Open SQLite with WAL and bound delivery re-dispatch by ownership (closes #256)

internal/delivery/engine.go

@@ -41,6 +41,31 @@ const (
 	// sweep runs.
 	retrySweepInterval = 60 * time.Second
 
+	// pendingSweepMinAge is how long a delivery must have sat
+	// untouched at pending before the sweep will look at it.
+	//
+	// It is not what keeps the sweep off live work — inflightSet is,
+	// and it is exact. This bound sets the re-dispatch cadence for a
+	// delivery that really is stranded: without it, a delivery the
+	// database will not let the engine settle would be re-sent on
+	// every 60-second tick.
+	//
+	// It is nonetheless set clear of the longest legitimate attempt,
+	// so that the two guards do not both have to be right. That
+	// length is MaxTargetTimeoutSeconds (300s), the per-target
+	// timeout the target form accepts — not httpClientTimeout, which
+	// is merely the default. Fifteen minutes leaves a margin of
+	// three times the ceiling rather than the zero margin the two
+	// equal values would have given.
+	pendingSweepMinAge = 15 * time.Minute
+
+	// pendingSweepBatch bounds how many stranded pending deliveries
+	// one sweep of one webhook re-dispatches. The sweep runs every
+	// retrySweepInterval, so a larger backlog drains across
+	// successive sweeps instead of arriving as one burst against a
+	// database that was already struggling to accept writes.
+	pendingSweepBatch = 500
+
 	// MaxInlineBodySize is the maximum event body size that
 	// will be carried inline in a Task through the channel.
 	// Bodies at or above this size are left nil and fetched
@@ -157,6 +182,12 @@ type Engine struct {
 	// dbTarget is retained so the engine can reach the archive
 	// writer registry for webhook eviction and the idle sweep.
 	dbTarget *databaseTarget
+
+	// inflight is the set of deliveries this engine currently owns.
+	// Recovery and the sweeps re-dispatch only what it does not
+	// hold. Held by value: its zero value works, so no constructor
+	// can leave it out. See inflight.go.
+	inflight inflightSet
 }
 
 // New creates and registers the delivery engine with the
@@ -189,12 +220,27 @@ func New(
 // are ready.
 func (e *Engine) Notify(tasks []Task) {
 	for i := range tasks {
+		// Owned before it is queued, and until the worker that runs
+		// it returns. A task can sit in a 10000-deep channel for a
+		// long time on a healthy system, and nothing may re-send it
+		// while it waits. See inflight.go.
+		if !e.inflight.retainIdle(tasks[i].DeliveryID) {
+			e.log.Warn(
+				"delivery already in flight, not queued again",
+				"delivery_id", tasks[i].DeliveryID,
+				"event_id", tasks[i].EventID,
+			)
+
+			continue
+		}
+
 		select {
 		case e.deliveryCh <- tasks[i]:
 		default:
+			e.inflight.release(tasks[i].DeliveryID)
 			e.log.Warn(
 				"delivery channel full, "+
-					"task will be recovered on restart",
+					"task will be recovered by the sweep",
 				"delivery_id", tasks[i].DeliveryID,
 				"event_id", tasks[i].EventID,
 			)
@@ -229,10 +275,20 @@ func (e *Engine) ScheduleRetry(
 		"next_attempt", task.AttemptNum,
 	)
 
+	// The reference is taken here rather than when the timer fires,
+	// so the delivery stays owned across the whole backoff window.
+	// Its caller is a target inside Deliver, so the engine already
+	// owns it; this second reference is what keeps that ownership
+	// alive after the worker returns and the row sits at retrying
+	// with nothing running. Without it the sweep finds the row
+	// orphaned and sends it again.
+	e.inflight.retain(task.DeliveryID)
+
 	time.AfterFunc(delay, func() {
 		select {
 		case e.retryCh <- task:
 		default:
+			e.inflight.release(task.DeliveryID)
 			e.log.Warn(
 				"retry channel full, delivery "+
 					"will be recovered by periodic sweep",
@@ -332,13 +388,35 @@ func (e *Engine) worker(ctx context.Context) {
 		case <-ctx.Done():
 			return
 		case task := <-e.deliveryCh:
-			e.processNewTask(ctx, &task)
+			e.runTask(ctx, &task, e.processNewTask)
 		case task := <-e.retryCh:
-			e.processRetryTask(ctx, &task)
+			e.runTask(ctx, &task, e.processRetryTask)
 		}
 	}
 }
 
+// runTask runs one task and then drops the reference the queueing
+// side took on its delivery.
+//
+// The release is deferred rather than written after the call because
+// every early return inside the processing paths must drop it too: a
+// delivery whose database could not be opened is one the engine has
+// stopped working on, and leaving it owned would hide it from the
+// sweep forever.
+//
+// Ownership does not necessarily end here. A target that scheduled a
+// retry took its own reference before this one is dropped, so the
+// delivery stays owned through the backoff window.
+func (e *Engine) runTask(
+	ctx context.Context,
+	task *Task,
+	run func(context.Context, *Task),
+) {
+	defer e.inflight.release(task.DeliveryID)
+
+	run(ctx, task)
+}
+
 func (e *Engine) recoverPending(ctx context.Context) {
 	defer e.wg.Done()
 
@@ -526,7 +604,16 @@ func (e *Engine) recoverRetryingDeliveries(
 		return
 	}
 
+	settled := e.reconcileDelivered(
+		webhookDB, webhookID, retrying,
+		e.loadTargetMap(retrying),
+	)
+
 	for i := range retrying {
+		if _, ok := settled[retrying[i].ID]; ok {
+			continue
+		}
+
 		e.recoverSingleRetry(
 			webhookDB, webhookID, &retrying[i],
 		)
@@ -588,6 +675,10 @@ func (e *Engine) recoverSingleRetry(
 		d, webhookID, &event, &target, attemptNum+1,
 	)
 
+	if !e.rescheduleRecovered(webhookDB, task, remaining) {
+		return
+	}
+
 	e.log.Info(
 		"recovering retrying delivery",
 		"webhook_id", webhookID,
@@ -595,8 +686,6 @@ func (e *Engine) recoverSingleRetry(
 		"attempt", attemptNum,
 		"remaining_backoff", remaining,
 	)
-
-	e.ScheduleRetry(task, remaining)
 }
 
 func (e *Engine) recoverPendingDeliveries(
@@ -606,12 +695,14 @@ func (e *Engine) recoverPendingDeliveries(
 ) {
 	var deliveries []database.Delivery
 
+	// No Preload: event bodies are read one at a time in
+	// sendRecoveredDeliveries, and only for the deliveries actually
+	// being sent.
 	result := webhookDB.
 		Where(
 			"status = ?",
 			database.DeliveryStatusPending,
 		).
-		Preload("Event").
 		Find(&deliveries)
 
 	if result.Error != nil {
@@ -634,11 +725,137 @@ func (e *Engine) recoverPendingDeliveries(
 		"count", len(deliveries),
 	)
 
+	e.recoverPendingBatch(
+		ctx, webhookDB, webhookID, deliveries,
+	)
+}
+
+// recoverPendingBatch settles every delivery in the batch that was
+// already delivered, and re-dispatches only the rest. Both the
+// restart-time recovery and the periodic sweep go through it, so a
+// pending delivery is treated the same however it was found.
+func (e *Engine) recoverPendingBatch(
+	ctx context.Context,
+	webhookDB *gorm.DB,
+	webhookID string,
+	deliveries []database.Delivery,
+) {
 	targetMap := e.loadTargetMap(deliveries)
 
