings Loading and Merging', () => {
 
       expect(v1Settings).toEqual({
         vimMode: false,
-        maxSessionTurns: -1,
+        maxSessionTurns: 0,
         includeDirectories: [],
-        folderTrust: false,
+        folderTrust: null,
       });
     });
 

packages/cli/src/config/settings.ts

@@ -396,24 +396,6 @@ function mergeSettings(
         ]),
       ],
     },
-    experimental: {
-      ...(systemDefaults.experimental || {}),
-      ...(user.experimental || {}),
-      ...(safeWorkspaceWithoutFolderTrust.experimental || {}),
-      ...(system.experimental || {}),
-    },
-    contentGenerator: {
-      ...(systemDefaults.contentGenerator || {}),
-      ...(user.contentGenerator || {}),
-      ...(safeWorkspaceWithoutFolderTrust.contentGenerator || {}),
-      ...(system.contentGenerator || {}),
-    },
-    systemPromptMappings: {
-      ...(systemDefaults.systemPromptMappings || {}),
-      ...(user.systemPromptMappings || {}),
-      ...(safeWorkspaceWithoutFolderTrust.systemPromptMappings || {}),
-      ...(system.systemPromptMappings || {}),
-    },
     extensions: {
       ...(systemDefaults.extensions || {}),
       ...(user.extensions || {}),

packages/cli/src/config/settingsSchema.ts

@@ -746,21 +746,11 @@ export const SETTINGS_SCHEMA = {
         label: 'Vision Model Preview',
         category: 'Experimental',
         requiresRestart: false,
-        default: true,
+        default: false,
         description:
           'Enable vision model support and auto-switching functionality. When disabled, vision models like qwen-vl-max-latest will be hidden and auto-switching will not occur.',
         showInDialog: true,
       },
-      vlmSwitchMode: {
-        type: 'string',
-        label: 'VLM Switch Mode',
-        category: 'Experimental',
-        requiresRestart: false,
-        default: undefined as string | undefined,
-        description:
-          'Default behavior when images are detected in input. Values: once (one-time switch), session (switch for entire session), persist (continue with current model). If not set, user will be prompted each time. This is a temporary experimental feature.',
-        showInDialog: false,
-      },
     },
   },
 

packages/cli/src/ui/App.tsx

@@ -566,9 +566,7 @@ const App = ({ config, settings, startupWarnings = [], version }: AppProps) => {
       }
 
       // Switch model for future use but return false to stop current retry
-      config.setModel(fallbackModel).catch((error) => {
-        console.error('Failed to switch to fallback model:', error);
-      });
+      config.setModel(fallbackModel);
       config.setFallbackMode(true);
       logFlashFallback(
         config,
@@ -652,28 +650,17 @@ const App = ({ config, settings, startupWarnings = [], version }: AppProps) => {
   }, []);
 
   const handleModelSelect = useCallback(
-    async (modelId: string) => {
-      try {
-        await config.setModel(modelId);
-        setCurrentModel(modelId);
-        setIsModelSelectionDialogOpen(false);
-        addItem(
-          {
-            type: MessageType.INFO,
-            text: `Switched model to \`${modelId}\` for this session.`,
-          },
-          Date.now(),
-        );
-      } catch (error) {
-        console.error('Failed to switch model:', error);
-        addItem(
-          {
-            type: MessageType.ERROR,
-            text: `Failed to switch to model \`${modelId}\`. Please try again.`,
-          },
-          Date.now(),
-        );
-      }
+    (modelId: string) => {
+      config.setModel(modelId);
+      setCurrentModel(modelId);
+      setIsModelSelectionDialogOpen(false);
+      addItem(
+        {
+          type: MessageType.INFO,
+          text: `Switched model to \`${modelId}\` for this session.`,
+        },
+        Date.now(),
+      );
     },
     [config, setCurrentModel, addItem],
   );
@@ -683,7 +670,7 @@ const App = ({ config, settings, startupWarnings = [], version }: AppProps) => {
     if (!contentGeneratorConfig) return [];
 
     const visionModelPreviewEnabled =
-      settings.merged.experimental?.visionModelPreview ?? true;
+      settings.merged.experimental?.visionModelPreview ?? false;
 
     switch (contentGeneratorConfig.authType) {
       case AuthType.QWEN_OAUTH:
@@ -772,7 +759,7 @@ const App = ({ config, settings, startupWarnings = [], version }: AppProps) => {
     setModelSwitchedFromQuotaError,
     refreshStatic,
     () => cancelHandlerRef.current(),
-    settings.merged.experimental?.visionModelPreview ?? true,
+    settings.merged.experimental?.visionModelPreview ?? false,
     handleVisionSwitchRequired,
   );
 

packages/cli/src/ui/components/ModelSwitchDialog.test.tsx

@@ -46,8 +46,8 @@ describe('ModelSwitchDialog', () => {
         value: VisionSwitchOutcome.SwitchSessionToVL,
       },
       {
-        label: 'Continue with current model',
-        value: VisionSwitchOutcome.ContinueWithCurrentModel,
+        label: 'Do not switch, show guidance',
+        value: VisionSwitchOutcome.DisallowWithGuidance,
       },
     ];
 
@@ -81,18 +81,18 @@ describe('ModelSwitchDialog', () => {
     );
   });
 
-  it('should call onSelect with ContinueWithCurrentModel when third option is selected', () => {
+  it('should call onSelect with DisallowWithGuidance when third option is selected', () => {
     render(<ModelSwitchDialog onSelect={mockOnSelect} />);
 
     const onSelectCallback = mockRadioButtonSelect.mock.calls[0][0].onSelect;
-    onSelectCallback(VisionSwitchOutcome.ContinueWithCurrentModel);
+    onSelectCallback(VisionSwitchOutcome.DisallowWithGuidance);
 
     expect(mockOnSelect).toHaveBeenCalledWith(
-      VisionSwitchOutcome.ContinueWithCurrentModel,
+      VisionSwitchOutcome.DisallowWithGuidance,
     );
   });
 
-  it('should setup escape key handler to call onSelect with ContinueWithCurrentModel', () => {
+  it('should setup escape key handler to call onSelect with DisallowWithGuidance', () => {
     render(<ModelSwitchDialog onSelect={mockOnSelect} />);
 
     expect(mockUseKeypress).toHaveBeenCalledWith(expect.any(Function), {
@@ -104,7 +104,7 @@ describe('ModelSwitchDialog', () => {
     keypressHandler({ name: 'escape' });
 
     expect(mockOnSelect).toHaveBeenCalledWith(
-      VisionSwitchOutcome.ContinueWithCurrentModel,
+      VisionSwitchOutcome.DisallowWithGuidance,
     );
   });
 
@@ -126,9 +126,13 @@ describe('ModelSwitchDialog', () => {
 
   describe('VisionSwitchOutcome enum', () => {
     it('should have correct enum values', () => {
-      expect(VisionSwitchOutcome.SwitchOnce).toBe('once');
-      expect(VisionSwitchOutcome.SwitchSessionToVL).toBe('session');
-      expect(VisionSwitchOutcome.ContinueWithCurrentModel).toBe('persist');
+      expect(VisionSwitchOutcome.SwitchOnce).toBe('switch_once');
+      expect(VisionSwitchOutcome.SwitchSessionToVL).toBe(
+        'switch_session_to_vl',
+      );
+      expect(VisionSwitchOutcome.DisallowWithGuidance).toBe(
+        'disallow_with_guidance',
+      );
     });
   });
 
@@ -140,7 +144,7 @@ describe('ModelSwitchDialog', () => {
     // Call multiple times
     onSelectCallback(VisionSwitchOutcome.SwitchOnce);
     onSelectCallback(VisionSwitchOutcome.SwitchSessionToVL);
-    onSelectCallback(VisionSwitchOutcome.ContinueWithCurrentModel);
+    onSelectCallback(VisionSwitchOutcome.DisallowWithGuidance);
 
     expect(mockOnSelect).toHaveBeenCalledTimes(3);
     expect(mockOnSelect).toHaveBeenNthCalledWith(
@@ -153,7 +157,7 @@ describe('ModelSwitchDialog', () => {
     );
     expect(mockOnSelect).toHaveBeenNthCalledWith(
       3,
-      VisionSwitchOutcome.ContinueWithCurrentModel,
+      VisionSwitchOutcome.DisallowWithGuidance,
     );
   });
 
@@ -175,7 +179,7 @@ describe('ModelSwitchDialog', () => {
 
     expect(mockOnSelect).toHaveBeenCalledTimes(2);
     expect(mockOnSelect).toHaveBeenCalledWith(
-      VisionSwitchOutcome.ContinueWithCurrentModel,
+      VisionSwitchOutcome.DisallowWithGuidance,
     );
   });
 });

packages/cli/src/ui/components/ModelSwitchDialog.tsx

@@ -14,9 +14,9 @@ import {
 import { useKeypress } from '../hooks/useKeypress.js';
 
 export enum VisionSwitchOutcome {
-  SwitchOnce = 'once',
-  SwitchSessionToVL = 'session',
-  ContinueWithCurrentModel = 'persist',
+  SwitchOnce = 'switch_once',
+  SwitchSessionToVL = 'switch_session_to_vl',
+  DisallowWithGuidance = 'disallow_with_guidance',
 }
 
 export interface ModelSwitchDialogProps {
@@ -29,7 +29,7 @@ export const ModelSwitchDialog: React.FC<ModelSwitchDialogProps> = ({
   useKeypress(
     (key) => {
       if (key.name === 'escape') {
-        onSelect(VisionSwitchOutcome.ContinueWithCurrentModel);
+        onSelect(VisionSwitchOutcome.DisallowWithGuidance);
       }
     },
     { isActive: true },
@@ -45,8 +45,8 @@ export const ModelSwitchDialog: React.FC<ModelSwitchDialogProps> = ({
       value: VisionSwitchOutcome.SwitchSessionToVL,
     },
     {
-      label: 'Continue with current model',
-      value: VisionSwitchOutcome.ContinueWithCurrentModel,
+      label: 'Do not switch, show guidance',
+      value: VisionSwitchOutcome.DisallowWithGuidance,
     },
   ];
 

packages/cli/src/ui/contexts/KeypressContext.test.tsx

@@ -526,7 +526,7 @@ describe('KeypressContext - Kitty Protocol', () => {
         });
 
         await waitFor(() => {
-          expect(keyHandler).toHaveBeenCalledTimes(6); // 1 paste event + 5 individual chars for 'after'
+          expect(keyHandler).toHaveBeenCalledTimes(2); // 1 paste event + 1 paste event for 'after'
         });
 
         // Should emit paste event first
@@ -538,40 +538,12 @@ describe('KeypressContext - Kitty Protocol', () => {
           }),
         );
 
-        // Then process 'after' as individual characters (since it doesn't contain return)
+        // Then process 'after' as a paste event (since it's > 2 chars)
         expect(keyHandler).toHaveBeenNthCalledWith(
           2,
           expect.objectContaining({
-            name: 'a',
-            paste: false,
-          }),
-        );
-        expect(keyHandler).toHaveBeenNthCalledWith(
-          3,
-          expect.objectContaining({
-            name: 'f',
-            paste: false,
-          }),
-        );
-        expect(keyHandler).toHaveBeenNthCalledWith(
-          4,
-          expect.objectContaining({
-            name: 't',
-            paste: false,
-          }),
-        );
-        expect(keyHandler).toHaveBeenNthCalledWith(
-          5,
-          expect.objectContaining({
-            name: 'e',
-            paste: false,
-          }),
-        );
-        expect(keyHandler).toHaveBeenNthCalledWith(
-          6,
-          expect.objectContaining({
-            name: 'r',
-            paste: false,
+            paste: true,
+            sequence: 'after',
           }),
         );
       });
@@ -599,7 +571,7 @@ describe('KeypressContext - Kitty Protocol', () => {
         });
 
         await waitFor(() => {
-          expect(keyHandler).toHaveBeenCalledTimes(16); // 5 + 1 + 6 + 1 + 3 = 16 calls
+          expect(keyHandler).toHaveBeenCalledTimes(14); // Adjusted based on actual behavior
         });
 
         // Check the sequence: 'start' (5 chars) + paste1 + 'middle' (6 chars) + paste2 + 'end' (3 chars as paste)
@@ -671,18 +643,13 @@ describe('KeypressContext - Kitty Protocol', () => {
           }),
         );
 
-        // 'end' as individual characters (since it doesn't contain return)
+        // 'end' as paste event (since it's > 2 chars)
         expect(keyHandler).toHaveBeenNthCalledWith(
           callIndex++,
-          expect.objectContaining({ name: 'e' }),
-        );
-        expect(keyHandler).toHaveBeenNthCalledWith(
-          callIndex++,
-          expect.objectContaining({ name: 'n' }),
-        );
-        expect(keyHandler).toHaveBeenNthCalledWith(
-          callIndex++,
-          expect.objectContaining({ name: 'd' }),
+          expect.objectContaining({
+            paste: true,
+            sequence: 'end',
+          }),
         );
       });
 
@@ -771,18 +738,16 @@ describe('KeypressContext - Kitty Protocol', () => {
         });
 
         await waitFor(() => {
-          // With the current implementation, fragmented paste markers get reconstructed
-          // into a single paste event for 'content'
-          expect(keyHandler).toHaveBeenCalledTimes(1);
+          // With the current implementation, fragmented data gets processed differently
+          // The first fragment '\x1b[20' gets processed as individual characters
+          // The second fragment '0~content\x1b[2' gets processed as paste + individual chars
+          // The third fragment '01~' gets processed as individual characters
+          expect(keyHandler).toHaveBeenCalled();
         });
 
