feat: adding integration tests

#### Description

- pages that hardcoded `100vh` minus a guess at what sits above them
came out taller
than the pane they live in, which showed up as scroll that should not be
there. they
  now take what the layout gives them.
- most of the `100vh` in the app turned out to be harmless.. either
flex-shrink absorbs
it or the pane scrolls anyway. those are left alone, only the ones with
a real symptom
  are changed here.
- alert rules and triggered alerts also needed the AlertList tabs chain
to hand height
  down, that page uses antd `Tabs` directly instead of `RouteTab`.
- licenses, status and support pages had `max-height: 100vh` with
`overflow: hidden` and
no inner scroller, so anything past a viewport was clipped with no way
to reach it.
  removed the cap on all three.

#### Issues closed by this PR

Part of https://github.com/SigNoz/engineering-pod/issues/6074


#### Screenshots/ Screen recording

Home page


https://github.com/user-attachments/assets/8ba3e3c9-1959-4393-b503-ddf579e9d139

Without bottom strip


https://github.com/user-attachments/assets/2ee08181-710a-4c34-a4e7-893c4a320453



Status page

<img width="1728" height="1000" alt="status"
src="https://github.com/user-attachments/assets/f44ec7d7-4ee0-4866-9a90-fe25622fe25b"
/>

Without bottom strip

<img width="1728" height="997" alt="status2"
src="https://github.com/user-attachments/assets/be57dce6-65ca-4450-8f0d-0337625a1d64"
/>

Alert rules


https://github.com/user-attachments/assets/7cc25f56-54e4-4489-bdb4-453409151bac

Triggered alerts


https://github.com/user-attachments/assets/2d8e1885-7cad-4659-90f6-59960f4afce8

Without bottom strip



https://github.com/user-attachments/assets/5247f6c0-3675-4910-b1e4-4076bf93c16e



Support
<img width="1728" height="997" alt="support"
src="https://github.com/user-attachments/assets/c2b3c0b2-2abd-4538-bb52-2660e75817b3"
/>

Trace funnel



https://github.com/user-attachments/assets/c4872135-3cb5-4348-b6c6-2d3e4dabdc1b

Without bottom strip


https://github.com/user-attachments/assets/aef94d5d-02e5-4154-995b-76819d55c2d8


Trace details



https://github.com/user-attachments/assets/24d701b0-296f-4fb4-ba9d-615a47b33285

Without bottom strip


https://github.com/user-attachments/assets/23083f20-67bf-4b06-aaec-aba390a6f594



#### Additional Information

- every page here was checked on screen before and after. the ones left
untouched
(infra hosts/k8s, traces + llm explorer list views, llm settings tables,
the k8s logs
  drawer) were checked too and are fine.

docs/api/openapi.yml

@@ -1763,12 +1763,15 @@ components:
           additionalProperties: {}
           nullable: true
           type: object
+        syncState:
+          $ref: '#/components/schemas/CloudintegrationtypesSyncState'
         timestampMillis:
           format: int64
           type: integer
       required:
       - timestampMillis
       - data
+      - syncState
       type: object
     CloudintegrationtypesAzureAccountConfig:
       properties:
@@ -2013,6 +2016,8 @@ components:
           format: date-time
           nullable: true
           type: string
+        syncState:
+          $ref: '#/components/schemas/CloudintegrationtypesSyncState'
       required:
       - account_id
       - cloud_account_id
@@ -2022,6 +2027,7 @@ components:
       - providerAccountId
       - integrationConfig
       - removedAt
+      - syncState
       type: object
     CloudintegrationtypesGettableServicesMetadata:
       properties:
@@ -2121,6 +2127,9 @@ components:
           type: object
         providerAccountId:
           type: string
+        syncedVersion:
+          nullable: true
+          type: integer
       required:
       - data
       type: object
@@ -2133,6 +2142,18 @@ components:
         gcp:
           $ref: '#/components/schemas/CloudintegrationtypesGCPIntegrationConfig'
       type: object
+    CloudintegrationtypesRegionState:
+      enum:
+      - present
+      - removed
+      type: string
+    CloudintegrationtypesRegionSyncState:
+      properties:
+        state:
+          $ref: '#/components/schemas/CloudintegrationtypesRegionState'
+      required:
+      - state
+      type: object
     CloudintegrationtypesService:
       properties:
         assets:
@@ -2274,6 +2295,23 @@ components:
         metrics:
           type: boolean
       type: object
+    CloudintegrationtypesSyncState:
+      nullable: true
+      properties:
+        inSync:
+          type: boolean
+        regions:
+          additionalProperties:
+            $ref: '#/components/schemas/CloudintegrationtypesRegionSyncState'
+          type: object
+        version:
+          format: int64
+          type: integer
+      required:
+      - version
+      - inSync
+      - regions
+      type: object
     CloudintegrationtypesUpdatableAccount:
       properties:
         config:

ee/modules/cloudintegration/implcloudintegration/module.go

@@ -188,27 +188,41 @@ func (module *module) AgentCheckIn(ctx context.Context, orgID valuer.UUID, provi
 		return nil, err
 	}
 
+	// Get account as domain object for config access (enabled regions, etc.)
+	domainAccount, err := cloudintegrationtypes.NewAccountFromStorable(account)
+	if err != nil {
+		return nil, err
+	}
+
+	syncState := domainAccount.NextSyncState(req.SyncedVersion)
+
 	// If account has been removed (disconnected), return a minimal response with empty integration config.
 	// The agent uses this response to clean up resources
 	if account.RemovedAt != nil {
+		// Heartbeat stays frozen after removal, only the sync state is updated.
+		if domainAccount.AgentReport != nil && syncState != nil {
+			domainAccount.AgentReport.SyncState = syncState
+			account.Update(account.AccountID, domainAccount.AgentReport)
+
+			err = module.store.UpdateAgentReport(ctx, account)
+			if err != nil {
+				return nil, err
+			}
+		}
+
 		return cloudintegrationtypes.NewAgentCheckInResponse(
 			req.ProviderAccountID,
 			account.ID.StringValue(),
 			new(cloudintegrationtypes.ProviderIntegrationConfig),
 			account.RemovedAt,
+			syncState,
 		), nil
 	}
 
 	// update account with cloud provider account id and agent report (heartbeat)
-	account.Update(&req.ProviderAccountID, cloudintegrationtypes.NewAgentReport(req.Data))
+	account.Update(&req.ProviderAccountID, cloudintegrationtypes.NewAgentReport(req.Data, syncState))
 
-	err = module.store.UpdateAccount(ctx, account)
-	if err != nil {
-		return nil, err
-	}
-
-	// Get account as domain object for config access (enabled regions, etc.)
-	domainAccount, err := cloudintegrationtypes.NewAccountFromStorable(account)
+	err = module.store.UpdateAgentReport(ctx, account)
 	if err != nil {
 		return nil, err
 	}
@@ -234,6 +248,7 @@ func (module *module) AgentCheckIn(ctx context.Context, orgID valuer.UUID, provi
 		account.ID.StringValue(),
 		integrationConfig,
 		account.RemovedAt,
+		syncState,
 	), nil
 }
 

frontend/src/api/generated/services/sigNoz.schemas.ts

@@ -3366,6 +3366,37 @@ export interface CloudintegrationtypesAWSServiceConfigDTO {
 	metrics?: CloudintegrationtypesAWSServiceMetricsConfigDTO;
 }
 
+export enum CloudintegrationtypesRegionStateDTO {
+	present = 'present',
+	removed = 'removed',
+}
+export interface CloudintegrationtypesRegionSyncStateDTO {
+	state: CloudintegrationtypesRegionStateDTO;
+}
+
+export type CloudintegrationtypesSyncStateDTORegions = {
+	[key: string]: CloudintegrationtypesRegionSyncStateDTO;
+};
+
+/**
+ * @nullable
+ */
+export type CloudintegrationtypesSyncStateDTO = {
+	/**
+	 * @type boolean
+	 */
+	inSync: boolean;
+	/**
+	 * @type object
+	 */
+	regions: CloudintegrationtypesSyncStateDTORegions;
+	/**
+	 * @type integer
+	 * @format int64
+	 */
+	version: number;
+} | null;
+
 export type CloudintegrationtypesAgentReportDTODataAnyOf = {
 	[key: string]: unknown;
 };
@@ -3384,6 +3415,7 @@ export type CloudintegrationtypesAgentReportDTO = {
 	 * @type object,null
 	 */
 	data: CloudintegrationtypesAgentReportDTOData;
+	syncState: CloudintegrationtypesSyncStateDTO | null;
 	/**
 	 * @type integer
 	 * @format int64
@@ -3812,6 +3844,7 @@ export interface CloudintegrationtypesGettableAgentCheckInDTO {
 	 * @format date-time
 	 */
 	removedAt: string | null;
+	syncState: CloudintegrationtypesSyncStateDTO | null;
 }
 
 export interface CloudintegrationtypesServiceMetadataDTO {
@@ -3882,6 +3915,10 @@ export interface CloudintegrationtypesPostableAgentCheckInDTO {
 	 * @type string
 	 */
 	providerAccountId?: string;
+	/**
+	 * @type integer,null
+	 */
+	syncedVersion?: number | null;
 }
 
 export interface CloudintegrationtypesStorableIntegrationDashboardDTO {

frontend/src/constants/localStorage.ts

@@ -47,4 +47,5 @@ export enum LOCALSTORAGE {
 	DASHBOARDS_LIST_VIEWS = 'DASHBOARDS_LIST_VIEWS',
 	DASHBOARD_V2_PANEL_COLUMN_WIDTHS = 'DASHBOARD_V2_PANEL_COLUMN_WIDTHS',
 	LLM_ATTRIBUTE_MAPPING_TEST_SPAN = 'LLM_ATTRIBUTE_MAPPING_TEST_SPAN',
+	SAVED_VIEW_ENABLED = 'SAVED_VIEW_ENABLED',
 }

frontend/src/container/AIAssistant/components/MessageBubble/MessageBubble.module.scss

@@ -75,38 +75,6 @@
 	word-break: break-word;
 }
 
-// Error bubble: a subtle error-tinted callout replacing the default
-// assistant background, rendered when a turn fails.
-.bubble.error {
-	.assistant & {
-		background: var(--callout-error-background);
-		border: 1px solid var(--callout-error-border);
-	}
-}
-
-.errorContent {
-	display: flex;
-	align-items: flex-start;
-	gap: 8px;
-}
-
-.errorIcon {
-	flex-shrink: 0;
-	margin-top: 2px;
-	color: var(--destructive);
-}
-
-.errorText {
-	color: var(--callout-error-title);
-	white-space: pre-wrap;
-	word-break: break-word;
-}
-
-.retryButton {
-	margin-top: 6px;
-	align-self: flex-start;
-}
-
 // User-bubble row: pencil button sits to the LEFT of the bubble within
 // the right-aligned message line, so it visually "ends" at the bubble's
 // right edge while keeping the bubble in its original position.

frontend/src/container/AIAssistant/components/MessageBubble/MessageBubble.tsx

@@ -2,10 +2,6 @@ import React, { useMemo } from 'react';
 import cx from 'classnames';
 import ReactMarkdown from 'react-markdown';
 import remarkGfm from 'remark-gfm';
-import { Button } from '@signozhq/ui/button';
-import { RotateCw, TriangleAlert } from '@signozhq/icons';
-
-import { RetryActionDTO } from 'api/ai-assistant/sigNozAIAssistantAPI.schemas';
 
 // Side-effect: registers all built-in block types into the BlockRegistry
 import '../blocks';
@@ -108,23 +104,18 @@ function renderGroup(group: RenderGroup): JSX.Element {
 interface MessageBubbleProps {
 	message: Message;
 	onRegenerate?: () => void;
-	onRetry?: () => void;
 	isLastAssistant?: boolean;
 }
 
 export default function MessageBubble({
 	message,
 	onRegenerate,
-	onRetry,
 	isLastAssistant = false,
 }: MessageBubbleProps): JSX.Element {
 	const variant = useVariant();
 	const isCompact = variant === 'panel';
 	const isUser = message.role === 'user';
-	const isError = !isUser && Boolean(message.isError);
 	const hasBlocks = !isUser && message.blocks && message.blocks.length > 0;
-	const showRetry =
-		isError && message.retryAction === RetryActionDTO.manual && Boolean(onRetry);
 
 	// Recompute groups only when the blocks array identity changes — store
 	// updates that don't touch this message's blocks should not re-render the
@@ -147,7 +138,7 @@ export default function MessageBubble({
 		<div className={messageClass} data-testid={`ai-message-${message.id}`}>
 			<div className={bodyClass}>
 				<div className={styles.bubbleRow}>
-					<div className={cx(styles.bubble, { [styles.error]: isError })}>
+					<div className={styles.bubble}>
 						{message.attachments && message.attachments.length > 0 && (
 							<div className={styles.attachments}>
 								{message.attachments.map((att) => {
@@ -170,11 +161,6 @@ export default function MessageBubble({
 
 						{isUser ? (
 							<p className={styles.text}>{message.content}</p>
-						) : isError ? (
-							<div className={styles.errorContent}>
-								<TriangleAlert size={14} className={styles.errorIcon} />
-								<span className={styles.errorText}>{message.content}</span>
-							</div>
 						) : hasBlocks ? (
 							<MessageContext.Provider value={{ messageId: message.id }}>
 								{groups.map((g) => renderGroup(g))}
@@ -197,21 +183,7 @@ export default function MessageBubble({
 					</div>
 				</div>
 
-				{showRetry && (
-					<Button
-						className={styles.retryButton}
-						size="sm"
-						variant="ghost"
-						color="secondary"
-						onClick={onRetry}
-						testId={`ai-message-retry-${message.id}`}
-					>
-						<RotateCw size={12} />
-						Retry
-					</Button>
-				)}
-
-				{!isUser && !isError && !message.isRateLimitError && (
+				{!isUser && !message.isRateLimitError && (
 					<MessageFeedback
 						message={message}
 						onRegenerate={onRegenerate}

frontend/src/container/AIAssistant/components/MessageBubble/__tests__/MessageBubble.test.tsx

