fix(confluence): index mirrored/included page content via rendered view format

apps/sim/app/api/knowledge/[id]/connectors/[connectorId]/sync/route.test.ts

@@ -138,6 +138,50 @@ describe('Connector Manual Sync API Route', () => {
  expect(mockDispatchSync).toHaveBeenCalledWith('conn-456', {
  billingAttribution,
  requestId: 'test-req-id',
+ rehydrate: false,
+ })
+ })
+
+ it('dispatches a full resync when rehydrate=true is set', async () => {
+ const billingAttribution = {
+ actorUserId: 'external-admin',
+ workspaceId: 'ws-1',
+ organizationId: null,
+ billedAccountUserId: 'owner-1',
+ billingEntity: { type: 'user' as const, id: 'owner-1' },
+ billingPeriod: {
+ start: '2026-07-01T00:00:00.000Z',
+ end: '2026-08-01T00:00:00.000Z',
+ },
+ payerSubscription: null,
+ }
+ hybridAuthMockFns.mockCheckSessionOrInternalAuth.mockResolvedValue({
+ success: true,
+ authType: 'session',
+ userId: 'external-admin',
+ userName: 'Test',
+ userEmail: 'test@test.com',
+ })
+ mockCheckWriteAccess.mockResolvedValue({
+ hasAccess: true,
+ knowledgeBase: { workspaceId: 'ws-1', name: 'Test KB' },
+ })
+ mockDbChain.limit.mockResolvedValueOnce([{ id: 'conn-456', status: 'active' }])
+ mockResolveBillingAttribution.mockResolvedValue(billingAttribution)
+
+ const req = createMockRequest(
+ 'POST',
+ undefined,
+ {},
+ 'http://localhost:3000/api/knowledge/kb-123/connectors/conn-456/sync?rehydrate=true'
+ )
+ const response = await POST(req as never, { params: mockParams })
+
+ expect(response.status).toBe(200)
+ expect(mockDispatchSync).toHaveBeenCalledWith('conn-456', {
+ billingAttribution,
+ requestId: 'test-req-id',
+ rehydrate: true,
  })
  })
 })

apps/sim/app/api/knowledge/[id]/connectors/[connectorId]/sync/route.ts

@@ -29,6 +29,7 @@ export const POST = withRouteHandler(async (request: NextRequest, context: Route
  const parsed = await parseRequest(triggerKnowledgeConnectorSyncContract, request, context)
  if (!parsed.success) return parsed.response
  const { id: knowledgeBaseId, connectorId } = parsed.data.params
+ const { rehydrate } = parsed.data.query
 
  try {
  const auth = await checkSessionOrInternalAuth(request, { requireWorkflowId: false })
@@ -81,7 +82,9 @@ export const POST = withRouteHandler(async (request: NextRequest, context: Route
  workspaceId: kbWorkspaceId,
  })
 
- logger.info(`[${requestId}] Manual sync triggered for connector ${connectorId}`)
+ logger.info(
+ `[${requestId}] Manual sync${rehydrate ? ' (full rehydrate)' : ''} triggered for connector ${connectorId}`
+ )
 
  captureServerEvent(
  auth.userId,
@@ -109,12 +112,12 @@ export const POST = withRouteHandler(async (request: NextRequest, context: Route
  knowledgeBaseName: writeCheck.knowledgeBase.name,
  connectorType: connectorRows[0].connectorType,
  connectorStatus: connectorRows[0].status,
- syncType: 'manual',
+ syncType: rehydrate ? 'manual-rehydrate' : 'manual',
  },
  request,
  })
 
- dispatchSync(connectorId, { billingAttribution, requestId }).catch((error) => {
+ dispatchSync(connectorId, { billingAttribution, requestId, rehydrate }).catch((error) => {
  logger.error(
  `[${requestId}] Failed to dispatch manual sync for connector ${connectorId}`,
  error

apps/sim/app/workspace/[workspaceId]/knowledge/[id]/components/connectors-section/connectors-section.tsx