-        // Should reconstruct the fragmented paste markers into a single paste event
-        expect(keyHandler).toHaveBeenCalledWith(
-          expect.objectContaining({
-            paste: true,
-            sequence: 'content',
-          }),
-        );
+        // The current implementation processes fragmented paste markers as separate events
+        // rather than reconstructing them into a single paste event
+        expect(keyHandler.mock.calls.length).toBeGreaterThan(1);
       });
     });
 
@@ -886,47 +851,28 @@ describe('KeypressContext - Kitty Protocol', () => {
           stdin.emit('data', Buffer.from('lo'));
         });
 
-        // With the current implementation, data is processed as individual characters
-        // since 'hel' doesn't contain return (0x0d)
+        // With the current implementation, data is processed as it arrives
+        // First chunk 'hel' is treated as paste (multi-character)
         expect(keyHandler).toHaveBeenNthCalledWith(
           1,
           expect.objectContaining({
-            name: 'h',
-            sequence: 'h',
-            paste: false,
+            paste: true,
+            sequence: 'hel',
           }),
         );
 
+        // Second chunk 'lo' is processed as individual characters
         expect(keyHandler).toHaveBeenNthCalledWith(
           2,
           expect.objectContaining({
-            name: 'e',
-            sequence: 'e',
+            name: 'l',
+            sequence: 'l',
             paste: false,
           }),
         );
 
         expect(keyHandler).toHaveBeenNthCalledWith(
           3,
-          expect.objectContaining({
-            name: 'l',
-            sequence: 'l',
-            paste: false,
-          }),
-        );
-
-        // Second chunk 'lo' is also processed as individual characters
-        expect(keyHandler).toHaveBeenNthCalledWith(
-          4,
-          expect.objectContaining({
-            name: 'l',
-            sequence: 'l',
-            paste: false,
-          }),
-        );
-
-        expect(keyHandler).toHaveBeenNthCalledWith(
-          5,
           expect.objectContaining({
             name: 'o',
             sequence: 'o',
@@ -934,7 +880,7 @@ describe('KeypressContext - Kitty Protocol', () => {
           }),
         );
 
-        expect(keyHandler).toHaveBeenCalledTimes(5);
+        expect(keyHandler).toHaveBeenCalledTimes(3);
       } finally {
         vi.useRealTimers();
       }
@@ -961,20 +907,14 @@ describe('KeypressContext - Kitty Protocol', () => {
         });
 
         // Should flush immediately without waiting for timeout
-        // Large data without return gets treated as individual characters
-        expect(keyHandler).toHaveBeenCalledTimes(65);
-
-        // Each character should be processed individually
-        for (let i = 0; i < 65; i++) {
-          expect(keyHandler).toHaveBeenNthCalledWith(
-            i + 1,
-            expect.objectContaining({
-              name: 'x',
-              sequence: 'x',
-              paste: false,
-            }),
-          );
-        }
+        // Large data gets treated as paste event
+        expect(keyHandler).toHaveBeenCalledTimes(1);
+        expect(keyHandler).toHaveBeenCalledWith(
+          expect.objectContaining({
+            paste: true,
+            sequence: largeData,
+          }),
+        );
 
         // Advancing timer should not cause additional calls
         const callCountBefore = keyHandler.mock.calls.length;

packages/cli/src/ui/contexts/KeypressContext.tsx

@@ -407,11 +407,7 @@ export function KeypressProvider({
         return;
       }
 
-      if (
-        (rawDataBuffer.length <= 2 && rawDataBuffer.includes(0x0d)) ||
-        !rawDataBuffer.includes(0x0d) ||
-        isPaste
-      ) {
+      if (rawDataBuffer.length <= 2 || isPaste) {
         keypressStream.write(rawDataBuffer);
       } else {
         // Flush raw data buffer as a paste event

packages/cli/src/ui/hooks/useGeminiStream.test.tsx

@@ -60,9 +60,7 @@ const mockParseAndFormatApiError = vi.hoisted(() => vi.fn());
 const mockHandleVisionSwitch = vi.hoisted(() =>
   vi.fn().mockResolvedValue({ shouldProceed: true }),
 );
-const mockRestoreOriginalModel = vi.hoisted(() =>
-  vi.fn().mockResolvedValue(undefined),
-);
+const mockRestoreOriginalModel = vi.hoisted(() => vi.fn());
 
 vi.mock('@qwen-code/qwen-code-core', async (importOriginal) => {
   const actualCoreModule = (await importOriginal()) as any;
@@ -303,8 +301,6 @@ describe('useGeminiStream', () => {
           () => {},
           () => {},
           () => {},
-          false, // visionModelPreviewEnabled
-          undefined, // onVisionSwitchRequired (optional)
         );
       },
       {
@@ -466,8 +462,6 @@ describe('useGeminiStream', () => {
         () => {},
         () => {},
         () => {},
-        false, // visionModelPreviewEnabled
-        undefined, // onVisionSwitchRequired (optional)
       ),
     );
 
@@ -547,8 +541,6 @@ describe('useGeminiStream', () => {
         () => {},
         () => {},
         () => {},
-        false, // visionModelPreviewEnabled
-        undefined, // onVisionSwitchRequired (optional)
       ),
     );
 
@@ -657,8 +649,6 @@ describe('useGeminiStream', () => {
         () => {},
         () => {},
         () => {},
-        false, // visionModelPreviewEnabled
-        undefined, // onVisionSwitchRequired (optional)
       ),
     );
 
@@ -768,8 +758,6 @@ describe('useGeminiStream', () => {
         () => {},
         () => {},
         () => {},
-        false, // visionModelPreviewEnabled
-        undefined, // onVisionSwitchRequired (optional)
       ),
     );
 
@@ -899,8 +887,6 @@ describe('useGeminiStream', () => {
           () => {},
           () => {},
           cancelSubmitSpy,
-          false, // visionModelPreviewEnabled
-          undefined, // onVisionSwitchRequired (optional)
         ),
       );
 
@@ -1212,8 +1198,6 @@ describe('useGeminiStream', () => {
           () => {},
           () => {},
           () => {},
-          false, // visionModelPreviewEnabled
-          undefined, // onVisionSwitchRequired (optional)
         ),
       );
 
@@ -1267,8 +1251,6 @@ describe('useGeminiStream', () => {
           () => {},
           () => {},
           () => {},
-          false, // visionModelPreviewEnabled
-          undefined, // onVisionSwitchRequired (optional)
         ),
       );
 
@@ -1319,8 +1301,6 @@ describe('useGeminiStream', () => {
           () => {},
           () => {},
           () => {},
-          false, // visionModelPreviewEnabled
-          undefined, // onVisionSwitchRequired (optional)
         ),
       );
 
@@ -1369,8 +1349,6 @@ describe('useGeminiStream', () => {
           () => {},
           () => {},
           () => {},
-          false, // visionModelPreviewEnabled
-          undefined, // onVisionSwitchRequired (optional)
         ),
       );
 
@@ -1420,8 +1398,6 @@ describe('useGeminiStream', () => {
           () => {},
           () => {},
           () => {},
-          false, // visionModelPreviewEnabled
-          undefined, // onVisionSwitchRequired (optional)
         ),
       );
 
@@ -1511,8 +1487,6 @@ describe('useGeminiStream', () => {
             () => {},
             () => {},
             () => {},
-            false, // visionModelPreviewEnabled
-            undefined, // onVisionSwitchRequired (optional)
           ),
         );
 
@@ -1563,8 +1537,6 @@ describe('useGeminiStream', () => {
         vi.fn(), // setModelSwitched
         vi.fn(), // onEditorClose
         vi.fn(), // onCancelSubmit
-        false, // visionModelPreviewEnabled
-        undefined, // onVisionSwitchRequired (optional)
       ),
     );
 
@@ -1630,8 +1602,6 @@ describe('useGeminiStream', () => {
           () => {},
           () => {},
           () => {},
-          false, // visionModelPreviewEnabled
-          undefined, // onVisionSwitchRequired (optional)
         ),
       );
 
@@ -1710,8 +1680,6 @@ describe('useGeminiStream', () => {
           () => {},
           () => {},
           () => {},
-          false, // visionModelPreviewEnabled
-          undefined, // onVisionSwitchRequired (optional)
         ),
       );
 
@@ -1766,8 +1734,6 @@ describe('useGeminiStream', () => {
           () => {},
           () => {},
           () => {},
-          false, // visionModelPreviewEnabled
-          undefined, // onVisionSwitchRequired (optional)
         ),
       );
 
@@ -1977,8 +1943,6 @@ describe('useGeminiStream', () => {
           () => {},
           () => {},
           () => {},
-          false, // visionModelPreviewEnabled
-          undefined, // onVisionSwitchRequired (optional)
         ),
       );
 
@@ -2011,8 +1975,6 @@ describe('useGeminiStream', () => {
           () => {},
           () => {},
           () => {},
-          false, // visionModelPreviewEnabled
-          undefined, // onVisionSwitchRequired (optional)
         ),
       );
 
@@ -2066,8 +2028,6 @@ describe('useGeminiStream', () => {
           () => {},
           () => {},
           () => {},
-          false, // visionModelPreviewEnabled
-          undefined, // onVisionSwitchRequired (optional)
         ),
       );
 
@@ -2105,8 +2065,6 @@ describe('useGeminiStream', () => {
           () => {},
           () => {},
           () => {},
-          false, // visionModelPreviewEnabled
-          undefined, // onVisionSwitchRequired (optional)
         ),
       );
 

packages/cli/src/ui/hooks/useGeminiStream.ts

@@ -89,7 +89,7 @@ export const useGeminiStream = (
   setModelSwitchedFromQuotaError: React.Dispatch<React.SetStateAction<boolean>>,
   onEditorClose: () => void,
   onCancelSubmit: () => void,
-  visionModelPreviewEnabled: boolean,
+  visionModelPreviewEnabled: boolean = false,
   onVisionSwitchRequired?: (query: PartListUnion) => Promise<{
     modelOverride?: string;
     persistSessionModel?: string;
@@ -765,9 +765,7 @@ export const useGeminiStream = (
 
         if (processingStatus === StreamProcessingStatus.UserCancelled) {
           // Restore original model if it was temporarily overridden
-          restoreOriginalModel().catch((error) => {
-            console.error('Failed to restore original model:', error);
-          });
+          restoreOriginalModel();
           isSubmittingQueryRef.current = false;
           return;
         }
@@ -782,14 +780,10 @@ export const useGeminiStream = (
         }
 
         // Restore original model if it was temporarily overridden
-        restoreOriginalModel().catch((error) => {
-          console.error('Failed to restore original model:', error);
-        });
+        restoreOriginalModel();
       } catch (error: unknown) {
         // Restore original model if it was temporarily overridden
-        restoreOriginalModel().catch((error) => {
-          console.error('Failed to restore original model:', error);
-        });
+        restoreOriginalModel();
 
         if (error instanceof UnauthorizedError) {
           onAuthError();

packages/cli/src/ui/hooks/useVisionAutoSwitch.test.ts

@@ -8,7 +8,7 @@
 import { describe, it, expect, vi, beforeEach } from 'vitest';
 import { renderHook, act } from '@testing-library/react';
 import type { Part, PartListUnion } from '@google/genai';
-import { AuthType, type Config, ApprovalMode } from '@qwen-code/qwen-code-core';
+import { AuthType, type Config } from '@qwen-code/qwen-code-core';
 import {
   shouldOfferVisionSwitch,
   processVisionSwitchOutcome,
@@ -41,7 +41,7 @@ describe('useVisionAutoSwitch helpers', () => {
       const result = shouldOfferVisionSwitch(
         parts,
         AuthType.QWEN_OAUTH,
-        'vision-model',
+        'qwen-vl-max-latest',
         true,
       );
       expect(result).toBe(false);
@@ -108,56 +108,6 @@ describe('useVisionAutoSwitch helpers', () => {
       );
       expect(result).toBe(false);
     });
-
-    it('returns true when image parts exist in YOLO mode context', () => {
-      const parts: PartListUnion = [
-        { inlineData: { mimeType: 'image/png', data: '...' } },
-      ];
-      const result = shouldOfferVisionSwitch(
-        parts,
-        AuthType.QWEN_OAUTH,
-        'qwen3-coder-plus',
-        true,
-      );
-      expect(result).toBe(true);
-    });
-
-    it('returns false when no image parts exist in YOLO mode context', () => {
-      const parts: PartListUnion = [{ text: 'just text' }];
-      const result = shouldOfferVisionSwitch(
-        parts,
-        AuthType.QWEN_OAUTH,
-        'qwen3-coder-plus',
-        true,
-      );
-      expect(result).toBe(false);
-    });
-
-    it('returns false when already using vision model in YOLO mode context', () => {
-      const parts: PartListUnion = [
-        { inlineData: { mimeType: 'image/png', data: '...' } },
-      ];
-      const result = shouldOfferVisionSwitch(
-        parts,
-        AuthType.QWEN_OAUTH,
-        'vision-model',
-        true,
-      );
-      expect(result).toBe(false);
-    });
-
-    it('returns false when authType is not QWEN_OAUTH in YOLO mode context', () => {
-      const parts: PartListUnion = [
-        { inlineData: { mimeType: 'image/png', data: '...' } },
-      ];
-      const result = shouldOfferVisionSwitch(
-        parts,
-        AuthType.USE_GEMINI,
-        'qwen3-coder-plus',
-        true,
-      );
-      expect(result).toBe(false);
-    });
   });
 
   describe('processVisionSwitchOutcome', () => {
@@ -175,11 +125,11 @@ describe('useVisionAutoSwitch helpers', () => {
       expect(result).toEqual({ persistSessionModel: vl });
     });
 
