feat: add yolo mode support to auto vision model switch (#652)

* feat: add yolo mode support to auto vision model switch

* feat: add cli args & env variables for switch behavoir

* fix: use dedicated model names and settings

* docs: add vision model instructions

* fix: failed test case

* fix: setModel failure

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

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

packages/cli/src/config/config.ts

@@ -82,6 +82,7 @@ export interface CliArgs {
   includeDirectories: string[] | undefined;
   tavilyApiKey: string | undefined;
   screenReader: boolean | undefined;
+  vlmSwitchMode: string | undefined;
 }
 
 export async function parseArguments(settings: Settings): Promise<CliArgs> {
@@ -249,6 +250,13 @@ 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(
@@ -524,6 +532,9 @@ 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,
@@ -630,6 +641,7 @@ 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

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

packages/cli/src/config/settings.ts

@@ -396,6 +396,24 @@ 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

@@ -746,11 +746,21 @@ export const SETTINGS_SCHEMA = {
         label: 'Vision Model Preview',
         category: 'Experimental',
         requiresRestart: false,
-        default: false,
+        default: true,
         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,
+      },
     },
   },