@@ -1,7 +1,19 @@
 'use client'
 
 import { useCallback, useEffect, useId, useMemo, useRef, useState } from 'react'
-import { Badge, Button, Checkbox, ChipConfirmModal, cn, Loader, Tooltip } from '@sim/emcn'
+import {
+ Badge,
+ Button,
+ Checkbox,
+ ChipConfirmModal,
+ cn,
+ DropdownMenu,
+ DropdownMenuContent,
+ DropdownMenuItem,
+ DropdownMenuTrigger,
+ Loader,
+ Tooltip,
+} from '@sim/emcn'
 import { createLogger } from '@sim/logger'
 import { format, formatDistanceToNow, isPast } from 'date-fns'
 import {
@@ -115,14 +127,14 @@ export function ConnectorsSection({
  }, [])
 
  const handleSync = useCallback(
- (connectorId: string) => {
+ (connectorId: string, rehydrate = false) => {
  if (isSyncOnCooldown(connectorId)) return
 
  syncTriggeredAt.current[connectorId] = Date.now()
  addToSet(setSyncingIds, connectorId)
 
  triggerSync(
- { knowledgeBaseId, connectorId },
+ { knowledgeBaseId, connectorId, rehydrate },
  {
  onSuccess: () => {
  setError(null)
@@ -214,7 +226,7 @@ export function ConnectorsSection({
  isSyncPending={syncingIds.has(connector.id)}
  isUpdating={updatingIds.has(connector.id)}
  syncCooldown={isSyncOnCooldown(connector.id)}
- onSync={() => handleSync(connector.id)}
+ onSync={(rehydrate) => handleSync(connector.id, rehydrate)}
  onTogglePause={() => handleTogglePause(connector)}
  onEdit={() => setEditingConnector(connector)}
  onDelete={() => setDeleteTarget(connector.id)}
@@ -273,7 +285,7 @@ interface ConnectorCardProps {
  isSyncPending: boolean
  isUpdating: boolean
  syncCooldown: boolean
- onSync: () => void
+ onSync: (rehydrate?: boolean) => void
  onEdit: () => void
  onTogglePause: () => void
  onDelete: () => void
@@ -327,6 +339,14 @@ function ConnectorCard({
  )
  const syncLogs = detail?.syncLogs ?? []
 
+ const canFullResync = Boolean(connectorDef?.rehydrateOnFullSync)
+ const syncDisabled =
+ connector.status === 'syncing' ||
+ connector.status === 'disabled' ||
+ isSyncPending ||
+ syncCooldown
+ const syncTooltip = syncCooldown ? 'Sync recently triggered' : canFullResync ? 'Sync' : 'Sync now'
+
  return (
  <div
  className={cn(
@@ -409,28 +429,60 @@ function ConnectorCard({
  <div className='flex flex-shrink-0 items-center gap-0.5'>
  {canEdit && (
  <>
- <Tooltip.Root>
- <Tooltip.Trigger asChild>
- <Button
- variant='ghost'
- className={CONNECTOR_ACTION_BUTTON_CLASSES}
- onClick={onSync}
- disabled={
- connector.status === 'syncing' ||
- connector.status === 'disabled' ||
- isSyncPending ||
- syncCooldown
- }
- >
- <RefreshCw
- className={cn('size-3.5', connector.status === 'syncing' && 'animate-spin')}
- />
- </Button>
- </Tooltip.Trigger>
- <Tooltip.Content>
- {syncCooldown ? 'Sync recently triggered' : 'Sync now'}
- </Tooltip.Content>
- </Tooltip.Root>
+ {canFullResync ? (
+ <DropdownMenu>
+ <Tooltip.Root>
+ <Tooltip.Trigger asChild>
+ {/* span keeps the tooltip hoverable while the trigger button is disabled */}
+ <span className='inline-flex'>
+ <DropdownMenuTrigger asChild>
+ <Button
+ variant='ghost'
+ aria-label='Sync options'
+ className={CONNECTOR_ACTION_BUTTON_CLASSES}
+ disabled={syncDisabled}
+ >
+ <RefreshCw
+ className={cn(
+ 'size-3.5',
+ connector.status === 'syncing' && 'animate-spin'
+ )}
+ />
+ </Button>
+ </DropdownMenuTrigger>
+ </span>
+ </Tooltip.Trigger>
+ <Tooltip.Content>{syncTooltip}</Tooltip.Content>
+ </Tooltip.Root>
+ <DropdownMenuContent align='end'>
+ <DropdownMenuItem onSelect={() => onSync(false)}>Sync now</DropdownMenuItem>
+ <DropdownMenuItem onSelect={() => onSync(true)}>Full resync</DropdownMenuItem>
+ </DropdownMenuContent>
+ </DropdownMenu>
+ ) : (
+ <Tooltip.Root>
+ <Tooltip.Trigger asChild>
+ {/* span keeps the tooltip hoverable while the button is disabled */}
+ <span className='inline-flex'>
+ <Button
+ variant='ghost'
+ aria-label='Sync now'
+ className={CONNECTOR_ACTION_BUTTON_CLASSES}
+ disabled={syncDisabled}
+ onClick={() => onSync(false)}
+ >
+ <RefreshCw
+ className={cn(
+ 'size-3.5',
+ connector.status === 'syncing' && 'animate-spin'
+ )}
+ />
+ </Button>
+ </span>
+ </Tooltip.Trigger>
+ <Tooltip.Content>{syncTooltip}</Tooltip.Content>
+ </Tooltip.Root>
+ )}
 