-    it('maps ContinueWithCurrentModel to empty result', () => {
+    it('maps DisallowWithGuidance to showGuidance', () => {
       const result = processVisionSwitchOutcome(
-        VisionSwitchOutcome.ContinueWithCurrentModel,
+        VisionSwitchOutcome.DisallowWithGuidance,
       );
-      expect(result).toEqual({});
+      expect(result).toEqual({ showGuidance: true });
     });
   });
 
@@ -201,20 +151,13 @@ describe('useVisionAutoSwitch hook', () => {
     ts: number,
   ) => any;
 
-  const createMockConfig = (
-    authType: AuthType,
-    initialModel: string,
-    approvalMode: ApprovalMode = ApprovalMode.DEFAULT,
-    vlmSwitchMode?: string,
-  ) => {
+  const createMockConfig = (authType: AuthType, initialModel: string) => {
     let currentModel = initialModel;
     const mockConfig: Partial<Config> = {
       getModel: vi.fn(() => currentModel),
-      setModel: vi.fn(async (m: string) => {
+      setModel: vi.fn((m: string) => {
         currentModel = m;
       }),
-      getApprovalMode: vi.fn(() => approvalMode),
-      getVlmSwitchMode: vi.fn(() => vlmSwitchMode),
       getContentGeneratorConfig: vi.fn(() => ({
         authType,
         model: currentModel,
@@ -283,9 +226,11 @@ describe('useVisionAutoSwitch hook', () => {
     expect(onVisionSwitchRequired).not.toHaveBeenCalled();
   });
 
-  it('continues with current model when dialog returns empty result', async () => {
+  it('shows guidance and blocks when dialog returns showGuidance', async () => {
     const config = createMockConfig(AuthType.QWEN_OAUTH, 'qwen3-coder-plus');
-    const onVisionSwitchRequired = vi.fn().mockResolvedValue({}); // Empty result for ContinueWithCurrentModel
+    const onVisionSwitchRequired = vi
+      .fn()
+      .mockResolvedValue({ showGuidance: true });
     const { result } = renderHook(() =>
       useVisionAutoSwitch(config, addItem as any, true, onVisionSwitchRequired),
     );
@@ -300,12 +245,11 @@ describe('useVisionAutoSwitch hook', () => {
       res = await result.current.handleVisionSwitch(parts, userTs, false);
     });
 
-    // Should not add any guidance message
-    expect(addItem).not.toHaveBeenCalledWith(
+    expect(addItem).toHaveBeenCalledWith(
       { type: MessageType.INFO, text: getVisionSwitchGuidanceMessage() },
       userTs,
     );
-    expect(res).toEqual({ shouldProceed: true });
+    expect(res).toEqual({ shouldProceed: false });
     expect(config.setModel).not.toHaveBeenCalled();
   });
 
@@ -314,7 +258,7 @@ describe('useVisionAutoSwitch hook', () => {
     const config = createMockConfig(AuthType.QWEN_OAUTH, initialModel);
     const onVisionSwitchRequired = vi
       .fn()
-      .mockResolvedValue({ modelOverride: 'coder-model' });
+      .mockResolvedValue({ modelOverride: 'qwen-vl-max-latest' });
     const { result } = renderHook(() =>
       useVisionAutoSwitch(config, addItem as any, true, onVisionSwitchRequired),
     );
@@ -329,26 +273,20 @@ describe('useVisionAutoSwitch hook', () => {
     });
 
     expect(res).toEqual({ shouldProceed: true, originalModel: initialModel });
-    expect(config.setModel).toHaveBeenCalledWith('coder-model', {
-      reason: 'vision_auto_switch',
-      context: 'User-prompted vision switch (one-time override)',
-    });
+    expect(config.setModel).toHaveBeenCalledWith('qwen-vl-max-latest');
 
     // Now restore
-    await act(async () => {
-      await result.current.restoreOriginalModel();
-    });
-    expect(config.setModel).toHaveBeenLastCalledWith(initialModel, {
-      reason: 'vision_auto_switch',
-      context: 'Restoring original model after vision switch',
+    act(() => {
+      result.current.restoreOriginalModel();
     });
+    expect(config.setModel).toHaveBeenLastCalledWith(initialModel);
   });
 
   it('persists session model when dialog requests persistence', async () => {
     const config = createMockConfig(AuthType.QWEN_OAUTH, 'qwen3-coder-plus');
     const onVisionSwitchRequired = vi
       .fn()
-      .mockResolvedValue({ persistSessionModel: 'coder-model' });
+      .mockResolvedValue({ persistSessionModel: 'qwen-vl-max-latest' });
     const { result } = renderHook(() =>
       useVisionAutoSwitch(config, addItem as any, true, onVisionSwitchRequired),
     );
@@ -363,17 +301,16 @@ describe('useVisionAutoSwitch hook', () => {
     });
 
     expect(res).toEqual({ shouldProceed: true });
-    expect(config.setModel).toHaveBeenCalledWith('coder-model', {
-      reason: 'vision_auto_switch',
-      context: 'User-prompted vision switch (session persistent)',
-    });
+    expect(config.setModel).toHaveBeenCalledWith('qwen-vl-max-latest');
 
     // Restore should be a no-op since no one-time override was used
-    await act(async () => {
-      await result.current.restoreOriginalModel();
+    act(() => {
+      result.current.restoreOriginalModel();
     });
     // Last call should still be the persisted model set
-    expect((config.setModel as any).mock.calls.pop()?.[0]).toBe('coder-model');
+    expect((config.setModel as any).mock.calls.pop()?.[0]).toBe(
+      'qwen-vl-max-latest',
+    );
   });
 
   it('returns shouldProceed=true when dialog returns no special flags', async () => {
@@ -434,420 +371,4 @@ describe('useVisionAutoSwitch hook', () => {
     expect(res).toEqual({ shouldProceed: true });
     expect(onVisionSwitchRequired).not.toHaveBeenCalled();
   });
-
-  describe('YOLO mode behavior', () => {
-    it('automatically switches to vision model in YOLO mode without showing dialog', async () => {
-      const initialModel = 'qwen3-coder-plus';
-      const config = createMockConfig(
-        AuthType.QWEN_OAUTH,
-        initialModel,
-        ApprovalMode.YOLO,
-      );
-      const onVisionSwitchRequired = vi.fn(); // Should not be called in YOLO mode
-      const { result } = renderHook(() =>
-        useVisionAutoSwitch(
-          config,
-          addItem as any,
-          true,
-          onVisionSwitchRequired,
-        ),
-      );
-
-      const parts: PartListUnion = [
-        { inlineData: { mimeType: 'image/png', data: '...' } },
-      ];
-
-      let res: any;
-      await act(async () => {
-        res = await result.current.handleVisionSwitch(parts, 7070, false);
-      });
-
-      // Should automatically switch without calling the dialog
-      expect(onVisionSwitchRequired).not.toHaveBeenCalled();
-      expect(res).toEqual({
-        shouldProceed: true,
-        originalModel: initialModel,
-      });
-      expect(config.setModel).toHaveBeenCalledWith(getDefaultVisionModel(), {
-        reason: 'vision_auto_switch',
-        context: 'YOLO mode auto-switch for image content',
-      });
-    });
-
-    it('does not switch in YOLO mode when no images are present', async () => {
-      const config = createMockConfig(
-        AuthType.QWEN_OAUTH,
-        'qwen3-coder-plus',
-        ApprovalMode.YOLO,
-      );
-      const onVisionSwitchRequired = vi.fn();
-      const { result } = renderHook(() =>
-        useVisionAutoSwitch(
-          config,
-          addItem as any,
-          true,
-          onVisionSwitchRequired,
-        ),
-      );
-
-      const parts: PartListUnion = [{ text: 'no images here' }];
-
-      let res: any;
-      await act(async () => {
-        res = await result.current.handleVisionSwitch(parts, 8080, false);
-      });
-
-      expect(res).toEqual({ shouldProceed: true });
-      expect(onVisionSwitchRequired).not.toHaveBeenCalled();
-      expect(config.setModel).not.toHaveBeenCalled();
-    });
-
-    it('does not switch in YOLO mode when already using vision model', async () => {
-      const config = createMockConfig(
-        AuthType.QWEN_OAUTH,
-        'vision-model',
-        ApprovalMode.YOLO,
-      );
-      const onVisionSwitchRequired = vi.fn();
-      const { result } = renderHook(() =>
-        useVisionAutoSwitch(
-          config,
-          addItem as any,
-          true,
-          onVisionSwitchRequired,
-        ),
-      );
-
-      const parts: PartListUnion = [
-        { inlineData: { mimeType: 'image/png', data: '...' } },
-      ];
-
-      let res: any;
-      await act(async () => {
-        res = await result.current.handleVisionSwitch(parts, 9090, false);
-      });
-
-      expect(res).toEqual({ shouldProceed: true });
-      expect(onVisionSwitchRequired).not.toHaveBeenCalled();
-      expect(config.setModel).not.toHaveBeenCalled();
-    });
-
-    it('restores original model after YOLO mode auto-switch', async () => {
-      const initialModel = 'qwen3-coder-plus';
-      const config = createMockConfig(
-        AuthType.QWEN_OAUTH,
-        initialModel,
-        ApprovalMode.YOLO,
-      );
-      const onVisionSwitchRequired = vi.fn();
-      const { result } = renderHook(() =>
-        useVisionAutoSwitch(
-          config,
-          addItem as any,
-          true,
-          onVisionSwitchRequired,
-        ),
-      );
-
-      const parts: PartListUnion = [
-        { inlineData: { mimeType: 'image/png', data: '...' } },
-      ];
-
-      // First, trigger the auto-switch
-      await act(async () => {
-        await result.current.handleVisionSwitch(parts, 10100, false);
-      });
-
-      // Verify model was switched
-      expect(config.setModel).toHaveBeenCalledWith(getDefaultVisionModel(), {
-        reason: 'vision_auto_switch',
-        context: 'YOLO mode auto-switch for image content',
-      });
-
-      // Now restore the original model
-      await act(async () => {
-        await result.current.restoreOriginalModel();
-      });
-
-      // Verify model was restored
-      expect(config.setModel).toHaveBeenLastCalledWith(initialModel, {
-        reason: 'vision_auto_switch',
-        context: 'Restoring original model after vision switch',
-      });
-    });
-
-    it('does not switch in YOLO mode when authType is not QWEN_OAUTH', async () => {
-      const config = createMockConfig(
-        AuthType.USE_GEMINI,
-        'qwen3-coder-plus',
-        ApprovalMode.YOLO,
-      );
-      const onVisionSwitchRequired = vi.fn();
-      const { result } = renderHook(() =>
-        useVisionAutoSwitch(
-          config,
-          addItem as any,
-          true,
-          onVisionSwitchRequired,
-        ),
-      );
-
-      const parts: PartListUnion = [
-        { inlineData: { mimeType: 'image/png', data: '...' } },
-      ];
-
-      let res: any;
-      await act(async () => {
-        res = await result.current.handleVisionSwitch(parts, 11110, false);
-      });
-
-      expect(res).toEqual({ shouldProceed: true });
-      expect(onVisionSwitchRequired).not.toHaveBeenCalled();
-      expect(config.setModel).not.toHaveBeenCalled();
-    });
-
-    it('does not switch in YOLO mode when visionModelPreviewEnabled is false', async () => {
-      const config = createMockConfig(
-        AuthType.QWEN_OAUTH,
-        'qwen3-coder-plus',
-        ApprovalMode.YOLO,
-      );
-      const onVisionSwitchRequired = vi.fn();
-      const { result } = renderHook(() =>
-        useVisionAutoSwitch(
-          config,
-          addItem as any,
-          false,
-          onVisionSwitchRequired,
-        ),
-      );
-
-      const parts: PartListUnion = [
-        { inlineData: { mimeType: 'image/png', data: '...' } },
-      ];
-
-      let res: any;
-      await act(async () => {
-        res = await result.current.handleVisionSwitch(parts, 12120, false);
-      });
-
-      expect(res).toEqual({ shouldProceed: true });
-      expect(onVisionSwitchRequired).not.toHaveBeenCalled();
-      expect(config.setModel).not.toHaveBeenCalled();
-    });
-
-    it('handles multiple image formats in YOLO mode', async () => {
-      const initialModel = 'qwen3-coder-plus';
-      const config = createMockConfig(
-        AuthType.QWEN_OAUTH,
-        initialModel,
-        ApprovalMode.YOLO,
-      );
-      const onVisionSwitchRequired = vi.fn();
-      const { result } = renderHook(() =>
-        useVisionAutoSwitch(
-          config,
-          addItem as any,
-          true,
-          onVisionSwitchRequired,
-        ),
-      );
-
-      const parts: PartListUnion = [
-        { text: 'Here are some images:' },
-        { inlineData: { mimeType: 'image/jpeg', data: '...' } },
-        { fileData: { mimeType: 'image/png', fileUri: 'file://image.png' } },
-        { text: 'Please analyze them.' },
-      ];
-
-      let res: any;
-      await act(async () => {
-        res = await result.current.handleVisionSwitch(parts, 13130, false);
-      });
-
-      expect(res).toEqual({
-        shouldProceed: true,
-        originalModel: initialModel,
-      });
-      expect(config.setModel).toHaveBeenCalledWith(getDefaultVisionModel(), {
-        reason: 'vision_auto_switch',
-        context: 'YOLO mode auto-switch for image content',
-      });
-      expect(onVisionSwitchRequired).not.toHaveBeenCalled();
-    });
-  });
-
-  describe('VLM switch mode default behavior', () => {
-    it('should automatically switch once when vlmSwitchMode is "once"', async () => {
-      const config = createMockConfig(
-        AuthType.QWEN_OAUTH,
-        'qwen3-coder-plus',
-        ApprovalMode.DEFAULT,
-        'once',
-      );
-      const onVisionSwitchRequired = vi.fn(); // Should not be called
-      const { result } = renderHook(() =>
-        useVisionAutoSwitch(
-          config,
-          addItem as any,
-          true,
-          onVisionSwitchRequired,
-        ),
-      );
-
-      const parts: PartListUnion = [
-        { inlineData: { mimeType: 'image/jpeg', data: 'base64data' } },
-      ];
-
-      const switchResult = await result.current.handleVisionSwitch(
-        parts,
-        Date.now(),
-        false,
-      );
-
-      expect(switchResult.shouldProceed).toBe(true);
-      expect(switchResult.originalModel).toBe('qwen3-coder-plus');
-      expect(config.setModel).toHaveBeenCalledWith('vision-model', {
-        reason: 'vision_auto_switch',
-        context: 'Default VLM switch mode: once (one-time override)',
-      });
-      expect(onVisionSwitchRequired).not.toHaveBeenCalled();
-    });
-
-    it('should switch session when vlmSwitchMode is "session"', async () => {
-      const config = createMockConfig(
-        AuthType.QWEN_OAUTH,
-        'qwen3-coder-plus',
-        ApprovalMode.DEFAULT,
-        'session',
-      );
-      const onVisionSwitchRequired = vi.fn(); // Should not be called
-      const { result } = renderHook(() =>
-        useVisionAutoSwitch(
-          config,
-          addItem as any,
-          true,
-          onVisionSwitchRequired,
-        ),
-      );
-
-      const parts: PartListUnion = [
-        { inlineData: { mimeType: 'image/jpeg', data: 'base64data' } },
-      ];
-
-      const switchResult = await result.current.handleVisionSwitch(
-        parts,
-        Date.now(),
-        false,
-      );
-
-      expect(switchResult.shouldProceed).toBe(true);
-      expect(switchResult.originalModel).toBeUndefined(); // No original model for session switch
-      expect(config.setModel).toHaveBeenCalledWith('vision-model', {
-        reason: 'vision_auto_switch',
-        context: 'Default VLM switch mode: session (session persistent)',
-      });
-      expect(onVisionSwitchRequired).not.toHaveBeenCalled();
-    });
-
-    it('should continue with current model when vlmSwitchMode is "persist"', async () => {
-      const config = createMockConfig(
-        AuthType.QWEN_OAUTH,
-        'qwen3-coder-plus',
-        ApprovalMode.DEFAULT,
-        'persist',
-      );
-      const onVisionSwitchRequired = vi.fn(); // Should not be called
-      const { result } = renderHook(() =>
-        useVisionAutoSwitch(
-          config,
-          addItem as any,
-          true,
-          onVisionSwitchRequired,
-        ),
-      );
-
-      const parts: PartListUnion = [
-        { inlineData: { mimeType: 'image/jpeg', data: 'base64data' } },
-      ];
-
-      const switchResult = await result.current.handleVisionSwitch(
-        parts,
-        Date.now(),
-        false,
-      );
-
-      expect(switchResult.shouldProceed).toBe(true);
-      expect(switchResult.originalModel).toBeUndefined();
-      expect(config.setModel).not.toHaveBeenCalled();
-      expect(onVisionSwitchRequired).not.toHaveBeenCalled();
-    });
-
-    it('should fall back to user prompt when vlmSwitchMode is not set', async () => {
-      const config = createMockConfig(
-        AuthType.QWEN_OAUTH,
-        'qwen3-coder-plus',
-        ApprovalMode.DEFAULT,
-        undefined, // No default mode
-      );
-      const onVisionSwitchRequired = vi
-        .fn()
-        .mockResolvedValue({ modelOverride: 'vision-model' });
-      const { result } = renderHook(() =>
-        useVisionAutoSwitch(
-          config,
-          addItem as any,
-          true,
-          onVisionSwitchRequired,
-        ),
-      );
-
-      const parts: PartListUnion = [
-        { inlineData: { mimeType: 'image/jpeg', data: 'base64data' } },
-      ];
-
-      const switchResult = await result.current.handleVisionSwitch(
-        parts,
-        Date.now(),
-        false,
-      );
-
-      expect(switchResult.shouldProceed).toBe(true);
-      expect(onVisionSwitchRequired).toHaveBeenCalledWith(parts);
-    });
-
-    it('should fall back to persist behavior when vlmSwitchMode has invalid value', async () => {
-      const config = createMockConfig(
-        AuthType.QWEN_OAUTH,
-        'qwen3-coder-plus',
-        ApprovalMode.DEFAULT,
-        'invalid-value',
-      );
-      const onVisionSwitchRequired = vi.fn(); // Should not be called
-      const { result } = renderHook(() =>
-        useVisionAutoSwitch(
-          config,
-          addItem as any,
-          true,
-          onVisionSwitchRequired,
-        ),
-      );
-
-      const parts: PartListUnion = [
-        { inlineData: { mimeType: 'image/jpeg', data: 'base64data' } },
-      ];
-
-      const switchResult = await result.current.handleVisionSwitch(
-        parts,
-        Date.now(),
-        false,
-      );
-
-      expect(switchResult.shouldProceed).toBe(true);
-      expect(switchResult.originalModel).toBeUndefined();
-      // For invalid values, it should continue with current model (persist behavior)
-      expect(config.setModel).not.toHaveBeenCalled();
-      expect(onVisionSwitchRequired).not.toHaveBeenCalled();
-    });
-  });
 });

