fix(core): rotate session ID on model fallback to prevent stateful API errors (#28469)

packages/core/src/availability/autoRoutingFallback.integration.test.ts

@@ -414,4 +414,86 @@ describe('Auto Routing Fallback Integration', () => {
       'Pro success',
     );
   });
+
+  it('should rotate session ID on fallback and retry successfully with the Flash model', async () => {
+    const originalSessionId = 'test-session-rotate-id';
+    config = new Config({
+      sessionId: originalSessionId,
+      targetDir: '/test',
+      debugMode: false,
+      cwd: '/test',
+      model: PREVIEW_GEMINI_MODEL_AUTO,
+    });
+
+    vi.spyOn(config, 'isInteractive').mockReturnValue(true);
+
+    client = new BaseLlmClient(
+      fakeGenerator,
+      config,
+      AuthType.LOGIN_WITH_GOOGLE,
+    );
+
+    let attemptsPro = 0;
+    let attemptsFlash = 0;
+
+    const mockGoogleApiError = {
+      code: 429,
+      message:
+        'Automatically switching from gemini-2.5-pro to gemini-2.5-flash for faster responses for the remainder of this session. Possible reasons for this are...',
+      details: [],
+    };
+
+    vi.spyOn(fakeGenerator, 'generateContent').mockImplementation(
+      async (params) => {
+        if (params.model === PREVIEW_GEMINI_MODEL) {
+          attemptsPro++;
+          throw new RetryableQuotaError(
+            'Quota exceeded for Pro',
+            mockGoogleApiError,
+            0,
+          );
+        } else if (params.model === PREVIEW_GEMINI_FLASH_MODEL) {
+          attemptsFlash++;
+          return {
+            candidates: [
+              {
+                content: {
+                  role: 'model',
+                  parts: [{ text: 'Flash success after rotation' }],
+                },
+              },
+            ],
+          } as unknown as GenerateContentResponse;
+        }
+        throw new Error(`Unexpected model: ${params.model}`);
+      },
+    );
+
+    config.setFallbackModelHandler(
+      async (_failed, _fallback, _error): Promise<FallbackIntent | null> =>
+        'retry_always', // Approve switch to Flash
+    );
+
+    const promise = client.generateContent({
+      modelConfigKey: { model: PREVIEW_GEMINI_MODEL, isChatModel: true },
+      contents: [{ role: 'user', parts: [{ text: 'test query' }] }],
+      abortSignal: new AbortController().signal,
+      promptId: 'test-prompt',
+      role: LlmRole.UTILITY_TOOL,
+    });
+
+    await vi.runAllTimersAsync();
+    const result = await promise;
+
+    // Verify it resolved to Flash success instead of failing with Please submit a new query
+    expect(result.candidates?.[0]?.content?.parts?.[0]?.text).toBe(
+      'Flash success after rotation',
+    );
+    expect(attemptsPro).toBe(3);
+    expect(attemptsFlash).toBe(1);
+
+    // Verify session ID has been rotated
+    expect(config.getSessionId()).not.toBe(originalSessionId);
+    expect(config.getSessionId()).toBeDefined();
+  });
 });

packages/core/src/code_assist/server.ts

@@ -86,6 +86,10 @@ export class CodeAssistServer implements ContentGenerator {
     readonly config?: Config,
   ) {}
 
+  getEffectiveSessionId(): string | undefined {
+    return this.config?.getSessionId() ?? this.sessionId;
+  }
+
   async generateContentStream(
     req: GenerateContentParameters,
     userPromptId: string,
@@ -117,7 +121,7 @@ export class CodeAssistServer implements ContentGenerator {
           req,
           userPromptId,
           this.projectId,
-          this.sessionId,
+          this.getEffectiveSessionId(),
           enabledCreditTypes,
         ),
         req.config?.abortSignal,
@@ -153,7 +157,7 @@ export class CodeAssistServer implements ContentGenerator {
           translatedResponse,
           streamingLatency,
           req.config?.abortSignal,
-          server.sessionId, // Use sessionId as trajectoryId
+          server.getEffectiveSessionId(), // Use sessionId as trajectoryId
         );
 
         if (response.consumedCredits) {
@@ -204,7 +208,7 @@ export class CodeAssistServer implements ContentGenerator {
         req,
         userPromptId,
         this.projectId,
-        this.sessionId,
+        this.getEffectiveSessionId(),
         undefined,
       ),
       req.config?.abortSignal,
@@ -224,7 +228,7 @@ export class CodeAssistServer implements ContentGenerator {
       translatedResponse,
       streamingLatency,
       req.config?.abortSignal,
-      this.sessionId, // Use sessionId as trajectoryId
+      this.getEffectiveSessionId(), // Use sessionId as trajectoryId
     );
 
     if (response.remainingCredits) {

packages/core/src/config/config.ts

@@ -1861,6 +1861,10 @@ export class Config implements McpContext, AgentLoopContext {
     }
   }
 
+  rotateSessionId(sessionId: string): void {
+    this._sessionId = sessionId;
+  }
+
   resetNewSessionState(sessionId: string): void {
     this.setSessionId(sessionId);
   }

packages/core/src/fallback/handler.test.ts

@@ -67,6 +67,7 @@ const createMockConfig = (overrides: Partial<Config> = {}): Config =>
     setActiveModel: vi.fn(),
     setModel: vi.fn(),
     activateFallbackMode: vi.fn(),
+    rotateSessionId: vi.fn(),
     getModelAvailabilityService: vi.fn(() =>
       createAvailabilityServiceMock({
         selectedModel: FALLBACK_MODEL,

packages/core/src/fallback/handler.ts

@@ -5,6 +5,7 @@
  */
 
 import type { Config } from '../config/config.js';
+import { createSessionId } from '../utils/session.js';
 import {
   openBrowserSecurely,
   shouldLaunchBrowser,
@@ -161,8 +162,9 @@ async function processIntent(
 ): Promise<boolean> {
   switch (intent) {
     case 'retry_always':
-      // TODO(telemetry): Implement generic fallback event logging. Existing
-      // logFlashFallback is specific to a single Model.
+      // Rotate the session ID to ensure the backend treats the retried request
+      // as a brand-new session, preventing stateful model-switching errors.
+      config.rotateSessionId(createSessionId());
       config.activateFallbackMode(fallbackModel, failedModel);
       return true;