-	e.sendRecoveredDeliveries(
-		ctx, deliveries, webhookID, targetMap,
+	settled := e.reconcileDelivered(
+		webhookDB, webhookID, deliveries, targetMap,
 	)
+
+	e.sendRecoveredDeliveries(
+		ctx, webhookDB, deliveries, webhookID,
+		targetMap, settled,
+	)
+}
+
+// reconcileDelivered finds the deliveries in a recovered batch that
+// already have a successful DeliveryResult, marks them delivered, and
+// returns their ids so the caller does not send them a second time.
+//
+// This is the state the engine previously had no way to represent. A
+// delivery is left in a non-terminal state by a failed bookkeeping
+// write, and that covers two different histories: nothing was ever
+// sent, or the send reached the receiver and only the status write
+// failed. Re-sending was the sole option, so every stranded row
+// produced a duplicate at the receiver and an event log that recorded
+// one attempt for two POSTs. A successful result row distinguishes
+// them: it is written before the status, so its presence means the
+// wire I/O happened and was recorded, and all that is missing is the
+// status.
+//
+// Every recovery path runs this, not only the pending one. A delivery
+// abandoned at retrying can hold a successful result just as a pending
+// one can — a second attempt that reached the receiver and whose status
+// write then failed sits at retrying with success recorded — and
+// re-sending it is the same duplicate.
+//
+// Deliveries whose result row itself never landed are not in the
+// returned set and are re-sent, recorded as the further attempt they
+// are. That is honest at-least-once delivery rather than a silent
+// duplicate.
+func (e *Engine) reconcileDelivered(
+	webhookDB *gorm.DB,
+	webhookID string,
+	deliveries []database.Delivery,
+	targetMap map[string]database.Target,
+) map[string]struct{} {
+	settled := make(map[string]struct{})
+
+	if len(deliveries) == 0 {
+		return settled
+	}
+
+	ids := make([]string, 0, len(deliveries))
+	for i := range deliveries {
+		ids = append(ids, deliveries[i].ID)
+	}
+
+	var deliveredIDs []string
+
+	err := webhookDB.
+		Model(&database.DeliveryResult{}).
+		Where(
+			"delivery_id IN ? AND success = ?", ids, true,
+		).
+		Distinct().
+		Pluck("delivery_id", &deliveredIDs).Error
+	if err != nil {
+		// Every delivery stays out of the settled set, so the batch
+		// is re-sent exactly as it was before this check existed.
+		// That is the safe direction: a duplicate delivery beats
+		// declaring a delivery successful on a query that failed.
+		e.log.Error(
+			"failed to query successful delivery results; "+
+				"pending deliveries will be re-sent",
+			"webhook_id", webhookID,
+			"error", err,
+		)
+
+		return settled
+	}
+
+	for _, id := range deliveredIDs {
+		settled[id] = struct{}{}
+	}
+
+	if len(settled) == 0 {
+		return settled
+	}
+
+	e.log.Info(
+		"settling recovered deliveries that already succeeded",
+		"webhook_id", webhookID,
+		"count", len(settled),
+	)
+
+	for i := range deliveries {
+		if _, ok := settled[deliveries[i].ID]; !ok {
+			continue
+		}
+
+		// A delivery the engine is working on right now settles
+		// itself; writing over it from here would race that worker.
+		if !e.inflight.retainIdle(deliveries[i].ID) {
+			delete(settled, deliveries[i].ID)
+
+			continue
+		}
+
+		e.settleStatus(
+			webhookDB,
+			&deliveries[i],
+			targetMap[deliveries[i].TargetID].Type,
+			database.DeliveryStatusDelivered,
+		)
+
+		e.inflight.release(deliveries[i].ID)
+	}
+
+	return settled
 }
 
 func (e *Engine) retrySweep(ctx context.Context) {
@@ -722,6 +939,11 @@ func (e *Engine) sweepWebhookRetries(
 		return
 	}
 
+	settled := e.reconcileDelivered(
+		webhookDB, webhookID, retrying,
+		e.loadTargetMap(retrying),
+	)
+
 	for i := range retrying {
 		select {
 		case <-ctx.Done():
@@ -729,10 +951,70 @@ func (e *Engine) sweepWebhookRetries(
 		default:
 		}
 
+		if _, ok := settled[retrying[i].ID]; ok {
+			continue
+		}
+
 		e.sweepSingleRetry(
 			webhookDB, webhookID, &retrying[i],
 		)
 	}
+
+	e.sweepWebhookPending(ctx, webhookDB, webhookID)
+}
+
+// sweepWebhookPending recovers deliveries stranded at pending.
+//
+// A delivery is created pending and leaves that state only when its
+// outcome is written, so a pending row the engine does not own is one
+// whose bookkeeping write failed — the state that used to sit there
+// until a restart, and then produce a duplicate at the receiver. The
+// sweep gives it the same reconcile-then-dispatch treatment restart
+// recovery gets, so it costs a minute rather than an operator
+// noticing.
+//
+// What keeps the sweep off live work is ownership, checked per
+// delivery in takeForRedispatch, not the age bound in this query.
+// A delivery waiting in deliveryCh is pending and arbitrarily old —
+// the channel holds 10000 tasks and 10 workers drain it — so
+// reasoning from the row's age alone re-sends it. See inflight.go.
+func (e *Engine) sweepWebhookPending(
+	ctx context.Context,
+	webhookDB *gorm.DB,
+	webhookID string,
+) {
+	var pending []database.Delivery
+
+	err := webhookDB.
+		Where(
+			"status = ? AND updated_at < ?",
+			database.DeliveryStatusPending,
+			time.Now().Add(-pendingSweepMinAge),
+		).
+		Limit(pendingSweepBatch).
+		Find(&pending).Error
+	if err != nil {
+		e.log.Error(
+			"retry sweep: "+
+				"failed to query pending deliveries",
+			"webhook_id", webhookID,
+			"error", err,
+		)
+
+		return
+	}
+
+	if len(pending) == 0 {
+		return
+	}
+
+	e.log.Info(
+		"retry sweep: recovering stranded pending deliveries",
+		"webhook_id", webhookID,
+		"count", len(pending),
+	)
+
+	e.recoverPendingBatch(ctx, webhookDB, webhookID, pending)
 }
 
 // sweepSingleRetry re-enqueues an orphaned retrying delivery
@@ -789,17 +1071,20 @@ func (e *Engine) sweepSingleRetry(
 		d, webhookID, &event, &target, attemptNum+1,
 	)
 
-	select {
-	case e.retryCh <- task:
-		e.log.Info(
-			"retry sweep: "+
-				"recovered orphaned retrying delivery",
-			"delivery_id", d.ID,
-			"webhook_id", webhookID,
-			"attempt", attemptNum+1,
-		)
-	default:
+	if !e.redispatch(
+		e.retryCh, webhookDB, task,
+		database.DeliveryStatusRetrying,
+	) {
+		return
 	}
+
+	e.log.Info(
+		"retry sweep: "+
+			"recovered orphaned retrying delivery",
+		"delivery_id", d.ID,
+		"webhook_id", webhookID,
+		"attempt", attemptNum+1,
+	)
 }
 
 // failUnretryableRetry terminally fails an orphaned retrying
@@ -822,6 +1107,16 @@ func (e *Engine) failUnretryableRetry(
 	d *database.Delivery,
 	target *database.Target,
 ) {
+	// Terminal, and reached from the recovery paths, so it takes
+	// ownership like every other write they make: a delivery the
+	// engine is still attempting must not be failed underneath the
+	// worker running it.
+	if !e.inflight.retainIdle(d.ID) {
+		return
+	}
+
+	defer e.inflight.release(d.ID)
+
 	e.log.Warn(
 		"failing orphaned retrying delivery: target "+
 			"type no longer supports retries",
@@ -839,7 +1134,7 @@ func (e *Engine) failUnretryableRetry(
 		target.Type,
 	)
 
-	e.recordResult(
+	err := e.recordResult(
 		webhookDB,
 		d,
 		e.countAttempts(webhookDB, d.ID)+1,
@@ -849,6 +1144,11 @@ func (e *Engine) failUnretryableRetry(
 		reason,
 		0,
 	)
+	if err != nil {
+		e.bookkeepingFailed(d, err)
+
+		return
+	}
 
 	// The type is passed rather than assigned onto d: the delivery
 	// is loaded here without its target relation, and populating
@@ -856,7 +1156,7 @@ func (e *Engine) failUnretryableRetry(
 	// whole target row — plaintext config, which for a slack target
 	// is the credential — into the per-webhook event database. See
 	// https://git.eeqj.de/sneak/webhooker/issues/206.
-	e.updateDeliveryStatus(
+	e.settleStatus(
 		webhookDB, d, target.Type,
 		database.DeliveryStatusFailed,
 	)
@@ -878,7 +1178,7 @@ func (e *Engine) processDelivery(
 			"type", d.Target.Type,
 		)
 