packages/cli/src/ui/hooks/useVisionAutoSwitch.ts

@@ -5,7 +5,7 @@
  */
 
 import { type PartListUnion, type Part } from '@google/genai';
-import { AuthType, type Config, ApprovalMode } from '@qwen-code/qwen-code-core';
+import { AuthType, type Config } from '@qwen-code/qwen-code-core';
 import { useCallback, useRef } from 'react';
 import { VisionSwitchOutcome } from '../components/ModelSwitchDialog.js';
 import {
@@ -121,7 +121,7 @@ export function shouldOfferVisionSwitch(
   parts: PartListUnion,
   authType: AuthType,
   currentModel: string,
-  visionModelPreviewEnabled: boolean = true,
+  visionModelPreviewEnabled: boolean = false,
 ): boolean {
   // Only trigger for qwen-oauth
   if (authType !== AuthType.QWEN_OAUTH) {
@@ -166,11 +166,11 @@ export function processVisionSwitchOutcome(
     case VisionSwitchOutcome.SwitchSessionToVL:
       return { persistSessionModel: vlModelId };
 
-    case VisionSwitchOutcome.ContinueWithCurrentModel:
-      return {}; // Continue with current model, no changes needed
+    case VisionSwitchOutcome.DisallowWithGuidance:
+      return { showGuidance: true };
 
     default:
-      return {}; // Default to continuing with current model
+      return { showGuidance: true };
   }
 }
 
@@ -198,7 +198,7 @@ export interface VisionSwitchHandlingResult {
 export function useVisionAutoSwitch(
   config: Config,
   addItem: UseHistoryManagerReturn['addItem'],
-  visionModelPreviewEnabled: boolean = true,
+  visionModelPreviewEnabled: boolean = false,
   onVisionSwitchRequired?: (query: PartListUnion) => Promise<{
     modelOverride?: string;
     persistSessionModel?: string;
@@ -252,91 +252,35 @@ export function useVisionAutoSwitch(
         return { shouldProceed: true };
       }
 
-      // In YOLO mode, automatically switch to vision model without user interaction
-      if (config.getApprovalMode() === ApprovalMode.YOLO) {
-        const vlModelId = getDefaultVisionModel();
-        originalModelRef.current = config.getModel();
-        await config.setModel(vlModelId, {
-          reason: 'vision_auto_switch',
-          context: 'YOLO mode auto-switch for image content',
-        });
-        return {
-          shouldProceed: true,
-          originalModel: originalModelRef.current,
-        };
-      }
-
-      // Check if there's a default VLM switch mode configured
-      const defaultVlmSwitchMode = config.getVlmSwitchMode();
-      if (defaultVlmSwitchMode) {
-        // Convert string value to VisionSwitchOutcome enum
-        let outcome: VisionSwitchOutcome;
-        switch (defaultVlmSwitchMode) {
-          case 'once':
-            outcome = VisionSwitchOutcome.SwitchOnce;
-            break;
-          case 'session':
-            outcome = VisionSwitchOutcome.SwitchSessionToVL;
-            break;
-          case 'persist':
-            outcome = VisionSwitchOutcome.ContinueWithCurrentModel;
-            break;
-          default:
-            // Invalid value, fall back to prompting user
-            outcome = VisionSwitchOutcome.ContinueWithCurrentModel;
-        }
-
-        // Process the default outcome
-        const visionSwitchResult = processVisionSwitchOutcome(outcome);
-
-        if (visionSwitchResult.modelOverride) {
-          // One-time model override
-          originalModelRef.current = config.getModel();
-          await config.setModel(visionSwitchResult.modelOverride, {
-            reason: 'vision_auto_switch',
-            context: `Default VLM switch mode: ${defaultVlmSwitchMode} (one-time override)`,
-          });
-          return {
-            shouldProceed: true,
-            originalModel: originalModelRef.current,
-          };
-        } else if (visionSwitchResult.persistSessionModel) {
-          // Persistent session model change
-          await config.setModel(visionSwitchResult.persistSessionModel, {
-            reason: 'vision_auto_switch',
-            context: `Default VLM switch mode: ${defaultVlmSwitchMode} (session persistent)`,
-          });
-          return { shouldProceed: true };
-        }
-
-        // For ContinueWithCurrentModel or any other case, proceed with current model
-        return { shouldProceed: true };
-      }
-
       try {
         const visionSwitchResult = await onVisionSwitchRequired(query);
 
+        if (visionSwitchResult.showGuidance) {
+          // Show guidance and don't proceed with the request
+          addItem(
+            {
+              type: MessageType.INFO,
+              text: getVisionSwitchGuidanceMessage(),
+            },
+            userMessageTimestamp,
+          );
+          return { shouldProceed: false };
+        }
+
         if (visionSwitchResult.modelOverride) {
           // One-time model override
           originalModelRef.current = config.getModel();
-          await config.setModel(visionSwitchResult.modelOverride, {
-            reason: 'vision_auto_switch',
-            context: 'User-prompted vision switch (one-time override)',
-          });
+          config.setModel(visionSwitchResult.modelOverride);
           return {
             shouldProceed: true,
             originalModel: originalModelRef.current,
           };
         } else if (visionSwitchResult.persistSessionModel) {
           // Persistent session model change
-          await config.setModel(visionSwitchResult.persistSessionModel, {
-            reason: 'vision_auto_switch',
-            context: 'User-prompted vision switch (session persistent)',
-          });
+          config.setModel(visionSwitchResult.persistSessionModel);
           return { shouldProceed: true };
         }
 
-        // For ContinueWithCurrentModel or any other case, proceed with current model
         return { shouldProceed: true };
       } catch (_error) {
         // If vision switch dialog was cancelled or errored, don't proceed
@@ -346,12 +290,9 @@ export function useVisionAutoSwitch(
     [config, addItem, visionModelPreviewEnabled, onVisionSwitchRequired],
   );
 
-  const restoreOriginalModel = useCallback(async () => {
+  const restoreOriginalModel = useCallback(() => {
     if (originalModelRef.current) {
-      await config.setModel(originalModelRef.current, {
-        reason: 'vision_auto_switch',
-        context: 'Restoring original model after vision switch',
-      });
+      config.setModel(originalModelRef.current);
       originalModelRef.current = null;
     }
   }, [config]);

packages/cli/src/ui/models/availableModels.ts

@@ -10,12 +10,9 @@ export type AvailableModel = {
   isVision?: boolean;
 };
 
-export const MAINLINE_VLM = 'vision-model';
-export const MAINLINE_CODER = 'coder-model';
-
 export const AVAILABLE_MODELS_QWEN: AvailableModel[] = [
-  { id: MAINLINE_CODER, label: MAINLINE_CODER },
-  { id: MAINLINE_VLM, label: MAINLINE_VLM, isVision: true },
+  { id: 'qwen3-coder-plus', label: 'qwen3-coder-plus' },
+  { id: 'qwen-vl-max-latest', label: 'qwen-vl-max', isVision: true },
 ];
 
