feat(knowledge): add Live sync option to KB connectors + fix embeddin…

…g billing (#3959) * feat(knowledge): add Live sync option to KB connector modal for Max/Enterprise users Adds a "Live" (every 5 min) sync frequency option gated to Max and Enterprise plan users. Includes client-side badge + disabled state, shared sync intervals constant, and server-side plan validation on both POST and PATCH connector routes. * fix(knowledge): record embedding usage cost for KB document processing Adds billing tracking to the KB embedding pipeline, which was previously generating OpenAI API calls with no cost recorded. Token counts are now captured from the actual API response and recorded via recordUsage after successful embedding insertion. BYOK workspaces are excluded from billing. Applies to all execution paths: direct, BullMQ, and Trigger.dev. * fix(knowledge): simplify embedding billing — use calculateCost, return modelName - Use calculateCost() from @/providers/utils instead of inline formula, consistent with how LLM billing works throughout the platform - Return modelName from GenerateEmbeddingsResult so billing uses the actual model (handles custom Azure deployments) instead of a hardcoded fallback string - Fix docs-chunker.ts empty-path fallback to satisfy full GenerateEmbeddingsResult type * fix(knowledge): remove dev bypass from hasLiveSyncAccess * chore(knowledge): rename sync-intervals to consts, fix stale TSDoc comment * improvement(knowledge): extract MaxBadge component, capture billing config once per document * fix(knowledge): add knowledge-base to usage_log_source enum, fix docs-chunker type * fix(knowledge): generate migration for knowledge-base usage_log_source enum value * fix(knowledge): add knowledge-base to usage_log_source enum via drizzle-kit * fix(knowledge): fix search embedding test mocks, parallelize billing lookups * fix(knowledge): warn when embedding model has no pricing entry * fix(knowledge): call checkAndBillOverageThreshold after embedding usage
simstudioai · waleedlatif1 · Apr 5, 2026 · Apr 4, 2026 · Apr 4, 2026 · Apr 4, 2026
commit ce53275e9d5f8e78b7bcf810041fb4b7e67e99f7
diff --git a/apps/sim/app/api/knowledge/[id]/connectors/[connectorId]/route.ts b/apps/sim/app/api/knowledge/[id]/connectors/[connectorId]/route.ts
@@ -13,6 +13,7 @@ import { z } from 'zod'
 import { decryptApiKey } from '@/lib/api-key/crypto'
 import { AuditAction, AuditResourceType, recordAudit } from '@/lib/audit/log'
 import { checkSessionOrInternalAuth } from '@/lib/auth/hybrid'
+import { hasLiveSyncAccess } from '@/lib/billing/core/subscription'
 import { generateRequestId } from '@/lib/core/utils/request'
 import { deleteDocumentStorageFiles } from '@/lib/knowledge/documents/service'
 import { cleanupUnusedTagDefinitions } from '@/lib/knowledge/tags/service'
@@ -116,6 +117,20 @@ export async function PATCH(request: NextRequest, { params }: RouteParams) {
       )
     }
 
+    if (
+      parsed.data.syncIntervalMinutes !== undefined &&
+      parsed.data.syncIntervalMinutes > 0 &&
+      parsed.data.syncIntervalMinutes < 60
+    ) {
+      const canUseLiveSync = await hasLiveSyncAccess(auth.userId)
+      if (!canUseLiveSync) {
+        return NextResponse.json(
+          { error: 'Live sync requires a Max or Enterprise plan' },
+          { status: 403 }
+        )
+      }
+    }
+
     if (parsed.data.sourceConfig !== undefined) {
       const existingRows = await db
         .select()

diff --git a/apps/sim/app/api/knowledge/[id]/connectors/route.ts b/apps/sim/app/api/knowledge/[id]/connectors/route.ts
@@ -7,6 +7,7 @@ import { z } from 'zod'
 import { encryptApiKey } from '@/lib/api-key/crypto'
 import { AuditAction, AuditResourceType, recordAudit } from '@/lib/audit/log'
 import { checkSessionOrInternalAuth } from '@/lib/auth/hybrid'
+import { hasLiveSyncAccess } from '@/lib/billing/core/subscription'
 import { generateRequestId } from '@/lib/core/utils/request'
 import { dispatchSync } from '@/lib/knowledge/connectors/sync-engine'
 import { allocateTagSlots } from '@/lib/knowledge/constants'
@@ -97,6 +98,16 @@ export async function POST(request: NextRequest, { params }: { params: Promise<{
 
     const { connectorType, credentialId, apiKey, sourceConfig, syncIntervalMinutes } = parsed.data
 