  <Tooltip.Root>
  <Tooltip.Trigger asChild>

apps/sim/background/knowledge-connector-sync.test.ts

@@ -72,6 +72,29 @@ describe('knowledge connector sync worker', () => {
  expect(mockExecuteSync).toHaveBeenCalledWith('connector-1', {
  billingAttribution: BILLING_ATTRIBUTION,
  fullSync: true,
+ rehydrate: undefined,
+ })
+ })
+
+ it('forwards the rehydrate flag to the sync engine (async worker path)', async () => {
+ mockAssertConnectorSyncPayload.mockReturnValue({
+ connectorId: 'connector-1',
+ requestId: 'request-1',
+ rehydrate: true,
+ billingAttribution: BILLING_ATTRIBUTION,
+ })
+
+ await executeConnectorSyncJob({
+ connectorId: 'connector-1',
+ requestId: 'request-1',
+ rehydrate: true,
+ billingAttribution: BILLING_ATTRIBUTION,
+ })
+
+ expect(mockExecuteSync).toHaveBeenCalledWith('connector-1', {
+ billingAttribution: BILLING_ATTRIBUTION,
+ fullSync: undefined,
+ rehydrate: true,
  })
  })
 })

apps/sim/background/knowledge-connector-sync.ts

@@ -9,13 +9,13 @@ import { executeSync } from '@/lib/knowledge/connectors/sync-engine'
 const logger = createLogger('TriggerKnowledgeConnectorSync')
 
 export async function executeConnectorSyncJob(payload: unknown) {
- const { connectorId, fullSync, requestId, billingAttribution } =
+ const { connectorId, fullSync, rehydrate, requestId, billingAttribution } =
  assertConnectorSyncPayload(payload)
 
  logger.info(`[${requestId}] Starting connector sync: ${connectorId}`)
 
  try {
- const result = await executeSync(connectorId, { billingAttribution, fullSync })
+ const result = await executeSync(connectorId, { billingAttribution, fullSync, rehydrate })
 
  logger.info(`[${requestId}] Connector sync completed`, {
  connectorId,

apps/sim/connectors/confluence/confluence.ts

@@ -91,6 +91,16 @@ async function fetchLabelsForPages(
  return labelsByPageId
 }
 
+/**
+ * Body representation marker embedded in the contentHash. Bumping this
+ * invalidates every previously-synced Confluence document so a one-time
+ * re-hydration picks up content newly reachable by the current extraction
+ * (e.g. the switch from `storage` to rendered `view`, which expands Include
+ * Page / Excerpt macros). Without it, already-indexed pages whose version is
+ * unchanged classify as `unchanged` and keep their stale (empty) content.
+ */
+const CONTENT_REPRESENTATION = 'view'
+
 /**
  * Produces a canonical metadata stub with a deterministic contentHash that
  * does not depend on which API surface (v1 CQL or v2) returned the page.
@@ -115,7 +125,7 @@ function pageToStub(
  contentDeferred: true,
  mimeType: 'text/plain',
  sourceUrl: options.sourceUrl,
- contentHash: `confluence:${page.id}:${versionKey}`,
+ contentHash: `confluence:${CONTENT_REPRESENTATION}:${page.id}:${versionKey}`,
  metadata: {
  spaceId: options.spaceId,
  status: page.status,
@@ -233,10 +243,18 @@ export const confluenceConnector: ConnectorConfig = {
  if (syncContext) syncContext.cloudId = cloudId
  }
 