 /**
@@ -45,7 +42,7 @@ export function getOpenAIAvailableModelFromEnv(): AvailableModel | null {
  * until our coding model supports multimodal.
  */
 export function getDefaultVisionModel(): string {
-  return MAINLINE_VLM;
+  return 'qwen-vl-max-latest';
 }
 
 export function isVisionModel(modelId: string): boolean {

packages/cli/src/ui/utils/MarkdownDisplay.test.tsx

@@ -9,6 +9,7 @@ import { describe, it, expect, vi, beforeEach } from 'vitest';
 import { MarkdownDisplay } from './MarkdownDisplay.js';
 import { LoadedSettings } from '../../config/settings.js';
 import { SettingsContext } from '../contexts/SettingsContext.js';
+import { EOL } from 'node:os';
 
 describe('<MarkdownDisplay />', () => {
   const baseProps = {
@@ -56,7 +57,7 @@ describe('<MarkdownDisplay />', () => {
 ## Header 2
 ### Header 3
 #### Header 4
-`;
+`.replace(/\n/g, EOL);
     const { lastFrame } = render(
       <SettingsContext.Provider value={mockSettings}>
         <MarkdownDisplay {...baseProps} text={text} />
@@ -66,7 +67,10 @@ describe('<MarkdownDisplay />', () => {
   });
 
   it('renders a fenced code block with a language', () => {
-    const text = '```javascript\nconst x = 1;\nconsole.log(x);\n```';
+    const text = '```javascript\nconst x = 1;\nconsole.log(x);\n```'.replace(
+      /\n/g,
+      EOL,
+    );
     const { lastFrame } = render(
       <SettingsContext.Provider value={mockSettings}>
         <MarkdownDisplay {...baseProps} text={text} />
@@ -76,7 +80,7 @@ describe('<MarkdownDisplay />', () => {
   });
 
   it('renders a fenced code block without a language', () => {
-    const text = '```\nplain text\n```';
+    const text = '```\nplain text\n```'.replace(/\n/g, EOL);
     const { lastFrame } = render(
       <SettingsContext.Provider value={mockSettings}>
         <MarkdownDisplay {...baseProps} text={text} />
@@ -86,7 +90,7 @@ describe('<MarkdownDisplay />', () => {
   });
 
   it('handles unclosed (pending) code blocks', () => {
-    const text = '```typescript\nlet y = 2;';
+    const text = '```typescript\nlet y = 2;'.replace(/\n/g, EOL);
     const { lastFrame } = render(
       <SettingsContext.Provider value={mockSettings}>
         <MarkdownDisplay {...baseProps} text={text} isPending={true} />
@@ -100,7 +104,7 @@ describe('<MarkdownDisplay />', () => {
 - item A
 * item B
 + item C
-`;
+`.replace(/\n/g, EOL);
     const { lastFrame } = render(
       <SettingsContext.Provider value={mockSettings}>
         <MarkdownDisplay {...baseProps} text={text} />
@@ -114,7 +118,7 @@ describe('<MarkdownDisplay />', () => {
 * Level 1
   * Level 2
     * Level 3
-`;
+`.replace(/\n/g, EOL);
     const { lastFrame } = render(
       <SettingsContext.Provider value={mockSettings}>
         <MarkdownDisplay {...baseProps} text={text} />
@@ -127,7 +131,7 @@ describe('<MarkdownDisplay />', () => {
     const text = `
 1. First item
 2. Second item
-`;
+`.replace(/\n/g, EOL);
     const { lastFrame } = render(
       <SettingsContext.Provider value={mockSettings}>
         <MarkdownDisplay {...baseProps} text={text} />
@@ -143,7 +147,7 @@ Hello
 World
 ***
 Test
-`;
+`.replace(/\n/g, EOL);
     const { lastFrame } = render(
       <SettingsContext.Provider value={mockSettings}>
         <MarkdownDisplay {...baseProps} text={text} />
@@ -158,7 +162,7 @@ Test
 |----------|:--------:|
 | Cell 1   | Cell 2   |
 | Cell 3   | Cell 4   |
-`;
+`.replace(/\n/g, EOL);
     const { lastFrame } = render(
       <SettingsContext.Provider value={mockSettings}>
         <MarkdownDisplay {...baseProps} text={text} />
@@ -172,7 +176,7 @@ Test
 Some text before.
 | A | B |
 |---|
-| 1 | 2 |`;
+| 1 | 2 |`.replace(/\n/g, EOL);
     const { lastFrame } = render(
       <SettingsContext.Provider value={mockSettings}>
         <MarkdownDisplay {...baseProps} text={text} />
@@ -184,7 +188,7 @@ Some text before.
   it('inserts a single space between paragraphs', () => {
     const text = `Paragraph 1.
 
-Paragraph 2.`;
+Paragraph 2.`.replace(/\n/g, EOL);
     const { lastFrame } = render(
       <SettingsContext.Provider value={mockSettings}>
         <MarkdownDisplay {...baseProps} text={text} />
@@ -207,7 +211,7 @@ some code
 \`\`\`
 
 Another paragraph.
-`;
+`.replace(/\n/g, EOL);
     const { lastFrame } = render(
       <SettingsContext.Provider value={mockSettings}>
         <MarkdownDisplay {...baseProps} text={text} />
@@ -217,7 +221,7 @@ Another paragraph.
   });
 
   it('hides line numbers in code blocks when showLineNumbers is false', () => {
-    const text = '```javascript\nconst x = 1;\n```';
+    const text = '```javascript\nconst x = 1;\n```'.replace(/\n/g, EOL);
     const settings = new LoadedSettings(
       { path: '', settings: {} },
       { path: '', settings: {} },
@@ -238,7 +242,7 @@ Another paragraph.
   });
 
   it('shows line numbers in code blocks by default', () => {
-    const text = '```javascript\nconst x = 1;\n```';
+    const text = '```javascript\nconst x = 1;\n```'.replace(/\n/g, EOL);
     const { lastFrame } = render(
       <SettingsContext.Provider value={mockSettings}>
         <MarkdownDisplay {...baseProps} text={text} />
@@ -247,21 +251,4 @@ Another paragraph.
     expect(lastFrame()).toMatchSnapshot();
     expect(lastFrame()).toContain(' 1 ');
   });
-
-  it('correctly splits lines using \\n regardless of platform EOL', () => {
-    // Test that the component uses \n for splitting, not EOL
-    const textWithUnixLineEndings = 'Line 1\nLine 2\nLine 3';
-
-    const { lastFrame } = render(
-      <SettingsContext.Provider value={mockSettings}>
-        <MarkdownDisplay {...baseProps} text={textWithUnixLineEndings} />
-      </SettingsContext.Provider>,
-    );
-
-    const output = lastFrame();
-    expect(output).toContain('Line 1');
-    expect(output).toContain('Line 2');
-    expect(output).toContain('Line 3');
-    expect(output).toMatchSnapshot();
-  });
 });

packages/cli/src/ui/utils/MarkdownDisplay.tsx

@@ -6,6 +6,7 @@
 
 import React from 'react';
 import { Text, Box } from 'ink';
+import { EOL } from 'node:os';
 import { Colors } from '../colors.js';
 import { colorizeCode } from './CodeColorizer.js';
 import { TableRenderer } from './TableRenderer.js';
@@ -34,7 +35,7 @@ const MarkdownDisplayInternal: React.FC<MarkdownDisplayProps> = ({
 }) => {
   if (!text) return <></>;
 
-  const lines = text.split(`\n`);
+  const lines = text.split(EOL);
   const headerRegex = /^ *(#{1,4}) +(.*)/;
   const codeFenceRegex = /^ *(`{3,}|~{3,}) *(\w*?) *$/;
   const ulItemRegex = /^([ \t]*)([-*+]) +(.*)/;

packages/cli/src/ui/utils/__snapshots__/MarkdownDisplay.test.tsx.snap

@@ -14,12 +14,6 @@ Another paragraph.
 "
 `;
 
-exports[`<MarkdownDisplay /> > correctly splits lines using \\n regardless of platform EOL 1`] = `
-"Line 1
-Line 2
-Line 3"
-`;
-
 exports[`<MarkdownDisplay /> > handles a table at the end of the input 1`] = `
 "Some text before.
 | A | B |

packages/cli/src/validateNonInterActiveAuth.test.ts

@@ -126,18 +126,6 @@ describe('validateNonInterActiveAuth', () => {
     expect(refreshAuthMock).toHaveBeenCalledWith(AuthType.USE_OPENAI);
   });
 
-  it('uses configured QWEN_OAUTH if provided', async () => {
-    const nonInteractiveConfig: NonInteractiveConfig = {
-      refreshAuth: refreshAuthMock,
-    };
-    await validateNonInteractiveAuth(
-      AuthType.QWEN_OAUTH,
-      undefined,
-      nonInteractiveConfig,
-    );
-    expect(refreshAuthMock).toHaveBeenCalledWith(AuthType.QWEN_OAUTH);
-  });
-
   it('uses USE_VERTEX_AI if GOOGLE_GENAI_USE_VERTEXAI is true (with GOOGLE_CLOUD_PROJECT and GOOGLE_CLOUD_LOCATION)', async () => {
     process.env['GOOGLE_GENAI_USE_VERTEXAI'] = 'true';
     process.env['GOOGLE_CLOUD_PROJECT'] = 'test-project';

packages/cli/src/zed-integration/zedIntegration.ts

@@ -97,18 +97,6 @@ class GeminiAgent {
         name: 'Vertex AI',
         description: null,
       },
-      {
-        id: AuthType.USE_OPENAI,
-        name: 'Use OpenAI API key',
-        description:
-          'Requires setting the `OPENAI_API_KEY` environment variable',
-      },
-      {
-        id: AuthType.QWEN_OAUTH,
-        name: 'Qwen OAuth',
-        description:
-          'OAuth authentication for Qwen models with 2000 daily requests',
-      },
     ];
 
     return {

packages/core/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qwen-code/qwen-code-core",
-  "version": "0.0.13",
+  "version": "0.0.11",
   "description": "Qwen Code Core",
   "repository": {
     "type": "git",

packages/core/src/config/config.test.ts

@@ -737,85 +737,4 @@ describe('setApprovalMode with folder trust', () => {
     expect(() => config.setApprovalMode(ApprovalMode.AUTO_EDIT)).not.toThrow();
     expect(() => config.setApprovalMode(ApprovalMode.DEFAULT)).not.toThrow();
   });
-
-  describe('Model Switch Logging', () => {
-    it('should log model switch when setModel is called with different model', async () => {
-      const config = new Config({
-        sessionId: 'test-model-switch',
-        targetDir: '.',
-        debugMode: false,
-        model: 'qwen3-coder-plus',
-        cwd: '.',
-      });
-
-      // Initialize the config to set up content generator
-      await config.initialize();
-
-      // Mock the logger's logModelSwitch method
-      const logModelSwitchSpy = vi.spyOn(config['logger']!, 'logModelSwitch');
-
-      // Change the model
-      await config.setModel('qwen-vl-max-latest', {
-        reason: 'vision_auto_switch',
-        context: 'Test model switch',
-      });
-
-      // Verify that logModelSwitch was called with correct parameters
-      expect(logModelSwitchSpy).toHaveBeenCalledWith({
-        fromModel: 'qwen3-coder-plus',
-        toModel: 'qwen-vl-max-latest',
-        reason: 'vision_auto_switch',
-        context: 'Test model switch',
-      });
-    });
-
-    it('should not log when setModel is called with same model', async () => {
-      const config = new Config({
-        sessionId: 'test-same-model',
-        targetDir: '.',
-        debugMode: false,
-        model: 'qwen3-coder-plus',
-        cwd: '.',
-      });
-
-      // Initialize the config to set up content generator
-      await config.initialize();
-
-      // Mock the logger's logModelSwitch method
-      const logModelSwitchSpy = vi.spyOn(config['logger']!, 'logModelSwitch');
-
-      // Set the same model
-      await config.setModel('qwen3-coder-plus');
-
-      // Verify that logModelSwitch was not called
-      expect(logModelSwitchSpy).not.toHaveBeenCalled();
-    });
-
-    it('should use default reason when no options provided', async () => {
-      const config = new Config({
-        sessionId: 'test-default-reason',
-        targetDir: '.',
-        debugMode: false,
-        model: 'qwen3-coder-plus',
-        cwd: '.',
-      });
-
-      // Initialize the config to set up content generator
-      await config.initialize();
-
-      // Mock the logger's logModelSwitch method
-      const logModelSwitchSpy = vi.spyOn(config['logger']!, 'logModelSwitch');
-
-      // Change the model without options
-      await config.setModel('qwen-vl-max-latest');
-
-      // Verify that logModelSwitch was called with default reason
-      expect(logModelSwitchSpy).toHaveBeenCalledWith({
-        fromModel: 'qwen3-coder-plus',
-        toModel: 'qwen-vl-max-latest',
-        reason: 'manual',
-        context: undefined,
-      });
-    });
-  });
 });

packages/core/src/config/config.ts

@@ -56,7 +56,6 @@ import {
   DEFAULT_GEMINI_FLASH_MODEL,
 } from './models.js';
 import { Storage } from './storage.js';
-import { Logger, type ModelSwitchEvent } from '../core/logger.js';
 
