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

@@ -737,4 +737,85 @@ 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

@@ -56,6 +56,7 @@ 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 };
@@ -239,6 +240,7 @@ export interface ConfigParameters {
   extensionManagement?: boolean;
   enablePromptCompletion?: boolean;
   skipLoopDetection?: boolean;
+  vlmSwitchMode?: string;
 }
 
 export class Config {
@@ -330,9 +332,11 @@ 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;
@@ -424,8 +428,15 @@ 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);
     }
@@ -517,21 +528,47 @@ export class Config {
     return this.contentGeneratorConfig?.model || this.model;
   }
 
-  setModel(newModel: string): void {
+  async setModel(
+    newModel: string,
+    options?: {
+      reason?: ModelSwitchEvent['reason'];
+      context?: string;
+    },
+  ): Promise<void> {
+    const oldModel = this.getModel();
+
     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()) {
-      // Use async operation but don't await to avoid blocking
-      geminiClient.reinitialize().catch((error) => {
+      // Now await the reinitialize operation to ensure completion
+      try {
+        await geminiClient.reinitialize();
+      } catch (error) {
         console.error(
           'Failed to reinitialize chat with updated config:',
           error,
         );
-      });
+        throw error; // Re-throw to let callers handle the error
+      }
     }
   }
 
@@ -938,6 +975,10 @@ 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', () => {
+    it('should only mark as switched if contentGeneratorConfig exists', async () => {
       // 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
-      newConfig.setModel(DEFAULT_GEMINI_FLASH_MODEL);
+      await newConfig.setModel(DEFAULT_GEMINI_FLASH_MODEL);
       expect(newConfig.isInFallbackMode()).toBe(false);
     });
   });
 
   describe('getModel', () => {
-    it('should return contentGeneratorConfig model if available', () => {
+    it('should return contentGeneratorConfig model if available', async () => {
       // Simulate initialized content generator config
-      config.setModel(DEFAULT_GEMINI_FLASH_MODEL);
+      await 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', () => {
-      config.setModel(DEFAULT_GEMINI_FLASH_MODEL);
+    it('should persist switched state throughout session', async () => {
+      await 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

@@ -4,11 +4,10 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-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_QWEN_MODEL = 'coder-model';
+export const DEFAULT_QWEN_FLASH_MODEL = 'coder-model';
 
-export const DEFAULT_GEMINI_MODEL = 'qwen3-coder-plus';
+export const DEFAULT_GEMINI_MODEL = 'coder-model';
 export const DEFAULT_GEMINI_FLASH_MODEL = 'gemini-2.5-flash';
 export const DEFAULT_GEMINI_FLASH_LITE_MODEL = 'gemini-2.5-flash-lite';