-		e.updateDeliveryStatus(
+		e.settleStatus(
 			webhookDB, d, d.Target.Type,
 			database.DeliveryStatusFailed,
 		)
@@ -910,6 +1210,14 @@ func (e *Engine) observeAttempt(
 // recordResult persists a DeliveryResult row describing a
 // single attempt. It is a cross-target helper the targets
 // call.
+//
+// It returns its error rather than swallowing it. A DeliveryResult
+// row is the only record that an attempt happened at all, so a
+// caller that ignored a failed write would go on to mark the
+// delivery delivered — leaving the event log claiming one attempt
+// for a receiver that got two. Every caller must instead stop
+// advancing the delivery's status and let it stay in the
+// non-terminal state it already holds; see bookkeepingFailed.
 func (e *Engine) recordResult(
 	webhookDB *gorm.DB,
 	d *database.Delivery,
@@ -918,7 +1226,7 @@ func (e *Engine) recordResult(
 	statusCode int,
 	respBody, errMsg string,
 	durationMs int64,
-) {
+) error {
 	result := &database.DeliveryResult{
 		DeliveryID:   d.ID,
 		AttemptNum:   attemptNum,
@@ -931,12 +1239,44 @@ func (e *Engine) recordResult(
 
 	err := webhookDB.Create(result).Error
 	if err != nil {
-		e.log.Error(
-			"failed to record delivery result",
-			"delivery_id", d.ID,
-			"error", err,
+		return fmt.Errorf(
+			"recording delivery result for %s: %w", d.ID, err,
 		)
 	}
+
+	return nil
+}
+
+// bookkeepingFailed reports that a delivery's own record of what
+// happened could not be written, and deliberately writes nothing in
+// response.
+//
+// Leaving the row alone is the whole point. A delivery is created
+// pending and only ever leaves that state through
+// updateDeliveryStatus, so a delivery whose bookkeeping write failed
+// is still pending or retrying — the two non-terminal states, per
+// DeliveryStatus.Terminal — and both are swept and recovered. Writing
+// anything here would need the very database that just refused a
+// write, and would be one more thing to fail; not writing cannot.
+//
+// The cost is honest at-least-once behaviour: a send that reached the
+// receiver but whose result row did not land is attempted again, and
+// recorded as the further attempt it is. What no longer happens is the
+// silent duplicate — a second POST the event log denies ever
+// occurred. Where the result row *did* land and only the status write
+// failed, reconcileDelivered settles the row without re-sending.
+func (e *Engine) bookkeepingFailed(
+	d *database.Delivery, err error,
+) {
+	e.log.Error(
+		"delivery bookkeeping write failed; leaving delivery "+
+			"in a recoverable state",
+		"delivery_id", d.ID,
+		"event_id", d.EventID,
+		"target_id", d.TargetID,
+		"status", d.Status,
+		"error", err,
+	)
 }
 
 // updateDeliveryStatus persists a new status for a delivery.
@@ -952,26 +1292,51 @@ func (e *Engine) recordResult(
 //
 // The counter moves only after the row is written, so a transition
 // the database rejected is not claimed as an outcome that happened.
+// For the same reason the error is returned rather than logged and
+// dropped: a delivery whose status write failed has not reached that
+// status, and its caller must not act as though it had.
 func (e *Engine) updateDeliveryStatus(
 	webhookDB *gorm.DB,
 	d *database.Delivery,
 	targetType database.TargetType,
 	status database.DeliveryStatus,
-) {
+) error {
 	err := webhookDB.Model(d).
 		Update("status", status).Error
 	if err != nil {
-		e.log.Error(
-			"failed to update delivery status",
-			"delivery_id", d.ID,
-			"status", status,
-			"error", err,
+		return fmt.Errorf(
+			"updating delivery %s to status %s: %w",
+			d.ID, status, err,
 		)
-
-		return
 	}
 
-	e.mtr.DeliveryStatusChanged(targetType, status)
+	// An empty type means the target row is gone — a delivery being
+	// settled long after its target was deleted. The row still has to
+	// be settled, but the counter is left alone rather than given a
+	// series labelled with the empty string.
+	if targetType != "" {
+		e.mtr.DeliveryStatusChanged(targetType, status)
+	}
+
+	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
+// statement rather than four lines of identical error handling.
+func (e *Engine) settleStatus(
+	webhookDB *gorm.DB,
+	d *database.Delivery,
+	targetType database.TargetType,
+	status database.DeliveryStatus,
+) {
+	err := e.updateDeliveryStatus(
+		webhookDB, d, targetType, status,
+	)
+	if err != nil {
+		e.bookkeepingFailed(d, err)
+	}
 }
 
 func truncate(s string, maxLen int) string {
@@ -1065,6 +1430,184 @@ func (e *Engine) countAttempts(
 	return int(resultCount)
 }
 
+// takeForRedispatch decides whether a recovered delivery may be sent
+// again, and takes it if so. It is the single gate every re-dispatch
+// path goes through, and it asks two separate questions in order.
+//
+// First, does the engine already own this delivery? Ownership is
+// exact and mutually exclusive, so a delivery queued, being attempted,
+// or waiting out a retry backoff is refused here, and two dispatchers
+// racing for the same delivery cannot both win. See inflight.go.
+//
+// Second, is the row still in the status that made it eligible? The
+// batch was read some time ago and a worker may have settled a row
+// since. The check is a conditional update rather than a read so the
+// answer cannot go stale between asking and acting.
+//
+// Stamping updated_at is the same statement, and it is a cadence
+// control rather than a claim: the pending sweep selects on that
+// column, so a delivery handed out now is not selected again on the
+// next tick a minute later but after pendingSweepMinAge. A delivery
+// the database refuses to settle is therefore retried on that
+// interval instead of every tick.
+//
+// A failed write is a refusal. It means the database is not accepting
+// writes, which is the condition that stranded the delivery in the
+// first place; an attempt that cannot be recorded is exactly the
+// unlogged duplicate this is all here to prevent.
+//
+// The caller must release ownership if it then fails to queue the
+// task.
+func (e *Engine) takeForRedispatch(
+	webhookDB *gorm.DB,
+	deliveryID string,
+	eligible database.DeliveryStatus,
+) bool {
+	if !e.inflight.retainIdle(deliveryID) {
+		return false
+	}
+
+	res := webhookDB.
+		Model(&database.Delivery{}).
+		Where(
+			"id = ? AND status = ?", deliveryID, eligible,
+		).
+		UpdateColumn("updated_at", time.Now())
+
+	if res.Error != nil {
+		e.log.Error(
+			"failed to mark delivery for re-dispatch; "+
+				"leaving it for a later sweep",
+			"delivery_id", deliveryID,
+			"error", res.Error,
+		)
+		e.inflight.release(deliveryID)
+
+		return false
+	}
+
+	if res.RowsAffected != 1 {
+		// Settled underneath us between the query and here.
+		e.inflight.release(deliveryID)
+
+		return false
+	}
+
+	return true
+}
+
+// queueRecovered puts an owned delivery's task on a worker channel,
+// dropping the ownership the gate took if it does not fit.
+func (e *Engine) queueRecovered(
+	ch chan<- Task, task Task,
+) bool {
+	select {
+	case ch <- task:
+		return true
+	default:
+		e.inflight.release(task.DeliveryID)
+		e.log.Warn(
+			"worker channel full during recovery; "+
+				"delivery will be recovered by a later sweep",
+			"delivery_id", task.DeliveryID,
+			"webhook_id", task.WebhookID,
+		)
+
+		return false
+	}
+}
+
+// redispatch hands a recovered delivery to a worker channel through
+// takeForRedispatch, and reports whether the task was queued.
+func (e *Engine) redispatch(
+	ch chan<- Task,
+	webhookDB *gorm.DB,
+	task Task,
+	eligible database.DeliveryStatus,
+) bool {
+	if !e.takeForRedispatch(
+		webhookDB, task.DeliveryID, eligible,
+	) {
+		return false
+	}
+
+	return e.queueRecovered(ch, task)
+}
+
+// rescheduleRecovered hands an orphaned retrying delivery back to the
+// retry timer, through the same gate. It reports whether the delivery
+// was rescheduled.
+//
+// The reference taken by the gate is dropped as soon as ScheduleRetry
+// has taken its own, which it does before returning: what keeps the
+// delivery owned through the backoff window is ScheduleRetry's
+// reference, not this one.
+func (e *Engine) rescheduleRecovered(
+	webhookDB *gorm.DB, task Task, delay time.Duration,
+) bool {
+	if !e.takeForRedispatch(
+		webhookDB, task.DeliveryID,
+		database.DeliveryStatusRetrying,
+	) {
+		return false
+	}
+
+	defer e.inflight.release(task.DeliveryID)
+
+	e.ScheduleRetry(task, delay)
+
+	return true
+}
+
+// countAttemptsBatch counts the recorded attempts of every delivery
+// in a batch with one grouped query, keyed by delivery id. Deliveries
+// with no attempts are simply absent from the result, which reads back
+// as the zero this caller wants.
+//
+// One query rather than one per delivery: this runs on the recovery
+// path, which is a burst of writes against a database that has just
+// been under enough contention to strand these rows in the first
+// place. See https://git.eeqj.de/sneak/webhooker/issues/256.
+func (e *Engine) countAttemptsBatch(
+	webhookDB *gorm.DB, deliveries []database.Delivery,
+) map[string]int {
+	counts := make(map[string]int, len(deliveries))
+
+	if len(deliveries) == 0 {
+		return counts
+	}
+
+	ids := make([]string, 0, len(deliveries))
+	for i := range deliveries {
+		ids = append(ids, deliveries[i].ID)
+	}
+
+	// One delivery id per recorded attempt, tallied here rather than
+	// grouped in SQL: internal/gormlog forbids (*gorm.DB).Scan, which
+	// a GROUP BY into a struct would need, and an attempt row per
+	// delivery is bounded by the target's MaxRetries.
+	var attemptIDs []string
+
+	err := webhookDB.
+		Model(&database.DeliveryResult{}).
+		Where("delivery_id IN ?", ids).
+		Pluck("delivery_id", &attemptIDs).Error
+	if err != nil {
+		e.log.Error(
+			"failed to count delivery attempts for recovery",
+			"error", err,
+		)
+
+		return counts
+	}
+
+	for _, id := range attemptIDs {
+		counts[id]++
+	}
+
+	return counts
+}
+
 func (e *Engine) loadEvent(
 	webhookDB *gorm.DB, eventID string,
 ) (database.Event, error) {
@@ -1132,6 +1675,10 @@ func buildRecoveryTask(
 func (e *Engine) loadTargetMap(
 	deliveries []database.Delivery,
 ) map[string]database.Target {
+	if len(deliveries) == 0 {
+		return nil
+	}
+
 	seen := make(map[string]bool)
 