+    if (syncIntervalMinutes > 0 && syncIntervalMinutes < 60) {
+      const canUseLiveSync = await hasLiveSyncAccess(auth.userId)
+      if (!canUseLiveSync) {
+        return NextResponse.json(
+          { error: 'Live sync requires a Max or Enterprise plan' },
+          { status: 403 }
+        )
+      }
+    }
+
     const connectorConfig = CONNECTOR_REGISTRY[connectorType]
     if (!connectorConfig) {
       return NextResponse.json(

diff --git a/apps/sim/app/api/knowledge/search/utils.test.ts b/apps/sim/app/api/knowledge/search/utils.test.ts
@@ -5,6 +5,7 @@
  * @vitest-environment node
  */
 import { createEnvMock, databaseMock, loggerMock } from '@sim/testing'
+import { mockNextFetchResponse } from '@sim/testing/mocks'
 import { beforeEach, describe, expect, it, vi } from 'vitest'
 
 vi.mock('drizzle-orm')
@@ -14,16 +15,6 @@ vi.mock('@/lib/knowledge/documents/utils', () => ({
   retryWithExponentialBackoff: (fn: any) => fn(),
 }))
 
-vi.stubGlobal(
-  'fetch',
-  vi.fn().mockResolvedValue({
-    ok: true,
-    json: async () => ({
-      data: [{ embedding: [0.1, 0.2, 0.3] }],
-    }),
-  })
-)
-
 vi.mock('@/lib/core/config/env', () => createEnvMock())
 
 import {
@@ -178,17 +169,16 @@ describe('Knowledge Search Utils', () => {
         OPENAI_API_KEY: 'test-openai-key',
       })
 
-      const fetchSpy = vi.mocked(fetch)
-      fetchSpy.mockResolvedValueOnce({
-        ok: true,
-        json: async () => ({
+      mockNextFetchResponse({
+        json: {
           data: [{ embedding: [0.1, 0.2, 0.3] }],
-        }),
-      } as any)
+          usage: { prompt_tokens: 1, total_tokens: 1 },
+        },
+      })
 
       const result = await generateSearchEmbedding('test query')
 
-      expect(fetchSpy).toHaveBeenCalledWith(
+      expect(vi.mocked(fetch)).toHaveBeenCalledWith(
         'https://test.openai.azure.com/openai/deployments/text-embedding-ada-002/embeddings?api-version=2024-12-01-preview',
         expect.objectContaining({
           headers: expect.objectContaining({
@@ -209,17 +199,16 @@ describe('Knowledge Search Utils', () => {
         OPENAI_API_KEY: 'test-openai-key',
       })
 
-      const fetchSpy = vi.mocked(fetch)
-      fetchSpy.mockResolvedValueOnce({
-        ok: true,
-        json: async () => ({
+      mockNextFetchResponse({
+        json: {
           data: [{ embedding: [0.1, 0.2, 0.3] }],
-        }),
-      } as any)
+          usage: { prompt_tokens: 1, total_tokens: 1 },
+        },
+      })
 
       const result = await generateSearchEmbedding('test query')
 
-      expect(fetchSpy).toHaveBeenCalledWith(
+      expect(vi.mocked(fetch)).toHaveBeenCalledWith(
         'https://api.openai.com/v1/embeddings',
         expect.objectContaining({
           headers: expect.objectContaining({
@@ -243,17 +232,16 @@ describe('Knowledge Search Utils', () => {
         OPENAI_API_KEY: 'test-openai-key',
       })
 
-      const fetchSpy = vi.mocked(fetch)
-      fetchSpy.mockResolvedValueOnce({
-        ok: true,
-        json: async () => ({
+      mockNextFetchResponse({
+        json: {
           data: [{ embedding: [0.1, 0.2, 0.3] }],
-        }),
-      } as any)
+          usage: { prompt_tokens: 1, total_tokens: 1 },
+        },
+      })
 
       await generateSearchEmbedding('test query')
 
-      expect(fetchSpy).toHaveBeenCalledWith(
+      expect(vi.mocked(fetch)).toHaveBeenCalledWith(
         expect.stringContaining('api-version='),
         expect.any(Object)
       )
@@ -273,17 +261,16 @@ describe('Knowledge Search Utils', () => {
         OPENAI_API_KEY: 'test-openai-key',
       })
 
-      const fetchSpy = vi.mocked(fetch)
-      fetchSpy.mockResolvedValueOnce({
-        ok: true,
-        json: async () => ({
+      mockNextFetchResponse({
+        json: {
           data: [{ embedding: [0.1, 0.2, 0.3] }],
-        }),
-      } as any)
+          usage: { prompt_tokens: 1, total_tokens: 1 },
+        },
+      })
 
       await generateSearchEmbedding('test query', 'text-embedding-3-small')
 
