Add per-webhook event retention reaper (closes #63) (#78)

Enforces each webhook's `RetentionDays` so per-webhook SQLite files no longer grow without bound.

## Reaper

New `RetentionReaper` in `internal/database/retention.go`. A background ticker runs each sweep: it lists all webhooks from the main DB and, for each webhook with a positive `RetentionDays`, opens its per-webhook DB via `WebhookDBManager.GetDB` and deletes every `Event` (and its dependent `Delivery` and `DeliveryResult` rows) whose `CreatedAt` is older than `RetentionDays` days.

- Deletions run in foreign-key-safe order: delivery results, then deliveries, then events.
- Deletes are unscoped (hard deletes) so rows are physically removed and disk is reclaimed, rather than GORM soft-deleting them.
- `RetentionDays <= 0` means retain forever; those webhooks are skipped.
- Webhooks whose per-webhook DB does not yet exist are skipped.

## Config

`internal/config/config.go` gains `RetentionSweepInterval` (env `RETENTION_SWEEP_INTERVAL`, parsed as a Go duration, default `1h`) via a new `envDuration` helper, following the existing env-helper conventions.

## Wiring

`cmd/webhooker/main.go` registers `database.NewRetentionReaper` as an fx provider and forces its construction in `fx.Invoke`. The reaper starts its sweep loop on an fx `OnStart` hook and stops cleanly on `OnStop` via context cancellation, matching the existing lifecycle components.

## Test

`internal/database/retention_test.go` seeds an old event chain (event + delivery + result, 40 days old) and a recent one (1 day old) in a real per-webhook DB and asserts a single sweep removes only the expired chain while keeping the recent one. A second test forces a non-positive `RetentionDays` and asserts an ancient event is retained.

Note: the `Webhook.RetentionDays` column carries `gorm:"default:30"`, so a `0` passed to a GORM `Create` is replaced by the default; the test forces the value with an explicit column update to exercise the retain-forever path. No model changes were made.

Validated with `docker build .` (fmt-check, lint, test, build) exit 0.

Closes #63

Co-authored-by: sneak <sneak@sneak.berlin>
Reviewed-on: #78
Co-authored-by: clawbot <clawbot@noreply.example.org>
Co-committed-by: clawbot <clawbot@noreply.example.org>