 	targetIDs := make([]string, 0, len(deliveries))
@@ -1168,12 +1715,33 @@ func (e *Engine) loadTargetMap(
 	return targetMap
 }
 
+// sendRecoveredDeliveries re-dispatches pending deliveries, skipping
+// the ids in settled — those already reached their receiver and have
+// been marked delivered by reconcileDelivered.
+//
+// The skip and takeForRedispatch's status check answer different
+// questions and neither replaces the other. This one is "did this
+// delivery already succeed", which is what settles the row to
+// delivered instead of sending it, and which is the only thing that
+// keeps the retrying paths from terminally failing a delivery that
+// reconcile just settled. The status check is "is the row still what
+// the batch query said it was", which catches a worker settling it to
+// anything at all in between.
 func (e *Engine) sendRecoveredDeliveries(
 	ctx context.Context,
+	webhookDB *gorm.DB,
 	deliveries []database.Delivery,
 	webhookID string,
 	targetMap map[string]database.Target,
+	settled map[string]struct{},
 ) {
+	// The attempt number continues each delivery's own history
+	// rather than restarting at 1. A recovered delivery may already
+	// have recorded attempts, and numbering the next one 1 again
+	// both collides in the event log and hands the retry path a
+	// backoff computed from the wrong attempt.
+	attempts := e.countAttemptsBatch(webhookDB, deliveries)
+
 	for i := range deliveries {
 		select {
 		case <-ctx.Done():
@@ -1181,6 +1749,10 @@ func (e *Engine) sendRecoveredDeliveries(
 		default:
 		}
 
+		if _, ok := settled[deliveries[i].ID]; ok {
+			continue
+		}
+
 		target, ok := targetMap[deliveries[i].TargetID]
 		if !ok {
 			e.log.Error(
@@ -1192,22 +1764,40 @@ func (e *Engine) sendRecoveredDeliveries(
 			continue
 		}
 
+		if !e.takeForRedispatch(
+			webhookDB, deliveries[i].ID,
+			database.DeliveryStatusPending,
+		) {
+			continue
+		}
+
+		// The body is read here, one delivery at a time and only for
+		// deliveries that are actually being sent, rather than
+		// preloaded across the whole batch. A batch is up to
+		// pendingSweepBatch rows at up to the 1 MB ingest cap, and
+		// most of a sweep's batch is refused by the gate above — so
+		// preloading would hold hundreds of megabytes per webhook per
+		// tick to build tasks it then discards.
+		event, err := e.loadEvent(
+			webhookDB, deliveries[i].EventID,
+		)
+		if err != nil {
+			e.log.Error(
+				"failed to load event for recovered delivery",
+				"delivery_id", deliveries[i].ID,
+				"event_id", deliveries[i].EventID,
+				"error", err,
+			)
+			e.inflight.release(deliveries[i].ID)
+
+			continue
+		}
+
 		task := buildRecoveryTask(
-			&deliveries[i], webhookID,
-			&deliveries[i].Event, &target, 1,
+			&deliveries[i], webhookID, &event, &target,
+			attempts[deliveries[i].ID]+1,
 		)
 
-		select {
-		case e.deliveryCh <- task:
-		default:
-			e.log.Warn(
-				"delivery channel full during "+
-					"recovery, remaining deliveries "+
-					"will be recovered on next restart",
-				"delivery_id", deliveries[i].ID,
-			)
-
-			return
-		}
+		e.queueRecovered(e.deliveryCh, task)
 	}
 }

internal/delivery/engine_integration_test.go

@@ -2,7 +2,6 @@ package delivery_test
 
 import (
 	"context"
-	"database/sql"
 	"encoding/json"
 	"fmt"
 	"io"
@@ -70,11 +69,12 @@ func iMainDB(t *testing.T) *gorm.DB {
 		t.TempDir(), "main-test.db",
 	)
 
-	dsn := fmt.Sprintf(
-		"file:%s?cache=shared&mode=rwc", dbPath,
+	// Opened the way the service opens the main database, so these
+	// tests cannot pass against journal and locking settings
+	// production does not use.
+	sqlDB, err := database.OpenSQLite(
+		dbPath, database.SQLiteModeCreate,
 	)
-
-	sqlDB, err := sql.Open("sqlite", dsn)
 	require.NoError(t, err)
 
 	t.Cleanup(func() { _ = sqlDB.Close() })

internal/delivery/engine_test.go

@@ -3,7 +3,6 @@ package delivery_test
 import (
 	"bytes"
 	"context"
-	"database/sql"
 	"encoding/json"
 	"fmt"
 	"log/slog"
@@ -37,11 +36,12 @@ func testWebhookDB(t *testing.T) *gorm.DB {
 		t.TempDir(), "events-test.db",
 	)
 
-	dsn := fmt.Sprintf(
-		"file:%s?cache=shared&mode=rwc", dbPath,
+	// Opened the way the service opens a per-webhook database, so
+	// these tests cannot pass against journal and locking settings
+	// production does not use.
+	sqlDB, err := database.OpenSQLite(
+		dbPath, database.SQLiteModeCreate,
 	)
-
-	sqlDB, err := sql.Open("sqlite", dsn)
 	require.NoError(t, err)
 
 	t.Cleanup(func() { _ = sqlDB.Close() })

internal/delivery/export_test.go

@@ -33,6 +33,11 @@ const (
 	// response is written against this number, so a test has to
 	// be able to name it.
 	ExportMaxBodyLog = maxBodyLog
+
+	// ExportPendingSweepMinAge is how long a delivery must sit at
+	// pending before the sweep treats it as stranded. A test has to
+	// name it to age a row past the bound.
+	ExportPendingSweepMinAge = pendingSweepMinAge
 )
 
 // ExportIsBlockedIP exposes isBlockedIP for testing.
@@ -286,6 +291,26 @@ func (e *Engine) ExportWedgeWorker(release <-chan struct{}) {
 	})
 }
 
