Add a statistics pane to the webhook page (closes #368)
check / check (push) Waiting to run

The webhook page opens with a statistics pane: entrypoints and targets, deliveries in progress, the last arrival, the retention period; events, deliveries and failures, lifetime and within retention; and events, failures and failure percentage over 10 minutes and 24 hours.

Running totals, one row per target plus one for events, sit in each webhook's event database and are written in the same transaction as the rows they count; retention prunes in paused, stoppable batches and subtracts what it removes. Window figures are index-range counts on a new finished_at column. An existing event database must be recreated.

Model: opus-5-5
This commit was merged in pull request #403.
This commit is contained in:
2026-10-02 06:41:00 +02:00
parent 43ed8d4834
commit 803a94be37
23 changed files with 2072 additions and 118 deletions
+72 -17
View File
@@ -93,11 +93,11 @@ func TestEventTierQueriesUseTheirIndexes(t *testing.T) {
deliveries []database.Delivery
results []database.DeliveryResult
depths []struct{ Depth int }
removed []database.TargetTotals
)
byStatus := "idx_deliveries_status (status=? AND deleted_at=?)"
byEvent := "idx_deliveries_event_id (event_id=? AND deleted_at=?)"
byAge := "idx_events_deleted_at_created_at (deleted_at=? AND created_at<?)"
// The delivery engine: recovery and the retry sweep, the sweep for
// stranded pending deliveries, and the queue depth count.
@@ -123,25 +123,80 @@ func TestEventTierQueriesUseTheirIndexes(t *testing.T) {
Order("attempt_num ASC").Find(&results),
"idx_delivery_results_delivery_id (delivery_id=? AND deleted_at=?)")
// Retention's three deletes (reapExpired), whose subqueries are built
// afresh for each statement as it builds them.
expiredEventIDs := func() *gorm.DB {
return dry.Model(&database.Event{}).Select("id").
Where("created_at < ?", cutoff)
}
// Retention (reapExpired, deleteEvents): one batch of expired
// events, then their attempts, deliveries and the events.
var expired []string
assertPlanUses(t, db, dry.Unscoped().Model(&database.Event{}).
Where("created_at < ?", cutoff).
Limit(database.ExportReapBatchSize).Pluck("id", &expired),
"idx_events_created_at (created_at<?)")
assertPlanUses(t, db, dry.Unscoped().Where(
"delivery_id IN (?)", dry.Model(&database.Delivery{}).
Select("id").Where("event_id IN (?)", expiredEventIDs()),
"delivery_id IN (?)", dry.Unscoped().Model(&database.Delivery{}).
Select("id").Where("event_id IN ?", ids),
).Delete(&database.DeliveryResult{}),
"idx_delivery_results_delivery_id (delivery_id=?)", byEvent, byAge)
assertPlanUses(t, db, dry.Unscoped().Where(
"event_id IN (?)", expiredEventIDs(),
).Delete(&database.Delivery{}),
"idx_deliveries_event_id (event_id=?)", byAge)
assertPlanUses(t, db, dry.Unscoped().Where(
"created_at < ?", cutoff,
).Delete(&database.Event{}), "idx_events_created_at (created_at<?)")
"idx_delivery_results_delivery_id (delivery_id=?)",
"idx_deliveries_event_id (event_id=?)")
assertPlanUses(t, db, dry.Unscoped().Model(&database.Delivery{}).
Select("target_id, count(*) AS deliveries_removed, "+
"count(CASE WHEN status = ? THEN 1 END) AS failed_removed",
database.DeliveryStatusFailed).
Where("event_id IN ?", ids).Group("target_id").Find(&removed),
"idx_deliveries_event_id (event_id=?)")
assertPlanUses(t, db, dry.Unscoped().Where("event_id IN ?", ids).
Delete(&database.Delivery{}), "idx_deliveries_event_id (event_id=?)")
assertPlanUses(t, db, dry.Unscoped().Where("id IN ?", ids).
Delete(&database.Event{}), "sqlite_autoindex_events_1 (id=?)")
}
// TestStatisticsQueriesUseTheirIndexes does the same for the webhook
// page's statistics (readEventStats in the handlers): deliveries in
// progress, each target's deliveries finished since a time, which must
// come from the index alone, and events received since a time.
func TestStatisticsQueriesUseTheirIndexes(t *testing.T) {
t.Parallel()
mgr, lc := setupTestWebhookDBManager(t)
ctx := context.Background()
require.NoError(t, lc.Start(ctx))
defer func() { require.NoError(t, lc.Stop(ctx)) }()
db, err := mgr.GetDB(uuid.New().String())
require.NoError(t, err)
dry := db.Session(&gorm.Session{DryRun: true})
since := time.Now()
var (
count int64
byTarget []struct{ TargetID string }
)
assertPlanUses(t, db, dry.Model(&database.Delivery{}).
Where("status IN ?", []database.DeliveryStatus{
database.DeliveryStatusPending,
database.DeliveryStatusRetrying,
}).Count(&count),
"idx_deliveries_status (status=? AND deleted_at=?)")
assertPlanUses(t, db, dry.Model(&database.Delivery{}).
Select("target_id, "+
"count(CASE WHEN status = ? THEN 1 END) AS delivered, "+
"count(CASE WHEN status = ? THEN 1 END) AS failed",
database.DeliveryStatusDelivered,
database.DeliveryStatusFailed).
Where("status IN ? AND finished_at >= ?",
[]database.DeliveryStatus{
database.DeliveryStatusDelivered,
database.DeliveryStatusFailed,
}, since).
Group("target_id").Find(&byTarget),
"COVERING INDEX idx_deliveries_status "+
"(status=? AND deleted_at=? AND finished_at>?)")
assertPlanUses(t, db, dry.Model(&database.Event{}).
Where("created_at >= ?", since).Count(&count),
"idx_events_deleted_at_created_at "+
"(deleted_at=? AND created_at>?)")
}
// assertPlanUses asserts that SQLite's plan for a statement GORM built