Add functional test for request-ID stability across server-side retries

Use a package-level atomic to fail StartActivityExecution once after the
activity is created at history, triggering the RetryableInterceptor.
Without the fix, the retry generates a new request ID and gets
ActivityExecutionAlreadyStarted. With the fix, the retry reuses the
same request ID and the dedup succeeds.

Author: dandavison

chasm/lib/activity/frontend.go

@@ -2,6 +2,7 @@ package activity
 
 import (
 	"context"
+	"sync/atomic"
 
 	"github.com/google/uuid"
 	apiactivitypb "go.temporal.io/api/activity/v1" //nolint:importas
@@ -35,6 +36,10 @@ type FrontendHandler interface {
 
 var ErrStandaloneActivityDisabled = serviceerror.NewUnimplemented("Standalone activity is disabled")
 
+// TestStartFailOnce, when set to true, causes the next StartActivityExecution to return Unavailable
+// after the activity is created. It fires once (CAS to false).
+var TestStartFailOnce atomic.Bool
+
 type frontendHandler struct {
 	FrontendHandler
 	client            activitypb.ActivityServiceClient
@@ -100,6 +105,13 @@ func (h *frontendHandler) StartActivityExecution(ctx context.Context, req *workf
 		NamespaceId:     namespaceID.String(),
 		FrontendRequest: modifiedReq,
 	})
+	if err != nil {
+		return nil, err
+	}
+
+	if TestStartFailOnce.CompareAndSwap(true, false) {
+		return nil, serviceerror.NewUnavailable("test: injected failure after successful creation")
+	}
 
 	return resp.GetFrontendResponse(), err
 }

tests/standalone_activity_test.go

@@ -270,6 +270,36 @@ func (s *standaloneActivityTestSuite) TestIDConflictPolicy() {
 	})
 }
 
+func (s *standaloneActivityTestSuite) TestServerGeneratedRequestIDStableAcrossRetries() {
+	t := s.T()
+	ctx, cancel := context.WithTimeout(t.Context(), 10*time.Second)
+	defer cancel()
+
+	activityID := testcore.RandomizeStr(t.Name())
+	taskQueue := testcore.RandomizeStr(t.Name())
+
+	// Make the handler fail once with a retryable error so the RetryableInterceptor retries.
+	activity.TestStartFailOnce.Store(true)
+
+	resp, err := s.FrontendClient().StartActivityExecution(ctx, &workflowservice.StartActivityExecutionRequest{
+		Namespace:    s.Namespace().String(),
+		ActivityId:   activityID,
+		ActivityType: s.tv.ActivityType(),
+		Identity:     s.tv.WorkerIdentity(),
+		Input:        defaultInput,
+		TaskQueue: &taskqueuepb.TaskQueue{
+			Name: taskQueue,
+		},
+		StartToCloseTimeout: durationpb.New(defaultStartToCloseTimeout),
+		// No RequestId — server generates one.
+	})
+	// With the fix, the retry uses the same request ID, so history recognizes it as a dedup
+	// and succeeds (with Started=false). Without the fix, the retry generates a new request ID
+	// and gets ActivityExecutionAlreadyStarted.
+	require.NoError(t, err)
+	require.NotNil(t, resp)
+}
+
 func (s *standaloneActivityTestSuite) TestPollActivityTaskQueue() {
 	t := s.T()
 	ctx, cancel := context.WithTimeout(t.Context(), 10*time.Second)