Files
webhooker/internal/handlers/webhook.go
sneak dfd559417e
All checks were successful
check / check (push) Successful in 3m10s
Expose delivery metrics on /metrics (closes #209)
/metrics carried only the inbound HTTP surface, so a destination
failing for an hour, a growing retry backlog and a stuck-open circuit
breaker were all invisible: the receive side stays healthy in each
case because it is.

New internal/metrics registers, on the existing default registry that
the go-http-metrics recorder and the promhttp handler already share:

- webhooker_events_received_total
- webhooker_delivery_attempts_total
- webhooker_deliveries_succeeded_total
- webhooker_deliveries_failed_total
- webhooker_delivery_retries_total
- webhooker_delivery_duration_seconds
- webhooker_deliveries_pending / _retrying
- webhooker_circuit_breakers_open

The route mounting is untouched.

Every delivery metric carries one label, target_type, whose domain is
the four target-type constants; anything outside it collapses to
"unknown" so no series can be minted from a UUID. Target ids, event
ids and entrypoint ids are deliberately not labels.

An attempt is counted, and its duration observed, only where one was
actually dispatched — the target's own result path, which is also
where the DeliveryResult is written. A delivery an open circuit
breaker refuses sends nothing and records no result row; counting it
would climb the attempts counter with no traffic behind it and pull
the duration quantiles down for as long as the breaker stayed open,
moving the metric the wrong way during the outage it exists to reveal.
The log and database targets now time their own work, so their result
rows carry a real duration too.

The outcome counters move after the status row is written rather than
before, so a transition the database rejected is never reported as an
outcome that happened.

The queue-depth gauges are counted out of the per-webhook databases by
a 30s sampler rather than tracked as deltas, which would need seeding
at startup and would drift on any transition that failed to persist.
They publish an "unknown" series from registration: deliveries queued
against a target that has since been deleted resolve to the empty type
and are folded there, because a backlog behind a deleted target is
precisely the one nobody is watching. The open-breaker gauge is
recounted from the target's breaker registry on every state change.

The orphaned-retry terminal path takes the target type as an argument
rather than attaching the loaded target to the delivery. That path
loads the delivery without its target relation on purpose: a populated
Delivery.Target makes GORM's SaveBeforeAssociations upsert the whole
target row on the status UPDATE, writing the plaintext target config —
the credential, for a slack target — into the per-webhook events
database. A test asserts that path leaves the targets table empty.
2026-08-20 05:08:31 +00:00