@@ -1,85 +0,0 @@
-import React from 'react';
-import { render, screen, userEvent } from 'tests/test-utils';
-import {
-	ErrorCodeDTO,
-	RetryActionDTO,
-} from 'api/ai-assistant/sigNozAIAssistantAPI.schemas';
-
-import { Message } from '../../../types';
-
-// react-markdown + remark-gfm are ESM-only and pull a large untransformed
-// dependency chain into jest. The error-rendering path under test renders
-// plain text (no markdown), so stub them to keep the import graph loadable.
-jest.mock('react-markdown', () => ({
-	__esModule: true,
-	default: ({ children }: { children?: React.ReactNode }): React.ReactNode =>
-		children,
-}));
-jest.mock('remark-gfm', () => ({
-	__esModule: true,
-	default: (): void => undefined,
-}));
-
-// eslint-disable-next-line import/first
-import MessageBubble from '../MessageBubble';
-
-function errorMessage(overrides: Partial<Message> = {}): Message {
-	return {
-		id: 'err-1',
-		role: 'assistant',
-		content: 'This conversation is still finishing a previous response.',
-		isError: true,
-		errorCode: ErrorCodeDTO.thread_busy,
-		retryAction: RetryActionDTO.manual,
-		createdAt: 0,
-		...overrides,
-	};
-}
-
-const retryButton = (): HTMLElement | null =>
-	screen.queryByRole('button', { name: /retry/i });
-
-describe('MessageBubble — error rendering', () => {
-	it('shows a Retry button for a manual error and invokes onRetry on click', async () => {
-		const onRetry = jest.fn();
-		render(<MessageBubble message={errorMessage()} onRetry={onRetry} />);
-
-		// Error copy is rendered, and the feedback bar is suppressed on errors.
-		expect(
-			screen.getByText(/still finishing a previous response/i),
-		).toBeInTheDocument();
-		expect(
-			screen.queryByRole('button', { name: /copy message/i }),
-		).not.toBeInTheDocument();
-
-		const button = retryButton();
-		expect(button).toBeInTheDocument();
-		await userEvent.click(button as HTMLElement);
-		expect(onRetry).toHaveBeenCalledTimes(1);
-	});
-
-	it('hides the Retry button when retryAction is none', () => {
-		render(
-			<MessageBubble
-				message={errorMessage({ retryAction: RetryActionDTO.none })}
-				onRetry={jest.fn()}
-			/>,
-		);
-		expect(retryButton()).not.toBeInTheDocument();
-	});
-
-	it('hides the Retry button when retryAction is auto', () => {
-		render(
-			<MessageBubble
-				message={errorMessage({ retryAction: RetryActionDTO.auto })}
-				onRetry={jest.fn()}
-			/>,
-		);
-		expect(retryButton()).not.toBeInTheDocument();
-	});
-
-	it('hides the Retry button when no onRetry handler is provided', () => {
-		render(<MessageBubble message={errorMessage()} />);
-		expect(retryButton()).not.toBeInTheDocument();
-	});
-});

frontend/src/container/AIAssistant/components/VirtualizedMessages/VirtualizedMessages.tsx

@@ -37,9 +37,6 @@ export default function VirtualizedMessages({
 	const regenerateAssistantMessage = useAIAssistantStore(
 		(s) => s.regenerateAssistantMessage,
 	);
-	const retryAssistantMessage = useAIAssistantStore(
-		(s) => s.retryAssistantMessage,
-	);
 	const { threadId } = useAIAssistantAnalyticsContext(conversationId);
 	const streamingStatus = useAIAssistantStore(
 		(s) => s.streams[conversationId]?.streamingStatus ?? '',
@@ -88,14 +85,6 @@ export default function VirtualizedMessages({
 		[conversationId, isStreaming, regenerateAssistantMessage, threadId],
 	);
 
-	const handleRetry = useCallback((): void => {
-		if (isStreaming) {
-			return;
-		}
-		void logEvent(AIAssistantEvents.RetryClicked, { threadId });
-		void retryAssistantMessage(conversationId);
-	}, [conversationId, isStreaming, retryAssistantMessage, threadId]);
-
 	// Scroll all the way to the actual bottom — including the 64px of bottom
 	// padding on the scroller — so the last bubble has visible breathing room
 	// above the disclaimer / input bar. Virtuoso's `scrollToIndex(LAST,
@@ -217,11 +206,6 @@ export default function VirtualizedMessages({
 									? (): void => handleRegenerate(msg.id)
 									: undefined
 							}
-							onRetry={
-								msg.isError && isLastAssistant && !showStreamingSlot
-									? handleRetry
-									: undefined
-							}
 							isLastAssistant={isLastAssistant}
 						/>
 					);

frontend/src/container/AIAssistant/events.ts

@@ -90,7 +90,6 @@ export enum AIAssistantEvents {
 	SuggestedPromptClicked = 'AI Assistant: Suggested prompt clicked',
 	CancelClicked = 'AI Assistant: Cancel clicked',
 	RegenerateClicked = 'AI Assistant: Regenerate clicked',
-	RetryClicked = 'AI Assistant: Retry clicked',
 	MessageCopied = 'AI Assistant: Message copied',
 	FeedbackSubmitted = 'AI Assistant: Feedback submitted',
 	ResourceOpened = 'AI Assistant: Resource opened',

frontend/src/container/AIAssistant/store/__tests__/useAIAssistantStore.test.ts

@@ -1,263 +0,0 @@
-import {
-	ErrorCodeDTO,
-	RetryActionDTO,
-} from 'api/ai-assistant/sigNozAIAssistantAPI.schemas';
-import type { SSEEvent } from 'api/ai-assistant/chat';
-
-import { useAIAssistantStore } from '../useAIAssistantStore';
-import type { Message } from '../../types';
-
-// The store talks to the chat API only through these named exports. Mock the
-// whole module so we can drive the SSE stream + REST calls deterministically.
-jest.mock('api/ai-assistant/chat', () => ({
-	__esModule: true,
-	createThread: jest.fn(),
-	sendMessage: jest.fn(),
-	streamEvents: jest.fn(),
-	approveExecution: jest.fn(),
-	clarifyExecution: jest.fn(),
-	regenerateMessage: jest.fn(),
-	rejectExecution: jest.fn(),
-	cancelExecution: jest.fn(),
-	listThreads: jest.fn(),
-	getThreadDetail: jest.fn(),
-	updateThread: jest.fn(),
-	submitFeedback: jest.fn(),
-}));
-
-// eslint-disable-next-line @typescript-eslint/no-var-requires, global-require
-const chat = jest.requireMock('api/ai-assistant/chat') as Record<
-	string,
-	jest.Mock
->;
-
-// Builds a single-use async stream from a fixed list of SSE events.
-async function* eventStream(events: SSEEvent[]): AsyncGenerator<SSEEvent> {
-	for (const event of events) {
-		yield event;
-	}
-}
-
-function errorEvent(
-	executionId: string,
-	code: ErrorCodeDTO,
-	retryAction: RetryActionDTO,
-): SSEEvent {
-	return {
-		type: 'error',
-		executionId,
-		error: { code, message: 'backend message' },
-		retryAction,
-	};
-}
-
-function lastMessage(conversationId: string): Message {
-	const conv = useAIAssistantStore.getState().conversations[conversationId];
-	return conv.messages[conv.messages.length - 1];
-}
-
-describe('useAIAssistantStore — streaming error handling', () => {
-	beforeEach(() => {
-		jest.clearAllMocks();
-		useAIAssistantStore.setState((s) => {
-			s.conversations = {};
-			s.streams = {};
-			s.activeConversationId = null;
-		});
-	});
-
-	it('commits a manually-retryable error bubble with friendly copy and metadata', async () => {
-		chat.createThread.mockResolvedValue('thread-1');
-		chat.sendMessage.mockResolvedValue('exec-1');
-		chat.streamEvents.mockReturnValueOnce(
-			eventStream([
-				errorEvent('exec-1', ErrorCodeDTO.thread_busy, RetryActionDTO.manual),
-			]),
-		);
-
-		useAIAssistantStore.getState().startNewConversation();
-		await useAIAssistantStore.getState().sendMessage('hello');
-
-		const conv = useAIAssistantStore.getState().conversations['thread-1'];
-		expect(conv.messages).toHaveLength(2);
-		expect(conv.messages[0]).toMatchObject({ role: 'user', content: 'hello' });
-		expect(conv.messages[1]).toMatchObject({
-			role: 'assistant',
-			isError: true,
-			errorCode: ErrorCodeDTO.thread_busy,
-			retryAction: RetryActionDTO.manual,
-		});
-		// Code-specific FE copy, not the raw backend message.
-		expect(conv.messages[1].content).toContain(
-			'still finishing a previous response',
-		);
-	});
-
-	it('replays the send on retry without re-pushing the user message', async () => {
-		chat.createThread.mockResolvedValue('thread-1');
-		chat.sendMessage.mockResolvedValue('exec-1');
-		chat.streamEvents.mockReturnValueOnce(
-			eventStream([
-				errorEvent('exec-1', ErrorCodeDTO.thread_busy, RetryActionDTO.manual),
-			]),
-		);
-
-		useAIAssistantStore.getState().startNewConversation();
-		await useAIAssistantStore.getState().sendMessage('hello');
-
-		// The retry succeeds this time.
-		chat.streamEvents.mockReturnValueOnce(
-			eventStream([
-				{
-					type: 'message',
-					executionId: 'exec-1',
-					messageId: 'm1',
-					delta: 'Hi there',
-					done: true,
-				},
-			]),
-		);
-
-		await useAIAssistantStore.getState().retryAssistantMessage('thread-1');
-
-		const conv = useAIAssistantStore.getState().conversations['thread-1'];
-		// Error bubble replaced by the assistant reply; the user message stays.
-		expect(conv.messages).toHaveLength(2);
-		expect(conv.messages[0]).toMatchObject({ role: 'user', content: 'hello' });
-		expect(conv.messages[1]).toMatchObject({
-			role: 'assistant',
-			content: 'Hi there',
-		});
-		expect(conv.messages[1].isError).toBeUndefined();
-		// Thread already existed on retry; the user message was never re-sent as new.
-		expect(chat.createThread).toHaveBeenCalledTimes(1);
-		expect(chat.sendMessage).toHaveBeenCalledTimes(2);
-	});
-
-	it('silently retries auto-flagged errors, then downgrades to manual once spent', async () => {
-		chat.createThread.mockResolvedValue('thread-2');
-		chat.sendMessage.mockResolvedValue('exec');
-		// Always auto-retryable: 1 initial attempt + MAX_AUTO_RETRIES (2) = 3 sends.
-		chat.streamEvents.mockImplementation(() =>
-			eventStream([
-				errorEvent('exec', ErrorCodeDTO.internal_error, RetryActionDTO.auto),
-			]),
-		);
-
-		useAIAssistantStore.getState().startNewConversation();
-		await useAIAssistantStore.getState().sendMessage('hi');
-
-		expect(chat.sendMessage).toHaveBeenCalledTimes(3);
-		expect(lastMessage('thread-2')).toMatchObject({
-			isError: true,
-			errorCode: ErrorCodeDTO.internal_error,
-			// Auto budget exhausted → presented as manual so a Retry button shows.
-			retryAction: RetryActionDTO.manual,
-		});
-	}, 10000);
-
-	it('marks rate-limit errors and offers no retry', async () => {
-		chat.createThread.mockResolvedValue('thread-3');
-		chat.sendMessage.mockResolvedValue('exec');
-		chat.streamEvents.mockReturnValueOnce(
-			eventStream([
-				errorEvent('exec', ErrorCodeDTO.hourly_message_limit, RetryActionDTO.none),
-			]),
-		);
-
-		useAIAssistantStore.getState().startNewConversation();
-		await useAIAssistantStore.getState().sendMessage('hi');
-
-		expect(lastMessage('thread-3')).toMatchObject({
-			isError: true,
-			isRateLimitError: true,
-			retryAction: RetryActionDTO.none,
-		});
-
-		// No retry thunk registered for a non-retryable error — retry is a no-op.
-		const before =
-			useAIAssistantStore.getState().conversations['thread-3'].messages.length;
-		await useAIAssistantStore.getState().retryAssistantMessage('thread-3');
-		expect(
-			useAIAssistantStore.getState().conversations['thread-3'].messages,
-		).toHaveLength(before);
-	});
-
-	it('recovers silently when an auto-flagged error succeeds on retry', async () => {
-		chat.createThread.mockResolvedValue('thread-4');
-		chat.sendMessage.mockResolvedValue('exec');
-		chat.streamEvents
-			.mockReturnValueOnce(
-				eventStream([
-					errorEvent('exec', ErrorCodeDTO.internal_error, RetryActionDTO.auto),
-				]),
-			)
-			.mockReturnValueOnce(
-				eventStream([
-					{
-						type: 'message',
-						executionId: 'exec',
-						messageId: 'm1',
-						delta: 'Recovered',
-						done: true,
-					},
-				]),
-			);
-
-		useAIAssistantStore.getState().startNewConversation();
-		await useAIAssistantStore.getState().sendMessage('hi');
-
-		// 1 initial attempt + 1 silent auto retry, then success — no error bubble.
-		expect(chat.sendMessage).toHaveBeenCalledTimes(2);
-		const conv = useAIAssistantStore.getState().conversations['thread-4'];
-		expect(conv.messages).toHaveLength(2);
-		expect(conv.messages[0]).toMatchObject({ role: 'user', content: 'hi' });
-		expect(conv.messages[1]).toMatchObject({
-			role: 'assistant',
-			content: 'Recovered',
-		});
-		expect(conv.messages.some((m) => m.isError)).toBe(false);
-	}, 10000);
-
-	it('replays the originating action on retry for a non-send error (approve)', async () => {
-		chat.approveExecution.mockResolvedValue('exec-a');
-		chat.streamEvents.mockReturnValueOnce(
-			eventStream([
-				errorEvent('exec-a', ErrorCodeDTO.thread_busy, RetryActionDTO.manual),
-			]),
-		);
-
-		const convId = useAIAssistantStore.getState().startNewConversation();
-		await useAIAssistantStore.getState().approveAction(convId, 'approval-1');
-
-		expect(lastMessage(convId)).toMatchObject({
-			isError: true,
-			retryAction: RetryActionDTO.manual,
-		});
-		expect(chat.approveExecution).toHaveBeenCalledTimes(1);
-
-		// Retry replays the approval (not a send) and succeeds this time.
-		chat.streamEvents.mockReturnValueOnce(
-			eventStream([
-				{
-					type: 'message',
-					executionId: 'exec-a',
-					messageId: 'm1',
-					delta: 'Approved',
-					done: true,
-				},
-			]),
-		);
-		await useAIAssistantStore.getState().retryAssistantMessage(convId);
-
-		const conv = useAIAssistantStore.getState().conversations[convId];
-		expect(conv.messages).toHaveLength(1);
-		expect(conv.messages[0]).toMatchObject({
-			role: 'assistant',
-			content: 'Approved',
-		});
-		expect(conv.messages[0].isError).toBeUndefined();
-		expect(chat.approveExecution).toHaveBeenCalledTimes(2);
-		expect(chat.sendMessage).not.toHaveBeenCalled();
-	});
-});

