Add a statistics pane to the webhook page (closes #368)

Each webhook's event database keeps one row of running totals: events,
deliveries and failures, and how many of each retention removed.
Storing an event, creating a delivery, a delivery becoming failed and
the retention sweep each update it in the transaction that writes or
deletes the rows it counts. Deliveries get a finished_at column, the
last column of the status index, so the last-10-minutes and
last-24-hours figures are index-range counts. The pane is its own
template, included at the top of the page.

The schema changes in place with nothing back-filled, so an existing
database must be recreated.

Model: opus-5-5

internal/delivery/delivery_totals_test.go

@@ -0,0 +1,100 @@
+package delivery_test
+
+import (
+	"testing"
+	"time"
+
+	"github.com/google/uuid"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"gorm.io/gorm"
+	"sneak.berlin/go/webhooker/internal/database"
+)
+
+// failureTotal reads the running failure total of a webhook database.
+func failureTotal(t *testing.T, db *gorm.DB) int64 {
+	t.Helper()
+
+	var totals database.Totals
+
+	require.NoError(t, db.Take(&totals).Error)
+
+	return totals.Failures
+}
+
+// TestUpdateDeliveryStatus_FinishTimeAndFailureTotal pins what a status
+// write records for the webhook page's statistics: the time a delivery
+// finished, set only when it becomes delivered or failed, and one more
+// on the failure total when it fails.
+func TestUpdateDeliveryStatus_FinishTimeAndFailureTotal(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		status   database.DeliveryStatus
+		finished bool
+		failures int64
+	}{
+		{database.DeliveryStatusRetrying, false, 0},
+		{database.DeliveryStatusDelivered, true, 0},
+		{database.DeliveryStatusFailed, true, 1},
+	}
+
+	for _, tt := range tests {
+		t.Run(string(tt.status), func(t *testing.T) {
+			t.Parallel()
+
+			db := testWebhookDB(t)
+			e := testEngine(t, 1)
+			event := seedEvent(t, db, `{}`)
+			d := seedDelivery(
+				t, db, event.ID, uuid.New().String(),
+				database.DeliveryStatusPending,
+			)
+
+			before := time.Now()
+
+			require.NoError(t, e.ExportUpdateDeliveryStatus(
+				db, &d, tt.status,
+			))
+
+			var stored database.Delivery
+
+			require.NoError(t, db.First(&stored, "id = ?", d.ID).Error)
+			assert.Equal(t, tt.status, stored.Status)
+
+			if tt.finished {
+				require.NotNil(t, stored.FinishedAt)
+				assert.False(t, stored.FinishedAt.Before(before))
+			} else {
+				assert.Nil(t, stored.FinishedAt)
+			}
+
+			assert.Equal(t, tt.failures, failureTotal(t, db))
+		})
+	}
+}
+
+// TestUpdateDeliveryStatus_DeletedDeliveryIsNotCounted covers a
+// delivery retention deleted while the engine still held it. Failing
+// it afterwards writes no row, so it adds no failure either: retention
+// has already counted what it removed.
+func TestUpdateDeliveryStatus_DeletedDeliveryIsNotCounted(t *testing.T) {
+	t.Parallel()
+
+	db := testWebhookDB(t)
+	e := testEngine(t, 1)
+	event := seedEvent(t, db, `{}`)
+	d := seedDelivery(
+		t, db, event.ID, uuid.New().String(),
+		database.DeliveryStatusRetrying,
+	)
+
+	require.NoError(t, db.Unscoped().
+		Delete(&database.Delivery{}, "id = ?", d.ID).Error)
+
+	require.NoError(t, e.ExportUpdateDeliveryStatus(
+		db, &d, database.DeliveryStatusFailed,
+	))
+
+	assert.Zero(t, failureTotal(t, db))
+}

internal/delivery/engine.go

@@ -1554,8 +1554,9 @@ func (e *Engine) updateDeliveryStatus(
 	targetType database.TargetType,
 	status database.DeliveryStatus,
 ) error {
-	err := webhookDB.Model(d).
-		Update("status", status).Error
+	err := webhookDB.Transaction(func(tx *gorm.DB) error {
+		return writeDeliveryStatus(tx, d, status)
+	})
 	if err != nil {
 		return fmt.Errorf(
 			"updating delivery %s to status %s: %w",
@@ -1574,6 +1575,33 @@ func (e *Engine) updateDeliveryStatus(
 	return nil
 }
 
+// writeDeliveryStatus writes a delivery's new status. A delivery that
+// becomes delivered or failed also gets the time it finished, and a
+// failed one is added to the webhook's running failure total. The
+// failure is counted only if the row was still there to update:
+// retention may have deleted it while the engine was working on it.
+func writeDeliveryStatus(
+	tx *gorm.DB,
+	d *database.Delivery,
+	status database.DeliveryStatus,
+) error {
+	columns := map[string]any{"status": status}
+	if status.Terminal() {
+		columns["finished_at"] = time.Now()
+	}
+
+	res := tx.Model(d).Updates(columns)
+	if res.Error != nil {
+		return res.Error
+	}
+
+	if status == database.DeliveryStatusFailed && res.RowsAffected > 0 {
+		return database.AddTotals(tx, database.Totals{Failures: 1})
+	}
+
+	return nil
+}
+
 // settleStatus moves a delivery to its outcome status and reports a
 // failed write through bookkeepingFailed, which leaves the row
 // recoverable. It exists so the target call sites read as one

internal/delivery/engine_test.go

@@ -57,7 +57,9 @@ func testWebhookDB(t *testing.T) *gorm.DB {
 		&database.Event{},
 		&database.Delivery{},
 		&database.DeliveryResult{},
+		&database.Totals{},
 	))
+	require.NoError(t, db.Create(&database.Totals{}).Error)
 
 	return db
 }

internal/delivery/export_test.go

@@ -150,6 +150,16 @@ func (e *Engine) ExportDeliverSlack(
 	)
 }
 
+// ExportUpdateDeliveryStatus exposes updateDeliveryStatus. It passes no
+// target type, so no metric moves.
+func (e *Engine) ExportUpdateDeliveryStatus(
+	webhookDB *gorm.DB,
+	d *database.Delivery,
+	status database.DeliveryStatus,
+) error {
+	return e.updateDeliveryStatus(webhookDB, d, "", status)
+}
+
 // ExportProcessNewTask exposes processNewTask.
 func (e *Engine) ExportProcessNewTask(
 	ctx context.Context, task *Task,