+// ExportInflightHeld reports how many deliveries the engine currently
+// owns, so a test can prove ownership is released rather than leaked.
+func (e *Engine) ExportInflightHeld() int {
+	return e.inflight.held()
+}
+
+// ExportRetainDelivery takes the first reference on a delivery, as the
+// queueing side does. It lets a test put a delivery into the state a
+// worker or a full channel would, without running the pool.
+func (e *Engine) ExportRetainDelivery(deliveryID string) bool {
+	return e.inflight.retainIdle(deliveryID)
+}
+
+// ExportRecoverRetryingDeliveries exposes recoverRetryingDeliveries.
+func (e *Engine) ExportRecoverRetryingDeliveries(
+	webhookDB *gorm.DB, webhookID string,
+) {
+	e.recoverRetryingDeliveries(webhookDB, webhookID)
+}
+
 // ExportDeliveryCh returns the delivery channel.
 func (e *Engine) ExportDeliveryCh() chan Task {
 	return e.deliveryCh

internal/delivery/inflight.go

@@ -0,0 +1,110 @@
+package delivery
+
+import "sync"
+
+// inflightSet records which deliveries the engine currently owns.
+//
+// A delivery is owned from the moment a task for it is handed to a
+// channel or to a retry timer until the engine has no further plan for
+// it in memory. Restart recovery and both arms of the periodic sweep
+// re-dispatch only deliveries the set does not hold, which is what
+// makes them exact rather than a guess about how long a row has sat at
+// pending.
+//
+// This replaces reasoning from timestamps. A delivery's row says
+// pending from creation until its outcome is written, which covers
+// four different situations — never dispatched, waiting in a channel,
+// being attempted right now, and genuinely stranded — and no column
+// distinguishes them. Only the engine knows which, and it knows
+// exactly. `deliveryChannelSize` is 10000 against 10 workers, so a
+// perfectly healthy delivery can wait far longer than any age bound
+// worth setting before its attempt even begins; an age bound alone
+// re-sends it. See
+// https://git.eeqj.de/sneak/webhooker/issues/256.
+//
+// In-memory state is sufficient because a data directory admits one
+// process: internal/datadir takes an flock on it at startup and a
+// second instance refuses to run. Deliveries owned by a process that
+// died are not in any successor's set, and restart recovery is what
+// picks those up.
+//
+// References are counted rather than held as a plain set because
+// ownership outlives the worker that took it. A target that schedules
+// a retry from inside Deliver adds a reference while the worker still
+// holds one, so the delivery stays owned across the gap between the
+// worker returning and the timer firing — the window in which a sweep
+// would otherwise find the row at retrying and send it again.
+//
+// The zero value is ready to use, and the Engine holds one by value.
+// That is deliberate: an engine built by a constructor that forgot to
+// initialise this would not refuse to re-dispatch anything, and the
+// symptom would be duplicate deliveries rather than a failure anybody
+// notices.
+type inflightSet struct {
+	mu  sync.Mutex
+	ids map[string]int
+}
+
+// retain adds a reference to a delivery the caller already knows the
+// engine owns, so that ownership survives the current holder letting
+// go. It cannot fail.
+func (s *inflightSet) retain(deliveryID string) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	if s.ids == nil {
+		s.ids = make(map[string]int)
+	}
+
+	s.ids[deliveryID]++
+}
+
+// retainIdle takes the first reference on a delivery, and reports
+// whether it got it. It fails when the engine already owns the
+// delivery, which is what makes two claimants — restart recovery and
+// the sweep run concurrently, or two sweep arms — mutually exclusive
+// rather than merely atomic.
+func (s *inflightSet) retainIdle(deliveryID string) bool {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	if s.ids[deliveryID] > 0 {
+		return false
+	}
+
+	if s.ids == nil {
+		s.ids = make(map[string]int)
+	}
+
+	s.ids[deliveryID] = 1
+
+	return true
+}
+
+// release drops one reference. The delivery becomes eligible for
+// re-dispatch again once the last one goes.
+func (s *inflightSet) release(deliveryID string) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	n := s.ids[deliveryID] - 1
+	if n <= 0 {
+		delete(s.ids, deliveryID)
+
+		return
+	}
+
+	s.ids[deliveryID] = n
+}
+
+// held reports how many deliveries the engine currently owns. It
+// exists so a test can assert that ownership is released rather than
+// leaked: a reference that is never dropped hides its delivery from
+// every sweep for the life of the process, which is the one way this
+// mechanism can fail silently.
+func (s *inflightSet) held() int {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	return len(s.ids)
+}