frontend/src/container/AIAssistant/store/useAIAssistantStore.ts

@@ -8,7 +8,6 @@ import type {
 	MessageActionDTO,
 	MessageSummaryDTOBlocksAnyOfItem,
 } from 'api/ai-assistant/sigNozAIAssistantAPI.schemas';
-import { RetryActionDTO } from 'api/ai-assistant/sigNozAIAssistantAPI.schemas';
 
 import {
 	approveExecution,
@@ -36,10 +35,7 @@ import {
 	MessageBlock,
 	MessageRole,
 } from '../types';
-import {
-	resolveAssistantError,
-	type AssistantErrorResolution,
-} from '../utils/resolveAssistantError';
+import { resolveAssistantErrorMessage } from '../utils/resolveAssistantErrorMessage';
 
 // ---------------------------------------------------------------------------
 // Types used by module-level helpers
@@ -60,15 +56,6 @@ interface SSEStreamCtx {
 
 const streamControllers = new Map<string, AbortController>();
 
-/**
- * Per-conversation retry thunks for the most recent failed turn. Populated by
- * `finalizeStreamingError` when the error is manually retryable; consumed by
- * the `retryAssistantMessage` action when the user clicks Retry. Transient
- * (not persisted) — it shares the in-memory lifetime of the error bubble it
- * backs, so a page reload drops both together.
- */
-const retryRegistry = new Map<string, () => Promise<void>>();
-
 function abortStream(conversationId: string): void {
 	const ctrl = streamControllers.get(conversationId);
 	if (ctrl) {
@@ -210,7 +197,7 @@ function resetStreamingState(
  * Marker thrown by `runStreamingLoop` when an SSE event reports
  * `invalid_token`. Callers that own an originating action (sendMessage /
  * approve / clarify / regenerate) catch this and re-issue that action via
- * `streamWithRetry`; the retry's first REST call will 401, at which point
+ * `streamWithAuthRetry`; the retry's first REST call will 401, at which point
  * the shared axios `interceptorRejected` rotates the access token and replays.
  */
 class AuthExpiredError extends Error {
@@ -220,50 +207,27 @@ class AuthExpiredError extends Error {
 	}
 }
 
-/** Capped silent re-attempts for backend-flagged transient (`auto`) errors. */
-const MAX_AUTO_RETRIES = 2;
-/** Backoff before each auto re-attempt, indexed by prior auto-retry count. */
-const AUTO_RETRY_BACKOFF_MS = [500, 1500];
-
-function delay(ms: number): Promise<void> {
-	return new Promise((resolve) => {
-		setTimeout(resolve, ms);
-	});
-}
-
-/** True when the SSE error carries the backend's `retryAction: 'auto'` flag. */
-function isAutoRetryableError(err: unknown): boolean {
-	return (
-		(err as { retryAction?: unknown } | undefined)?.retryAction ===
-		RetryActionDTO.auto
-	);
-}
-
 /**
  * Runs the originating action (e.g. sendMessage POST) and streams the
- * resulting execution, with two independent retry budgets:
- *
- *   • Auth — on `AuthExpiredError` (SSE `invalid_token`), re-issues `start`
- *     once. The retry's REST call 401s, the shared axios interceptor rotates
- *     the access token + replays, and the new SSE picks up the rotated token.
- *     Backend flags `invalid_token` as `manual`, so only a fresh execution helps.
- *   • Auto — on an SSE error the backend flagged `retryAction: 'auto'`
- *     (transient), silently re-issues `start` up to `MAX_AUTO_RETRIES` times
- *     with backoff. Once exhausted the error propagates so the caller can
- *     surface a manual Retry affordance.
- *
- * Both reset the stream state before re-attempting so a dead execution's
- * partial output isn't concatenated onto the retry.
+ * resulting execution. On `AuthExpiredError`, re-issues `start` once — the
+ * retry's REST call hits 401, the shared axios interceptor rotates the
+ * access token and replays, and the new SSE picks up the rotated token from
+ * localStorage. Backend signals `retryAction: 'manual'` for `invalid_token`,
+ * so the dead execution can't be resumed — only a fresh one helps.
  */
-async function streamWithRetry(
+async function streamWithAuthRetry(
 	conversationId: string,
 	start: () => Promise<string>,
 	set: StoreSetter,
 ): Promise<void> {
-	let authRetried = false;
-	let autoRetries = 0;
-
-	for (;;) {
+	for (let attempt = 0; attempt <= 1; attempt += 1) {
+		if (attempt > 0) {
+			// Drop any partial content/events from the previous attempt so the
+			// retried execution's stream isn't concatenated with the dead one.
+			set((s) => {
+				resetStreamingState(s, conversationId);
+			});
+		}
 		// eslint-disable-next-line no-await-in-loop
 		const executionId = await start();
 		const ctrl = newStreamController(conversationId);
@@ -278,28 +242,10 @@ async function streamWithRetry(
 			return;
 		} catch (err) {
 			streamControllers.delete(conversationId);
-
-			if (err instanceof AuthExpiredError && !authRetried) {
-				authRetried = true;
-			} else if (isAutoRetryableError(err) && autoRetries < MAX_AUTO_RETRIES) {
-				// eslint-disable-next-line no-await-in-loop
-				await delay(AUTO_RETRY_BACKOFF_MS[autoRetries] ?? 1500);
-				autoRetries += 1;
-			} else {
-				if (isAutoRetryableError(err)) {
-					// Auto-retry budget spent — present the failure as manually
-					// retryable so the caller surfaces a Retry button rather than
-					// silently giving up.
-					(err as { retryAction?: RetryActionDTO }).retryAction =
-						RetryActionDTO.manual;
-				}
-				throw err;
+			if (err instanceof AuthExpiredError && attempt < 1) {
+				continue;
 			}
-
-			// Drop partial content/events from the failed attempt before retrying.
-			set((s) => {
-				resetStreamingState(s, conversationId);
-			});
+			throw err;
 		}
 	}
 }
@@ -312,7 +258,7 @@ async function streamWithRetry(
  *
  * On an `invalid_token` error event (e.g. MCP auth expired mid-execution),
  * throws `AuthExpiredError` so the caller can re-issue the originating
- * action via `streamWithRetry`. We don't refresh here ourselves — the
+ * action via `streamWithAuthRetry`. We don't refresh here ourselves — the
  * retry's REST call will 401 and the shared axios `interceptorRejected`
  * handles rotation + replay. Throws on any other `error` event — the
  * caller's catch block handles UI feedback.
@@ -538,37 +484,20 @@ function hasPendingInput(conversationId: string, get: StoreGetter): boolean {
 	return Boolean(stream?.pendingApproval || stream?.pendingClarification);
 }
 
-/**
- * Commits a failed turn as an error message and removes the stream entry.
- * When the failure is manually retryable and a `retry` thunk is supplied, the
- * thunk is stashed in `retryRegistry` so the bubble's Retry button can replay
- * the originating action.
- */
 function finalizeStreamingError(
 	conversationId: string,
-	resolution: AssistantErrorResolution,
+	errorContent: string,
 	set: StoreSetter,
-	retry?: () => Promise<void>,
+	isRateLimit = false,
 ): void {
-	const { message, code, retryAction, isRateLimit } = resolution;
-
-	if (retryAction === RetryActionDTO.manual && retry) {
-		retryRegistry.set(conversationId, retry);
-	} else {
-		retryRegistry.delete(conversationId);
-	}
-
 	set((s) => {
 		const conv = s.conversations[conversationId];
 		if (conv) {
 			conv.messages.push({
 				id: uuidv4(),
 				role: 'assistant',
-				content: message,
+				content: errorContent,
 				createdAt: Date.now(),
-				isError: true,
-				retryAction,
-				...(code ? { errorCode: code } : {}),
 				...(isRateLimit ? { isRateLimitError: true } : {}),
 			});
 			conv.updatedAt = Date.now();
@@ -577,40 +506,6 @@ function finalizeStreamingError(
 	});
 }
 
-/**
- * Shared streaming wrapper for actions that have no pre-stream setup beyond
- * resetting state (approve / clarify / regenerate). Streams the execution,
- * finalizes the message on success, and on failure resolves the error +
- * registers `retry` (the caller's own re-invocation) so the bubble can replay
- * it. `sendMessage` does not use this — it owns thread-creation/re-keying and
- * runs its own equivalent loop.
- */
-async function streamAndFinalize(
-	conversationId: string,
-	start: () => Promise<string>,
-	fallback: string,
-	logLabel: string,
-	set: StoreSetter,
-	get: StoreGetter,
-	retry: () => Promise<void>,
-): Promise<void> {
-	try {
-		await streamWithRetry(conversationId, start, set);
-		if (!hasPendingInput(conversationId, get)) {
-			finalizeStreamingMessage(conversationId, set, get);
-		}
-	} catch (err) {
-		// Abort errors are expected when the user cancels — not a failure.
-		if (err instanceof DOMException && err.name === 'AbortError') {
-			return;
-		}
-		// eslint-disable-next-line no-console
-		console.error(logLabel, err);
-		const resolution = resolveAssistantError(err, fallback);
-		finalizeStreamingError(conversationId, resolution, set, retry);
-	}
-}
-
 // ---------------------------------------------------------------------------
 // Store interface
 // ---------------------------------------------------------------------------
@@ -669,8 +564,6 @@ export interface AIAssistantStore {
 		conversationId: string,
 		messageId: string,
 	) => Promise<void>;
-	/** Replays the originating action for a manually-retryable error bubble. */
-	retryAssistantMessage: (conversationId: string) => Promise<void>;
 	submitMessageFeedback: (
 		messageId: string,
 		rating: FeedbackRating,
@@ -984,7 +877,7 @@ export const useAIAssistantStore = create<AIAssistantStore>()(
 					// there's no "originating action" to redo — reopening the
 					// same dead executionId would just re-emit the failure.
 					// Let the error bubble; the user can send a new message,
-					// which will go through `streamWithRetry`.
+					// which will go through `streamWithAuthRetry`.
 					if (
 						detail.activeExecutionId &&
 						!streamControllers.has(threadId) &&
@@ -1167,7 +1060,7 @@ export const useAIAssistantStore = create<AIAssistantStore>()(
 				attachments?: MessageAttachment[],
 				contexts?: MessageContext[],
 			): Promise<void> => {
-				const convId = get().activeConversationId;
+				let convId = get().activeConversationId;
 				if (!convId || !get().conversations[convId]) {
 					return;
 				}
@@ -1200,75 +1093,63 @@ export const useAIAssistantStore = create<AIAssistantStore>()(
 				};
 
 				set((state) => {
-					const conv = state.conversations[convId];
+					const conv = state.conversations[convId!];
 					conv.messages.push(userMessage);
 					conv.updatedAt = Date.now();
 					if (!conv.title && text.trim()) {
 						conv.title = deriveTitle(text);
 					}
-					resetStreamingState(state, convId);
+					resetStreamingState(state, convId!);
 				});
 
-				// The full send — ensure a backend thread exists (re-keying the
-				// optimistic client UUID on first send), POST the message, and
-				// stream the reply. Defined as a closure so the error bubble's
-				// Retry button can replay it without re-pushing the user message.
-				const runSend = async (cid: string): Promise<void> => {
-					let targetConvId = cid;
-					try {
-						let { threadId } = get().conversations[targetConvId];
-						if (!threadId) {
-							threadId = await createThread();
-							// Re-key the conversation from client UUID to backend threadId
-							// so fetchThreads won't create a duplicate entry later.
-							const oldId = targetConvId;
-							const newId = threadId;
-							set((s) => {
-								const conv = s.conversations[oldId];
-								if (conv) {
-									conv.id = newId;
-									conv.threadId = newId;
-									s.conversations[newId] = conv;
-									delete s.conversations[oldId];
-									if (s.activeConversationId === oldId) {
-										s.activeConversationId = newId;
-									}
-									const stream = s.streams[oldId];
-									if (stream) {
-										s.streams[newId] = stream;
-										delete s.streams[oldId];
-									}
+				try {
+					let { threadId } = get().conversations[convId];
+					if (!threadId) {
+						threadId = await createThread();
+						// Re-key the conversation from client UUID to backend threadId
+						// so fetchThreads won't create a duplicate entry later.
+						const oldId = convId;
+						convId = threadId;
+						set((s) => {
+							const conv = s.conversations[oldId];
+							if (conv) {
+								conv.id = convId!;
+								conv.threadId = convId!;
+								s.conversations[convId!] = conv;
+								delete s.conversations[oldId];
+								if (s.activeConversationId === oldId) {
+									s.activeConversationId = convId!;
 								}
-							});
-							targetConvId = newId;
-						}
-						const tid = threadId;
-						await streamWithRetry(
-							targetConvId,
-							() => sendMessageToThread(tid, text, contexts),
-							set,
-						);
-
-						if (!hasPendingInput(targetConvId, get)) {
-							finalizeStreamingMessage(targetConvId, set, get);
-						}
-					} catch (err) {
-						// Abort errors are expected when the user cancels — not a failure.
-						if (err instanceof DOMException && err.name === 'AbortError') {
-							return;
-						}
-						console.error('[AIAssistant] sendMessage failed:', err);
-						const resolution = resolveAssistantError(
-							err,
-							'Something went wrong while fetching the response. Please try again.',
-						);
-						finalizeStreamingError(targetConvId, resolution, set, () =>
-							runSend(targetConvId),
-						);
+								const stream = s.streams[oldId];
+								if (stream) {
+									s.streams[convId!] = stream;
+									delete s.streams[oldId];
+								}
+							}
+						});
 					}
-				};
+					const tid = threadId;
+					await streamWithAuthRetry(
+						convId,
+						() => sendMessageToThread(tid, text, contexts),
+						set,
+					);
 