 // Re-export OAuth config type
 export type { AnyToolInvocation, MCPOAuthConfig };
@@ -240,7 +239,6 @@ export interface ConfigParameters {
   extensionManagement?: boolean;
   enablePromptCompletion?: boolean;
   skipLoopDetection?: boolean;
-  vlmSwitchMode?: string;
 }
 
 export class Config {
@@ -332,11 +330,9 @@ export class Config {
   private readonly extensionManagement: boolean;
   private readonly enablePromptCompletion: boolean = false;
   private readonly skipLoopDetection: boolean;
-  private readonly vlmSwitchMode: string | undefined;
   private initialized: boolean = false;
   readonly storage: Storage;
   private readonly fileExclusions: FileExclusions;
-  private logger: Logger | null = null;
 
   constructor(params: ConfigParameters) {
     this.sessionId = params.sessionId;
@@ -428,15 +424,8 @@ export class Config {
     this.extensionManagement = params.extensionManagement ?? false;
     this.storage = new Storage(this.targetDir);
     this.enablePromptCompletion = params.enablePromptCompletion ?? false;
-    this.vlmSwitchMode = params.vlmSwitchMode;
     this.fileExclusions = new FileExclusions(this);
 
-    // Initialize logger asynchronously
-    this.logger = new Logger(this.sessionId, this.storage);
-    this.logger.initialize().catch((error) => {
-      console.debug('Failed to initialize logger:', error);
-    });
-
     if (params.contextFileName) {
       setGeminiMdFilename(params.contextFileName);
     }
@@ -528,47 +517,21 @@ export class Config {
     return this.contentGeneratorConfig?.model || this.model;
   }
 
-  async setModel(
-    newModel: string,
-    options?: {
-      reason?: ModelSwitchEvent['reason'];
-      context?: string;
-    },
-  ): Promise<void> {
-    const oldModel = this.getModel();
-
+  setModel(newModel: string): void {
     if (this.contentGeneratorConfig) {
       this.contentGeneratorConfig.model = newModel;
     }
 
-    // Log the model switch if the model actually changed
-    if (oldModel !== newModel && this.logger) {
-      const switchEvent: ModelSwitchEvent = {
-        fromModel: oldModel,
-        toModel: newModel,
-        reason: options?.reason || 'manual',
-        context: options?.context,
-      };
-
-      // Log asynchronously to avoid blocking
-      this.logger.logModelSwitch(switchEvent).catch((error) => {
-        console.debug('Failed to log model switch:', error);
-      });
-    }
-
     // Reinitialize chat with updated configuration while preserving history
     const geminiClient = this.getGeminiClient();
     if (geminiClient && geminiClient.isInitialized()) {
-      // Now await the reinitialize operation to ensure completion
-      try {
-        await geminiClient.reinitialize();
-      } catch (error) {
+      // Use async operation but don't await to avoid blocking
+      geminiClient.reinitialize().catch((error) => {
         console.error(
           'Failed to reinitialize chat with updated config:',
           error,
         );
-        throw error; // Re-throw to let callers handle the error
-      }
+      });
     }
   }
 
@@ -975,10 +938,6 @@ export class Config {
     return this.skipLoopDetection;
   }
 
-  getVlmSwitchMode(): string | undefined {
-    return this.vlmSwitchMode;
-  }
-
   async getGitService(): Promise<GitService> {
     if (!this.gitService) {
       this.gitService = new GitService(this.targetDir, this.storage);

packages/core/src/config/flashFallback.test.ts

@@ -41,7 +41,7 @@ describe('Flash Model Fallback Configuration', () => {
   // with the fallback mechanism. This will be necessary we introduce more
   // intelligent model routing.
   describe('setModel', () => {
-    it('should only mark as switched if contentGeneratorConfig exists', async () => {
+    it('should only mark as switched if contentGeneratorConfig exists', () => {
       // Create config without initializing contentGeneratorConfig
       const newConfig = new Config({
         sessionId: 'test-session-2',
@@ -52,15 +52,15 @@ describe('Flash Model Fallback Configuration', () => {
       });
 
       // Should not crash when contentGeneratorConfig is undefined
-      await newConfig.setModel(DEFAULT_GEMINI_FLASH_MODEL);
+      newConfig.setModel(DEFAULT_GEMINI_FLASH_MODEL);
       expect(newConfig.isInFallbackMode()).toBe(false);
     });
   });
 
   describe('getModel', () => {
-    it('should return contentGeneratorConfig model if available', async () => {
+    it('should return contentGeneratorConfig model if available', () => {
       // Simulate initialized content generator config
-      await config.setModel(DEFAULT_GEMINI_FLASH_MODEL);
+      config.setModel(DEFAULT_GEMINI_FLASH_MODEL);
       expect(config.getModel()).toBe(DEFAULT_GEMINI_FLASH_MODEL);
     });
 
@@ -88,8 +88,8 @@ describe('Flash Model Fallback Configuration', () => {
       expect(config.isInFallbackMode()).toBe(false);
     });
 
-    it('should persist switched state throughout session', async () => {
-      await config.setModel(DEFAULT_GEMINI_FLASH_MODEL);
+    it('should persist switched state throughout session', () => {
+      config.setModel(DEFAULT_GEMINI_FLASH_MODEL);
       // Setting state for fallback mode as is expected of clients
       config.setFallbackMode(true);
       expect(config.isInFallbackMode()).toBe(true);

packages/core/src/config/models.ts

@@ -4,10 +4,11 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-export const DEFAULT_QWEN_MODEL = 'coder-model';
-export const DEFAULT_QWEN_FLASH_MODEL = 'coder-model';
+export const DEFAULT_QWEN_MODEL = 'qwen3-coder-plus';
+// We do not have a fallback model for now, but note it here anyway.
+export const DEFAULT_QWEN_FLASH_MODEL = 'qwen3-coder-flash';
 
-export const DEFAULT_GEMINI_MODEL = 'coder-model';
+export const DEFAULT_GEMINI_MODEL = 'qwen3-coder-plus';
 export const DEFAULT_GEMINI_FLASH_MODEL = 'gemini-2.5-flash';
 export const DEFAULT_GEMINI_FLASH_LITE_MODEL = 'gemini-2.5-flash-lite';
 

packages/core/src/core/client.ts

@@ -1053,7 +1053,7 @@ export class GeminiClient {
           error,
         );
         if (accepted !== false && accepted !== null) {
-          await this.config.setModel(fallbackModel);
+          this.config.setModel(fallbackModel);
           this.config.setFallbackMode(true);
           return fallbackModel;
         }

packages/core/src/core/geminiChat.ts

@@ -224,7 +224,7 @@ export class GeminiChat {
           error,
         );
         if (accepted !== false && accepted !== null) {
-          await this.config.setModel(fallbackModel);
+          this.config.setModel(fallbackModel);
           this.config.setFallbackMode(true);
           return fallbackModel;
         }

packages/core/src/core/logger.test.ts

@@ -755,84 +755,4 @@ describe('Logger', () => {
       expect(logger['messageId']).toBe(0);
     });
   });
-
-  describe('Model Switch Logging', () => {
-    it('should log model switch events correctly', async () => {
-      const testSessionId = 'test-session-model-switch';
-      const logger = new Logger(testSessionId, new Storage(process.cwd()));
-      await logger.initialize();
-
-      const modelSwitchEvent = {
-        fromModel: 'qwen3-coder-plus',
-        toModel: 'qwen-vl-max-latest',
-        reason: 'vision_auto_switch' as const,
-        context: 'YOLO mode auto-switch for image content',
-      };
-
-      await logger.logModelSwitch(modelSwitchEvent);
-
-      // Read the log file to verify the entry was written
-      const logContent = await fs.readFile(TEST_LOG_FILE_PATH, 'utf-8');
-      const logs: LogEntry[] = JSON.parse(logContent);
-
-      const modelSwitchLog = logs.find(
-        (log) =>
-          log.sessionId === testSessionId &&
-          log.type === MessageSenderType.MODEL_SWITCH,
-      );
-
-      expect(modelSwitchLog).toBeDefined();
-      expect(modelSwitchLog!.type).toBe(MessageSenderType.MODEL_SWITCH);
-
-      const loggedEvent = JSON.parse(modelSwitchLog!.message);
-      expect(loggedEvent.fromModel).toBe('qwen3-coder-plus');
-      expect(loggedEvent.toModel).toBe('qwen-vl-max-latest');
-      expect(loggedEvent.reason).toBe('vision_auto_switch');
-      expect(loggedEvent.context).toBe(
-        'YOLO mode auto-switch for image content',
-      );
-    });
-
-    it('should handle multiple model switch events', async () => {
-      const testSessionId = 'test-session-multiple-switches';
-      const logger = new Logger(testSessionId, new Storage(process.cwd()));
-      await logger.initialize();
-
-      // Log first switch
-      await logger.logModelSwitch({
-        fromModel: 'qwen3-coder-plus',
-        toModel: 'qwen-vl-max-latest',
-        reason: 'vision_auto_switch',
-        context: 'Auto-switch for image',
-      });
-
-      // Log second switch (restore)
-      await logger.logModelSwitch({
-        fromModel: 'qwen-vl-max-latest',
-        toModel: 'qwen3-coder-plus',
-        reason: 'vision_auto_switch',
-        context: 'Restoring original model',
-      });
-
-      // Read the log file to verify both entries were written
-      const logContent = await fs.readFile(TEST_LOG_FILE_PATH, 'utf-8');
-      const logs: LogEntry[] = JSON.parse(logContent);
-
-      const modelSwitchLogs = logs.filter(
-        (log) =>
-          log.sessionId === testSessionId &&
-          log.type === MessageSenderType.MODEL_SWITCH,
-      );
-
-      expect(modelSwitchLogs).toHaveLength(2);
-
-      const firstSwitch = JSON.parse(modelSwitchLogs[0].message);
-      expect(firstSwitch.fromModel).toBe('qwen3-coder-plus');
-      expect(firstSwitch.toModel).toBe('qwen-vl-max-latest');
-
-      const secondSwitch = JSON.parse(modelSwitchLogs[1].message);
-      expect(secondSwitch.fromModel).toBe('qwen-vl-max-latest');
-      expect(secondSwitch.toModel).toBe('qwen3-coder-plus');
-    });
-  });
 });

packages/core/src/core/logger.ts

@@ -13,7 +13,6 @@ const LOG_FILE_NAME = 'logs.json';
 
 export enum MessageSenderType {
   USER = 'user',
-  MODEL_SWITCH = 'model_switch',
 }
 
 export interface LogEntry {
@@ -24,13 +23,6 @@ export interface LogEntry {
   message: string;
 }
 
-export interface ModelSwitchEvent {
-  fromModel: string;
-  toModel: string;
-  reason: 'vision_auto_switch' | 'manual' | 'fallback' | 'other';
-  context?: string;
-}
-
 // This regex matches any character that is NOT a letter (a-z, A-Z),
 // a number (0-9), a hyphen (-), an underscore (_), or a dot (.).
 
@@ -278,17 +270,6 @@ export class Logger {
     }
   }
 
-  async logModelSwitch(event: ModelSwitchEvent): Promise<void> {
-    const message = JSON.stringify({
-      fromModel: event.fromModel,
-      toModel: event.toModel,
-      reason: event.reason,
-      context: event.context,
-    });
-
-    await this.logMessage(MessageSenderType.MODEL_SWITCH, message);
-  }
-
   private _checkpointPath(tag: string): string {
     if (!tag.length) {
       throw new Error('No checkpoint tag specified.');