internal/delivery/inflight_test.go

@@ -0,0 +1,428 @@
+package delivery_test
+
+import (
+	"context"
+	"path/filepath"
+	"strings"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/google/uuid"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/delivery"
+)
+
+// These tests pin the rule that decides whether a delivery may be
+// handed back to a worker: the engine re-dispatches only what it does
+// not already own. Age alone is not that rule — a healthy delivery
+// waiting in a 10000-deep channel is old and must not be re-sent. See
+// https://git.eeqj.de/sneak/webhooker/issues/256.
+
+// fSweepSetup seeds the main database with the webhook row the sweep
+// enumerates, and returns the setup.
+func fSweepSetup(
+	t *testing.T, targetID, name string,
+) iSetup {
+	t.Helper()
+
+	s := newISetup(t)
+
+	iCreateTarget(t, s.MainDB, targetID,
+		s.WebhookID, name,
+		database.TargetTypeLog, "", 0,
+	)
+
+	require.NoError(t, s.MainDB.Create(&database.Webhook{
+		BaseModel: database.BaseModel{ID: s.WebhookID},
+		UserID:    uuid.New().String(),
+		Name:      name,
+	}).Error)
+
+	return s
+}
+
+// fDrain collects every task the engine has queued.
+//
+// Every caller drives the dispatch paths synchronously and has already
+// waited for them to return, so anything they queued is in the channel
+// by now. The short grace covers nothing but scheduler jitter, and is
+// kept small because one of these tests runs the drain forty times.
+func fDrain(e *delivery.Engine) []delivery.Task {
+	var out []delivery.Task
+
+	for {
+		select {
+		case task := <-e.ExportDeliveryCh():
+			out = append(out, task)
+		case task := <-e.ExportRetryCh():
+			out = append(out, task)
+		case <-time.After(25 * time.Millisecond):
+			return out
+		}
+	}
+}
+
+// TestArchiveHandleIsWAL closes the last gap in the durability
+// evidence: the main and per-webhook tiers each assert their journal
+// mode on a live handle, and the archive tier gets its settings from
+// the same code path but nothing checked the running file.
+func TestArchiveHandleIsWAL(t *testing.T) {
+	t.Parallel()
+
+	w := delivery.NewExportArchiveWriter(
+		filepath.Join(t.TempDir(), "archive-wal.db"),
+		archiveTestLogger(), 0,
+	)
+
+	require.NoError(t, w.Open(0))
+
+	var mode string
+
+	row := w.DB().Raw("pragma journal_mode").Row()
+	require.NoError(t, row.Scan(&mode))
+	assert.Equal(t, "wal", strings.ToLower(mode))
+
+	var busy string
+
+	row = w.DB().Raw("pragma busy_timeout").Row()
+	require.NoError(t, row.Scan(&busy))
+	assert.Equal(t, "10000", busy)
+}
+
+// TestSweepLeavesAQueuedDeliveryAlone is the case the age bound cannot
+// see. The delivery is queued and untouched, so its row is arbitrarily
+// old and still perfectly healthy; only ownership distinguishes it
+// from a stranded one.
+func TestSweepLeavesAQueuedDeliveryAlone(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "queued")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"queued":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+	rAgePending(t, s.WebhookDB, d.ID)
+
+	// Queued exactly as the receiver queues it, and never dequeued:
+	// no workers are running in this engine.
+	s.Engine.Notify([]delivery.Task{{
+		DeliveryID: d.ID,
+		EventID:    event.ID,
+		WebhookID:  s.WebhookID,
+		TargetID:   targetID,
+	}})
+
+	require.Equal(t, 1, s.Engine.ExportInflightHeld())
+
+	s.Engine.ExportSweepWebhookRetries(
+		context.Background(), s.WebhookID,
+	)
+
+	tasks := fDrain(s.Engine)
+	assert.Len(
+		t, tasks, 1,
+		"the sweep must not queue a delivery that is "+
+			"already waiting for a worker",
+	)
+}
+
+// TestRecoveryAndSweepDoNotDoubleDispatch drives the two entry points
+// the engine starts concurrently against one aged pending row. Before
+// ownership they both dispatched it.
+func TestRecoveryAndSweepDoNotDoubleDispatch(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "racing")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"racing":true}`,
+	)
+
+	ctx := context.Background()
+
+	for range 40 {
+		d := iSeedDelivery(
+			t, s.WebhookDB, event.ID, targetID,
+			database.DeliveryStatusPending,
+		)
+		rAgePending(t, s.WebhookDB, d.ID)
+
+		var wg sync.WaitGroup
+
+		wg.Go(func() {
+			s.Engine.ExportRecoverPendingDeliveries(
+				ctx, s.WebhookDB, s.WebhookID,
+			)
+		})
+		wg.Go(func() {
+			s.Engine.ExportSweepWebhookRetries(
+				ctx, s.WebhookID,
+			)
+		})
+		wg.Wait()
+
+		tasks := fDrain(s.Engine)
+		require.Len(
+			t, tasks, 1,
+			"delivery %s dispatched %d times",
+			d.ID, len(tasks),
+		)
+
+		// No worker runs in this engine, so the reference the winner
+		// took is never released and earlier iterations' deliveries
+		// stay owned — which is itself the property under test, since
+		// both paths see them on every subsequent pass.
+	}
+}
+
+// TestConcurrentClaimsOfOneDeliveryYieldOneOwner exercises the
+// exclusion directly, rather than arguing it from a SQL predicate.
+func TestConcurrentClaimsOfOneDeliveryYieldOneOwner(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	eng := newISetup(t).Engine
+	deliveryID := uuid.New().String()
+
+	var (
+		wg  sync.WaitGroup
+		mu  sync.Mutex
+		won int
+	)
+
+	for range 64 {
+		wg.Go(func() {
+			if eng.ExportRetainDelivery(deliveryID) {
+				mu.Lock()
+				won++
+				mu.Unlock()
+			}
+		})
+	}
+
+	wg.Wait()
+
+	assert.Equal(t, 1, won)
+	assert.Equal(t, 1, eng.ExportInflightHeld())
+}
+
+// TestOwnershipIsReleasedAfterDelivery guards the other direction: a
+// leaked reference hides a delivery from every sweep for the life of
+// the process.
+func TestOwnershipIsReleasedAfterDelivery(t *testing.T) {
+	t.Parallel()
+
+	s := newISetup(t)
+	targetID := uuid.New().String()
+
+	iCreateTarget(t, s.MainDB, targetID,
+		s.WebhookID, "released",
+		database.TargetTypeLog, "", 0,
+	)
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"released":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+
+	s.Engine.ExportStart()
+
+	defer func() {
+		require.NoError(
+			t, s.Engine.ExportStop(context.Background()),
+		)
+	}()
+
+	body := `{"released":true}`
+
+	s.Engine.Notify([]delivery.Task{{
+		DeliveryID:   d.ID,
+		EventID:      event.ID,
+		WebhookID:    s.WebhookID,
+		TargetID:     targetID,
+		TargetName:   "released",
+		TargetType:   database.TargetTypeLog,
+		Body:         &body,
+		EntrypointID: event.EntrypointID,
+	}})
+
+	iWaitForDelivered(t, s.WebhookDB, d.ID)
+
+	assert.Eventually(
+		t,
+		func() bool {
+			return s.Engine.ExportInflightHeld() == 0
+		},
+		2*time.Second, 20*time.Millisecond,
+		"the delivery stayed owned after it was delivered",
+	)
+}
+
+// TestRetryingRecoverySkipsASuccessfulResult is the retrying-side twin
+// of the pending reconcile. A second attempt that reached the receiver
+// and whose status write then failed sits at retrying holding a
+// successful result, and re-sending it is the same duplicate.
+func TestRetryingRecoverySkipsASuccessfulResult(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "retry-settled")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"retry":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusRetrying,
+	)
+	rSeedResult(t, s.WebhookDB, d.ID, 1, false)
+	rSeedResult(t, s.WebhookDB, d.ID, 2, true)
+
+	s.Engine.ExportRecoverRetryingDeliveries(
+		s.WebhookDB, s.WebhookID,
+	)
+
+	assert.Empty(
+		t, fDrain(s.Engine),
+		"a retrying delivery holding a successful result "+
+			"must not be sent again",
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, d.ID,
+		database.DeliveryStatusDelivered,
+	)
+}
+
+// TestRetryingSweepSkipsASuccessfulResult is the same rule on the
+// periodic sweep's retrying arm.
+func TestRetryingSweepSkipsASuccessfulResult(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "retry-swept")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"swept":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusRetrying,
+	)
+	rSeedResult(t, s.WebhookDB, d.ID, 1, false)
+	rSeedResult(t, s.WebhookDB, d.ID, 2, true)
+
+	s.Engine.ExportSweepWebhookRetries(
+		context.Background(), s.WebhookID,
+	)
+
+	assert.Empty(t, fDrain(s.Engine))
+
+	iAssertStatus(
+		t, s.WebhookDB, d.ID,
+		database.DeliveryStatusDelivered,
+	)
+
+	var attempts int64
+
+	require.NoError(t, s.WebhookDB.
+		Model(&database.DeliveryResult{}).
+		Where("delivery_id = ?", d.ID).
+		Count(&attempts).Error)
+	assert.Equal(
+		t, int64(2), attempts,
+		"settling must not invent an attempt",
+	)
+}
+
+// TestScheduledRetryIsNotSweptDuringBackoff closes the window between
+// a target scheduling a retry and the timer firing. The row says
+// retrying and nothing is running, which is exactly what an orphaned
+// retry looks like from the database.
+func TestScheduledRetryIsNotSweptDuringBackoff(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "backoff")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"backoff":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusRetrying,
+	)
+
+	s.Engine.ExportScheduleRetry(delivery.Task{
+		DeliveryID: d.ID,
+		EventID:    event.ID,
+		WebhookID:  s.WebhookID,
+		TargetID:   targetID,
+		AttemptNum: 2,
+	}, time.Hour)
+
+	require.Equal(t, 1, s.Engine.ExportInflightHeld())
+
+	s.Engine.ExportSweepWebhookRetries(
+		context.Background(), s.WebhookID,
+	)
+
+	assert.Empty(
+		t, fDrain(s.Engine),
+		"the sweep must not duplicate a retry that is "+
+			"already scheduled",
+	)
+}
+
+// TestRedispatchStampsTheRow pins the cadence control: a stranded
+// delivery that has just been handed out is not selected again by the
+// next tick a minute later.
+func TestRedispatchStampsTheRow(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "stamped")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"stamped":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+	rAgePending(t, s.WebhookDB, d.ID)
+
+	ctx := context.Background()
+
+	s.Engine.ExportSweepWebhookRetries(ctx, s.WebhookID)
+	require.Len(t, fDrain(s.Engine), 1)
+
+	var row database.Delivery
+
+	require.NoError(t, s.WebhookDB.
+		First(&row, "id = ?", d.ID).Error)
+	assert.WithinDuration(
+		t, time.Now(), row.UpdatedAt, time.Minute,
+		"a re-dispatched delivery must be stamped so the "+
+			"next tick does not select it again",
+	)
+}

internal/delivery/queue_depth_gormlog_test.go

@@ -3,8 +3,6 @@ package delivery_test
 import (
 	"bytes"
 	"context"
-	"database/sql"
-	"fmt"
 	"log/slog"
 	"net/http"
 	"path/filepath"
@@ -54,12 +52,10 @@ func (q *qdSyncBuf) String() string {
 func qdMainDB(t *testing.T, log *slog.Logger) *gorm.DB {
 	t.Helper()
 
