test(execution): cover inline admission lease

Co-authored-by: Cursor <cursoragent@cursor.com>

Author: akshay326

apps/sim/app/api/workflows/[id]/execute/route.async.test.ts

@@ -34,6 +34,11 @@ const {
   mockReleaseExecutionIdClaim,
   mockReleaseExecutionSlot,
   mockRequireBillingAttributionHeader,
+  mockShouldExecuteInline,
+  mockStartJob,
+  mockCompleteJob,
+  mockMarkJobFailed,
+  mockExecuteWorkflowJob,
   mockValidatePublicApiAllowed,
 } = vi.hoisted(() => ({
   mockAssertBillingAttributionSnapshot: vi.fn((value: unknown) => {
@@ -52,6 +57,11 @@ const {
   mockReleaseExecutionIdClaim: vi.fn(),
   mockReleaseExecutionSlot: vi.fn(),
   mockRequireBillingAttributionHeader: vi.fn(),
+  mockShouldExecuteInline: vi.fn(() => false),
+  mockStartJob: vi.fn(),
+  mockCompleteJob: vi.fn(),
+  mockMarkJobFailed: vi.fn(),
+  mockExecuteWorkflowJob: vi.fn(),
   mockValidatePublicApiAllowed: vi.fn(),
 }))
 
@@ -114,11 +124,11 @@ vi.mock('@/lib/execution/payloads/store', () => ({
 vi.mock('@/lib/core/async-jobs', () => ({
   getJobQueue: vi.fn().mockResolvedValue({
     enqueue: mockEnqueue,
-    startJob: vi.fn(),
-    completeJob: vi.fn(),
-    markJobFailed: vi.fn(),
+    startJob: mockStartJob,
+    completeJob: mockCompleteJob,
+    markJobFailed: mockMarkJobFailed,
   }),
-  shouldExecuteInline: vi.fn().mockReturnValue(false),
+  shouldExecuteInline: mockShouldExecuteInline,
 }))
 
 vi.mock('@/lib/core/utils/urls', () => ({
@@ -136,7 +146,7 @@ vi.mock('@/lib/execution/call-chain', () => ({
 vi.mock('@/lib/logs/execution/logging-session', () => loggingSessionMock)
 
 vi.mock('@/background/workflow-execution', () => ({
-  executeWorkflowJob: vi.fn(),
+  executeWorkflowJob: mockExecuteWorkflowJob,
 }))
 
 vi.mock('@sim/utils/id', () => ({
@@ -288,6 +298,8 @@ describe('workflow execute async route', () => {
   beforeEach(() => {
     vi.clearAllMocks()
     resetDbChainMock()
+    mockShouldExecuteInline.mockReturnValue(false)
+    mockExecuteWorkflowJob.mockResolvedValue({ success: true })
     mockGenerateId.mockReset().mockReturnValue('execution-123')
     mockClaimExecutionId.mockImplementation(async (executionId: string) => ({
       key: `workflow-execution-id:${executionId}`,
@@ -392,6 +404,36 @@ describe('workflow execute async route', () => {
     )
   })
 
+  it('retains the admission ticket until database-backed async execution finishes', async () => {
+    mockShouldExecuteInline.mockReturnValue(true)
+    let resolveInlineExecution!: () => void
+    const inlineExecution = new Promise<void>((resolve) => {
+      resolveInlineExecution = resolve
+    })
+    mockExecuteWorkflowJob.mockReturnValueOnce(inlineExecution)
+
+    const response = await POST(
+      createMockRequest(
+        'POST',
+        { input: { hello: 'world' } },
+        {
+          'Content-Type': 'application/json',
+          'X-Execution-Mode': 'async',
+        }
+      ),
+      { params: Promise.resolve({ id: 'workflow-1' }) }
+    )
+
+    expect(response.status).toBe(202)
+    expect(getAdmissionGateStatus().inflight).toBe(1)
+
+    resolveInlineExecution()
+    await vi.waitFor(() => {
+      expect(getAdmissionGateStatus().inflight).toBe(0)
+    })
+    expect(mockCompleteJob).toHaveBeenCalledWith('job-123', expect.anything())
+  })
+
   it('applies admission backpressure to session-backed async executions', async () => {
     hybridAuthMockFns.mockHasExternalApiCredentials.mockReturnValue(false)
     const heldTickets = Array.from({ length: getAdmissionGateStatus().maxInflight }, () =>

apps/sim/app/api/workflows/[id]/execute/route.ts

@@ -285,11 +285,6 @@ type AsyncExecutionParams = {
 interface AsyncExecutionResult {
   response: NextResponse
   retainExecutionClaim: boolean
-  /**
-   * When true, the caller must not release the admission ticket — ownership
-   * transferred to the in-process inline runner which releases on completion.
-   */
-  retainAdmissionTicket: boolean
 }
 
 /** Mutable bag so async inline work can retain the HTTP admission ticket. */
@@ -391,7 +386,6 @@ async function handleAsyncExecution(
     return {
       response: NextResponse.json({ error: 'Failed to queue async execution' }, { status: 500 }),
       retainExecutionClaim: false,
-      retainAdmissionTicket: false,
     }
   }
 
@@ -443,7 +437,6 @@ async function handleAsyncExecution(
       return {
         response: NextResponse.json({ error: 'Failed to queue async execution' }, { status: 500 }),
         retainExecutionClaim: false,
-        retainAdmissionTicket: false,
       }
     }
 
@@ -457,7 +450,6 @@ async function handleAsyncExecution(
         { status: 503, headers: { [WORKFLOW_EXECUTION_ID_HEADER]: executionId } }
       ),
       retainExecutionClaim: true,
-      retainAdmissionTicket: false,
     }
   }
 
@@ -521,7 +513,6 @@ async function handleAsyncExecution(
       { status: 202 }
     ),
     retainExecutionClaim: true,
-    retainAdmissionTicket: executeInline,
   }
 }
 

apps/sim/scripts/load/README.md

@@ -10,7 +10,7 @@ These local-only Artillery scenarios exercise `POST /api/workflows/[id]/execute`
 
 The default rates are tuned for these local limits:
 
-- `ADMISSION_GATE_MAX_INFLIGHT=500`
+- `ADMISSION_GATE_MAX_INFLIGHT=10`
 
 The admission gate caps total in-flight requests per pod.
 
@@ -23,7 +23,7 @@ Default profile:
 - Starts at `2` requests per second
 - Ramps to `8` requests per second
 - Holds there for `20` seconds
-- Good for validating queueing against a Free workspace concurrency of `5`
+- Good for validating queueing against a Free workspace concurrency of `10`
 
 ```bash
 WORKFLOW_ID=<workflow-id> \
@@ -103,5 +103,5 @@ Optional variables:
 - `load:workflow` is an alias for `load:workflow:baseline`
 - All scenarios send `x-execution-mode: async`
 - Artillery output will show request counts and response codes, which is usually enough for quick local verification
-- At these defaults, you should see `429` responses when approaching `ADMISSION_GATE_MAX_INFLIGHT=500`
+- At these defaults, you should see `429` responses when approaching `ADMISSION_GATE_MAX_INFLIGHT=10`
 - If you still see lots of `429` or `ETIMEDOUT` responses locally, lower the rates again before increasing durations