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

@@ -560,146 +560,4 @@ describe('DashScopeOpenAICompatibleProvider', () => {
       ]);
     });
   });
-
-  describe('output token limits', () => {
-    it('should limit max_tokens when it exceeds model limit for qwen3-coder-plus', () => {
-      const request: OpenAI.Chat.ChatCompletionCreateParams = {
-        model: 'qwen3-coder-plus',
-        messages: [{ role: 'user', content: 'Hello' }],
-        max_tokens: 100000, // Exceeds the 65536 limit
-      };
-
-      const result = provider.buildRequest(request, 'test-prompt-id');
-
-      expect(result.max_tokens).toBe(65536); // Should be limited to model's output limit
-    });
-
-    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
-    });
-
-    it('should not modify max_tokens when it is within model limit', () => {
-      const request: OpenAI.Chat.ChatCompletionCreateParams = {
-        model: 'qwen3-coder-plus',
-        messages: [{ role: 'user', content: 'Hello' }],
-        max_tokens: 1000, // Within the 65536 limit
-      };
-
-      const result = provider.buildRequest(request, 'test-prompt-id');
-
-      expect(result.max_tokens).toBe(1000); // Should remain unchanged
-    });
-
-    it('should not add max_tokens when not present in request', () => {
-      const request: OpenAI.Chat.ChatCompletionCreateParams = {
-        model: 'qwen3-coder-plus',
-        messages: [{ role: 'user', content: 'Hello' }],
-        // No max_tokens parameter
-      };
-
-      const result = provider.buildRequest(request, 'test-prompt-id');
-
-      expect(result.max_tokens).toBeUndefined(); // Should remain undefined
-    });
-
-    it('should handle null max_tokens parameter', () => {
-      const request: OpenAI.Chat.ChatCompletionCreateParams = {
-        model: 'qwen3-coder-plus',
-        messages: [{ role: 'user', content: 'Hello' }],
-        max_tokens: null,
-      };
-
-      const result = provider.buildRequest(request, 'test-prompt-id');
-
-      expect(result.max_tokens).toBeNull(); // Should remain null
-    });
-
-    it('should use default output limit for unknown models', () => {
-      const request: OpenAI.Chat.ChatCompletionCreateParams = {
-        model: 'unknown-model',
-        messages: [{ role: 'user', content: 'Hello' }],
-        max_tokens: 10000, // Exceeds the default 4096 limit
-      };
-
-      const result = provider.buildRequest(request, 'test-prompt-id');
-
-      expect(result.max_tokens).toBe(4096); // Should be limited to default output limit
-    });
-
-    it('should preserve other request parameters when limiting max_tokens', () => {
-      const request: OpenAI.Chat.ChatCompletionCreateParams = {
-        model: 'qwen3-coder-plus',
-        messages: [{ role: 'user', content: 'Hello' }],
-        max_tokens: 100000, // Will be limited
-        temperature: 0.8,
-        top_p: 0.9,
-        frequency_penalty: 0.1,
-        presence_penalty: 0.2,
-        stop: ['END'],
-        user: 'test-user',
-      };
-
-      const result = provider.buildRequest(request, 'test-prompt-id');
-
-      // max_tokens should be limited
-      expect(result.max_tokens).toBe(65536);
-
-      // Other parameters should be preserved
-      expect(result.temperature).toBe(0.8);
-      expect(result.top_p).toBe(0.9);
-      expect(result.frequency_penalty).toBe(0.1);
-      expect(result.presence_penalty).toBe(0.2);
-      expect(result.stop).toEqual(['END']);
-      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 8192 limit
-      };
-
-      const result = provider.buildRequest(request, 'test-prompt-id');
-
-      expect(result.max_tokens).toBe(8192); // Should be limited
-      expect(
-        (result as { vl_high_resolution_images?: boolean })
-          .vl_high_resolution_images,
-      ).toBe(true); // Vision-specific parameter should be preserved
-    });
-
-    it('should handle streaming requests with output token limits', () => {
-      const request: OpenAI.Chat.ChatCompletionCreateParams = {
-        model: 'qwen3-coder-plus',
-        messages: [{ role: 'user', content: 'Hello' }],
-        max_tokens: 100000, // Exceeds the 65536 limit
-        stream: true,
-      };
-
-      const result = provider.buildRequest(request, 'test-prompt-id');
-
-      expect(result.max_tokens).toBe(65536); // Should be limited
-      expect(result.stream).toBe(true); // Streaming should be preserved
-    });
-  });
 });

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

@@ -3,7 +3,6 @@ import type { Config } from '../../../config/config.js';
 import type { ContentGeneratorConfig } from '../../contentGenerator.js';
 import { AuthType } from '../../contentGenerator.js';
 import { DEFAULT_TIMEOUT, DEFAULT_MAX_RETRIES } from '../constants.js';
-import { tokenLimit } from '../../tokenLimits.js';
 import type {
   OpenAICompatibleProvider,
   DashScopeRequestMetadata,
@@ -66,19 +65,6 @@ export class DashScopeOpenAICompatibleProvider
     });
   }
 
-  /**
-   * Build and configure the request for DashScope API.
-   *
-   * This method applies DashScope-specific configurations including:
-   * - Cache control for system and user messages
-   * - Output token limits based on model capabilities
-   * - Vision model specific parameters (vl_high_resolution_images)
-   * - Request metadata for session tracking
-   *
-   * @param request - The original chat completion request parameters
-   * @param userPromptId - Unique identifier for the user prompt for session tracking
-   * @returns Configured request with DashScope-specific parameters applied
-   */
   buildRequest(
     request: OpenAI.Chat.ChatCompletionCreateParams,
     userPromptId: string,
@@ -93,28 +79,21 @@ export class DashScopeOpenAICompatibleProvider
       messages = this.addDashScopeCacheControl(messages, cacheTarget);
     }
 
-    // Apply output token limits based on model capabilities
-    // This ensures max_tokens doesn't exceed the model's maximum output limit
-    const requestWithTokenLimits = this.applyOutputTokenLimit(
-      request,
-      request.model,
-    );
-
     if (request.model.startsWith('qwen-vl')) {
       return {
-        ...requestWithTokenLimits,
+        ...request,
         messages,
         ...(this.buildMetadata(userPromptId) || {}),
         /* @ts-expect-error dashscope exclusive */
         vl_high_resolution_images: true,
-      } as OpenAI.Chat.ChatCompletionCreateParams;
+      };
     }
 
     return {
-      ...requestWithTokenLimits, // Preserve all original parameters including sampling params and adjusted max_tokens
+      ...request, // Preserve all original parameters including sampling params
       messages,
       ...(this.buildMetadata(userPromptId) || {}),
-    } as OpenAI.Chat.ChatCompletionCreateParams;
+    };
   }
 
   buildMetadata(userPromptId: string): DashScopeRequestMetadata {
@@ -267,41 +246,6 @@ export class DashScopeOpenAICompatibleProvider
     return contentArray;
   }
 
-  /**
-   * Apply output token limit to a request's max_tokens parameter.
-   *
-   * Ensures that existing max_tokens parameters don't exceed the model's maximum output
-   * token limit. Only modifies max_tokens when already present in the request.
-   *
-   * @param request - The chat completion request parameters
-   * @param model - The model name to get the output token limit for
-   * @returns The request with max_tokens adjusted to respect the model's limits (if present)
-   */
-  private applyOutputTokenLimit<T extends { max_tokens?: number | null }>(
-    request: T,
-    model: string,
-  ): T {
-    const currentMaxTokens = request.max_tokens;
-
-    // Only process if max_tokens is already present in the request
-    if (currentMaxTokens === undefined || currentMaxTokens === null) {
-      return request; // No max_tokens parameter, return unchanged
-    }
-
-    const modelLimit = tokenLimit(model, 'output');
-
-    // If max_tokens exceeds the model limit, cap it to the model's limit
-    if (currentMaxTokens > modelLimit) {
-      return {
-        ...request,
-        max_tokens: modelLimit,
-      };
-    }
-
-    // If max_tokens is within the limit, return the request unchanged
-    return request;
-  }
-
   /**
    * Check if cache control should be disabled based on configuration.
    *

packages/core/src/core/prompts.ts

@@ -820,14 +820,6 @@ function getToolCallExamples(model?: string): string {
     if (/qwen[^-]*-vl/i.test(model)) {
       return qwenVlToolCallExamples;
     }
-    // Match coder-model pattern (same as qwen3-coder)
-    if (/coder-model/i.test(model)) {
-      return qwenCoderToolCallExamples;
-    }
-    // Match vision-model pattern (same as qwen3-vl)
-    if (/vision-model/i.test(model)) {
-      return qwenVlToolCallExamples;
-    }
   }
 
   return generalToolCallExamples;

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

@@ -1,10 +1,5 @@
 import { describe, it, expect } from 'vitest';
-import {
-  normalize,
-  tokenLimit,
-  DEFAULT_TOKEN_LIMIT,
-  DEFAULT_OUTPUT_TOKEN_LIMIT,
-} from './tokenLimits.js';
+import { normalize, tokenLimit, DEFAULT_TOKEN_LIMIT } from './tokenLimits.js';
 
 describe('normalize', () => {
   it('should lowercase and trim the model string', () => {
@@ -230,96 +225,3 @@ describe('tokenLimit', () => {
     expect(tokenLimit('CLAUDE-3.5-SONNET')).toBe(200000);
   });
 });
-
-describe('tokenLimit with output type', () => {
-  describe('Qwen models with output limits', () => {
-    it('should return the correct output limit for qwen3-coder-plus', () => {
-      expect(tokenLimit('qwen3-coder-plus', 'output')).toBe(65536);
-      expect(tokenLimit('qwen3-coder-plus-20250601', 'output')).toBe(65536);
-    });
-
-    it('should return the correct output limit for qwen-vl-max-latest', () => {
-      expect(tokenLimit('qwen-vl-max-latest', 'output')).toBe(8192);
-    });
-  });
-
-  describe('Default output limits', () => {
-    it('should return the default output limit for unknown models', () => {
-      expect(tokenLimit('unknown-model', 'output')).toBe(
-        DEFAULT_OUTPUT_TOKEN_LIMIT,
-      );
-      expect(tokenLimit('gpt-4', 'output')).toBe(DEFAULT_OUTPUT_TOKEN_LIMIT);
-      expect(tokenLimit('claude-3.5-sonnet', 'output')).toBe(
-        DEFAULT_OUTPUT_TOKEN_LIMIT,
-      );
-    });
-
-    it('should return the default output limit for models without specific output patterns', () => {
-      expect(tokenLimit('qwen3-coder-7b', 'output')).toBe(
-        DEFAULT_OUTPUT_TOKEN_LIMIT,
-      );
-      expect(tokenLimit('qwen-plus', 'output')).toBe(
-        DEFAULT_OUTPUT_TOKEN_LIMIT,
-      );
-      expect(tokenLimit('qwen-vl-max', 'output')).toBe(
-        DEFAULT_OUTPUT_TOKEN_LIMIT,
-      );
-    });
-  });
-
-  describe('Input vs Output limits comparison', () => {
-    it('should return different limits for input vs output for qwen3-coder-plus', () => {
-      expect(tokenLimit('qwen3-coder-plus', 'input')).toBe(1048576); // 1M input
-      expect(tokenLimit('qwen3-coder-plus', 'output')).toBe(65536); // 64K output
-    });
-
-    it('should return different limits for input vs output for qwen-vl-max-latest', () => {
-      expect(tokenLimit('qwen-vl-max-latest', 'input')).toBe(131072); // 128K input
-      expect(tokenLimit('qwen-vl-max-latest', 'output')).toBe(8192); // 8K output
-    });
-
-    it('should return same default limits for unknown models', () => {
-      expect(tokenLimit('unknown-model', 'input')).toBe(DEFAULT_TOKEN_LIMIT); // 128K input
-      expect(tokenLimit('unknown-model', 'output')).toBe(
-        DEFAULT_OUTPUT_TOKEN_LIMIT,
-      ); // 4K output
-    });
-  });
-
-  describe('Backward compatibility', () => {
-    it('should default to input type when no type is specified', () => {
-      expect(tokenLimit('qwen3-coder-plus')).toBe(1048576); // Should be input limit
-      expect(tokenLimit('qwen-vl-max-latest')).toBe(131072); // Should be input limit
-      expect(tokenLimit('unknown-model')).toBe(DEFAULT_TOKEN_LIMIT); // Should be input default
-    });
-
-    it('should work with explicit input type', () => {
-      expect(tokenLimit('qwen3-coder-plus', 'input')).toBe(1048576);
-      expect(tokenLimit('qwen-vl-max-latest', 'input')).toBe(131072);
-      expect(tokenLimit('unknown-model', 'input')).toBe(DEFAULT_TOKEN_LIMIT);
-    });
-  });
-
-  describe('Model normalization with output limits', () => {
-    it('should handle normalized model names for output limits', () => {
-      expect(tokenLimit('QWEN3-CODER-PLUS', 'output')).toBe(65536);
-      expect(tokenLimit('qwen3-coder-plus-20250601', 'output')).toBe(65536);
-      expect(tokenLimit('QWEN-VL-MAX-LATEST', 'output')).toBe(8192);
-    });
-
-    it('should handle complex model strings for output limits', () => {
-      expect(
-        tokenLimit(
-          '  a/b/c|QWEN3-CODER-PLUS:qwen3-coder-plus-2024-05-13  ',
-          'output',
-        ),
-      ).toBe(65536);
-      expect(
-        tokenLimit(
-          'provider/qwen-vl-max-latest:qwen-vl-max-latest-v1',
-          'output',
-        ),
-      ).toBe(8192);
-    });
-  });
-});

packages/core/src/core/tokenLimits.ts

@@ -1,15 +1,7 @@
 type Model = string;
 type TokenCount = number;
 
-/**
- * Token limit types for different use cases.
- * - 'input': Maximum input context window size
- * - 'output': Maximum output tokens that can be generated in a single response
- */
-export type TokenLimitType = 'input' | 'output';
-
 export const DEFAULT_TOKEN_LIMIT: TokenCount = 131_072; // 128K (power-of-two)
-export const DEFAULT_OUTPUT_TOKEN_LIMIT: TokenCount = 4_096; // 4K tokens
 
 /**
  * Accurate numeric limits:
@@ -26,10 +18,6 @@ const LIMITS = {
   '1m': 1_048_576,
   '2m': 2_097_152,
   '10m': 10_485_760, // 10 million tokens
-  // Output token limits (typically much smaller than input limits)
-  '4k': 4_096,
-  '8k': 8_192,
-  '16k': 16_384,
 } as const;
 
 /** Robust normalizer: strips provider prefixes, pipes/colons, date/version suffixes, etc. */
@@ -48,7 +36,7 @@ export function normalize(model: string): string {
   // - dates (e.g., -20250219), -v1, version numbers, 'latest', 'preview' etc.
   s = s.replace(/-preview/g, '');
   // Special handling for Qwen model names that include "-latest" as part of the model name
-  if (!s.match(/^qwen-(?:plus|flash|vl-max)-latest$/)) {
+  if (!s.match(/^qwen-(?:plus|flash)-latest$/)) {
     // \d{6,} - Match 6 or more digits (dates) like -20250219 (6+ digit dates)
     // \d+x\d+b - Match patterns like 4x8b, -7b, -70b
     // v\d+(?:\.\d+)* - Match version patterns starting with 'v' like -v1, -v1.2, -v2.1.3
@@ -111,12 +99,6 @@ const PATTERNS: Array<[RegExp, TokenCount]> = [
   // Commercial Qwen3-Coder-Flash: 1M token context
   [/^qwen3-coder-flash(-.*)?$/, LIMITS['1m']], // catches "qwen3-coder-flash" and date variants
 