-      expect(fetchSpy).toHaveBeenCalledWith(
+      expect(vi.mocked(fetch)).toHaveBeenCalledWith(
         'https://test.openai.azure.com/openai/deployments/custom-embedding-model/embeddings?api-version=2024-12-01-preview',
         expect.any(Object)
       )
@@ -311,13 +298,12 @@ describe('Knowledge Search Utils', () => {
         KB_OPENAI_MODEL_NAME: 'text-embedding-ada-002',
       })
 
-      const fetchSpy = vi.mocked(fetch)
-      fetchSpy.mockResolvedValueOnce({
+      mockNextFetchResponse({
         ok: false,
         status: 404,
         statusText: 'Not Found',
-        text: async () => 'Deployment not found',
-      } as any)
+        text: 'Deployment not found',
+      })
 
       await expect(generateSearchEmbedding('test query')).rejects.toThrow('Embedding API failed')
 
@@ -332,13 +318,12 @@ describe('Knowledge Search Utils', () => {
         OPENAI_API_KEY: 'test-openai-key',
       })
 
-      const fetchSpy = vi.mocked(fetch)
-      fetchSpy.mockResolvedValueOnce({
+      mockNextFetchResponse({
         ok: false,
         status: 429,
         statusText: 'Too Many Requests',
-        text: async () => 'Rate limit exceeded',
-      } as any)
+        text: 'Rate limit exceeded',
+      })
 
       await expect(generateSearchEmbedding('test query')).rejects.toThrow('Embedding API failed')
 
@@ -356,17 +341,16 @@ describe('Knowledge Search Utils', () => {
         KB_OPENAI_MODEL_NAME: 'text-embedding-ada-002',
       })
 
-      const fetchSpy = vi.mocked(fetch)
-      fetchSpy.mockResolvedValueOnce({
-        ok: true,
-        json: async () => ({
+      mockNextFetchResponse({
+        json: {
           data: [{ embedding: [0.1, 0.2, 0.3] }],
-        }),
-      } as any)
+          usage: { prompt_tokens: 1, total_tokens: 1 },
+        },
+      })
 
       await generateSearchEmbedding('test query')
 
-      expect(fetchSpy).toHaveBeenCalledWith(
+      expect(vi.mocked(fetch)).toHaveBeenCalledWith(
         expect.any(String),
         expect.objectContaining({
           body: JSON.stringify({
@@ -387,17 +371,16 @@ describe('Knowledge Search Utils', () => {
         OPENAI_API_KEY: 'test-openai-key',
       })
 
-      const fetchSpy = vi.mocked(fetch)
-      fetchSpy.mockResolvedValueOnce({
-        ok: true,
-        json: async () => ({
+      mockNextFetchResponse({
+        json: {
           data: [{ embedding: [0.1, 0.2, 0.3] }],
-        }),
-      } as any)
+          usage: { prompt_tokens: 1, total_tokens: 1 },
+        },
+      })
 
       await generateSearchEmbedding('test query', 'text-embedding-3-small')
 
-      expect(fetchSpy).toHaveBeenCalledWith(
+      expect(vi.mocked(fetch)).toHaveBeenCalledWith(
         expect.any(String),
         expect.objectContaining({
           body: JSON.stringify({

diff --git a/apps/sim/app/api/knowledge/utils.test.ts b/apps/sim/app/api/knowledge/utils.test.ts
@@ -77,6 +77,7 @@ vi.stubGlobal(
         { embedding: [0.1, 0.2], index: 0 },
         { embedding: [0.3, 0.4], index: 1 },
       ],
+      usage: { prompt_tokens: 2, total_tokens: 2 },
     }),
   })
 )
@@ -294,7 +295,7 @@ describe('Knowledge Utils', () => {
     it.concurrent('should return same length as input', async () => {
       const result = await generateEmbeddings(['a', 'b'])
 
-      expect(result.length).toBe(2)
+      expect(result.embeddings.length).toBe(2)
     })
 
     it('should use Azure OpenAI when Azure config is provided', async () => {
@@ -313,6 +314,7 @@ describe('Knowledge Utils', () => {
         ok: true,
         json: async () => ({
           data: [{ embedding: [0.1, 0.2], index: 0 }],
+          usage: { prompt_tokens: 1, total_tokens: 1 },
         }),
       } as any)
 