-				await runSend(convId);
+					if (!hasPendingInput(convId, get)) {
+						finalizeStreamingMessage(convId, set, get);
+					}
+				} catch (err) {
+					// Abort errors are expected when the user cancels — not a failure
+					if (err instanceof DOMException && err.name === 'AbortError') {
+						return;
+					}
+					console.error('[AIAssistant] sendMessage failed:', err);
+					const { message, isRateLimit } = resolveAssistantErrorMessage(
+						err,
+						'Something went wrong while fetching the response. Please try again.',
+					);
+					finalizeStreamingError(convId, message, set, isRateLimit);
+				}
 			},
 
 			approveAction: async (
@@ -1286,17 +1167,26 @@ export const useAIAssistantStore = create<AIAssistantStore>()(
 					}
 				});
 
-				const run = (): Promise<void> =>
-					streamAndFinalize(
+				try {
+					await streamWithAuthRetry(
 						conversationId,
 						() => approveExecution(approvalId),
-						'Something went wrong while processing the approval. Please try again.',
-						'[AIAssistant] approveAction failed:',
 						set,
-						get,
-						run,
 					);
-				await run();
+					if (!hasPendingInput(conversationId, get)) {
+						finalizeStreamingMessage(conversationId, set, get);
+					}
+				} catch (err) {
+					if (err instanceof DOMException && err.name === 'AbortError') {
+						return;
+					}
+					console.error('[AIAssistant] approveAction failed:', err);
+					const { message, isRateLimit } = resolveAssistantErrorMessage(
+						err,
+						'Something went wrong while processing the approval. Please try again.',
+					);
+					finalizeStreamingError(conversationId, message, set, isRateLimit);
+				}
 			},
 
 			rejectAction: async (
@@ -1356,17 +1246,26 @@ export const useAIAssistantStore = create<AIAssistantStore>()(
 					resetStreamingState(s, conversationId);
 				});
 
-				const run = (): Promise<void> =>
-					streamAndFinalize(
+				try {
+					await streamWithAuthRetry(
 						conversationId,
 						() => regenerateMessage(messageId),
-						'Something went wrong while regenerating the response. Please try again.',
-						'[AIAssistant] regenerateAssistantMessage failed:',
 						set,
-						get,
-						run,
 					);
-				await run();
+					if (!hasPendingInput(conversationId, get)) {
+						finalizeStreamingMessage(conversationId, set, get);
+					}
+				} catch (err) {
+					if (err instanceof DOMException && err.name === 'AbortError') {
+						return;
+					}
+					console.error('[AIAssistant] regenerateAssistantMessage failed:', err);
+					const { message, isRateLimit } = resolveAssistantErrorMessage(
+						err,
+						'Something went wrong while regenerating the response. Please try again.',
+					);
+					finalizeStreamingError(conversationId, message, set, isRateLimit);
+				}
 			},
 
 			submitMessageFeedback: async (
@@ -1413,42 +1312,26 @@ export const useAIAssistantStore = create<AIAssistantStore>()(
 					}
 				});
 
-				const run = (): Promise<void> =>
-					streamAndFinalize(
+				try {
+					await streamWithAuthRetry(
 						conversationId,
 						() => clarifyExecution(clarificationId, answers),
-						'Something went wrong while processing your answers. Please try again.',
-						'[AIAssistant] submitClarification failed:',
 						set,
-						get,
-						run,
 					);
-				await run();
-			},
-
-			retryAssistantMessage: async (conversationId: string): Promise<void> => {
-				const retry = retryRegistry.get(conversationId);
-				if (!retry) {
-					return;
-				}
-				retryRegistry.delete(conversationId);
-
-				// Drop the trailing error bubble we're retrying from and reset the
-				// stream so the in-progress retry renders immediately. The retry
-				// thunk replays the originating action without re-pushing the
-				// user's message.
-				set((s) => {
-					const conv = s.conversations[conversationId];
-					if (conv) {
-						const last = conv.messages[conv.messages.length - 1];
-						if (last?.isError) {
-							conv.messages.pop();
-						}
+					if (!hasPendingInput(conversationId, get)) {
+						finalizeStreamingMessage(conversationId, set, get);
 					}
-					resetStreamingState(s, conversationId);
-				});
-
-				await retry();
+				} catch (err) {
+					if (err instanceof DOMException && err.name === 'AbortError') {
+						return;
+					}
+					console.error('[AIAssistant] submitClarification failed:', err);
+					const { message, isRateLimit } = resolveAssistantErrorMessage(
+						err,
+						'Something went wrong while processing your answers. Please try again.',
+					);
+					finalizeStreamingError(conversationId, message, set, isRateLimit);
+				}
 			},
 		})),
 		{

frontend/src/container/AIAssistant/types.ts

@@ -15,11 +15,9 @@
 import type {
 	ApprovalEventDTO,
 	ClarificationEventDTO,
-	ErrorCodeDTO,
 	FeedbackRatingDTO,
 	MessageActionDTO,
 	MessageActionKindDTO,
-	RetryActionDTO,
 } from 'api/ai-assistant/sigNozAIAssistantAPI.schemas';
 
 /** Client-only file attachment — no API equivalent (uploads happen via data URLs). */
@@ -93,18 +91,6 @@ export interface Message {
 	 * bar (copy/vote/regenerate) is hidden — retrying would just 429 again.
 	 */
 	isRateLimitError?: boolean;
-	/**
-	 * Marks an assistant message that represents a failed turn. Drives the
-	 * error styling and replaces the feedback bar with a retry affordance.
-	 */
-	isError?: boolean;
-	/** Known backend error code for the failure, when recognised. */
-	errorCode?: ErrorCodeDTO;
-	/**
-	 * Retry semantics for a failed turn — `manual` renders an inline Retry
-	 * button on the error bubble; `none`/`auto` render no button.
-	 */
-	retryAction?: RetryActionDTO;
 	createdAt: number;
 }
 

frontend/src/container/AIAssistant/utils/__tests__/resolveAssistantError.test.ts

@@ -1,154 +0,0 @@
-import { AxiosError } from 'axios';
-import {
-	ErrorCodeDTO,
-	RetryActionDTO,
-} from 'api/ai-assistant/sigNozAIAssistantAPI.schemas';
-
-import { resolveAssistantError } from '../resolveAssistantError';
-
-const FALLBACK = 'Something went wrong. Please try again.';
-
-function restError(status: number, code: string, message: string): AxiosError {
-	const err = new AxiosError('Request failed');
-	err.response = {
-		status,
-		data: { error: { code, message } },
-	} as AxiosError['response'];
-	return err;
-}
-
-describe('resolveAssistantError', () => {
-	describe('message resolution', () => {
-		it('prefers code-specific FE copy over the backend message', () => {
-			const err = restError(409, ErrorCodeDTO.thread_busy, 'raw backend phrasing');
-
-			const { message } = resolveAssistantError(err, FALLBACK);
-			expect(message).toBe(
-				'This conversation is still finishing a previous response. Give it a moment and try again.',
-			);
-		});
-
-		it('falls through to the backend message for a known code without FE copy', () => {
-			const err = restError(
-				400,
-				ErrorCodeDTO.message_not_found,
-				'No such message exists.',
-			);
-
-			expect(resolveAssistantError(err, FALLBACK)).toStrictEqual({
-				message: 'No such message exists.',
-				code: ErrorCodeDTO.message_not_found,
-				retryAction: RetryActionDTO.none,
-				isRateLimit: false,
-			});
-		});
-
-		it('falls back when the error code is not in ErrorCodeDTO', () => {
-			const err = restError(400, 'future_unknown_code', 'Backend-only message');
-
-			expect(resolveAssistantError(err, FALLBACK)).toStrictEqual({
-				message: FALLBACK,
-				code: undefined,
-				retryAction: RetryActionDTO.none,
-				isRateLimit: false,
-			});
-		});
-	});
-
-	describe('rate limiting', () => {
-		it('marks HTTP 429 responses as rate limited and non-retryable', () => {
-			const err = restError(
-				429,
-				ErrorCodeDTO.hourly_message_limit,
-				'Hourly limit reached.',
-			);
-
-			expect(resolveAssistantError(err, FALLBACK)).toStrictEqual({
-				message: "You've reached the hourly message limit. Please try again later.",
-				code: ErrorCodeDTO.hourly_message_limit,
-				retryAction: RetryActionDTO.none,
-				isRateLimit: true,
-			});
-		});
-
-		it('treats known SSE rate-limit codes as rate limited', () => {
-			const err = Object.assign(new Error('Daily token limit exceeded.'), {
-				code: ErrorCodeDTO.daily_token_limit,
-			});
-
-			const res = resolveAssistantError(err, FALLBACK);
-			expect(res.isRateLimit).toBe(true);
-			expect(res.retryAction).toBe(RetryActionDTO.none);
-		});
-
-		it('marks 429 as rate limited even when the code is unknown', () => {
-			const err = restError(429, 'future_unknown_code', 'Too many requests');
-
-			expect(resolveAssistantError(err, FALLBACK)).toStrictEqual({
-				message: FALLBACK,
-				code: undefined,
-				retryAction: RetryActionDTO.none,
-				isRateLimit: true,
-			});
-		});
-	});
-
-	describe('retryAction resolution', () => {
-		it('honours an explicit retryAction from an SSE error event', () => {
-			const err = Object.assign(new Error('Transient hiccup'), {
-				code: ErrorCodeDTO.internal_error,
-				retryAction: RetryActionDTO.auto,
-			});
-
-			expect(resolveAssistantError(err, FALLBACK).retryAction).toBe(
-				RetryActionDTO.auto,
-			);
-		});
-
-		it('forces none for non-retryable permission errors', () => {
-			const err = restError(403, ErrorCodeDTO.permission_denied, 'forbidden');
-
-			expect(resolveAssistantError(err, FALLBACK).retryAction).toBe(
-				RetryActionDTO.none,
-			);
-		});
-
-		it('derives manual for 409 conflicts', () => {
-			const err = restError(409, ErrorCodeDTO.thread_has_active_execution, 'busy');
-
-			expect(resolveAssistantError(err, FALLBACK).retryAction).toBe(
-				RetryActionDTO.manual,
-			);
-		});
-
-		it('derives manual for 5xx responses', () => {
-			const err = restError(503, 'future_unknown_code', 'unavailable');
-
-			expect(resolveAssistantError(err, FALLBACK).retryAction).toBe(
-				RetryActionDTO.manual,
-			);
-		});
-
-		it('derives manual for network failures with no response', () => {
-			const err = new AxiosError('Network Error');
-
-			expect(resolveAssistantError(err, FALLBACK).retryAction).toBe(
-				RetryActionDTO.manual,
-			);
-		});
-
-		it('derives none for other 4xx responses', () => {
-			const err = restError(400, 'future_unknown_code', 'bad request');
-
-			expect(resolveAssistantError(err, FALLBACK).retryAction).toBe(
-				RetryActionDTO.none,
-			);
-		});
-
-		it('defaults to manual for non-Axios errors with no code', () => {
-			expect(resolveAssistantError(new Error('boom'), FALLBACK).retryAction).toBe(
-				RetryActionDTO.manual,
-			);
-		});
-	});
-});

frontend/src/container/AIAssistant/utils/__tests__/resolveAssistantErrorMessage.test.ts

