TODO.md

@@ -20,6 +20,10 @@ main cannot regress.
 
 # Completed Steps
 
+- 2026-09-22: Fixed the flaky `t.TempDir` cleanup race in
+  `internal/service/webhook` by tracking the async deployment goroutine
+  in a `sync.WaitGroup` and exposing `WaitForDeployments`; tests now
+  synchronize on completion instead of sleeping (#198).
 - 2026-09-22: Linting now runs only in Docker. Added `Dockerfile.lint`
   (pinned golangci-lint v2.12.2, cache-busted via a `GATE_RUN` build arg
   so the linter always executes), reduced `script/lint` to building it,

internal/service/webhook/webhook.go

@@ -6,6 +6,7 @@ import (
 	"database/sql"
 	"fmt"
 	"log/slog"
+	"sync"
 
 	"go.uber.org/fx"
 
@@ -31,6 +32,10 @@ type Service struct {
 	db     *database.Database
 	deploy *deploy.Service
 	params *ServiceParams
+
+	// deployments tracks the deployment goroutines started by
+	// triggerDeployment so callers can wait for them to finish.
+	deployments sync.WaitGroup
 }
 
 // New creates a new webhook Service.
@@ -108,6 +113,14 @@ func (svc *Service) HandleWebhook(
 	return nil
 }
 
+// WaitForDeployments blocks until every deployment goroutine started by
+// HandleWebhook has finished, including all writes under the data
+// directory. It exists so callers and tests can synchronize on async
+// deployment completion instead of polling or sleeping.
+func (svc *Service) WaitForDeployments() {
+	svc.deployments.Wait()
+}
+
 func (svc *Service) triggerDeployment(
 	ctx context.Context,
 	app *models.App,
@@ -117,7 +130,7 @@ func (svc *Service) triggerDeployment(
 	eventID := event.ID
 	appName := app.Name
 
-	go func() {
+	svc.deployments.Go(func() {
 		// Use context.WithoutCancel to ensure deployment completes
 		// even if the HTTP request context is cancelled.
 		deployCtx := context.WithoutCancel(ctx)
@@ -130,5 +143,5 @@ func (svc *Service) triggerDeployment(
 		// Mark event as processed
 		event.Processed = true
 		_ = event.Save(deployCtx)
-	}()
+	})
 }

internal/service/webhook/webhook_test.go

@@ -7,7 +7,6 @@ import (
 	"os"
 	"path/filepath"
 	"testing"
-	"time"
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
@@ -828,8 +827,9 @@ func TestExtractBranch(testingT *testing.T) {
 			)
 			require.NoError(t, err)
 
-			// Allow async deployment goroutine to complete before test cleanup
-			time.Sleep(100 * time.Millisecond)
+			// Wait for the async deployment goroutine to finish so its
+			// writes under the temp dir complete before test cleanup.
+			svc.WaitForDeployments()
 
 			events, err := app.GetWebhookEvents(context.Background(), 10)
 			require.NoError(t, err)
@@ -867,8 +867,9 @@ func TestHandleWebhookMatchingBranch(t *testing.T) {
 	)
 	require.NoError(t, err)
 
-	// Allow async deployment goroutine to complete before test cleanup
-	time.Sleep(100 * time.Millisecond)
+	// Wait for the async deployment goroutine to finish so its writes
+	// under the temp dir complete before test cleanup.
+	svc.WaitForDeployments()
 
 	events, err := app.GetWebhookEvents(context.Background(), 10)
 	require.NoError(t, err)
@@ -962,8 +963,9 @@ func assertHandleWebhookDeploys(
 	err := svc.HandleWebhook(context.Background(), app, source, pushEventType, payload)
 	require.NoError(t, err)
 
-	// Allow async deployment goroutine to complete before test cleanup
-	time.Sleep(100 * time.Millisecond)
+	// Wait for the async deployment goroutine to finish so its writes
+	// under the temp dir complete before test cleanup.
+	svc.WaitForDeployments()
 
 	events, err := app.GetWebhookEvents(context.Background(), 10)
 	require.NoError(t, err)