367 lines
7.9 KiB
Go

package handlers
import (
"encoding/json"
"io"
"net/http"
"github.com/go-chi/chi"
"gorm.io/gorm"
"sneak.berlin/go/webhooker/internal/database"
"sneak.berlin/go/webhooker/internal/delivery"
"sneak.berlin/go/webhooker/internal/logfield"
)
const (
// maxWebhookBodySize is the maximum allowed webhook
// request body (1 MB).
maxWebhookBodySize = 1 << maxBodyShift
)
// HandleWebhook handles incoming webhook requests at entrypoint
// URLs.
func (h *Handlers) HandleWebhook() http.HandlerFunc {
return func(w http.ResponseWriter, r *http.Request) {
if r.Method != http.MethodPost {
w.Header().Set("Allow", "POST")
http.Error(
w,
"Method Not Allowed",
http.StatusMethodNotAllowed,
)
return
}
entrypointUUID := chi.URLParam(r, "uuid")
if entrypointUUID == "" {
http.NotFound(w, r)
return
}
entrypoint, ok := h.lookupEntrypoint(
w, r, entrypointUUID,
)
if !ok {
return
}
// Logged only once the UUID is known to name a real
// entrypoint. The UUID comes straight out of the path on
// the one unauthenticated endpoint, so logging it before
// the lookup let a client write an INFO line per invented
// path; the request itself is already in the access log
// and a miss is already logged at DEBUG.
h.log.Info("webhook request received",
"entrypoint_uuid", entrypointUUID,
"method", r.Method,
"remote_addr", r.RemoteAddr,
)
if !entrypoint.Active {
http.Error(w, "Gone", http.StatusGone)
return
}
h.processWebhookRequest(w, r, entrypoint)
}
}
// processWebhookRequest reads the body, serializes headers,
// loads targets, and delivers the event.
func (h *Handlers) processWebhookRequest(
w http.ResponseWriter,
r *http.Request,
entrypoint database.Entrypoint,
) {
body, ok := h.readWebhookBody(w, r)
if !ok {
return
}
headersJSON, err := json.Marshal(r.Header)
if err != nil {
h.serverError(w, "failed to serialize headers", err)
return
}
targets, err := h.loadActiveTargets(entrypoint.WebhookID)
if err != nil {
h.serverError(w, "failed to query targets", err)
return
}
h.createAndDeliverEvent(
w, r, entrypoint, body, headersJSON, targets,
)
}
// loadActiveTargets returns all active targets for a webhook.
func (h *Handlers) loadActiveTargets(
webhookID string,
) ([]database.Target, error) {
var targets []database.Target
err := h.db.DB().Where(
"webhook_id = ? AND active = ?",
webhookID, true,
).Find(&targets).Error
return targets, err
}
// lookupEntrypoint finds an entrypoint by UUID path.
func (h *Handlers) lookupEntrypoint(
w http.ResponseWriter,
r *http.Request,
entrypointUUID string,
) (database.Entrypoint, bool) {
var entrypoint database.Entrypoint
result := h.db.DB().Where(
"path = ?", entrypointUUID,
).First(&entrypoint)
if result.Error != nil {
// The receiver is unauthenticated and /webhook/{uuid}
// matches any single segment, so this value is entirely
// client-chosen on exactly the branch where the lookup
// failed. DEBUG is off by default; the cap is what keeps
// turning it on from restoring an unbounded write.
h.log.Debug(
"entrypoint not found",
"path", logfield.Truncate(
entrypointUUID, logfield.MaxBytes,
),
)
http.NotFound(w, r)
return entrypoint, false
}
return entrypoint, true
}
// readWebhookBody reads and validates the request body size.
func (h *Handlers) readWebhookBody(
w http.ResponseWriter,
r *http.Request,
) ([]byte, bool) {
body, err := io.ReadAll(
io.LimitReader(r.Body, maxWebhookBodySize+1),
)
if err != nil {
h.log.Error(
"failed to read request body", "error", err,
)
http.Error(
w, "Bad request", http.StatusBadRequest,
)
return nil, false
}
if len(body) > maxWebhookBodySize {
http.Error(
w,
"Request body too large",
http.StatusRequestEntityTooLarge,
)
return nil, false
}
return body, true
}
// createAndDeliverEvent creates the event and delivery records
// then notifies the delivery engine.
func (h *Handlers) createAndDeliverEvent(
w http.ResponseWriter,
r *http.Request,
entrypoint database.Entrypoint,
body, headersJSON []byte,
targets []database.Target,
) {
tx, err := h.beginWebhookTx(w, entrypoint.WebhookID)
if err != nil {
return
}
event := h.buildEvent(r, entrypoint, headersJSON, body)
err = tx.Create(event).Error
if err != nil {
tx.Rollback()
h.serverError(w, "failed to create event", err)
return
}
bodyPtr := inlineBody(body)
tasks := h.buildDeliveryTasks(
w, tx, event, entrypoint, targets, bodyPtr,
)
if tasks == nil {
return
}
err = tx.Commit().Error
if err != nil {
h.serverError(w, "failed to commit transaction", err)
return
}
// Counted here, after the commit: an event is received once it
// is durably stored, which is what the delivery counters are
// compared against on a dashboard.
h.mtr.EventReceived()
h.finishWebhookResponse(w, event, entrypoint, tasks)
}
// beginWebhookTx opens a transaction on the per-webhook DB.
func (h *Handlers) beginWebhookTx(
w http.ResponseWriter,
webhookID string,
) (*gorm.DB, error) {
webhookDB, err := h.dbMgr.GetDB(webhookID)
if err != nil {
h.serverError(
w, "failed to get webhook database", err,
)
return nil, err
}
tx := webhookDB.Begin()
if tx.Error != nil {
h.serverError(
w, "failed to begin transaction", tx.Error,
)
return nil, tx.Error
}
return tx, nil
}
// inlineBody returns a pointer to body as a string if it fits
// within the inline size limit, or nil otherwise.
func inlineBody(body []byte) *string {
if len(body) < delivery.MaxInlineBodySize {
s := string(body)
return &s
}
return nil
}
// finishWebhookResponse notifies the delivery engine, logs the
// event, and writes the HTTP response.
func (h *Handlers) finishWebhookResponse(
w http.ResponseWriter,
event *database.Event,
entrypoint database.Entrypoint,
tasks []delivery.Task,
) {
if len(tasks) > 0 {
h.notifier.Notify(tasks)
}
h.log.Info("webhook event created",
"event_id", event.ID,
"webhook_id", entrypoint.WebhookID,
"entrypoint_id", entrypoint.ID,
"target_count", len(tasks),
)
w.WriteHeader(http.StatusOK)
_, err := w.Write([]byte(`{"status":"ok"}`))
if err != nil {
h.log.Error(
"failed to write response", "error", err,
)
}
}
// buildEvent creates a new Event struct from request data.
func (h *Handlers) buildEvent(
r *http.Request,
entrypoint database.Entrypoint,
headersJSON, body []byte,
) *database.Event {
return &database.Event{
WebhookID: entrypoint.WebhookID,
EntrypointID: entrypoint.ID,
Method: r.Method,
Headers: string(headersJSON),
Body: string(body),
ContentType: r.Header.Get("Content-Type"),
}
}
// buildDeliveryTasks creates delivery records in the
// transaction and returns tasks for the delivery engine.
// Returns nil if an error occurred.
func (h *Handlers) buildDeliveryTasks(
w http.ResponseWriter,
tx *gorm.DB,
event *database.Event,
entrypoint database.Entrypoint,
targets []database.Target,
bodyPtr *string,
) []delivery.Task {
tasks := make([]delivery.Task, 0, len(targets))
for i := range targets {
dlv := &database.Delivery{
EventID: event.ID,
TargetID: targets[i].ID,
Status: database.DeliveryStatusPending,
}
err := tx.Create(dlv).Error
if err != nil {
tx.Rollback()
h.log.Error(
"failed to create delivery",
"target_id", targets[i].ID,
"error", err,
)
http.Error(
w, "Internal server error",
http.StatusInternalServerError,
)
return nil
}
tasks = append(tasks, delivery.Task{
DeliveryID: dlv.ID,
EventID: event.ID,
WebhookID: entrypoint.WebhookID,
EntrypointID: entrypoint.ID,
TargetID: targets[i].ID,
TargetName: targets[i].Name,
TargetType: targets[i].Type,
TargetConfig: targets[i].Config,
MaxRetries: targets[i].MaxRetries,
Method: event.Method,
Headers: event.Headers,
ContentType: event.ContentType,
Body: bodyPtr,
AttemptNum: 1,
})
}
return tasks
}