@@ -0,0 +1,91 @@
+import { AxiosError } from 'axios';
+import { ErrorCodeDTO } from 'api/ai-assistant/sigNozAIAssistantAPI.schemas';
+
+import { resolveAssistantErrorMessage } from '../resolveAssistantErrorMessage';
+
+const FALLBACK = 'Something went wrong. Please try again.';
+
+describe('resolveAssistantErrorMessage', () => {
+	it('returns backend message for a known error code', () => {
+		const err = new AxiosError('Request failed');
+		err.response = {
+			status: 400,
+			data: {
+				error: {
+					code: ErrorCodeDTO.thread_busy,
+					message: 'This thread is busy. Try again shortly.',
+				},
+			},
+		} as AxiosError['response'];
+
+		expect(resolveAssistantErrorMessage(err, FALLBACK)).toStrictEqual({
+			message: 'This thread is busy. Try again shortly.',
+			isRateLimit: false,
+		});
+	});
+
+	it('falls back when error code is not in ErrorCodeDTO', () => {
+		const err = new AxiosError('Request failed');
+		err.response = {
+			status: 400,
+			data: {
+				error: {
+					code: 'future_unknown_code',
+					message: 'Backend-only message',
+				},
+			},
+		} as AxiosError['response'];
+
+		expect(resolveAssistantErrorMessage(err, FALLBACK)).toStrictEqual({
+			message: FALLBACK,
+			isRateLimit: false,
+		});
+	});
+
+	it('marks HTTP 429 responses as rate limited', () => {
+		const err = new AxiosError('Too many requests');
+		err.response = {
+			status: 429,
+			data: {
+				error: {
+					code: ErrorCodeDTO.hourly_message_limit,
+					message: 'Hourly limit reached.',
+				},
+			},
+		} as AxiosError['response'];
+
+		expect(resolveAssistantErrorMessage(err, FALLBACK)).toStrictEqual({
+			message: 'Hourly limit reached.',
+			isRateLimit: true,
+		});
+	});
+
+	it('uses backend message for known SSE rate-limit error codes', () => {
+		const err = Object.assign(new Error('Daily token limit exceeded.'), {
+			code: ErrorCodeDTO.daily_token_limit,
+		});
+
+		expect(resolveAssistantErrorMessage(err, FALLBACK)).toStrictEqual({
+			message: 'Daily token limit exceeded.',
+			isRateLimit: true,
+		});
+	});
+
+	it('marks 429 as rate limited even when error code is unknown', () => {
+		const err = new AxiosError('Too many requests');
+		err.response = {
+			status: 429,
+			data: {
+				error: {
+					code: 'future_unknown_code',
+					message: 'Too many requests',
+				},
+			},
+		} as AxiosError['response'];
+
+		expect(resolveAssistantErrorMessage(err, FALLBACK)).toStrictEqual({
+			message: FALLBACK,
+			isRateLimit: true,
+		});
+	});
+});

frontend/src/container/AIAssistant/utils/resolveAssistantError.ts

@@ -1,209 +0,0 @@
-import { isAxiosError } from 'axios';
-import {
-	ErrorCodeDTO,
-	RetryActionDTO,
-	type ErrorBodyDTO,
-	type ErrorResponseDTO,
-} from 'api/ai-assistant/sigNozAIAssistantAPI.schemas';
-
-export interface AssistantErrorResolution {
-	/** User-facing copy: code-specific FE copy → backend message → caller fallback. */
-	message: string;
-	/** Known backend error code, when one we recognise was supplied. */
-	code?: ErrorCodeDTO;
-	/**
-	 * Whether/how the failed action may be retried:
-	 *   • `auto`   — transient; the caller may silently re-attempt (capped).
-	 *   • `manual` — surface a Retry affordance to the user.
-	 *   • `none`   — retrying would re-fail deterministically; offer nothing.
-	 */
-	retryAction: RetryActionDTO;
-	/** Quota/limit error — callers hide the retry + feedback bar (retrying just re-limits). */
-	isRateLimit: boolean;
-}
-
-/** Quota/limit codes — surfaced as rate-limit errors (no retry, feedback bar hidden). */
-const RATE_LIMIT_ERROR_CODES = new Set<ErrorCodeDTO>([
-	ErrorCodeDTO.rate_limit_override_exceeds_ceiling,
-	ErrorCodeDTO.thread_message_limit,
-	ErrorCodeDTO.connection_limit_exceeded,
-	ErrorCodeDTO.hourly_message_limit,
-	ErrorCodeDTO.daily_message_limit,
-	ErrorCodeDTO.daily_token_limit,
-	ErrorCodeDTO.daily_cost_limit,
-	ErrorCodeDTO.budget_exceeded,
-]);
-
-/**
- * Codes whose retry would re-fail deterministically — permission/config/validation
- * failures. These force `retryAction: none` regardless of HTTP status.
- */
-const NON_RETRYABLE_CODES = new Set<ErrorCodeDTO>([
-	ErrorCodeDTO.permission_denied,
-	ErrorCodeDTO.user_disabled,
-	ErrorCodeDTO.org_disabled,
-	ErrorCodeDTO.validation_error,
-	ErrorCodeDTO.invalid_content_length,
-	ErrorCodeDTO.invalid_fork_target,
-	ErrorCodeDTO.missing_signoz_url,
-	ErrorCodeDTO.invalid_signoz_url,
-	ErrorCodeDTO.region_not_configured,
-]);
-
-/**
- * Code-specific, user-friendly copy. Takes precedence over the backend's raw
- * `error.message` so the user sees an actionable, consistent sentence rather
- * than internal phrasing. Codes absent here fall through to the backend message.
- */
-const ERROR_CODE_COPY: Partial<Record<ErrorCodeDTO, string>> = {
-	[ErrorCodeDTO.permission_denied]:
-		"You don't have permission to do that. Contact your workspace admin if you think this is a mistake.",
-	[ErrorCodeDTO.user_disabled]:
-		'Your access to the AI assistant has been disabled. Contact your workspace admin to re-enable it.',
-	[ErrorCodeDTO.org_disabled]:
-		'The AI assistant is disabled for your organisation. An admin can enable it in settings.',
-	[ErrorCodeDTO.thread_busy]:
-		'This conversation is still finishing a previous response. Give it a moment and try again.',
-	[ErrorCodeDTO.thread_has_active_execution]:
-		'This conversation is still finishing a previous response. Give it a moment and try again.',
-	[ErrorCodeDTO.hourly_message_limit]:
-		"You've reached the hourly message limit. Please try again later.",
-	[ErrorCodeDTO.daily_message_limit]:
-		"You've reached the daily message limit. Please try again tomorrow.",
-	[ErrorCodeDTO.daily_token_limit]:
-		"You've reached today's usage limit. Please try again tomorrow.",
-	[ErrorCodeDTO.daily_cost_limit]:
-		"You've reached today's usage limit. Please try again tomorrow.",
-	[ErrorCodeDTO.budget_exceeded]:
-		"You've reached your usage budget. Contact your workspace admin to raise it.",
-	[ErrorCodeDTO.thread_message_limit]:
-		'This conversation has reached its length limit. Start a new conversation to continue.',
-	[ErrorCodeDTO.connection_limit_exceeded]:
-		'Too many active conversations right now. Close one and try again.',
-	[ErrorCodeDTO.max_turns_exceeded]:
-		'The assistant reached the maximum number of steps for this request. Try rephrasing or breaking it into smaller asks.',
-	[ErrorCodeDTO.region_unreachable]:
-		"Couldn't reach your region's services. Please try again in a moment.",
-	[ErrorCodeDTO.region_not_configured]:
-		'No region is configured for the AI assistant yet. An admin can set this up in settings.',
-	[ErrorCodeDTO.mcp_unavailable]:
-		'A required service is temporarily unavailable. Please try again shortly.',
-	[ErrorCodeDTO.sandbox_unavailable]:
-		'The execution environment is temporarily unavailable. Please try again shortly.',
-	[ErrorCodeDTO.internal_error]:
-		'Something went wrong on our end. Please try again.',
-};
-
-function isErrorCodeDTO(code: string | undefined): code is ErrorCodeDTO {
-	return (
-		code !== undefined && (Object.values(ErrorCodeDTO) as string[]).includes(code)
-	);
-}
-
-function isRetryActionDTO(value: unknown): value is RetryActionDTO {
-	return (
-		typeof value === 'string' &&
-		(Object.values(RetryActionDTO) as string[]).includes(value)
-	);
-}
-
-/**
- * Pulls the structured error body out of either an Axios REST error or the
- * SSE error the streaming loop throws (a plain `Error` augmented with `code`).
- */
-function getErrorBody(err: unknown): ErrorBodyDTO | null {
-	if (isAxiosError(err)) {
-		return (err.response?.data as ErrorResponseDTO | undefined)?.error ?? null;
-	}
-
-	const code = (err as { code?: string } | undefined)?.code;
-	const message = err instanceof Error ? err.message : undefined;
-	if (!code || !message) {
-		return null;
-	}
-
-	return { code: code as ErrorCodeDTO, message };
-}
-
-function isRateLimit(code: ErrorCodeDTO | undefined, err: unknown): boolean {
-	if (isAxiosError(err) && err.response?.status === 429) {
-		return true;
-	}
-	return code !== undefined && RATE_LIMIT_ERROR_CODES.has(code);
-}
-
-/**
- * Resolves how the failed action may be retried. The backend's explicit signal
- * (SSE `ErrorEventDTO.retryAction`) is authoritative; otherwise we derive it
- * from the rate-limit/non-retryable code sets and the HTTP status.
- */
-function resolveRetryAction(
-	err: unknown,
-	code: ErrorCodeDTO | undefined,
-	rateLimited: boolean,
-): RetryActionDTO {
-	const explicit = (err as { retryAction?: unknown } | undefined)?.retryAction;
-	if (isRetryActionDTO(explicit)) {
-		return explicit;
-	}
-
-	if (rateLimited || (code !== undefined && NON_RETRYABLE_CODES.has(code))) {
-		return RetryActionDTO.none;
-	}
-
-	if (isAxiosError(err)) {
-		const status = err.response?.status;
-		// No response → network/timeout failure; retrying may well succeed.
-		if (status === undefined || status === 408) {
-			return RetryActionDTO.manual;
-		}
-		if (status === 401 || status === 403) {
-			return RetryActionDTO.none;
-		}
-		if (status === 409 || status >= 500) {
-			return RetryActionDTO.manual;
-		}
-		// Other 4xx (validation, bad request) re-fail deterministically.
-		return RetryActionDTO.none;
-	}
-
-	// Non-Axios transport/parse error with no code — let the user retry.
-	return RetryActionDTO.manual;
-}
-
-function resolveMessage(
-	code: ErrorCodeDTO | undefined,
-	body: ErrorBodyDTO | null,
-	fallback: string,
-): string {
-	if (code !== undefined && ERROR_CODE_COPY[code]) {
-		return ERROR_CODE_COPY[code] as string;
-	}
-	// Trust the backend's message only for codes we recognise — never surface
-	// raw text for unknown codes (could be an internal stack trace).
-	if (code !== undefined && body?.message.trim()) {
-		return body.message.trim();
-	}
-	return fallback;
-}
-
-/**
- * Single resolution point for both SSE and REST assistant errors. Maps the
- * error onto user-facing copy plus retry semantics, degrading gracefully for
- * unknown codes (falls back to `fallback` + a `manual` retry where sensible).
- */
-export function resolveAssistantError(
-	err: unknown,
-	fallback: string,
-): AssistantErrorResolution {
-	const body = getErrorBody(err);
-	const code = isErrorCodeDTO(body?.code) ? body?.code : undefined;
-	const rateLimited = isRateLimit(code, err);
-
-	return {
-		message: resolveMessage(code, body, fallback),
-		code,
-		retryAction: resolveRetryAction(err, code, rateLimited),
-		isRateLimit: rateLimited,
-	};
-}

frontend/src/container/AIAssistant/utils/resolveAssistantErrorMessage.ts

@@ -0,0 +1,71 @@
+import { isAxiosError } from 'axios';
+import {
+	ErrorCodeDTO,
+	type ErrorBodyDTO,
+	type ErrorResponseDTO,
+} from 'api/ai-assistant/sigNozAIAssistantAPI.schemas';
+
+export interface AssistantErrorResolution {
+	message: string;
+	isRateLimit: boolean;
+}
+
+function isErrorCodeDTO(code: string | undefined): code is ErrorCodeDTO {
+	return (
+		code !== undefined && (Object.values(ErrorCodeDTO) as string[]).includes(code)
+	);
+}
+
+const RATE_LIMIT_ERROR_CODES = new Set<ErrorCodeDTO>([
+	ErrorCodeDTO.rate_limit_override_exceeds_ceiling,
+	ErrorCodeDTO.thread_message_limit,
+	ErrorCodeDTO.connection_limit_exceeded,
+	ErrorCodeDTO.hourly_message_limit,
+	ErrorCodeDTO.daily_message_limit,
+	ErrorCodeDTO.daily_token_limit,
+	ErrorCodeDTO.daily_cost_limit,
+	ErrorCodeDTO.budget_exceeded,
+]);
+
+function isRateLimitError(code: string | undefined, err: unknown): boolean {
+	if (isAxiosError(err) && err.response?.status === 429) {
+		return true;
+	}
+
+	return isErrorCodeDTO(code) && RATE_LIMIT_ERROR_CODES.has(code);
+}
+
+function getErrorBody(err: unknown): ErrorBodyDTO | null {
+	if (isAxiosError(err)) {
+		return (err.response?.data as ErrorResponseDTO | undefined)?.error ?? null;
+	}
+
+	const code = (err as { code?: string } | undefined)?.code;
+	const message = err instanceof Error ? err.message : undefined;
+	if (!code || !message) {
+		return null;
+	}
+
+	return { code: code as ErrorCodeDTO, message };
+}
+
+/**
+ * Uses `error.message` when `error.code` is a known `ErrorCodeDTO`;
+ * otherwise returns `fallback`.
+ */
+export function resolveAssistantErrorMessage(
+	err: unknown,
+	fallback: string,
+): AssistantErrorResolution {
+	const body = getErrorBody(err);
+	const isRateLimit = isRateLimitError(body?.code, err);
+
+	if (body && isErrorCodeDTO(body.code) && body.message.trim()) {
+		return {
+			message: body.message.trim(),
+			isRateLimit,
+		};
+	}
+
+	return { message: fallback, isRateLimit: Boolean(isRateLimit) };
+}

frontend/src/container/AppLayout/AppLayout.styles.scss

@@ -53,6 +53,10 @@
 		z-index: 0;
 		background: var(--l1-background);
 
+		// Column so the bottom strip sits under the scrolling content, not inside it.
+		display: flex;
+		flex-direction: column;
+
 		&.full-screen-content {
 			width: 100%;
 		}
@@ -70,7 +74,9 @@
 
