WIP: root background loops at context.Background() (refs #97)

Incomplete: tests pass but three lint findings remain (funcorder on
registerHooks, unparam in engine_integration_test.go). Committed to
preserve work in progress; to be amended into a single clean commit.

internal/delivery/engine_lifecycle_test.go

@@ -0,0 +1,183 @@
+package delivery_test
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	"github.com/google/uuid"
+	"github.com/stretchr/testify/require"
+	"go.uber.org/fx"
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/delivery"
+)
+
+// hookStopTimeout bounds how long a lifecycle test waits for the
+// engine's OnStop hook to return before declaring the shutdown
+// hung.
+const hookStopTimeout = 10 * time.Second
+
+// recordingLifecycle is a minimal fx.Lifecycle that records the
+// hooks a component registers, so a test can invoke the real
+// OnStart/OnStop functions with a context of its choosing.
+type recordingLifecycle struct {
+	hooks []fx.Hook
+}
+
+func (l *recordingLifecycle) Append(h fx.Hook) {
+	l.hooks = append(l.hooks, h)
+}
+
+// startEngineViaHook drives the genuine fx hooks the application
+// registers for the engine, handing OnStart a context that is
+// already done. It returns the recorded lifecycle so the caller
+// can drive OnStop too.
+func startEngineViaHook(
+	t *testing.T, eng *delivery.Engine,
+) *recordingLifecycle {
+	t.Helper()
+
+	lc := &recordingLifecycle{}
+	eng.ExportRegisterHooks(lc)
+	require.Len(t, lc.hooks, 1)
+
+	// fx hands OnStart a context carrying the application start
+	// timeout, and cancels it when the start phase ends. An
+	// already-cancelled context is that same defect taken to its
+	// limit, and unlike a plain context.Background() it actually
+	// distinguishes a correctly rooted loop from a broken one.
+	hookCtx, cancel := context.WithCancel(context.Background())
+	cancel()
+
+	require.NoError(t, lc.hooks[0].OnStart(hookCtx))
+
+	return lc
+}
+
+// seedLogTask seeds a pending delivery for a log target and
+// returns its ID together with the task that drives it. The log
+// target needs no network, so a delivery completing proves only
+// that a worker picked the task up.
+func seedLogTask(
+	t *testing.T, s iSetup,
+) (string, delivery.Task) {
+	t.Helper()
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID,
+		`{"lifecycle":"hook-context"}`,
+	)
+	targetID := uuid.New().String()
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+
+	bodyStr := event.Body
+	task := iTask(
+		d, event, s.WebhookID, targetID,
+		"hook-context-test", "", 0, 1, &bodyStr,
+	)
+	task.TargetType = database.TargetTypeLog
+
+	return d.ID, task
+}
+
+// TestEngine_WorkersOutliveStartHookContext is the regression
+// test for a delivery engine that stopped delivering roughly
+// fifteen seconds after boot. fx calls OnStart with a context
+// carrying the application's start timeout (15s by default) and
+// cancels it when the start phase ends, so a worker pool rooted
+// in it exits shortly after startup: the process keeps accepting
+// and persisting events while nothing at all forwards them.
+//
+// Driving OnStart with an already-cancelled context is that
+// defect taken to its limit. A pool that inherits the hook
+// context never processes a single task; a correctly rooted pool
+// keeps working for as long as the process lives.
+func TestEngine_WorkersOutliveStartHookContext(t *testing.T) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	deliveryID, task := seedLogTask(t, s)
+
+	lc := startEngineViaHook(t, s.Engine)
+	t.Cleanup(func() {
+		_ = lc.hooks[0].OnStop(context.Background())
+	})
+
+	s.Engine.Notify([]delivery.Task{task})
+
+	iWaitForStatus(
+		t, s.WebhookDB, deliveryID,
+		database.DeliveryStatusDelivered,
+	)
+}
+
+// TestEngine_StopHookStopsWorkers proves the fix did not trade a
+// startup bug for a shutdown hang: now that the worker pool no
+// longer observes the start hook's cancellation, OnStop is the
+// only thing that can stop it, and it must both return promptly
+// and actually leave the pool drained.
+func TestEngine_StopHookStopsWorkers(t *testing.T) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	lc := startEngineViaHook(t, s.Engine)
+
+	// Let the pool prove it is running before stopping it, so a
+	// fast OnStop cannot pass by stopping something already dead.
+	firstID, firstTask := seedLogTask(t, s)
+	s.Engine.Notify([]delivery.Task{firstTask})
+	iWaitForStatus(
+		t, s.WebhookDB, firstID,
+		database.DeliveryStatusDelivered,
+	)
+
+	var stopErr error
+
+	stopped := make(chan struct{})
+
+	go func() {
+		defer close(stopped)
+
+		// stop blocks on the workers' WaitGroup, so returning at
+		// all proves every goroutine observed the cancellation.
+		stopErr = lc.hooks[0].OnStop(context.Background())
+	}()
+
+	select {
+	case <-stopped:
+	case <-time.After(hookStopTimeout):
+		t.Fatal(
+			"OnStop did not return: the delivery engine's " +
+				"WaitGroup is still waiting on a goroutine that " +
+				"never observed cancellation",
+		)
+	}
+
+	require.NoError(t, stopErr)
+
+	// With every worker gone, a freshly notified task must sit
+	// untouched in the queue rather than being delivered.
+	secondID, secondTask := seedLogTask(t, s)
+	s.Engine.Notify([]delivery.Task{secondTask})
+
+	time.Sleep(200 * time.Millisecond)
+
+	var after database.Delivery
+
+	require.NoError(
+		t,
+		s.WebhookDB.First(&after, "id = ?", secondID).Error,
+	)
+	require.Equal(
+		t,
+		database.DeliveryStatusPending,
+		after.Status,
+		"a stopped engine must not deliver anything",
+	)
+}