-	dsn := fmt.Sprintf(
-		"file:%s?cache=shared&mode=rwc",
+	sqlDB, err := database.OpenSQLite(
 		filepath.Join(t.TempDir(), "main-gormlog.db"),
+		database.SQLiteModeCreate,
 	)
-
-	sqlDB, err := sql.Open("sqlite", dsn)
 	require.NoError(t, err)
 
 	t.Cleanup(func() { _ = sqlDB.Close() })

internal/delivery/recovery_durability_test.go

@@ -0,0 +1,378 @@
+package delivery_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"sync/atomic"
+	"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"
+	"sneak.berlin/go/webhooker/internal/delivery"
+)
+
+// These tests cover the delivery half of
+// https://git.eeqj.de/sneak/webhooker/issues/256: a delivery that
+// reached its receiver but whose bookkeeping write failed used to be
+// left at pending and re-sent on the next restart, giving the receiver
+// a second copy while the event log recorded one attempt.
+
+// rSeedResult records a DeliveryResult against a delivery, standing in
+// for the attempt row the send path writes before the status.
+func rSeedResult(
+	t *testing.T,
+	db *gorm.DB,
+	deliveryID string,
+	attemptNum int,
+	success bool,
+) {
+	t.Helper()
+
+	require.NoError(t, db.Create(&database.DeliveryResult{
+		DeliveryID: deliveryID,
+		AttemptNum: attemptNum,
+		Success:    success,
+	}).Error)
+}
+
+// rAgePending backdates a delivery past the sweep's age bound, which is
+// what separates a stranded delivery from one a worker still holds.
+func rAgePending(
+	t *testing.T, db *gorm.DB, deliveryID string,
+) {
+	t.Helper()
+
+	old := time.Now().Add(
+		-2 * delivery.ExportPendingSweepMinAge,
+	)
+
+	require.NoError(t, db.Model(&database.Delivery{}).
+		Where("id = ?", deliveryID).
+		UpdateColumn("updated_at", old).Error)
+}
+
+func TestRecoverySkipsPendingWithSuccessfulResult(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	s := newISetup(t)
+	targetID := uuid.New().String()
+
+	iCreateTarget(t, s.MainDB, targetID,
+		s.WebhookID, "already-delivered",
+		database.TargetTypeLog, "", 0,
+	)
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"delivered":true}`,
+	)
+
+	// The delivery whose send succeeded and whose result row landed:
+	// only the status write failed, so it sits at pending.
+	done := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+	rSeedResult(t, s.WebhookDB, done.ID, 1, true)
+
+	// A delivery that was genuinely never attempted.
+	fresh := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+
+	s.Engine.ExportRecoverPendingDeliveries(
+		context.Background(), s.WebhookDB, s.WebhookID,
+	)
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		assert.Equal(
+			t, fresh.ID, task.DeliveryID,
+			"only the unattempted delivery may be re-sent",
+		)
+	case <-time.After(2 * time.Second):
+		t.Fatal("expected the unattempted delivery")
+	}
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		t.Fatalf(
+			"re-sent an already delivered delivery: %s",
+			task.DeliveryID,
+		)
+	case <-time.After(200 * time.Millisecond):
+	}
+
+	// It is settled rather than merely skipped: leaving it pending
+	// would strand it again on the next sweep.
+	iAssertStatus(
+		t, s.WebhookDB, done.ID,
+		database.DeliveryStatusDelivered,
+	)
+}
+
+// TestRecoveryContinuesTheAttemptNumbering pins the audit trail: a
+// recovered delivery that already recorded two attempts is re-sent as
+// attempt three, not as attempt one again.
+func TestRecoveryContinuesTheAttemptNumbering(t *testing.T) {
+	t.Parallel()
+
+	s := newISetup(t)
+	targetID := uuid.New().String()
+
+	iCreateTarget(t, s.MainDB, targetID,
+		s.WebhookID, "numbering",
+		database.TargetTypeLog, "", 0,
+	)
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"numbering":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+
+	rSeedResult(t, s.WebhookDB, d.ID, 1, false)
+	rSeedResult(t, s.WebhookDB, d.ID, 2, false)
+
+	s.Engine.ExportRecoverPendingDeliveries(
+		context.Background(), s.WebhookDB, s.WebhookID,
+	)
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		assert.Equal(t, d.ID, task.DeliveryID)
+		assert.Equal(t, 3, task.AttemptNum)
+	case <-time.After(2 * time.Second):
+		t.Fatal("expected the delivery to be recovered")
+	}
+}
+
+// TestSweepRecoversStrandedPending is the half that removes the
+// restart requirement: a delivery left at pending is picked up by the
+// periodic sweep.
+func TestSweepRecoversStrandedPending(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "stranded")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"stranded":true}`,
+	)
+
+	stranded := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+	rAgePending(t, s.WebhookDB, stranded.ID)
+
+	// A delivery a worker may still be holding: young, and therefore
+	// none of the sweep's business.
+	inFlight := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+
+	s.Engine.ExportSweepWebhookRetries(
+		context.Background(), s.WebhookID,
+	)
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		assert.Equal(t, stranded.ID, task.DeliveryID)
+	case <-time.After(2 * time.Second):
+		t.Fatal("expected the stranded delivery")
+	}
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		t.Fatalf(
+			"swept an in-flight delivery: %s",
+			task.DeliveryID,
+		)
+	case <-time.After(200 * time.Millisecond):
+	}
+
+	iAssertStatus(
+		t, s.WebhookDB, inFlight.ID,
+		database.DeliveryStatusPending,
+	)
+}
+
+// TestSweepClaimsAStrandedDeliveryOnlyOnce guards the repeat the sweep
+// would otherwise be: the row stays pending for as long as the attempt
+// runs, and a sweep a minute later must not send it a second time.
+func TestSweepClaimsAStrandedDeliveryOnlyOnce(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "claimed")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"claimed":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+	rAgePending(t, s.WebhookDB, d.ID)
+
+	ctx := context.Background()
+
+	s.Engine.ExportSweepWebhookRetries(ctx, s.WebhookID)
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		assert.Equal(t, d.ID, task.DeliveryID)
+	case <-time.After(2 * time.Second):
+		t.Fatal("expected the stranded delivery")
+	}
+
+	// The delivery is still pending — nothing has run it yet — but
+	// the claim must keep the next sweep off it.
+	iAssertStatus(
+		t, s.WebhookDB, d.ID,
+		database.DeliveryStatusPending,
+	)
+
+	s.Engine.ExportSweepWebhookRetries(ctx, s.WebhookID)
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		t.Fatalf(
+			"sent a claimed delivery again: %s",
+			task.DeliveryID,
+		)
+	case <-time.After(200 * time.Millisecond):
+	}
+}
+
+// TestSweepSettlesStrandedPendingWithoutResending is the sweep's own
+// version of the reconcile: a stranded delivery holding a successful
+// result is settled where it stands, and the receiver hears nothing.
+func TestSweepSettlesStrandedPendingWithoutResending(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "settled")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"settled":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+	rSeedResult(t, s.WebhookDB, d.ID, 1, true)
+	rAgePending(t, s.WebhookDB, d.ID)
+
+	s.Engine.ExportSweepWebhookRetries(
+		context.Background(), s.WebhookID,
+	)
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		t.Fatalf(
+			"re-sent a delivery that already succeeded: %s",
+			task.DeliveryID,
+		)
+	case <-time.After(200 * time.Millisecond):
+	}
+
+	iAssertStatus(
+		t, s.WebhookDB, d.ID,
+		database.DeliveryStatusDelivered,
+	)
+
+	var attempts int64
+
+	require.NoError(t, s.WebhookDB.
+		Model(&database.DeliveryResult{}).
+		Where("delivery_id = ?", d.ID).
+		Count(&attempts).Error)
+	assert.Equal(
+		t, int64(1), attempts,
+		"settling must not invent an attempt",
+	)
+}
+
+// TestFailedResultWriteLeavesDeliveryRecoverable is the rule the
+// targets now follow: a bookkeeping write that fails must not advance
+// the status, because pending and retrying are the states the sweeps
+// recover and delivered is a claim the database refused to record.
+func TestFailedResultWriteLeavesDeliveryRecoverable(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	s := newISetup(t)
+	targetID := uuid.New().String()
+
+	var hits atomic.Int64
+
+	ts := httptest.NewServer(http.HandlerFunc(
+		func(w http.ResponseWriter, _ *http.Request) {
+			hits.Add(1)
+			w.WriteHeader(http.StatusOK)
+		},
+	))
+	defer ts.Close()
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"unwritable":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+
+	// Drop the table the attempt row goes in, so the send succeeds
+	// and only the bookkeeping write fails.
+	require.NoError(
+		t,
+		s.WebhookDB.Exec("drop table delivery_results").Error,
+	)
+
+	full := &database.Delivery{
+		EventID:  event.ID,
+		TargetID: targetID,
+		Status:   database.DeliveryStatusPending,
+		Event:    event,
+		Target: database.Target{
+			Name:   "unwritable",
+			Type:   database.TargetTypeHTTP,
+			Config: iHTTPConfig(ts.URL),
+		},
+	}
+	full.ID = d.ID
+
+	s.Engine.ExportDeliverHTTP(
+		context.Background(), s.WebhookDB, full,
+		&delivery.Task{DeliveryID: d.ID, AttemptNum: 1},
+	)
+
+	assert.Equal(
+		t, int64(1), hits.Load(),
+		"the send itself must still happen",
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, d.ID,
+		database.DeliveryStatusPending,
+	)
+}

internal/delivery/target_database.go

@@ -58,12 +58,17 @@ func (t *databaseTarget) Deliver(
 			"error", err,
 		)
 
