Files
certctl/internal/api/handler/notifications.go
T
Shankar 15daf008aa I-005: notification retry loop + dead-letter queue
Critical alerts can no longer be silently dropped by a transient
notifier failure. Failed notification attempts now ride an exponential
backoff retry loop, with a 5-attempt budget before promotion to the
dead-letter queue for operator intervention.

Schema (migration 000016, idempotent):
- retry_count INTEGER NOT NULL DEFAULT 0
- next_retry_at TIMESTAMPTZ
- last_error TEXT
- idx_notification_events_retry_sweep partial index
  (next_retry_at) WHERE status='failed' AND next_retry_at IS NOT NULL
  Dead rows clear next_retry_at so the index stops matching them.

Service contract:
- NotificationService.RetryFailedNotifications drives 2^n-minute
  exponential backoff capped at 1h (notifRetryBackoffCap) with
  5-attempt budget (notifRetryMaxAttempts).
- Exhaustion (RetryCount >= notifRetryMaxAttempts-1) promotes to
  status='dead' via MarkAsDead.
- Non-terminal failures record via RecordFailedAttempt.
- Success path promotes to 'sent' without touching retry_count
  (audit preserves "delivered on attempt N").
- Missing-notifier branch defensively promotes to 'sent' to avoid
  wedging a row on a deleted channel.
- RequeueNotification operator escape hatch atomically resets
  retry_count -> 0, next_retry_at -> NULL, last_error -> NULL,
  status -> pending via notifRepo.Requeue.

Scheduler:
- New always-on notificationRetryLoop wired into the base loop set at
  CERTCTL_NOTIFICATION_RETRY_INTERVAL (default 2m).
- sync/atomic.Bool idempotency guard.
- sync.WaitGroup shutdown drain via WaitForCompletion.

StatsService:
- SetNotifRepo setter pattern preserves 9 pre-existing
  NewStatsService call sites (main.go + stats_test.go + 8 digest
  tests) without touching the constructor signature.
- DashboardSummary.NotificationsDead populated via
  notifRepo.CountByStatus(ctx, "dead") — nil-safe when unwired
  (reports zero on systems without a notification repository).
- CountByStatus error is non-fatal (dashboard summary is
  best-effort for this field).
- Prometheus certctl_notification_dead_total counter emitted from
  the same snapshot.

Handler:
- New POST /api/v1/notifications/{id}/requeue endpoint.
- dead status surfaces to MCP + CLI.

Frontend:
- NotificationsPage gains two-tab toolbar ("All" / "Dead letter")
  with queryKey: ['notifications', activeTab] so switching tabs
  doesn't serve stale data until the 30s refetch.
- Dead rows surface "Retry {n}/5" + truncated last_error with
  full-text title tooltip.
- Requeue mutation wrapped as
    mutationFn: (id: string) => requeueNotification(id)
  to prevent react-query v5's positional context argument from
  leaking into the API client — pinned against future refactors
  by strict-match toHaveBeenCalledWith('notif-dead-001') in
  NotificationsPage.test.tsx:181.