internal/database/retention.go

@@ -0,0 +1,252 @@
+package database
+
+import (
+	"context"
+	"fmt"
+	"log/slog"
+	"sync"
+	"time"
+
+	"go.uber.org/fx"
+	"gorm.io/gorm"
+	"sneak.berlin/go/webhooker/internal/config"
+	"sneak.berlin/go/webhooker/internal/logger"
+)
+
+// hoursPerDay converts a RetentionDays count into hours for cutoff
+// computation.
+const hoursPerDay = 24
+
+// RetentionReaperParams holds the fx dependencies for the
+// RetentionReaper.
+type RetentionReaperParams struct {
+	fx.In
+
+	Config    *config.Config
+	Database  *Database
+	DBManager *WebhookDBManager
+	Logger    *logger.Logger
+}
+
+// RetentionReaper periodically deletes expired events (and their
+// dependent deliveries and delivery results) from each per-webhook
+// database, enforcing every webhook's RetentionDays. Rows are removed
+// permanently so that per-webhook SQLite files do not grow without
+// bound.
+type RetentionReaper struct {
+	db        *Database
+	dbManager *WebhookDBManager
+	log       *slog.Logger
+	interval  time.Duration
+	cancel    context.CancelFunc
+	wg        sync.WaitGroup
+}
+
+// NewRetentionReaper creates the retention reaper and registers its
+// fx lifecycle hooks. The background sweep loop starts on OnStart and
+// stops cleanly on OnStop via context cancellation.
+func NewRetentionReaper(
+	lc fx.Lifecycle,
+	params RetentionReaperParams,
+) *RetentionReaper {
+	r := &RetentionReaper{
+		db:        params.Database,
+		dbManager: params.DBManager,
+		log:       params.Logger.Get(),
+		interval:  params.Config.RetentionSweepInterval,
+	}
+
+	lc.Append(fx.Hook{
+		OnStart: func(ctx context.Context) error {
+			r.start(ctx)
+
+			return nil
+		},
+		OnStop: func(_ context.Context) error {
+			r.stop()
+
+			return nil
+		},
+	})
+
+	return r
+}
+
+func (r *RetentionReaper) start(ctx context.Context) {
+	ctx, cancel := context.WithCancel(ctx)
+	r.cancel = cancel
+
+	r.wg.Add(1)
+
+	go r.run(ctx)
+
+	r.log.Info(
+		"retention reaper started",
+		"interval", r.interval.String(),
+	)
+}
+
+func (r *RetentionReaper) stop() {
+	r.log.Info("retention reaper stopping")
+
+	if r.cancel != nil {
+		r.cancel()
+	}
+
+	r.wg.Wait()
+	r.log.Info("retention reaper stopped")
+}
+
+func (r *RetentionReaper) run(ctx context.Context) {
+	defer r.wg.Done()
+
+	ticker := time.NewTicker(r.interval)
+	defer ticker.Stop()
+
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-ticker.C:
+			r.sweep(ctx)
+		}
+	}
+}
+
+// sweep lists every webhook from the main database and reaps expired
+// rows from each per-webhook database whose RetentionDays is positive.
+func (r *RetentionReaper) sweep(ctx context.Context) {
+	var webhooks []Webhook
+
+	err := r.db.DB().
+		Model(&Webhook{}).
+		Find(&webhooks).Error
+	if err != nil {
+		r.log.Error(
+			"retention sweep: failed to list webhooks",
+			"error", err,
+		)
+
+		return
+	}
+
+	for i := range webhooks {
+		select {
+		case <-ctx.Done():
+			return
+		default:
+		}
+
+		wh := webhooks[i]
+
+		// RetentionDays of zero or less means retain forever.
+		if wh.RetentionDays <= 0 {
+			continue
+		}
+
+		// Nothing to reap if the per-webhook database has never
+		// been created.
+		if !r.dbManager.DBExists(wh.ID) {
+			continue
+		}
+
+		r.reapWebhook(wh.ID, wh.RetentionDays)
+	}
+}
+
+// reapWebhook removes every expired event (and its dependents) from a
+// single webhook's database.
+func (r *RetentionReaper) reapWebhook(
+	webhookID string,
+	retentionDays int,
+) {
+	db, err := r.dbManager.GetDB(webhookID)
+	if err != nil {
+		r.log.Error(
+			"retention sweep: failed to open webhook database",
+			"webhook_id", webhookID,
+			"error", err,
+		)
+
+		return
+	}
+
+	cutoff := time.Now().Add(
+		-time.Duration(retentionDays*hoursPerDay) * time.Hour,
+	)
+
+	deleted, err := reapExpired(db, cutoff)
+	if err != nil {
+		r.log.Error(
+			"retention sweep: failed to reap expired events",
+			"webhook_id", webhookID,
+			"error", err,
+		)
+
+		return
+	}
+
+	if deleted > 0 {
+		r.log.Info(
+			"retention sweep: reaped expired events",
+			"webhook_id", webhookID,
+			"retention_days", retentionDays,
+			"events_deleted", deleted,
+		)
+	}
+}
+
+// reapExpired hard-deletes, in foreign-key-safe order, the delivery
+// results, deliveries, and events associated with events older than
+// cutoff. Deletes are unscoped so rows are physically removed rather
+// than soft-deleted, reclaiming disk. It returns the number of events
+// deleted.
+func reapExpired(db *gorm.DB, cutoff time.Time) (int64, error) {
+	// Fresh subqueries are built per statement to avoid reusing a
+	// mutated builder across executions.
+	expiredEventIDs := func() *gorm.DB {
+		return db.Model(&Event{}).
+			Select("id").
+			Where("created_at < ?", cutoff)
+	}
+	expiredDeliveryIDs := func() *gorm.DB {
+		return db.Model(&Delivery{}).
+			Select("id").
+			Where("event_id IN (?)", expiredEventIDs())
+	}
+
+	// 1. Delivery results whose delivery belongs to an expired event.
+	res := db.Unscoped().
+		Where("delivery_id IN (?)", expiredDeliveryIDs()).
+		Delete(&DeliveryResult{})
+	if res.Error != nil {
+		return 0, fmt.Errorf(
+			"deleting expired delivery results: %w",
+			res.Error,
+		)
+	}
+
+	// 2. Deliveries belonging to an expired event.
+	del := db.Unscoped().
+		Where("event_id IN (?)", expiredEventIDs()).
+		Delete(&Delivery{})
+	if del.Error != nil {
+		return 0, fmt.Errorf(
+			"deleting expired deliveries: %w",
+			del.Error,
+		)
+	}
+
+	// 3. The expired events themselves.
+	ev := db.Unscoped().
+		Where("created_at < ?", cutoff).
+		Delete(&Event{})
+	if ev.Error != nil {
+		return 0, fmt.Errorf(
+			"deleting expired events: %w",
+			ev.Error,
+		)
+	}
+
+	return ev.RowsAffected, nil
+}