 .chat-support-gateway {
 	position: fixed;
-	bottom: 20px;
+	// Lifted above the bottom strip. Don't extend this pattern — new fixed-bottom
+	// UI belongs in the bounded layout, not in another offset here.
+	bottom: calc(20px + var(--bottom-strip-height, 0px));
 	right: 20px;
 	z-index: 1000;
 

frontend/src/container/AppLayout/index.tsx

@@ -43,6 +43,7 @@ import { USER_PREFERENCES } from 'constants/userPreferences';
 import AIAssistantModal from 'container/AIAssistant/AIAssistantModal';
 import AIAssistantPanel from 'container/AIAssistant/AIAssistantPanel';
 import { useAIAssistantStore } from 'container/AIAssistant/store/useAIAssistantStore';
+import BottomStrip from 'container/BottomStrip';
 import SideNav from 'container/SideNav';
 import TopNav from 'container/TopNav';
 import dayjs from 'dayjs';
@@ -51,6 +52,7 @@ import { useIsDarkMode } from 'hooks/useDarkMode';
 import { useGetTenantLicense } from 'hooks/useGetTenantLicense';
 import { useIsAIAssistantEnabled } from 'hooks/useIsAIAssistantEnabled';
 import { useNotifications } from 'hooks/useNotifications';
+import { useSavedViewEnabled } from 'hooks/useSavedViewEnabled';
 import useTabVisibility from 'hooks/useTabFocus';
 import history from 'lib/history';
 import { isNull } from 'lodash-es';
@@ -402,6 +404,7 @@ function AppLayout(props: AppLayoutProps): JSX.Element {
 	}, [pathname]);
 
 	const isToDisplayLayout = isLoggedIn;
+	const isSavedViewEnabled = useSavedViewEnabled();
 
 	const routeKey = useMemo(() => getRouteKey(pathname), [pathname]);
 	const pageTitle = t(routeKey);
@@ -868,6 +871,10 @@ function AppLayout(props: AppLayoutProps): JSX.Element {
 								</OverlayScrollbar>
 							</LayoutContent>
 						</Sentry.ErrorBoundary>
+
+						{isSavedViewEnabled && isToDisplayLayout && !renderFullScreen && (
+							<BottomStrip />
+						)}
 					</div>
 
 					{isLoggedIn && isAIAssistantEnabled && (

frontend/src/container/AppLayout/styles.ts

@@ -12,8 +12,12 @@ export const Layout = styled(LayoutComponent)`
 	}
 `;
 
+// Takes the height left in `.app-content` after the bottom strip.
+// `min-height: 0` is not needed right now, overlayscrollbars already sets
+// `overflow: auto` here. Kept so this does not break if that goes away.
 export const LayoutContent = styled(LayoutComponent.Content)`
-	height: 100%;
+	flex: 1;
+	min-height: 0;
 	&::-webkit-scrollbar {
 		width: 0.1rem;
 	}

frontend/src/container/BottomStrip/BottomStrip.module.scss

@@ -0,0 +1,36 @@
+.strip {
+	display: flex;
+	align-items: center;
+	justify-content: space-between;
+	gap: var(--spacing-6);
+
+	flex-shrink: 0;
+	height: var(--bottom-strip-height);
+	padding: 0 var(--spacing-6);
+
+	background: var(--l2-background);
+	border-top: 1px solid var(--l2-border);
+
+	font-family: var(--font-family-sf-mono, monospace);
+
+	// Above page content, below the body-portalled overlays that are meant to
+	// cover the strip.
+	position: relative;
+	z-index: 1;
+}
+
+.left,
+.right {
+	display: flex;
+	align-items: center;
+	gap: var(--spacing-6);
+	min-width: 0;
+}
+
+// Temporary placeholder for the left slot. Replaced later.
+.version {
+	color: var(--l2-foreground);
+	white-space: nowrap;
+	overflow: hidden;
+	text-overflow: ellipsis;
+}

frontend/src/container/BottomStrip/__tests__/BottomStrip.test.tsx

@@ -0,0 +1,49 @@
+import { render } from 'tests/test-utils';
+
+import BottomStrip, {
+	BOTTOM_STRIP_HEIGHT,
+	BOTTOM_STRIP_HEIGHT_VAR,
+	BOTTOM_STRIP_ON_CLASS,
+} from '..';
+
+describe('BottomStrip', () => {
+	it('publishes the body class and height property while mounted', () => {
+		const { unmount } = render(<BottomStrip />);
+
+		expect(document.body.classList.contains(BOTTOM_STRIP_ON_CLASS)).toBe(true);
+		expect(document.body.style.getPropertyValue(BOTTOM_STRIP_HEIGHT_VAR)).toBe(
+			`${BOTTOM_STRIP_HEIGHT}px`,
+		);
+
+		unmount();
+
+		expect(document.body.classList.contains(BOTTOM_STRIP_ON_CLASS)).toBe(false);
+		expect(document.body.style.getPropertyValue(BOTTOM_STRIP_HEIGHT_VAR)).toBe(
+			'',
+		);
+	});
+
+	// The string is whatever the Go build injected, so it is rendered untouched —
+	// same as SideNav. Release tags carry the "v", local builds do not.
+	it.each([['v0.134.67'], ['main-64f1c2a']])(
+		'renders the build version %p exactly as given',
+		(version) => {
+			const { getByTestId } = render(<BottomStrip />, undefined, {
+				appContextOverrides: {
+					versionData: { version, ee: 'Y', setupCompleted: true },
+				},
+			});
+
+			expect(getByTestId('bottom-strip-version')).toHaveTextContent(version);
+		},
+	);
+
+	it('renders the strip without a version when none is available', () => {
+		const { getByTestId, queryByTestId } = render(<BottomStrip />, undefined, {
+			appContextOverrides: { versionData: null },
+		});
+
+		expect(getByTestId('bottom-strip')).toBeInTheDocument();
+		expect(queryByTestId('bottom-strip-version')).not.toBeInTheDocument();
+	});
+});

frontend/src/container/BottomStrip/index.tsx

@@ -0,0 +1,42 @@
+import { useLayoutEffect } from 'react';
+import { useAppContext } from 'providers/App/App';
+
+import styles from './BottomStrip.module.scss';
+
+export const BOTTOM_STRIP_HEIGHT = 24;
+
+export const BOTTOM_STRIP_ON_CLASS = 'bottom-strip-on';
+export const BOTTOM_STRIP_HEIGHT_VAR = '--bottom-strip-height';
+
+function BottomStrip(): JSX.Element {
+	const { versionData } = useAppContext();
+	const version = versionData?.version?.trim();
+
+	useLayoutEffect(() => {
+		document.body.classList.add(BOTTOM_STRIP_ON_CLASS);
+		document.body.style.setProperty(
+			BOTTOM_STRIP_HEIGHT_VAR,
+			`${BOTTOM_STRIP_HEIGHT}px`,
+		);
+
+		return (): void => {
+			document.body.classList.remove(BOTTOM_STRIP_ON_CLASS);
+			document.body.style.removeProperty(BOTTOM_STRIP_HEIGHT_VAR);
+		};
+	}, []);
+
+	return (
+		<div className={styles.strip} data-testid="bottom-strip">
+			<div className={styles.left}>
+				{version && (
+					<span className={styles.version} data-testid="bottom-strip-version">
+						{version}
+					</span>
+				)}
+			</div>
+			<div className={styles.right} />
+		</div>
+	);
+}
+
+export default BottomStrip;

frontend/src/container/CreateAlertV2/Footer/styles.scss

@@ -1,6 +1,8 @@
 .create-alert-v2-footer {
 	position: fixed;
-	bottom: 0;
+	// Lifted above the bottom strip. Don't extend this pattern — new fixed-bottom
+	// UI belongs in the bounded layout, not in another offset here.
+	bottom: var(--bottom-strip-height, 0px);
 	left: 63px;
 	right: 0;
 	background-color: var(--l1-background);

frontend/src/container/ExplorerOptions/ExplorerOptions.styles.scss

@@ -1,6 +1,8 @@
 .explorer-options-container {
 	position: fixed;
-	bottom: 0px;
+	// Lifted above the bottom strip. Don't extend this pattern — new fixed-bottom
+	// UI belongs in the bounded layout, not in another offset here.
+	bottom: var(--bottom-strip-height, 0px);
 	left: calc(50% + 240px);
 	transform: translate(calc(-50% - 120px), 0);
 	transition: left 0.2s linear;

frontend/src/container/ExplorerOptions/ExplorerOptionsHideArea.styles.scss

@@ -1,6 +1,8 @@
 .explorer-option-droppable-container {
 	position: fixed;
-	bottom: 0;
+	// Lifted above the bottom strip. Don't extend this pattern — new fixed-bottom
+	// UI belongs in the bounded layout, not in another offset here.
+	bottom: var(--bottom-strip-height, 0px);
 	width: -webkit-fill-available;
 	height: 24px;
 	display: flex;

frontend/src/container/Home/Home.styles.scss

@@ -1,7 +1,6 @@
 .home-container {
 	display: flex;
 	flex-direction: column;
-	min-height: 100vh;
 	overflow-y: auto;
 	height: 100%;
 	width: 100%;

frontend/src/container/Integrations/CloudIntegration/AmazonWebServices/__tests__/mockData.ts

@@ -24,6 +24,7 @@ const accountsResponse: ListAccounts200 = {
 				agentReport: {
 					timestampMillis: 1747114366214,
 					data: null,
+					syncState: null,
 				},
 				providerAccountId: PROVIDER_ACCOUNT_ID,
 				removedAt: null,

frontend/src/container/Licenses/Licenses.styles.scss

@@ -1,7 +1,4 @@
 .licenses-page {
-	max-height: 100vh;
-	overflow: hidden;
-
 	.licenses-page-header {
 		border-bottom: 1px solid var(--l1-border);
 		background: var(--l1-background);
@@ -32,7 +29,6 @@
 
 		.licenses-page-content {
 			flex: 1;
-			height: calc(100vh - 48px);
 			background: var(--l1-background);
 			padding: 10px 8px;
 			overflow-y: auto;

frontend/src/container/ListAlertRules/ListAlertRules.module.scss

@@ -2,7 +2,7 @@
 	display: flex;
 	flex-direction: column;
 	gap: 1rem;
-	height: calc(100vh - 62px);
+	flex: 1;
 	min-height: 400px;
 }
 

frontend/src/container/MetricsExplorer/Summary/Summary.styles.scss

@@ -181,7 +181,9 @@
 
 		.ant-pagination {
 			position: fixed;
-			bottom: 0;
+			// Lifted above the bottom strip. Don't extend this pattern — new
+			// fixed-bottom UI belongs in the bounded layout, not in another offset here.
+			bottom: var(--bottom-strip-height, 0px);
 			width: calc(100% - 54px);
 			background: var(--l1-background);
 			padding: 16px;

frontend/src/container/TriggeredAlerts/TriggeredAlerts.module.scss

@@ -2,7 +2,7 @@
 	display: flex;
 	flex-direction: column;
 	gap: 1rem;
-	height: calc(100vh - 62px);
+	flex: 1;
 	min-height: 400px;
 	padding-top: var(--spacing-8);
 }

frontend/src/container/Version/Version.styles.scss

@@ -1,7 +1,4 @@
 .version-container {
-	max-height: 100vh;
-	overflow: hidden;
-
 	.version-page-header {
 		border-bottom: 1px solid var(--l1-border);
 		background: var(--l1-background);

frontend/src/hooks/useSavedViewEnabled.ts

@@ -0,0 +1,11 @@
+import getLocalStorageKey from 'api/browser/localstorage/get';
+import { LOCALSTORAGE } from 'constants/localStorage';
+import { useState } from 'react';
+
+export function useSavedViewEnabled(): boolean {
+	const [isEnabled] = useState(
+		() => getLocalStorageKey(LOCALSTORAGE.SAVED_VIEW_ENABLED) === 'true',
+	);
+
+	return isEnabled;
+}

frontend/src/pages/AlertList/AlertList.styles.scss

@@ -1,4 +1,29 @@
 .alerts-container {
+	// Hands the page height down to the active tab so its content can bound itself
+	// instead of guessing with 100vh. Child combinators only, nested Tabs
+	// (Configuration) must not be caught.
+	flex: 1;
+	min-height: 0;
+
+	> .ant-tabs-content-holder {
+		display: flex;
+		flex-direction: column;
+
+		> .ant-tabs-content {
+			flex: 1;
+			min-height: 0;
+			display: flex;
+			flex-direction: column;
+
+			> .ant-tabs-tabpane-active {
+				flex: 1;
+				min-height: 0;
+				display: flex;
+				flex-direction: column;
+			}
+		}
+	}
+
 	.top-level-tab.periscope-tab {
 		padding: 2px 0;
 	}
@@ -40,5 +65,9 @@
 
 	.alert-rules-container {
 		margin-top: 10px;
+		flex: 1;
+		min-height: 0;
+		display: flex;
+		flex-direction: column;
 	}
 }

frontend/src/pages/DashboardPage/DashboardContainer/components/LockedIndicator/LockedIndicator.module.scss

@@ -2,7 +2,9 @@
 	display: flex;
 	flex-direction: column;
 	position: fixed;
-	bottom: 0;
+	// Lifted above the bottom strip. Don't extend this pattern — new fixed-bottom
+	// UI belongs in the bounded layout, not in another offset here.
+	bottom: var(--bottom-strip-height, 0px);
 	left: 0;
 	width: 100%;
 	z-index: 100;

frontend/src/pages/IntegrationsDetailsPage/CloudIntegration/stories/__story_mockdata__/cloudIntegration.ts

@@ -295,7 +295,11 @@ const account = (
 	provider,
 	providerAccountId: ACCOUNTS[provider][index],
 	config: accountConfig(provider),
-	agentReport: { timestampMillis: Date.now() - 45 * 1000, data: null },
+	agentReport: {
+		timestampMillis: Date.now() - 45 * 1000,
+		data: null,
+		syncState: null,
+	},
 	createdAt: new Date(Date.now() - 21 * 24 * 60 * 60 * 1000).toISOString(),
 	updatedAt: new Date(Date.now() - 60 * 60 * 1000).toISOString(),
 	removedAt: null,

frontend/src/pages/Support/Support.styles.scss

@@ -1,7 +1,4 @@
 .support-page-container {
-	max-height: 100vh;
-	overflow: hidden;
-
 	.support-page-header {
 		border-bottom: 1px solid var(--l1-border);
 		background: var(--l1-background);

frontend/src/pages/TraceDetailsV3/TraceDetailsV3.module.scss

@@ -1,5 +1,6 @@
 .root {
-	height: calc(100vh);
+	flex: 1;
+	min-height: 0;
 	display: flex;
 	flex-direction: column;
 }

frontend/src/pages/TracesFunnelDetails/TracesFunnelDetails.styles.scss

@@ -1,13 +1,24 @@
 .traces-funnel-details {
 	display: flex;
-	// 45px -> height of the tab bar
-	height: calc(100vh - 45px);
+	height: 100%;
 
