Add per-webhook event retention reaper (closes #63) (#78)
All checks were successful
check / check (push) Successful in 2m42s

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>
This commit was merged in pull request #78.
This commit is contained in:
2026-08-07 16:15:13 +02:00
committed by Jeffrey Paul
parent 8ea7f76540
commit f6b929f2d7
6 changed files with 722 additions and 13 deletions

View File

@@ -0,0 +1,277 @@
package database_test
import (
"context"
"testing"
"time"
"github.com/google/uuid"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"go.uber.org/fx/fxtest"
"gorm.io/gorm"
"gorm.io/gorm/clause"
"sneak.berlin/go/webhooker/internal/config"
"sneak.berlin/go/webhooker/internal/database"
"sneak.berlin/go/webhooker/internal/globals"
"sneak.berlin/go/webhooker/internal/logger"
)
// retentionTestEnv bundles the pieces a retention test drives.
type retentionTestEnv struct {
reaper *database.RetentionReaper
mainDB *database.Database
mgr *database.WebhookDBManager
}
func setupRetentionTest(t *testing.T) *retentionTestEnv {
t.Helper()
lc := fxtest.NewLifecycle(t)
g := &globals.Globals{
Appname: "webhooker-test",
Version: "test",
}
l, err := logger.New(lc, logger.LoggerParams{Globals: g})
require.NoError(t, err)
cfg := &config.Config{
DataDir: t.TempDir(),
Environment: "dev",
}
mainDB, err := database.New(lc, database.DatabaseParams{
Config: cfg,
Logger: l,
})
require.NoError(t, err)
mgr, err := database.NewWebhookDBManager(
lc,
database.WebhookDBManagerParams{Config: cfg, Logger: l},
)
require.NoError(t, err)
ctx := context.Background()
require.NoError(t, lc.Start(ctx))
t.Cleanup(func() { require.NoError(t, lc.Stop(ctx)) })
return &retentionTestEnv{
reaper: database.NewTestRetentionReaper(mainDB, mgr),
mainDB: mainDB,
mgr: mgr,
}
}
// createWebhook inserts a webhook row into the main database with the
// given retention policy and returns its ID.
func createWebhook(
t *testing.T,
db *gorm.DB,
retentionDays int,
) string {
t.Helper()
wh := &database.Webhook{
UserID: uuid.New().String(),
Name: "test-webhook",
RetentionDays: retentionDays,
}
require.NoError(
t,
db.Omit(clause.Associations).Create(wh).Error,
)
// The RetentionDays column carries a GORM default of 30, so a
// zero (or negative) value passed to Create is replaced by that
// default. Force the requested value explicitly so the
// retain-forever (<= 0) path can be exercised.
require.NoError(
t,
db.Model(wh).
Update("retention_days", retentionDays).Error,
)
return wh.ID
}
// eventChain is the set of row IDs seeded for a single event.
type eventChain struct {
eventID string
deliveryID string
resultID string
}
// seedEventChain creates an event with one delivery and one delivery
// result, all stamped with createdAt, and returns their IDs.
func seedEventChain(
t *testing.T,
db *gorm.DB,
webhookID string,
createdAt time.Time,
) eventChain {
t.Helper()
event := &database.Event{
WebhookID: webhookID,
EntrypointID: uuid.New().String(),
Method: "POST",
Body: `{"seed": true}`,
ContentType: "application/json",
}
event.CreatedAt = createdAt
require.NoError(t, db.Create(event).Error)
delivery := &database.Delivery{
EventID: event.ID,
TargetID: uuid.New().String(),
Status: database.DeliveryStatusDelivered,
}
delivery.CreatedAt = createdAt
require.NoError(t, db.Create(delivery).Error)
result := &database.DeliveryResult{
DeliveryID: delivery.ID,
AttemptNum: 1,
Success: true,
StatusCode: 200,
Duration: 10,
}
result.CreatedAt = createdAt
require.NoError(t, db.Create(result).Error)
return eventChain{
eventID: event.ID,
deliveryID: delivery.ID,
resultID: result.ID,
}
}
// countByID returns how many rows of model match the given id,
// counting even hard-deletable rows via Unscoped.
func countByID(
t *testing.T,
db *gorm.DB,
model any,
id string,
) int64 {
t.Helper()
var n int64
require.NoError(
t,
db.Unscoped().Model(model).
Where("id = ?", id).Count(&n).Error,
)
return n
}
func assertChainGone(
t *testing.T,
db *gorm.DB,
chain eventChain,
) {
t.Helper()
assert.Zero(
t,
countByID(t, db, &database.Event{}, chain.eventID),
"expired event should be removed",
)
assert.Zero(
t,
countByID(t, db, &database.Delivery{}, chain.deliveryID),
"expired delivery should be removed",
)
assert.Zero(
t,
countByID(
t, db, &database.DeliveryResult{}, chain.resultID,
),
"expired delivery result should be removed",
)
}
func assertChainPresent(
t *testing.T,
db *gorm.DB,
chain eventChain,
) {
t.Helper()
assert.Equal(
t,
int64(1),
countByID(t, db, &database.Event{}, chain.eventID),
"recent event should be retained",
)
assert.Equal(
t,
int64(1),
countByID(t, db, &database.Delivery{}, chain.deliveryID),
"recent delivery should be retained",
)
assert.Equal(
t,
int64(1),
countByID(
t, db, &database.DeliveryResult{}, chain.resultID,
),
"recent delivery result should be retained",
)
}
func TestRetentionReaper_ReapsExpiredKeepsRecent(t *testing.T) {
t.Parallel()
env := setupRetentionTest(t)
const retentionDays = 30
webhookID := createWebhook(
t, env.mainDB.DB(), retentionDays,
)
db, err := env.mgr.GetDB(webhookID)
require.NoError(t, err)
now := time.Now()
old := seedEventChain(
t, db, webhookID,
now.Add(-40*24*time.Hour),
)
recent := seedEventChain(
t, db, webhookID,
now.Add(-1*24*time.Hour),
)
env.reaper.ExportSweep(context.Background())
assertChainGone(t, db, old)
assertChainPresent(t, db, recent)
}
func TestRetentionReaper_RetainsForeverWhenNonPositive(t *testing.T) {
t.Parallel()
env := setupRetentionTest(t)
// RetentionDays of zero means retain forever.
webhookID := createWebhook(t, env.mainDB.DB(), 0)
db, err := env.mgr.GetDB(webhookID)
require.NoError(t, err)
ancient := seedEventChain(
t, db, webhookID,
time.Now().Add(-365*24*time.Hour),
)
env.reaper.ExportSweep(context.Background())
assertChainPresent(t, db, ancient)
}