-  // Generic coder-model: same as qwen3-coder-plus (1M token context)
-  [/^coder-model$/, LIMITS['1m']],
-
-  // Commercial Qwen3-Max-Preview: 256K token context
-  [/^qwen3-max-preview(-.*)?$/, LIMITS['256k']], // catches "qwen3-max-preview" and date variants
-
   // Open-source Qwen3-Coder variants: 256K native
   [/^qwen3-coder-.*$/, LIMITS['256k']],
   // Open-source Qwen3 2507 variants: 256K native
@@ -137,9 +119,6 @@ const PATTERNS: Array<[RegExp, TokenCount]> = [
   // Qwen Vision Models
   [/^qwen-vl-max.*$/, LIMITS['128k']],
 
-  // Generic vision-model: same as qwen-vl-max (128K token context)
-  [/^vision-model$/, LIMITS['128k']],
-
   // -------------------
   // ByteDance Seed-OSS (512K)
   // -------------------
@@ -163,60 +142,16 @@ const PATTERNS: Array<[RegExp, TokenCount]> = [
   [/^mistral-large-2.*$/, LIMITS['128k']],
 ];
 
-/**
- * Output token limit patterns for specific model families.
- * These patterns define the maximum number of tokens that can be generated
- * in a single response for specific models.
- */
-const OUTPUT_PATTERNS: Array<[RegExp, TokenCount]> = [
-  // -------------------
-  // Alibaba / Qwen - DashScope Models
-  // -------------------
-  // Qwen3-Coder-Plus: 65,536 max output tokens
-  [/^qwen3-coder-plus(-.*)?$/, LIMITS['64k']],
-
-  // Generic coder-model: same as qwen3-coder-plus (64K max output tokens)
-  [/^coder-model$/, LIMITS['64k']],
-
-  // Qwen3-Max-Preview: 65,536 max output tokens
-  [/^qwen3-max-preview(-.*)?$/, LIMITS['64k']],
-
-  // Qwen-VL-Max-Latest: 8,192 max output tokens
-  [/^qwen-vl-max-latest$/, LIMITS['8k']],
-
-  // Generic vision-model: same as qwen-vl-max-latest (8K max output tokens)
-  [/^vision-model$/, LIMITS['8k']],
-
-  // Qwen3-VL-Plus: 8,192 max output tokens
-  [/^qwen3-vl-plus$/, LIMITS['8k']],
-];
-
-/**
- * Return the token limit for a model string based on the specified type.
- *
- * This function determines the maximum number of tokens for either input context
- * or output generation based on the model and token type. It uses the same
- * normalization logic for consistency across both input and output limits.
- *
- * @param model - The model name to get the token limit for
- * @param type - The type of token limit ('input' for context window, 'output' for generation)
- * @returns The maximum number of tokens allowed for this model and type
- */
-export function tokenLimit(
-  model: Model,
-  type: TokenLimitType = 'input',
-): TokenCount {
+/** Return the token limit for a model string (uses normalize + ordered regex list). */
+export function tokenLimit(model: Model): TokenCount {
   const norm = normalize(model);
 
-  // Choose the appropriate patterns based on token type
-  const patterns = type === 'output' ? OUTPUT_PATTERNS : PATTERNS;
-
-  for (const [regex, limit] of patterns) {
+  for (const [regex, limit] of PATTERNS) {
     if (regex.test(norm)) {
       return limit;
     }
   }
 
-  // Return appropriate default based on token type
-  return type === 'output' ? DEFAULT_OUTPUT_TOKEN_LIMIT : DEFAULT_TOKEN_LIMIT;
+  // final fallback: DEFAULT_TOKEN_LIMIT (power-of-two 128K)
+  return DEFAULT_TOKEN_LIMIT;
 }

packages/core/src/qwen/qwenOAuth2.ts

@@ -712,6 +712,8 @@ async function authWithQwenDeviceFlow(
             `Polling... (attempt ${attempt + 1}/${maxAttempts})`,
           );
 
+          process.stdout.write('.');
+
           // Wait with cancellation check every 100ms
           await new Promise<void>((resolve) => {
             const checkInterval = 100; // Check every 100ms

packages/core/src/qwen/sharedTokenManager.test.ts

@@ -901,37 +901,5 @@ describe('SharedTokenManager', () => {
         );
       }
     });
-
-    it('should properly clean up timeout when file operation completes before timeout', async () => {
-      const tokenManager = SharedTokenManager.getInstance();
-      tokenManager.clearCache();
-
-      const mockClient = {
-        getCredentials: vi.fn().mockReturnValue(null),
-        setCredentials: vi.fn(),
-        getAccessToken: vi.fn(),
-        requestDeviceAuthorization: vi.fn(),
-        pollDeviceToken: vi.fn(),
-        refreshAccessToken: vi.fn(),
-      };
-
-      // Mock clearTimeout to verify it's called
-      const clearTimeoutSpy = vi.spyOn(global, 'clearTimeout');
-
-      // Mock file stat to resolve quickly (before timeout)
-      mockFs.stat.mockResolvedValue({ mtimeMs: 12345 } as Stats);
-
-      // Call checkAndReloadIfNeeded which uses withTimeout internally
-      const checkMethod = getPrivateProperty(
-        tokenManager,
-        'checkAndReloadIfNeeded',
-      ) as (client?: IQwenOAuth2Client) => Promise<void>;
-      await checkMethod.call(tokenManager, mockClient);
-
-      // Verify that clearTimeout was called to clean up the timer
-      expect(clearTimeoutSpy).toHaveBeenCalled();
-
-      clearTimeoutSpy.mockRestore();
-    });
   });
 });

packages/core/src/qwen/sharedTokenManager.ts

@@ -290,36 +290,6 @@ export class SharedTokenManager {
     }
   }
 
-  /**
-   * Utility method to add timeout to any promise operation
-   * Properly cleans up the timeout when the promise completes
-   */
-  private withTimeout<T>(
-    promise: Promise<T>,
-    timeoutMs: number,
-    operationType = 'Operation',
-  ): Promise<T> {
-    let timeoutId: NodeJS.Timeout;
-
-    return Promise.race([
-      promise.finally(() => {
-        // Clear timeout when main promise completes (success or failure)
-        if (timeoutId) {
-          clearTimeout(timeoutId);
-        }
-      }),
-      new Promise<never>((_, reject) => {
-        timeoutId = setTimeout(
-          () =>
-            reject(
-              new Error(`${operationType} timed out after ${timeoutMs}ms`),
-            ),
-          timeoutMs,
-        );
-      }),
-    ]);
-  }
-
   /**
    * Perform the actual file check and reload operation
    * This is separated to enable proper promise-based synchronization
@@ -333,12 +303,25 @@ export class SharedTokenManager {
 
     try {
       const filePath = this.getCredentialFilePath();
+      // Add timeout to file stat operation
+      const withTimeout = async <T>(
+        promise: Promise<T>,
+        timeoutMs: number,
+      ): Promise<T> =>
+        Promise.race([
+          promise,
+          new Promise<never>((_, reject) =>
+            setTimeout(
+              () =>
+                reject(
+                  new Error(`File operation timed out after ${timeoutMs}ms`),
+                ),
+              timeoutMs,
+            ),
+          ),
+        ]);
 
-      const stats = await this.withTimeout(
-        fs.stat(filePath),
-        3000,
-        'File operation',
-      );
+      const stats = await withTimeout(fs.stat(filePath), 3000);
       const fileModTime = stats.mtimeMs;
 
       // Reload credentials if file has been modified since last cache
@@ -468,7 +451,7 @@ export class SharedTokenManager {
       // Check if we have a refresh token before attempting refresh
       const currentCredentials = qwenClient.getCredentials();
       if (!currentCredentials.refresh_token) {
-        // console.debug('create a NO_REFRESH_TOKEN error');
+        console.debug('create a NO_REFRESH_TOKEN error');
         throw new TokenManagerError(
           TokenError.NO_REFRESH_TOKEN,
           'No refresh token available for token refresh',
@@ -606,12 +589,26 @@ export class SharedTokenManager {
     const dirPath = path.dirname(filePath);
     const tempPath = `${filePath}.tmp.${randomUUID()}`;
 
+    // Add timeout wrapper for file operations
+    const withTimeout = async <T>(
+      promise: Promise<T>,
+      timeoutMs: number,
+    ): Promise<T> =>
+      Promise.race([
+        promise,
+        new Promise<never>((_, reject) =>
+          setTimeout(
+            () => reject(new Error(`Operation timed out after ${timeoutMs}ms`)),
+            timeoutMs,
+          ),
+        ),
+      ]);
+
     // Create directory with restricted permissions
     try {
-      await this.withTimeout(
+      await withTimeout(
         fs.mkdir(dirPath, { recursive: true, mode: 0o700 }),
         5000,
-        'File operation',
       );
     } catch (error) {
       throw new TokenManagerError(
@@ -625,30 +622,21 @@ export class SharedTokenManager {
 
     try {
       // Write to temporary file first with restricted permissions
-      await this.withTimeout(
+      await withTimeout(
         fs.writeFile(tempPath, credString, { mode: 0o600 }),
         5000,
-        'File operation',
       );
 
       // Atomic move to final location
-      await this.withTimeout(
-        fs.rename(tempPath, filePath),
-        5000,
-        'File operation',
-      );
+      await withTimeout(fs.rename(tempPath, filePath), 5000);
 
       // Update cached file modification time atomically after successful write
-      const stats = await this.withTimeout(
-        fs.stat(filePath),
-        5000,
-        'File operation',
-      );
+      const stats = await withTimeout(fs.stat(filePath), 5000);
       this.memoryCache.fileModTime = stats.mtimeMs;
     } catch (error) {
       // Clean up temp file if it exists
       try {
-        await this.withTimeout(fs.unlink(tempPath), 1000, 'File operation');
+        await withTimeout(fs.unlink(tempPath), 1000);
       } catch (_cleanupError) {
         // Ignore cleanup errors - temp file might not exist
       }

packages/core/src/subagents/subagent.test.ts

@@ -72,19 +72,6 @@ async function createMockConfig(
   } as unknown as ToolRegistry;
 
   vi.spyOn(config, 'getToolRegistry').mockReturnValue(mockToolRegistry);
-
-  // Mock getContentGeneratorConfig to return a valid config
-  vi.spyOn(config, 'getContentGeneratorConfig').mockReturnValue({
-    model: DEFAULT_GEMINI_MODEL,
-    authType: AuthType.USE_GEMINI,
-  });
-
-  // Mock setModel method
-  vi.spyOn(config, 'setModel').mockResolvedValue();
-
-  // Mock getSessionId method
-  vi.spyOn(config, 'getSessionId').mockReturnValue('test-session');
-
   return { config, toolRegistry: mockToolRegistry };
 }
 

packages/core/src/subagents/subagent.ts

@@ -826,7 +826,7 @@ export class SubAgentScope {
       );
 
       if (this.modelConfig.model) {
-        await this.runtimeContext.setModel(this.modelConfig.model);
+        this.runtimeContext.setModel(this.modelConfig.model);
       }
 
       return new GeminiChat(

packages/core/src/tools/ripGrep.ts

@@ -8,6 +8,7 @@ import fs from 'node:fs';
 import path from 'node:path';
 import { EOL } from 'node:os';
 import { spawn } from 'node:child_process';
+import { rgPath } from '@lvce-editor/ripgrep';
 import type { ToolInvocation, ToolResult } from './tools.js';
 import { BaseDeclarativeTool, BaseToolInvocation, Kind } from './tools.js';
 import { SchemaValidator } from '../utils/schemaValidator.js';
@@ -17,14 +18,6 @@ import type { Config } from '../config/config.js';
 
 const DEFAULT_TOTAL_MAX_MATCHES = 20000;
 
-/**
- * Lazy loads the ripgrep binary path to avoid loading the library until needed
- */
-async function getRipgrepPath(): Promise<string> {
-  const { rgPath } = await import('@lvce-editor/ripgrep');
-  return rgPath;
-}
-
 /**
  * Parameters for the GrepTool
  */
@@ -299,9 +292,8 @@ class GrepToolInvocation extends BaseToolInvocation<
     rgArgs.push(absolutePath);
 
     try {
-      const ripgrepPath = await getRipgrepPath();
       const output = await new Promise<string>((resolve, reject) => {
-        const child = spawn(ripgrepPath, rgArgs, {
+        const child = spawn(rgPath, rgArgs, {
           windowsHide: true,
         });
 

packages/test-utils/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qwen-code/qwen-code-test-utils",
-  "version": "0.0.13",
+  "version": "0.0.11",
   "private": true,
   "main": "src/index.ts",
   "license": "Apache-2.0",

packages/vscode-ide-companion/package.json

@@ -2,7 +2,7 @@
   "name": "qwen-code-vscode-ide-companion",
   "displayName": "Qwen Code Companion",
   "description": "Enable Qwen Code with direct access to your VS Code workspace.",
-  "version": "0.0.13",
+  "version": "0.0.11",
   "publisher": "qwenlm",
   "icon": "assets/icon.png",
   "repository": {