 	&__steps-config {
 		flex-shrink: 0;
 		width: 600px;
 		border-right: 1px solid var(--l1-border);
+		// Positioning context for the absolute .steps-footer.
 		position: relative;
+		display: flex;
+		flex-direction: column;
+
+		// Scoped here so the modal usage of FunnelConfiguration on trace details
+		// stays in normal flow.
+		.funnel-configuration {
+			flex: 1;
+			min-height: 0;
+			display: flex;
+			flex-direction: column;
+		}
 	}
 	&__steps-results {
 		width: 100%;

frontend/src/pages/TracesFunnelDetails/components/FunnelConfiguration/FunnelConfiguration.styles.scss

@@ -4,14 +4,17 @@
 		flex-direction: column;
 		justify-content: flex-start;
 		&.funnel-details-page {
-			height: calc(
-				100vh - 170px
-			); // 64px bottom bar + 61px configuration header + 45px page navbar
+			flex: 1;
+			min-height: 0;
+			// .steps-footer is absolute against the config column, so its 64px is
+			// reserved rather than laid out.
+			margin-bottom: 64px;
 			overflow: auto;
 		}
 	}
 
 	&__header {
+		flex-shrink: 0;
 		display: flex;
 		align-items: center;
 		justify-content: space-between;

pkg/modules/cloudintegration/implcloudintegration/store.go

@@ -134,6 +134,24 @@ func (store *store) UpdateAccount(ctx context.Context, account *cloudintegration
 		BunDBCtx(ctx).
 		NewUpdate().
 		Model(account).
+		Column("config").
+		Column("updated_at").
+		WherePK().
+		Where("org_id = ?", account.OrgID).
+		Where("provider = ?", account.Provider).
+		Exec(ctx)
+
+	return err
+}
+
+func (store *store) UpdateAgentReport(ctx context.Context, account *cloudintegrationtypes.StorableCloudIntegration) error {
+	_, err := store.
+		store.
+		BunDBCtx(ctx).
+		NewUpdate().
+		Model(account).
+		Column("account_id").
+		Column("last_agent_report").
 		WherePK().
 		Where("org_id = ?", account.OrgID).
 		Where("provider = ?", account.Provider).

pkg/types/cloudintegrationtypes/account.go

@@ -26,6 +26,17 @@ type Account struct {
 type AgentReport struct {
 	TimestampMillis int64          `json:"timestampMillis" required:"true"`
 	Data            map[string]any `json:"data" required:"true" nullable:"true"`
+	SyncState       *SyncState     `json:"syncState" required:"true" nullable:"true"`
+}
+
+type SyncState struct {
+	Version int64                       `json:"version" required:"true"`
+	InSync  bool                        `json:"inSync" required:"true"`
+	Regions map[string]*RegionSyncState `json:"regions" required:"true" nullable:"false"`
+}
+
+type RegionSyncState struct {
+	State RegionState `json:"state" required:"true"`
 }
 
 type AccountConfig struct {
@@ -150,6 +161,7 @@ func NewAccountFromStorable(storableAccount *StorableCloudIntegration) (*Account
 		account.AgentReport = &AgentReport{
 			TimestampMillis: storableAccount.LastAgentReport.TimestampMillis,
 			Data:            storableAccount.LastAgentReport.Data,
+			SyncState:       NewSyncStateFromStorable(storableAccount.LastAgentReport.SyncState),
 		}
 	}
 
@@ -308,10 +320,101 @@ func NewAccountConfigFromUpdatable(provider CloudProviderType, config *Updatable
 	}
 }
 
-func NewAgentReport(data map[string]any) *AgentReport {
+func NewAgentReport(data map[string]any, syncState *SyncState) *AgentReport {
 	return &AgentReport{
 		TimestampMillis: time.Now().UnixMilli(),
 		Data:            data,
+		SyncState:       syncState,
+	}
+}
+
+// NewSyncState returns the sync state after a check-in without mutating previous.
+// The ack is applied before the config diff, so it is checked against the version the agent was last sent.
+func NewSyncState(previous *SyncState, regions []string, removed bool, syncedVersion *int64) *SyncState {
+	next := &SyncState{Version: 1, InSync: true, Regions: make(map[string]*RegionSyncState)}
+
+	// First check-in: seed from the config as in sync. Otherwise start from a copy of previous.
+	if previous == nil {
+		for _, region := range regions {
+			next.Regions[region] = &RegionSyncState{State: RegionStatePresent}
+		}
+	} else {
+		next.Version = previous.Version
+		next.InSync = previous.InSync
+		for region, regionSyncState := range previous.Regions {
+			next.Regions[region] = &RegionSyncState{State: regionSyncState.State}
+		}
+	}
+
+	// The agent synced this version, so its removed regions are cleaned up and can be dropped.
+	if syncedVersion != nil && *syncedVersion == next.Version {
+		next.InSync = true
+		for region, regionSyncState := range next.Regions {
+			if regionSyncState.State == RegionStateRemoved {
+				delete(next.Regions, region)
+			}
+		}
+	}
+
+	changed := false
+
+	if removed {
+		// Integration removed: every present region must be cleaned up.
+		for _, regionSyncState := range next.Regions {
+			if regionSyncState.State != RegionStateRemoved {
+				regionSyncState.State = RegionStateRemoved
+				changed = true
+			}
+		}
+	} else {
+		desiredRegions := make(map[string]struct{}, len(regions))
+		for _, region := range regions {
+			desiredRegions[region] = struct{}{}
+
+			regionSyncState, ok := next.Regions[region]
+			switch {
+			case !ok:
+				// Region added to the config.
+				next.Regions[region] = &RegionSyncState{State: RegionStatePresent}
+				changed = true
+			case regionSyncState.State == RegionStateRemoved:
+				// Region added back before its removal was acked.
+				regionSyncState.State = RegionStatePresent
+				changed = true
+			}
+		}
+
+		for region, regionSyncState := range next.Regions {
+			if _, desired := desiredRegions[region]; !desired && regionSyncState.State == RegionStatePresent {
+				// Region removed from the config.
+				regionSyncState.State = RegionStateRemoved
+				changed = true
+			}
+		}
+	}
+
+	if changed {
+		next.Version++
+		next.InSync = false
+	}
+
+	return next
+}
+
+func NewSyncStateFromStorable(storableSyncState *StorableSyncState) *SyncState {
+	if storableSyncState == nil {
+		return nil
+	}
+
+	regions := make(map[string]*RegionSyncState, len(storableSyncState.Regions))
+	for region, regionSyncState := range storableSyncState.Regions {
+		regions[region] = &RegionSyncState{State: regionSyncState.State}
+	}
+
+	return &SyncState{
+		Version: storableSyncState.Version,
+		InSync:  storableSyncState.InSync,
+		Regions: regions,
 	}
 }
 
@@ -335,6 +438,26 @@ func (account *Account) Update(provider CloudProviderType, config *AccountConfig
 	return nil
 }
 
+// NextSyncState returns the sync state for this check-in, or nil for providers without one.
+func (account *Account) NextSyncState(syncedVersion *int64) *SyncState {
+	if account.Provider != CloudProviderTypeAWS {
+		return nil
+	}
+
+	var previous *SyncState
+	if account.AgentReport != nil {
+		previous = account.AgentReport.SyncState
+	}
+
+	regions := account.Config.AWS.Regions
+	// Removed before the agent ever checked in: no region was sent to it, so there is nothing to clean up.
+	if account.AgentReport == nil && account.RemovedAt != nil {
+		regions = nil
+	}
+
+	return NewSyncState(previous, regions, account.RemovedAt != nil, syncedVersion)
+}
+
 func (postableAccount *PostableAccount) UnmarshalJSON(data []byte) error {
 	type Alias PostableAccount
 

pkg/types/cloudintegrationtypes/checkin.go

@@ -12,7 +12,8 @@ type AgentCheckInRequest struct {
 	ProviderAccountID  string      `json:"providerAccountId" required:"false"`
 	CloudIntegrationID valuer.UUID `json:"cloudIntegrationId" required:"false"`
 
-	Data map[string]any `json:"data" required:"true" nullable:"true"`
+	Data          map[string]any `json:"data" required:"true" nullable:"true"`
+	SyncedVersion *int64         `json:"syncedVersion" required:"false" nullable:"true"`
 }
 
 type PostableAgentCheckIn struct {
@@ -28,6 +29,7 @@ type AgentCheckInResponse struct {
 	ProviderAccountID  string                     `json:"providerAccountId" required:"true"`
 	IntegrationConfig  *ProviderIntegrationConfig `json:"integrationConfig" required:"true"`
 	RemovedAt          *time.Time                 `json:"removedAt" required:"true" nullable:"true"`
+	SyncState          *SyncState                 `json:"syncState" required:"true" nullable:"true"`
 }
 
 type GettableAgentCheckIn struct {
@@ -73,12 +75,13 @@ func NewGettableAgentCheckIn(provider CloudProviderType, resp *AgentCheckInRespo
 	return gettable
 }
 
-func NewAgentCheckInResponse(providerAccountID, cloudIntegrationID string, integrationConfig *ProviderIntegrationConfig, removedAt *time.Time) *AgentCheckInResponse {
+func NewAgentCheckInResponse(providerAccountID, cloudIntegrationID string, integrationConfig *ProviderIntegrationConfig, removedAt *time.Time, syncState *SyncState) *AgentCheckInResponse {
 	return &AgentCheckInResponse{
 		CloudIntegrationID: cloudIntegrationID,
 		ProviderAccountID:  providerAccountID,
 		IntegrationConfig:  integrationConfig,
 		RemovedAt:          removedAt,
+		SyncState:          syncState,
 	}
 }
 

pkg/types/cloudintegrationtypes/cloudintegration.go

@@ -25,6 +25,17 @@ var (
 	ErrCodeServiceDefinitionNotFound            = errors.MustNewCode("service_definition_not_found")
 )
 
+var (
+	RegionStatePresent = RegionState{valuer.NewString("present")}
+	RegionStateRemoved = RegionState{valuer.NewString("removed")}
+)
+
+type RegionState struct{ valuer.String }
+
+func (RegionState) Enum() []any {
+	return []any{RegionStatePresent, RegionStateRemoved}
+}
+
 // StorableCloudIntegration represents a cloud integration stored in the database.
 // This is also referred as "Account" in the context of cloud integrations.
 type StorableCloudIntegration struct {
@@ -43,8 +54,16 @@ type StorableCloudIntegration struct {
 // StorableAgentReport represents the last heartbeat and arbitrary data sent by the agent
 // as of now there is no use case for Data field, but keeping it for backwards compatibility with older structure.
 type StorableAgentReport struct {
-	TimestampMillis int64          `json:"timestamp_millis"` // backward compatibility
-	Data            map[string]any `json:"data"`
+	TimestampMillis int64              `json:"timestamp_millis"` // backward compatibility
+	Data            map[string]any     `json:"data"`
+	SyncState       *StorableSyncState `json:"sync_state,omitempty"`
+}
+
+// StorableSyncState holds every region sent to the agent. A removed region is dropped only after the agent acks Version.
+type StorableSyncState struct {
+	Version int64                       `json:"version"`
+	InSync  bool                        `json:"in_sync"`
+	Regions map[string]*RegionSyncState `json:"regions"`
 }
 
 // StorableCloudIntegrationService is to store service config for a cloud integration, which is a cloud provider specific configuration.
@@ -148,12 +167,30 @@ func NewStorableCloudIntegration(account *Account) (*StorableCloudIntegration, e
 		storableAccount.LastAgentReport = &StorableAgentReport{
 			TimestampMillis: account.AgentReport.TimestampMillis,
 			Data:            account.AgentReport.Data,
+			SyncState:       NewStorableSyncState(account.AgentReport.SyncState),
 		}
 	}
 
 	return storableAccount, nil
 }
 
+func NewStorableSyncState(syncState *SyncState) *StorableSyncState {
+	if syncState == nil {
+		return nil
+	}
+
+	regions := make(map[string]*RegionSyncState, len(syncState.Regions))
+	for region, regionSyncState := range syncState.Regions {
+		regions[region] = &RegionSyncState{State: regionSyncState.State}
+	}
+
+	return &StorableSyncState{
+		Version: syncState.Version,
+		InSync:  syncState.InSync,
+		Regions: regions,
+	}
+}
+
 // NewStorableCloudIntegrationService creates a new StorableCloudIntegrationService with
 // generated ID and timestamps from a CloudIntegrationService and its serialized config JSON.
 func NewStorableCloudIntegrationService(svc *CloudIntegrationService, configJSON string) *StorableCloudIntegrationService {
@@ -172,6 +209,7 @@ func (account *StorableCloudIntegration) Update(providerAccountID *string, agent
 		account.LastAgentReport = &StorableAgentReport{
 			TimestampMillis: agentReport.TimestampMillis,
 			Data:            agentReport.Data,
+			SyncState:       NewStorableSyncState(agentReport.SyncState),
 		}
 	}
 }

pkg/types/cloudintegrationtypes/store.go

@@ -25,9 +25,12 @@ type Store interface {
 	// CreateAccount creates a new cloud integration account
 	CreateAccount(ctx context.Context, account *StorableCloudIntegration) error
 
-	// UpdateAccount updates an existing cloud integration account
+	// UpdateAccount updates the user updatable fields (config) of an existing cloud integration account
 	UpdateAccount(ctx context.Context, account *StorableCloudIntegration) error
 