@@ -342,6 +344,7 @@ describe('Knowledge Utils', () => {
         ok: true,
         json: async () => ({
           data: [{ embedding: [0.1, 0.2], index: 0 }],
+          usage: { prompt_tokens: 1, total_tokens: 1 },
         }),
       } as any)
 

diff --git a/...space/[workspaceId]/knowledge/[id]/components/add-connector-modal/add-connector-modal.tsx b/...space/[workspaceId]/knowledge/[id]/components/add-connector-modal/add-connector-modal.tsx
@@ -19,26 +19,23 @@ import {
   ModalHeader,
   Tooltip,
 } from '@/components/emcn'
+import { getSubscriptionAccessState } from '@/lib/billing/client'
 import { consumeOAuthReturnContext } from '@/lib/credentials/client-state'
 import { getProviderIdFromServiceId, type OAuthProvider } from '@/lib/oauth'
 import { OAuthModal } from '@/app/workspace/[workspaceId]/components/oauth-modal'
 import { ConnectorSelectorField } from '@/app/workspace/[workspaceId]/knowledge/[id]/components/add-connector-modal/components/connector-selector-field'
+import { SYNC_INTERVALS } from '@/app/workspace/[workspaceId]/knowledge/[id]/components/consts'
+import { MaxBadge } from '@/app/workspace/[workspaceId]/knowledge/[id]/components/max-badge'
+import { isBillingEnabled } from '@/app/workspace/[workspaceId]/settings/navigation'
 import { getDependsOnFields } from '@/blocks/utils'
 import { CONNECTOR_REGISTRY } from '@/connectors/registry'
 import type { ConnectorConfig, ConnectorConfigField } from '@/connectors/types'
 import { useCreateConnector } from '@/hooks/queries/kb/connectors'
 import { useOAuthCredentials } from '@/hooks/queries/oauth/oauth-credentials'
+import { useSubscriptionData } from '@/hooks/queries/subscription'
 import type { SelectorKey } from '@/hooks/selectors/types'
 import { useCredentialRefreshTriggers } from '@/hooks/use-credential-refresh-triggers'
 
-const SYNC_INTERVALS = [
-  { label: 'Every hour', value: 60 },
-  { label: 'Every 6 hours', value: 360 },
-  { label: 'Daily', value: 1440 },
-  { label: 'Weekly', value: 10080 },
-  { label: 'Manual only', value: 0 },
-] as const
-
 const CONNECTOR_ENTRIES = Object.entries(CONNECTOR_REGISTRY)
 
 interface AddConnectorModalProps {
@@ -75,6 +72,10 @@ export function AddConnectorModal({
   const { workspaceId } = useParams<{ workspaceId: string }>()
   const { mutate: createConnector, isPending: isCreating } = useCreateConnector()
 
+  const { data: subscriptionResponse } = useSubscriptionData({ enabled: isBillingEnabled })
+  const subscriptionAccess = getSubscriptionAccessState(subscriptionResponse?.data)
+  const hasMaxAccess = !isBillingEnabled || subscriptionAccess.hasUsableMaxAccess
+
   const connectorConfig = selectedType ? CONNECTOR_REGISTRY[selectedType] : null
   const isApiKeyMode = connectorConfig?.auth.mode === 'apiKey'
   const connectorProviderId = useMemo(
@@ -528,8 +529,13 @@ export function AddConnectorModal({
                     onValueChange={(val) => setSyncInterval(Number(val))}
                   >
                     {SYNC_INTERVALS.map((interval) => (
-                      <ButtonGroupItem key={interval.value} value={String(interval.value)}>
+                      <ButtonGroupItem
+                        key={interval.value}
+                        value={String(interval.value)}
+                        disabled={interval.requiresMax && !hasMaxAccess}
+                      >
                         {interval.label}
+                        {interval.requiresMax && !hasMaxAccess && <MaxBadge />}
                       </ButtonGroupItem>
                     ))}
                   </ButtonGroup>

diff --git a/apps/sim/app/workspace/[workspaceId]/knowledge/[id]/components/consts.ts b/apps/sim/app/workspace/[workspaceId]/knowledge/[id]/components/consts.ts
@@ -0,0 +1,8 @@
+export const SYNC_INTERVALS = [
+  { label: 'Live', value: 5, requiresMax: true },
+  { label: 'Every hour', value: 60, requiresMax: false },
+  { label: 'Every 6 hours', value: 360, requiresMax: false },
+  { label: 'Daily', value: 1440, requiresMax: false },
+  { label: 'Weekly', value: 10080, requiresMax: false },
+  { label: 'Manual only', value: 0, requiresMax: false },
+] as const