Add per-delivery replay to the event log (closes #203)
All checks were successful
check / check (push) Successful in 3m3s

A delivery that exhausted max_retries was failed forever. The event
body is durably stored, so the only way to get it delivered was to
download it and re-POST by hand.

The event log now offers a Replay action on any finished delivery.
Replay creates a NEW pending delivery for the same event and target
and hands it to the delivery engine through the same Notifier the
receiver uses, so it is retried, SSRF-guarded and circuit-broken
exactly as a first attempt. The original delivery's status,
timestamps and recorded attempts are never touched, and what is
re-sent is the stored event body, not the response the original
attempt received.

The target is read as it stands now, including soft-deleted rows so
that a deleted target refuses the replay with a message on the page
instead of erroring or delivering from stale configuration. A
deactivated target and a target id that names nothing refuse the same
way, as does a replay of a delivery the engine has not finished.

Two bounds on replay storms: the route carries a per-client POST rate
limit of 30 per minute, and the handler refuses a replay while an
earlier one for the same event and target is still pending or
retrying.

One new metric, webhooker_delivery_replays_total, on the existing
target_type label. A replay is a real delivery and moves the attempt,
outcome and duration series like any other; this counter is what
separates it from ordinary traffic without adding a dimension to
every existing series.

The delivery row is written with associations omitted and with
neither Event nor Target populated, so no target row reaches the
per-webhook event database.
This commit is contained in:
clawbot
2026-08-20 05:45:04 +00:00
committed by sneak
parent 9969694a47
commit ea6639ff31
12 changed files with 1240 additions and 14 deletions

View File

@@ -201,6 +201,18 @@ func (s *Server) setupSourceRoutes() {
"/logs/{eventID}/body",
s.h.HandleEventBodyDownload(),
)
// Replay is the one page action that queues outbound work:
// it creates a delivery from a stored event and hands it to
// the delivery engine. The rate limit is what bounds a
// held-down button or a scripted loop; the handler
// separately refuses a replay while an earlier one for the
// same event and target is still in flight. POST only, so
// the action cannot be taken by a link, a prefetch or an
// image tag.
r.With(s.mw.ReplayRateLimit()).Post(
"/deliveries/{deliveryID}/replay",
s.h.HandleDeliveryReplay(),
)
r.Post(
"/entrypoints",
s.h.HandleEntrypointCreate(),

View File

@@ -310,6 +310,75 @@ func (e *testEnv) seedEvent(
return event
}
// seedTarget creates an active HTTP target for a webhook.
func (e *testEnv) seedTarget(
t *testing.T,
webhookID string,
) *database.Target {
t.Helper()
tgt := &database.Target{
WebhookID: webhookID,
Name: "routed-target",
Type: database.TargetTypeHTTP,
Active: true,
Config: `{"url":"http://93.184.216.34/hook"}`,
}
require.NoError(
t,
e.db.DB().Omit(clause.Associations).Create(tgt).Error,
)
return tgt
}
// seedFailedDelivery records a terminally failed delivery of an event
// to a target in the webhook's own database.
func (e *testEnv) seedFailedDelivery(
t *testing.T,
webhookID, eventID, targetID string,
) *database.Delivery {
t.Helper()
webhookDB, err := e.dbMgr.GetDB(webhookID)
require.NoError(t, err)
dlv := &database.Delivery{
EventID: eventID,
TargetID: targetID,
Status: database.DeliveryStatusFailed,
}
require.NoError(
t,
webhookDB.Omit(clause.Associations).Create(dlv).Error,
)
return dlv
}
// countDeliveries reports how many deliveries a webhook's database
// holds.
func (e *testEnv) countDeliveries(
t *testing.T, webhookID string,
) int64 {
t.Helper()
webhookDB, err := e.dbMgr.GetDB(webhookID)
require.NoError(t, err)
var count int64
require.NoError(
t,
webhookDB.Model(&database.Delivery{}).
Count(&count).Error,
)
return count
}
// storedHash reads the current password hash for a username.
func (e *testEnv) storedHash(t *testing.T, username string) string {
t.Helper()
@@ -674,6 +743,85 @@ func TestSourceLogsBody_OtherUser404s(t *testing.T) {
assert.Equal(t, "/pages/login", anon.Header().Get("Location"))
}
// TestDeliveryReplay_PostOnlyAndCSRFProtected walks the replay action
// through the production router rather than a forged route context,
// which is the only way to prove what the route group actually gives
// it: a GET cannot trigger a replay, an unauthenticated request never
// reaches the handler, a POST without the token is refused by CSRF,
// and the form the template emits — token and action URL both — works
// as rendered.
func TestDeliveryReplay_PostOnlyAndCSRFProtected(t *testing.T) {
t.Parallel()
env := newTestEnv(t)
userID, _ := env.seedUser(t, "replayer", "somepassword")
cookies := env.authCookies(t, userID, "replayer")
wh := env.seedWebhook(t, userID)
tgt := env.seedTarget(t, wh.ID)
evt := env.seedEvent(t, wh.ID, `{"replay":"me"}`)
dlv := env.seedFailedDelivery(t, wh.ID, evt.ID, tgt.ID)
path := "/source/" + wh.ID + "/deliveries/" + dlv.ID +
"/replay"
assert.Equal(
t, http.StatusMethodNotAllowed,
env.get(path, cookies).Code,
"a replay must not be reachable by GET",
)
assert.Equal(
t, http.StatusForbidden,
env.post(path, url.Values{}, cookies).Code,
"a replay POST without a CSRF token must be refused",
)
anon := env.post(path, url.Values{}, nil)
assert.Equal(t, http.StatusForbidden, anon.Code)
require.Equal(
t, int64(1), env.countDeliveries(t, wh.ID),
"no refused request may have created a delivery",
)
// The token and the action URL both come out of the rendered
// page, so a typo in either the route pattern or the template
// fails here.
logsPath := "/source/" + wh.ID + "/logs"
token, cookies := env.csrfFrom(t, logsPath, cookies)
page := env.get(logsPath, cookies)
require.Equal(t, http.StatusOK, page.Code)
action := regexp.MustCompile(
`action="(/source/[^"]+/replay)"`,
).FindStringSubmatch(page.Body.String())
require.Len(
t, action, 2,
"a finished delivery should render a replay form",
)
form := url.Values{}
form.Set("csrf_token", token)
w := env.post(
html.UnescapeString(action[1]), form, cookies,
)
require.Equal(t, http.StatusSeeOther, w.Code)
assert.Equal(
t, logsPath+"?replay=queued",
w.Header().Get("Location"),
)
assert.Equal(
t, int64(2), env.countDeliveries(t, wh.ID),
"the replay appends a delivery",
)
}
// metricsConfig is a Config differing from the routing default only
// in the two /metrics credentials.
func metricsConfig(