+	// UpdateAgentReport updates the provider account id and last agent report of an existing cloud integration account
+	UpdateAgentReport(ctx context.Context, account *StorableCloudIntegration) error
+
 	// RemoveAccount marks a cloud integration account as removed by setting the RemovedAt field
 	RemoveAccount(ctx context.Context, orgID, id valuer.UUID, provider CloudProviderType) error
 

tests/fixtures/cloudintegrations.py

@@ -34,6 +34,8 @@ class ProviderAccountSpec:
     expected_config: Callable[[dict], dict]
     # only the suites that exercise updates need to supply it.
     updated_params: dict = field(default_factory=dict)
+    # params -> the agentReport.syncState the API is expected to return after the first check-in.
+    expected_sync_state: Callable[[dict], dict | None] = lambda p: None
     # id shown in parametrized test names; defaults to the provider slug.
     id: str = field(default="")
 
@@ -315,6 +317,7 @@ def simulate_agent_checkin(
     account_id: str,
     cloud_account_id: str,
     data: dict | None = None,
+    synced_version: int | None = None,
 ) -> requests.Response:
     endpoint = f"/api/v1/cloud_integrations/{cloud_provider}/accounts/check_in"
 
@@ -323,6 +326,8 @@ def simulate_agent_checkin(
         "providerAccountId": cloud_account_id,
         "data": data or {},
     }
+    if synced_version is not None:
+        checkin_payload["syncedVersion"] = synced_version
 
     response = requests.post(
         signoz.self.host_configs["8080"].get(endpoint),

tests/integration/tests/cloudintegrations/03_agent_check_in.py

@@ -3,6 +3,7 @@ from collections.abc import Callable
 from http import HTTPStatus
 
 import pytest
+import requests
 
 from fixtures import types
 from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD, add_license
@@ -152,3 +153,230 @@ def test_duplicate_cloud_account_checkins(
     # Second check-in: account2 tries to claim the same provider account ID → 409
     response = simulate_agent_checkin(signoz, admin_token, spec.provider, account2["id"], same_provider_account_id)
     assert response.status_code == HTTPStatus.CONFLICT, f"Expected 409 for duplicate providerAccountId, got {response.status_code}: {response.text}"
+
+
+def test_sync_state_drops_removed_region_after_ack(
+    signoz: types.SigNoz,
+    create_user_admin: types.Operation,  # pylint: disable=unused-argument
+    get_token: Callable[[str, str], str],
+    create_cloud_integration_account: Callable,
+) -> None:
+    admin_token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    account_id = create_cloud_integration_account(admin_token, "aws", regions=["us-east-1", "us-west-2"])["id"]
+    provider_account_id = str(uuid.uuid4())
+
+    response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id)
+    assert response.status_code == HTTPStatus.OK, response.text
+
+    response = requests.put(
+        signoz.self.host_configs["8080"].get(f"/api/v1/cloud_integrations/aws/accounts/{account_id}"),
+        headers={"Authorization": f"Bearer {admin_token}"},
+        json={"config": {"aws": {"regions": ["us-east-1"]}}},
+        timeout=10,
+    )
+    assert response.status_code == HTTPStatus.NO_CONTENT, response.text
+
+    response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id)
+    assert response.status_code == HTTPStatus.OK, response.text
+    assert response.json()["data"]["syncState"] == {
+        "version": 2,
+        "inSync": False,
+        "regions": {"us-east-1": {"state": "present"}, "us-west-2": {"state": "removed"}},
+    }, "removed region should be marked removed and the version bumped"
+
+    response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id, synced_version=2)
+    assert response.status_code == HTTPStatus.OK, response.text
+    assert response.json()["data"]["syncState"] == {
+        "version": 2,
+        "inSync": True,
+        "regions": {"us-east-1": {"state": "present"}},
+    }, "acked removed region should be dropped"
+
+
+def test_sync_state_keeps_removed_region_without_ack(
+    signoz: types.SigNoz,
+    create_user_admin: types.Operation,  # pylint: disable=unused-argument
+    get_token: Callable[[str, str], str],
+    create_cloud_integration_account: Callable,
+) -> None:
+    """The agent failed to clean up or crashed, so it never acks: the removed region stays and the version stays put."""
+    admin_token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    account_id = create_cloud_integration_account(admin_token, "aws", regions=["us-east-1", "us-west-2"])["id"]
+    provider_account_id = str(uuid.uuid4())
+
+    response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id)
+    assert response.status_code == HTTPStatus.OK, response.text
+
+    response = requests.put(
+        signoz.self.host_configs["8080"].get(f"/api/v1/cloud_integrations/aws/accounts/{account_id}"),
+        headers={"Authorization": f"Bearer {admin_token}"},
+        json={"config": {"aws": {"regions": ["us-east-1"]}}},
+        timeout=10,
+    )
+    assert response.status_code == HTTPStatus.NO_CONTENT, response.text
+
+    for _ in range(3):
+        response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id)
+        assert response.status_code == HTTPStatus.OK, response.text
+        assert response.json()["data"]["syncState"] == {
+            "version": 2,
+            "inSync": False,
+            "regions": {"us-east-1": {"state": "present"}, "us-west-2": {"state": "removed"}},
+        }, "unacked removed region should stay without bumping the version"
+
+
+@pytest.mark.parametrize("synced_version", [2, 9], ids=["stale", "ahead"])
+def test_sync_state_ignores_mismatched_ack(
+    signoz: types.SigNoz,
+    create_user_admin: types.Operation,  # pylint: disable=unused-argument
+    get_token: Callable[[str, str], str],
+    create_cloud_integration_account: Callable,
+    synced_version: int,
+) -> None:
+    """An ack for any version other than the current one (v3) is ignored,
+    so us-west-2, removed at v2 and still unacked, is not dropped.
+    """
+    admin_token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    account_id = create_cloud_integration_account(admin_token, "aws", regions=["us-east-1", "us-west-2"])["id"]
+    provider_account_id = str(uuid.uuid4())
+
+    response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id)
+    assert response.status_code == HTTPStatus.OK, response.text
+
+    for regions in (["us-east-1"], ["us-east-1", "eu-west-1"]):
+        response = requests.put(
+            signoz.self.host_configs["8080"].get(f"/api/v1/cloud_integrations/aws/accounts/{account_id}"),
+            headers={"Authorization": f"Bearer {admin_token}"},
+            json={"config": {"aws": {"regions": regions}}},
+            timeout=10,
+        )
+        assert response.status_code == HTTPStatus.NO_CONTENT, response.text
+
+        response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id)
+        assert response.status_code == HTTPStatus.OK, response.text
+
+    expected_sync_state = {
+        "version": 3,
+        "inSync": False,
+        "regions": {"us-east-1": {"state": "present"}, "us-west-2": {"state": "removed"}, "eu-west-1": {"state": "present"}},
+    }
+    assert response.json()["data"]["syncState"] == expected_sync_state
+
+    response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id, synced_version=synced_version)
+    assert response.status_code == HTTPStatus.OK, response.text
+    assert response.json()["data"]["syncState"] == expected_sync_state, "an ack for another version should be ignored"
+
+
+def test_sync_state_applies_ack_before_config_change(
+    signoz: types.SigNoz,
+    create_user_admin: types.Operation,  # pylint: disable=unused-argument
+    get_token: Callable[[str, str], str],
+    create_cloud_integration_account: Callable,
+) -> None:
+    """The user changes regions while the agent syncs: the ack for the version it synced still lands."""
+    admin_token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    account_id = create_cloud_integration_account(admin_token, "aws", regions=["us-east-1", "us-west-2"])["id"]
+    provider_account_id = str(uuid.uuid4())
+
+    response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id)
+    assert response.status_code == HTTPStatus.OK, response.text
+
+    for regions, synced_version in ((["us-east-1"], None), (["us-east-1", "eu-west-1"], 2)):
+        response = requests.put(
+            signoz.self.host_configs["8080"].get(f"/api/v1/cloud_integrations/aws/accounts/{account_id}"),
+            headers={"Authorization": f"Bearer {admin_token}"},
+            json={"config": {"aws": {"regions": regions}}},
+            timeout=10,
+        )
+        assert response.status_code == HTTPStatus.NO_CONTENT, response.text
+
+        response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id, synced_version=synced_version)
+        assert response.status_code == HTTPStatus.OK, response.text
+
+    assert response.json()["data"]["syncState"] == {
+        "version": 3,
+        "inSync": False,
+        "regions": {"us-east-1": {"state": "present"}, "eu-west-1": {"state": "present"}},
+    }, "ack should drop the removed region before the new region bumps the version"
+
+
+@pytest.mark.parametrize("synced_version", [1, None], ids=["agent_acks_synced_version", "agent_crashed"])
+def test_sync_state_region_removed_during_sync(
+    signoz: types.SigNoz,
+    create_user_admin: types.Operation,  # pylint: disable=unused-argument
+    get_token: Callable[[str, str], str],
+    create_cloud_integration_account: Callable,
+    synced_version: int | None,
+) -> None:
+    """The user removes a region while the agent syncs v1; whether the agent acks v1 or crashed, the region must not be lost."""
+    admin_token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    account_id = create_cloud_integration_account(admin_token, "aws", regions=["us-east-1", "us-west-2"])["id"]
+    provider_account_id = str(uuid.uuid4())
+
+    response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id)
+    assert response.status_code == HTTPStatus.OK, response.text
+    assert response.json()["data"]["syncState"] == {
+        "version": 1,
+        "inSync": True,
+        "regions": {"us-east-1": {"state": "present"}, "us-west-2": {"state": "present"}},
+    }
+
+    response = requests.put(
+        signoz.self.host_configs["8080"].get(f"/api/v1/cloud_integrations/aws/accounts/{account_id}"),
+        headers={"Authorization": f"Bearer {admin_token}"},
+        json={"config": {"aws": {"regions": ["us-east-1"]}}},
+        timeout=10,
+    )
+    assert response.status_code == HTTPStatus.NO_CONTENT, response.text
+
+    response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id, synced_version=synced_version)
+    assert response.status_code == HTTPStatus.OK, response.text
+    assert response.json()["data"]["syncState"] == {
+        "version": 2,
+        "inSync": False,
+        "regions": {"us-east-1": {"state": "present"}, "us-west-2": {"state": "removed"}},
+    }, "region removed mid-sync should be marked removed"
+
+    response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id, synced_version=2)
+    assert response.status_code == HTTPStatus.OK, response.text
+    assert response.json()["data"]["syncState"] == {
+        "version": 2,
+        "inSync": True,
+        "regions": {"us-east-1": {"state": "present"}},
+    }
+
+
+def test_sync_state_after_disconnect(
+    signoz: types.SigNoz,
+    create_user_admin: types.Operation,  # pylint: disable=unused-argument
+    get_token: Callable[[str, str], str],
+    create_cloud_integration_account: Callable,
+) -> None:
+    admin_token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    account_id = create_cloud_integration_account(admin_token, "aws", regions=["us-east-1", "us-west-2"])["id"]
+    provider_account_id = str(uuid.uuid4())
+
+    response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id)
+    assert response.status_code == HTTPStatus.OK, response.text
+
+    response = requests.delete(
+        signoz.self.host_configs["8080"].get(f"/api/v1/cloud_integrations/aws/accounts/{account_id}"),
+        headers={"Authorization": f"Bearer {admin_token}"},
+        timeout=10,
+    )
+    assert response.status_code == HTTPStatus.NO_CONTENT, response.text
+
+    for _ in range(2):
+        response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id)
+        assert response.status_code == HTTPStatus.OK, response.text
+        assert response.json()["data"]["removedAt"] is not None, "removedAt should be set after disconnect"
+        assert response.json()["data"]["syncState"] == {
+            "version": 2,
+            "inSync": False,
+            "regions": {"us-east-1": {"state": "removed"}, "us-west-2": {"state": "removed"}},
+        }, "every region should be removed once, without bumping the version on later check-ins"
+
+    for _ in range(2):
+        response = simulate_agent_checkin(signoz, admin_token, "aws", account_id, provider_account_id, synced_version=2)
+        assert response.status_code == HTTPStatus.OK, response.text
+        assert response.json()["data"]["syncState"] == {"version": 2, "inSync": True, "regions": {}}, "acked removal should leave no regions"

tests/integration/tests/cloudintegrations/04_accounts.py

@@ -21,6 +21,11 @@ AWS_ACCOUNT_SPEC = ProviderAccountSpec(
     updated_params={"deployment_region": "us-east-1", "regions": ["us-east-1", "us-west-2", "eu-west-1"]},
     build_config=lambda p: {"aws": {"deploymentRegion": p["deployment_region"], "regions": p["regions"]}},
     expected_config=lambda p: {"regions": p["regions"]},
+    expected_sync_state=lambda p: {
+        "version": 1,
+        "inSync": True,
+        "regions": {region: {"state": "present"} for region in p["regions"]},
+    },
 )
 
 GCP_ACCOUNT_SPEC = ProviderAccountSpec(
@@ -128,6 +133,7 @@ def test_list_accounts_after_checkin(
     assert found["providerAccountId"] == provider_account_id, "providerAccountId should match"
     assert found["config"][spec.provider] == spec.expected_config(spec.initial_params), "config should match account config"
     assert found["agentReport"] is not None, "agentReport should be present after check-in"
+    assert found["agentReport"]["syncState"] == spec.expected_sync_state(spec.initial_params), "syncState should be seeded from the account regions on first check-in"
     assert found["removedAt"] is None, "removedAt should be null for a live account"
 
 
@@ -282,6 +288,7 @@ def test_update_account_after_checkin_preserves_connected_status(
     assert found_after is not None, "Account must still be listed after config update (account_id should not be reset)"
     assert found_after["providerAccountId"] == provider_account_id, "providerAccountId should be preserved after update"
     assert found_after["agentReport"] is not None, "agentReport should be preserved after update"
+    assert found_after["agentReport"]["syncState"] == found_before["agentReport"]["syncState"], "config update must not change syncState"
     assert found_after["config"][spec.provider] == spec.expected_config(spec.updated_params), "Config should reflect the update"
     assert found_after["removedAt"] is None, "removedAt should still be null"