Closes I-005.
2026-04-19 15:17:27 +00:00

187 lines
6.1 KiB
Go

package handler
import (
"context"
"net/http"
"strconv"
"strings"
"github.com/shankar0123/certctl/internal/api/middleware"
"github.com/shankar0123/certctl/internal/domain"
)
// NotificationService defines the service interface for notification operations.
//
// ListNotificationsByStatus and RequeueNotification were added to close coverage
// gap I-005: the Dead letter tab on the GUI (?status=dead) needs a scoped
// listing path, and the Requeue action needs a dedicated endpoint that flips a
// dead notification back to 'pending' so the retry sweep can pick it up again.
type NotificationService interface {
ListNotifications(ctx context.Context, page, perPage int) ([]domain.NotificationEvent, int64, error)
ListNotificationsByStatus(ctx context.Context, status string, page, perPage int) ([]domain.NotificationEvent, int64, error)
GetNotification(ctx context.Context, id string) (*domain.NotificationEvent, error)
MarkAsRead(ctx context.Context, id string) error
RequeueNotification(ctx context.Context, id string) error
}
// NotificationHandler handles HTTP requests for notification operations.
type NotificationHandler struct {
svc NotificationService
}
// NewNotificationHandler creates a new NotificationHandler with a service dependency.
func NewNotificationHandler(svc NotificationService) NotificationHandler {
return NotificationHandler{svc: svc}
}
// ListNotifications lists notifications.
// GET /api/v1/notifications?page=1&per_page=50
func (h NotificationHandler) ListNotifications(w http.ResponseWriter, r *http.Request) {
if r.Method != http.MethodGet {
Error(w, http.StatusMethodNotAllowed, "Method not allowed")
return
}
requestID := middleware.GetRequestID(r.Context())
page := 1
perPage := 50
query := r.URL.Query()
if p := query.Get("page"); p != "" {
if parsed, err := strconv.Atoi(p); err == nil && parsed > 0 {
page = parsed
}
}
if pp := query.Get("per_page"); pp != "" {
if parsed, err := strconv.Atoi(pp); err == nil && parsed > 0 && parsed <= 500 {
perPage = parsed
}
}
// I-005: branch to the status-scoped listing path when ?status= is present
// so the Dead letter tab on the GUI (?status=dead) can filter server-side.
// Empty status delegates to the original ListNotifications path to preserve
// the default tab's existing behavior.
var (
notifications []domain.NotificationEvent
total int64
err error
)
if status := query.Get("status"); status != "" {
notifications, total, err = h.svc.ListNotificationsByStatus(r.Context(), status, page, perPage)
} else {
notifications, total, err = h.svc.ListNotifications(r.Context(), page, perPage)
}
if err != nil {
ErrorWithRequestID(w, http.StatusInternalServerError, "Failed to list notifications", requestID)
return
}
response := PagedResponse{
Data: notifications,
Total: total,
Page: page,
PerPage: perPage,
}
JSON(w, http.StatusOK, response)
}
// GetNotification retrieves a single notification by ID.
// GET /api/v1/notifications/{id}
func (h NotificationHandler) GetNotification(w http.ResponseWriter, r *http.Request) {
if r.Method != http.MethodGet {
Error(w, http.StatusMethodNotAllowed, "Method not allowed")
return
}
requestID := middleware.GetRequestID(r.Context())
id := strings.TrimPrefix(r.URL.Path, "/api/v1/notifications/")
parts := strings.Split(id, "/")
if len(parts) == 0 || parts[0] == "" {
ErrorWithRequestID(w, http.StatusBadRequest, "Notification ID is required", requestID)
return
}
id = parts[0]
notification, err := h.svc.GetNotification(r.Context(), id)
if err != nil {
ErrorWithRequestID(w, http.StatusNotFound, "Notification not found", requestID)
return
}
JSON(w, http.StatusOK, notification)
}
// MarkAsRead marks a notification as read.
// POST /api/v1/notifications/{id}/read
func (h NotificationHandler) MarkAsRead(w http.ResponseWriter, r *http.Request) {
if r.Method != http.MethodPost {
Error(w, http.StatusMethodNotAllowed, "Method not allowed")
return
}
requestID := middleware.GetRequestID(r.Context())
// Extract notification ID from path /api/v1/notifications/{id}/read
path := strings.TrimPrefix(r.URL.Path, "/api/v1/notifications/")
parts := strings.Split(path, "/")
if len(parts) < 2 || parts[0] == "" {
ErrorWithRequestID(w, http.StatusBadRequest, "Notification ID is required", requestID)
return
}
notificationID := parts[0]
if err := h.svc.MarkAsRead(r.Context(), notificationID); err != nil {
ErrorWithRequestID(w, http.StatusInternalServerError, "Failed to mark notification as read", requestID)
return
}
response := map[string]string{
"status": "marked_as_read",
}
JSON(w, http.StatusOK, response)
}
// RequeueNotification flips a dead notification back to 'pending' so the retry
// sweep (coverage gap I-005) can pick it up again on its next tick. The handler
// is strictly POST-only; GET/PUT/DELETE return 405. An empty id segment
// (/api/v1/notifications//requeue) returns 400. Service errors that carry a
// "not found" sentinel map to 404; all other service errors map to 500. This
// 404-vs-500 split mirrors GetCertificateDeployments at certificates.go:644.
// POST /api/v1/notifications/{id}/requeue
func (h NotificationHandler) RequeueNotification(w http.ResponseWriter, r *http.Request) {
if r.Method != http.MethodPost {
Error(w, http.StatusMethodNotAllowed, "Method not allowed")
return
}
requestID := middleware.GetRequestID(r.Context())
// Extract notification ID from path /api/v1/notifications/{id}/requeue
path := strings.TrimPrefix(r.URL.Path, "/api/v1/notifications/")
parts := strings.Split(path, "/")
if len(parts) < 2 || parts[0] == "" {
ErrorWithRequestID(w, http.StatusBadRequest, "Notification ID is required", requestID)
return
}
notificationID := parts[0]
if err := h.svc.RequeueNotification(r.Context(), notificationID); err != nil {
if strings.Contains(err.Error(), "not found") {
ErrorWithRequestID(w, http.StatusNotFound, "Notification not found", requestID)
return
}
ErrorWithRequestID(w, http.StatusInternalServerError, "Failed to requeue notification", requestID)
return
}
response := map[string]string{
"status": "requeued",
}
JSON(w, http.StatusOK, response)
}