fix(patch): cherry-pick 9a74271 to release/v0.33.0-preview.8-pr-21236 [CONFLICTS] (#21788)

Co-authored-by: Gaurav <39389231+gsquared94@users.noreply.github.com>
Co-authored-by: galz10 <galzahavi@google.com>

packages/cli/src/config/config.ts

@@ -875,6 +875,7 @@ export async function loadCliConfig(
     fakeResponses: argv.fakeResponses,
     recordResponses: argv.recordResponses,
     retryFetchErrors: settings.general?.retryFetchErrors,
+    billing: settings.billing,
     maxAttempts: settings.general?.maxAttempts,
     ptyInfo: ptyInfo?.name,
     disableLLMCorrection: settings.tools?.disableLLMCorrection,

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

@@ -110,7 +110,6 @@ async function handleOverageMenu(
     isDialogPending,
     setOverageMenuRequest,
     setModelSwitchedFromQuotaError,
-    historyManager,
   } = args;
 
   logBillingEvent(
@@ -155,13 +154,6 @@ async function handleOverageMenu(
       setModelSwitchedFromQuotaError(false);
       config.setQuotaErrorOccurred(false);
       config.setOverageStrategy('always');
-      historyManager.addItem(
-        {
-          type: MessageType.INFO,
-          text: `Using AI Credits for this request.`,
-        },
-        Date.now(),
-      );
       return 'retry_with_credits';
 
     case 'use_fallback':

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

@@ -271,6 +271,7 @@ describe('useGeminiStream', () => {
     addHistory: vi.fn(),
     getSessionId: vi.fn(() => 'test-session-id'),
     setQuotaErrorOccurred: vi.fn(),
+    resetBillingTurnState: vi.fn(),
     getQuotaErrorOccurred: vi.fn(() => false),
     getModel: vi.fn(() => 'gemini-2.5-pro'),
     getContentGeneratorConfig: vi.fn(() => ({

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

@@ -1374,6 +1374,9 @@ export const useGeminiStream = (
           if (!options?.isContinuation) {
             setModelSwitchedFromQuotaError(false);
             config.setQuotaErrorOccurred(false);
+            config.resetBillingTurnState(
+              settings.merged.billing?.overageStrategy,
+            );
             suppressedToolErrorCountRef.current = 0;
             suppressedToolErrorNoteShownRef.current = false;
             lowVerbosityFailureNoteShownRef.current = false;
@@ -1534,6 +1537,7 @@ export const useGeminiStream = (
       setThought,
       maybeAddSuppressedToolErrorNote,
       maybeAddLowVerbosityFailureNote,
+      settings.merged.billing?.overageStrategy,
     ],
   );
 

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

@@ -67,14 +67,6 @@ export function useQuotaAndFallback({
   const isDialogPending = useRef(false);
   const isValidationPending = useRef(false);
 
-  // Initial overage strategy from settings; runtime value read from config at call time.
-  const initialOverageStrategy =
-    (settings.merged.billing?.overageStrategy as
-      | 'ask'
-      | 'always'
-      | 'never'
-      | undefined) ?? 'ask';
-
   // Set up Flash fallback handler
   useEffect(() => {
     const fallbackHandler: FallbackModelHandler = async (
@@ -109,9 +101,7 @@ export function useQuotaAndFallback({
             ? getResetTimeMessage(error.retryDelayMs)
             : undefined;
 
-          const overageStrategy =
-            config.getBillingSettings().overageStrategy ??
-            initialOverageStrategy;
+          const overageStrategy = config.getBillingSettings().overageStrategy;
 
           const creditsResult = await handleCreditsFlow({
             config,
@@ -209,7 +199,6 @@ export function useQuotaAndFallback({
     userTier,
     paidTier,
     settings,
-    initialOverageStrategy,
     setModelSwitchedFromQuotaError,
     onShowAuthSelection,
     errorVerbosity,