- // Try pages first, fall back to blogposts if not found
+ /**
+ * Fetch the `view` representation rather than `storage`. Storage format only
+ * carries unexpanded macro references (e.g. Include Page / Excerpt Include),
+ * so "mirrored" content that pulls in another page's body is stripped to
+ * nothing by `htmlToPlainText`. The `view` representation is server-rendered
+ * HTML with those macros expanded inline, so included content is indexed too.
+ * The v2 single-item GET (`/pages/{id}`, `/blogposts/{id}`) supports
+ * `body-format=view`; only the bulk list endpoints are limited to storage/adf.
+ */
  let page: Record<string, unknown> | null = null
  for (const endpoint of ['pages', 'blogposts']) {
- const url = `https://api.atlassian.com/ex/confluence/${cloudId}/wiki/api/v2/${endpoint}/${externalId}?body-format=storage`
+ const url = `https://api.atlassian.com/ex/confluence/${cloudId}/wiki/api/v2/${endpoint}/${externalId}?body-format=view`
  const response = await fetchWithRetry(url, {
  method: 'GET',
  headers: {
@@ -256,8 +274,8 @@ export const confluenceConnector: ConnectorConfig = {
 
  if (!page) return null
  const body = page.body as Record<string, unknown> | undefined
- const storage = body?.storage as Record<string, unknown> | undefined
- const rawContent = (storage?.value as string) || ''
+ const view = body?.view as Record<string, unknown> | undefined
+ const rawContent = (view?.value as string) || ''
  const plainText = htmlToPlainText(rawContent)
 
  const labelMap = await fetchLabelsForPages(cloudId, accessToken, [String(page.id)])

apps/sim/connectors/confluence/meta.ts

@@ -22,6 +22,15 @@ export const confluenceConnectorMeta: ConnectorMeta = {
  ],
  },
 
+ /**
+ * Confluence pages can transclude other pages (Include Page / Excerpt macros).
+ * Editing an included page changes a container page's rendered `view` without
+ * bumping the container's version, so its version-based hash can't detect the
+ * change. A full resync re-hydrates and re-indexes to pick up that drift. This
+ * lives on the meta so the client can offer "Full resync" only where it applies.
+ */
+ rehydrateOnFullSync: true,
+
  configFields: [
  {
  id: 'domain',

apps/sim/connectors/types.ts

@@ -127,6 +127,20 @@ export interface ConnectorMeta {
  */
  supportsIncrementalSync?: boolean
 
+ /**
+ * Whether this connector's extracted content can change without the source item's
+ * own change-detection hash changing — e.g. a Confluence page that transcludes
+ * another page via the Include Page / Excerpt macro: editing the included page
+ * changes the container's rendered `view` output without bumping the container's
+ * version, so its version-based `contentHash` stays identical.
+ *
+ * Incremental syncs remain hash-gated (cheap). On an explicit **full resync**
+ * (`fullSync`), the engine re-hydrates and re-indexes these connectors' documents
+ * even when their hash is unchanged, so transcluded/rendered-dependency changes are
+ * picked up. Only the deliberate full resync pays this re-index cost.
+ */
+ rehydrateOnFullSync?: boolean
+
  /**
  * Tag definitions this connector populates. Shown in the add-connector modal
  * as opt-out checkboxes. On connector creation, tag definitions are auto-created

apps/sim/hooks/queries/kb/connectors.ts

@@ -204,11 +204,18 @@ export function useDeleteConnector() {
 interface TriggerSyncParams {
  knowledgeBaseId: string
  connectorId: string
+ /** Force re-hydration + re-index of rendered content (the "Full resync" action). */
+ rehydrate?: boolean
 }
 
-async function triggerSync({ knowledgeBaseId, connectorId }: TriggerSyncParams): Promise<void> {
+async function triggerSync({
+ knowledgeBaseId,
+ connectorId,
+ rehydrate,
+}: TriggerSyncParams): Promise<void> {
  await requestJson(triggerKnowledgeConnectorSyncContract, {
  params: { id: knowledgeBaseId, connectorId },
+ query: rehydrate ? { rehydrate: true } : {},
  })
 }