-		t.eng.recordResult(
+		recErr := t.eng.recordResult(
 			webhookDB, d, 1, false, 0, "",
 			err.Error(), elapsed.Milliseconds(),
 		)
+		if recErr != nil {
+			t.eng.bookkeepingFailed(d, recErr)
 
-		t.eng.updateDeliveryStatus(
+			return
+		}
+
+		t.eng.settleStatus(
 			webhookDB, d, d.Target.Type,
 			database.DeliveryStatusFailed,
 		)
@@ -71,12 +76,17 @@ func (t *databaseTarget) Deliver(
 		return
 	}
 
-	t.eng.recordResult(
+	recErr := t.eng.recordResult(
 		webhookDB, d, 1, true, 0, "", "",
 		elapsed.Milliseconds(),
 	)
+	if recErr != nil {
+		t.eng.bookkeepingFailed(d, recErr)
 
-	t.eng.updateDeliveryStatus(
+		return
+	}
+
+	t.eng.settleStatus(
 		webhookDB, d, d.Target.Type,
 		database.DeliveryStatusDelivered,
 	)

internal/delivery/target_database_archive.go

@@ -1,7 +1,6 @@
 package delivery
 
 import (
-	"database/sql"
 	"encoding/json"
 	"errors"
 	"fmt"
@@ -12,6 +11,7 @@ import (
 
 	"gorm.io/driver/sqlite"
 	"gorm.io/gorm"
+	"sneak.berlin/go/webhooker/internal/database"
 	"sneak.berlin/go/webhooker/internal/gormlog"
 )
 
@@ -30,13 +30,13 @@ const (
 	// path: open the archive file, creating it if missing, so a
 	// first write (or a write after the operator moved the file
 	// away) recreates it.
-	archiveModeCreate = "rwc"
+	archiveModeCreate = database.SQLiteModeCreate
 
 	// archiveModeExisting is the SQLite URI mode used by the idle
 	// sweep: open read-write but never create. A sweep must never
 	// conjure an empty archive file for a webhook that has a
 	// database target but has never received an event.
-	archiveModeExisting = "rw"
+	archiveModeExisting = database.SQLiteModeExisting
 )
 
 var (
@@ -273,9 +273,11 @@ func (w *archiveWriter) open(expiry time.Duration) error {
 func (w *archiveWriter) openMode(
 	mode string, expiry time.Duration,
 ) error {
-	dbURL := fmt.Sprintf("file:%s?mode=%s", w.path, mode)
-
-	sqlDB, err := sql.Open("sqlite", dbURL)
+	// Opened through database.OpenSQLite so an archive file carries
+	// the same WAL journaling, busy timeout, immediate-transaction
+	// locking, and pool bounds as every other database file. See
+	// internal/database/sqlite_open.go.
+	sqlDB, err := database.OpenSQLite(w.path, mode)
 	if err != nil {
 		return fmt.Errorf(
 			"opening archive database %s: %w", w.path, err,

internal/delivery/target_http.go

@@ -77,14 +77,19 @@ func (c *httpCore) fireAndForget(
 ) {
 	c.eng.observeAttempt(d.Target.Type, res.elapsed())
 
-	c.eng.recordResult(
+	err := c.eng.recordResult(
 		webhookDB, d, 1, res.success,
 		res.statusCode, res.respBody, res.errMsg,
 		res.duration,
 	)
+	if err != nil {
+		c.eng.bookkeepingFailed(d, err)
+
+		return
+	}
 
 	if res.success {
-		c.eng.updateDeliveryStatus(
+		c.eng.settleStatus(
 			webhookDB, d, d.Target.Type,
 			database.DeliveryStatusDelivered,
 		)
@@ -92,7 +97,7 @@ func (c *httpCore) fireAndForget(
 		return
 	}
 
-	c.eng.updateDeliveryStatus(
+	c.eng.settleStatus(
 		webhookDB, d, d.Target.Type,
 		database.DeliveryStatusFailed,
 	)
@@ -122,16 +127,25 @@ func (c *httpCore) withRetry(
 
 	c.eng.observeAttempt(d.Target.Type, res.elapsed())
 
-	c.eng.recordResult(
+	err := c.eng.recordResult(
 		webhookDB, d, attemptNum, res.success,
 		res.statusCode, res.respBody, res.errMsg,
 		res.duration,
 	)
+	if err != nil {
+		// The breaker still learns the outcome: it describes the
+		// target's health, which is unaffected by this database's.
+		c.recordCircuitOutcome(cb, res.success)
+
+		c.eng.bookkeepingFailed(d, err)
+
+		return
+	}
 
 	if res.success {
 		cb.RecordSuccess()
 
-		c.eng.updateDeliveryStatus(
+		c.eng.settleStatus(
 			webhookDB, d, d.Target.Type,
 			database.DeliveryStatusDelivered,
 		)
@@ -146,6 +160,20 @@ func (c *httpCore) withRetry(
 	)
 }
 
+// recordCircuitOutcome feeds one attempt's outcome to the target's
+// circuit breaker.
+func (c *httpCore) recordCircuitOutcome(
+	cb *CircuitBreaker, success bool,
+) {
+	if success {
+		cb.RecordSuccess()
+
+		return
+	}
+
+	cb.RecordFailure()
+}
+
 func (c *httpCore) circuitBreakerBlock(
 	webhookDB *gorm.DB,
 	d *database.Delivery,
@@ -169,7 +197,7 @@ func (c *httpCore) circuitBreakerBlock(
 		"cooldown_remaining", remaining,
 	)
 
-	c.eng.updateDeliveryStatus(
+	c.eng.settleStatus(
 		webhookDB, d, d.Target.Type,
 		database.DeliveryStatusRetrying,
 	)
@@ -189,7 +217,7 @@ func (c *httpCore) handleRetry(
 	attemptNum int,
 ) {
 	if attemptNum >= maxRetries {
-		c.eng.updateDeliveryStatus(
+		c.eng.settleStatus(
 			webhookDB, d, d.Target.Type,
 			database.DeliveryStatusFailed,
 		)
@@ -197,7 +225,7 @@ func (c *httpCore) handleRetry(
 		return
 	}
 
-	c.eng.updateDeliveryStatus(
+	c.eng.settleStatus(
 		webhookDB, d, d.Target.Type,
 		database.DeliveryStatusRetrying,
 	)
@@ -332,12 +360,17 @@ func (t *httpTarget) Deliver(
 			"error", err,
 		)
 
-		t.eng.recordResult(
+		recErr := t.eng.recordResult(
 			webhookDB, d, task.AttemptNum,
 			false, 0, "", err.Error(), 0,
 		)
+		if recErr != nil {
+			t.eng.bookkeepingFailed(d, recErr)
 
-		t.eng.updateDeliveryStatus(
+			return
+		}
+
+		t.eng.settleStatus(
 			webhookDB, d, d.Target.Type,
 			database.DeliveryStatusFailed,
 		)

internal/delivery/target_log.go

@@ -55,12 +55,17 @@ func (t *logTarget) Deliver(
 
 	t.eng.observeAttempt(d.Target.Type, elapsed)
 
-	t.eng.recordResult(
+	err := t.eng.recordResult(
 		webhookDB, d, 1, true, 0, "", "",
 		elapsed.Milliseconds(),
 	)
+	if err != nil {
+		t.eng.bookkeepingFailed(d, err)
 
-	t.eng.updateDeliveryStatus(
+		return
+	}
+
+	t.eng.settleStatus(
 		webhookDB, d, d.Target.Type,
 		database.DeliveryStatusDelivered,
 	)

internal/delivery/target_slack.go

@@ -95,12 +95,17 @@ func (t *slackTarget) failConfig(
 	d *database.Delivery,
 	err error,
 ) {
-	t.eng.recordResult(
+	recErr := t.eng.recordResult(
 		webhookDB, d, 1,
 		false, 0, "", err.Error(), 0,
 	)
+	if recErr != nil {
+		t.eng.bookkeepingFailed(d, recErr)
 
-	t.eng.updateDeliveryStatus(
+		return
+	}
+
+	t.eng.settleStatus(
 		webhookDB, d, d.Target.Type,
 		database.DeliveryStatusFailed,
 	)