Merge pull request #38 from Dvorinka/feat/operations-page

feat(ops): operations page — live jobs, queue depth, failures

ROADMAP2.md

@@ -290,9 +290,12 @@ and wired refs, one click or one CLI call.
   favicon, accent override, docs/support links. `GET /api/v1/branding`
   public + cached. **Containr/Vertice remains default;** this is for
   self-hosters who rebrand their instance.
-- [ ] **Operations page** — unified view of running/queued/failed jobs
-  (deploys, builds, backups, cron, scans, agent commands) — dflow's
-  bubble panel as a real page; flush/stuck-job tools once queue exists.
+- [x] **Operations page** — `GET /operations` aggregates active
+  deployments, in-memory deploy-queue depth (`Queue.Snapshot()`),
+  24h failures, cron runs and backups scoped to the caller's projects.
+  UI at `/operations` (Operate nav) with live refetch; `containr
+  operations` CLI + `containr_operations_get` MCP. Remaining: agent
+  commands once node fleet lands; flush/stuck-job tools.
 - [ ] **Interactive terminal** — upgrade exec to WS PTY (`xterm.js`);
   `nodes/:id/terminal` via agent (dflow's wetty without the extra
   container).

app/backend/internal/api/operations.go

@@ -0,0 +1,158 @@
+package api
+
+import (
+	"net/http"
+	"time"
+
+	"containr/internal/database"
+	"containr/internal/deployqueue"
+
+	"github.com/gin-gonic/gin"
+)
+
+// GET /operations — a single cross-cutting view of platform work: active
+// and recent deployments, the per-service deploy queue, recent cron runs,
+// and recent backups. Scoped to the caller's projects (admins see all).
+
+type operationDeployment struct {
+	ID          string     `json:"id"`
+	ServiceID   string     `json:"service_id"`
+	ServiceName string     `json:"service_name"`
+	ProjectName string     `json:"project_name"`
+	Status      string     `json:"status"`
+	Image       string     `json:"image"`
+	Error       *string    `json:"error,omitempty"`
+	StartedAt   *time.Time `json:"started_at,omitempty"`
+	CompletedAt *time.Time `json:"completed_at,omitempty"`
+	CreatedAt   time.Time  `json:"created_at"`
+}
+
+type operationCronRun struct {
+	ID         string     `json:"id"`
+	JobName    string     `json:"job_name"`
+	Schedule   string     `json:"schedule"`
+	Status     string     `json:"status"`
+	StartedAt  time.Time  `json:"started_at"`
+	FinishedAt *time.Time `json:"finished_at,omitempty"`
+	Error      *string    `json:"error,omitempty"`
+}
+
+type operationBackup struct {
+	ID         string     `json:"id"`
+	DatabaseID string     `json:"database_id"`
+	DBName     string     `json:"database_name"`
+	Status     string     `json:"status"`
+	Size       string     `json:"size"`
+	CreatedAt  time.Time  `json:"created_at"`
+	Completed  *time.Time `json:"completed_at,omitempty"`
+}
+
+func handleGetOperations(c *gin.Context) {
+	userID, ok := requireAuthenticatedUserID(c)
+	if !ok {
+		return
+	}
+	db := c.MustGet("db").(*database.DB)
+	isAdmin := contextIsAdmin(c)
+
+	// Same visibility rule as the deployment list endpoint.
+	visibility := `p.is_approved OR p.owner_id = $1 OR $2::bool
+	    OR EXISTS (SELECT 1 FROM project_members pm WHERE pm.project_id = p.id AND pm.user_id = $1)`
+
+	active := []operationDeployment{}
+	rows, err := db.Query(
+		`SELECT d.id, d.service_id, s.name, p.name, d.status,
+		        COALESCE(d.image_name, ''), d.error, d.started_at, d.completed_at, d.created_at
+		 FROM deployments d
+		 JOIN services s ON s.id = d.service_id
+		 JOIN projects p ON p.id = s.project_id
+		 WHERE d.status IN ('queued','pending','building','deploying','rolling_back')
+		   AND (`+visibility+`)
+		 ORDER BY d.created_at ASC`, userID, isAdmin)
+	if err == nil {
+		defer rows.Close()
+		for rows.Next() {
+			var d operationDeployment
+			var sid string
+			_ = rows.Scan(&d.ID, &sid, &d.ServiceName, &d.ProjectName, &d.Status, &d.Image, &d.Error, &d.StartedAt, &d.CompletedAt, &d.CreatedAt)
+			d.ServiceID = sid
+			active = append(active, d)
+		}
+	}
+
+	recentFailed := []operationDeployment{}
+	rows2, err2 := db.Query(
+		`SELECT d.id, d.service_id, s.name, p.name, d.status,
+		        COALESCE(d.image_name, ''), d.error, d.started_at, d.completed_at, d.created_at
+		 FROM deployments d
+		 JOIN services s ON s.id = d.service_id
+		 JOIN projects p ON p.id = s.project_id
+		 WHERE d.status IN ('failed','cancelled','rolled_back')
+		   AND d.updated_at > NOW() - INTERVAL '24 hours'
+		   AND (`+visibility+`)
+		 ORDER BY d.updated_at DESC
+		 LIMIT 20`, userID, isAdmin)
+	if err2 == nil {
+		defer rows2.Close()
+		for rows2.Next() {
+			var d operationDeployment
+			var sid string
+			_ = rows2.Scan(&d.ID, &sid, &d.ServiceName, &d.ProjectName, &d.Status, &d.Image, &d.Error, &d.StartedAt, &d.CompletedAt, &d.CreatedAt)
+			d.ServiceID = sid
+			recentFailed = append(recentFailed, d)
+		}
+	}
+
+	cronRuns := []operationCronRun{}
+	rows3, err3 := db.Query(
+		`SELECT e.id, j.name, j.schedule, e.status, e.started_at, e.finished_at, e.error
+		 FROM cron_executions e
+		 JOIN cron_jobs j ON j.id = e.cron_job_id
+		 JOIN projects p ON p.id = j.project_id
+		 WHERE e.started_at > NOW() - INTERVAL '24 hours'
+		   AND (`+visibility+`)
+		 ORDER BY e.started_at DESC
+		 LIMIT 30`, userID, isAdmin)
+	if err3 == nil {
+		defer rows3.Close()
+		for rows3.Next() {
+			var r operationCronRun
+			_ = rows3.Scan(&r.ID, &r.JobName, &r.Schedule, &r.Status, &r.StartedAt, &r.FinishedAt, &r.Error)
+			cronRuns = append(cronRuns, r)
+		}
+	}
+
+	backups := []operationBackup{}
+	rows4, err4 := db.Query(
+		`SELECT b.id, b.database_id, ds.name, b.status, b.size, b.created_at, b.completed_at
+		 FROM database_backups b
+		 JOIN database_services ds ON ds.id = b.database_id
+		 WHERE b.created_at > NOW() - INTERVAL '24 hours'
+		   AND (ds.user_id = $1 OR $2::bool)
+		 ORDER BY b.created_at DESC
+		 LIMIT 20`, userID, isAdmin)
+	if err4 == nil {
+		defer rows4.Close()
+		for rows4.Next() {
+			var b operationBackup
+			_ = rows4.Scan(&b.ID, &b.DatabaseID, &b.DBName, &b.Status, &b.Size, &b.CreatedAt, &b.Completed)
+			backups = append(backups, b)
+		}
+	}
+
+	var queue []deployqueue.ServiceQueueState
+	if queueValue, exists := c.Get("deploy_queue"); exists && queueValue != nil {
+		queue = queueValue.(*deployqueue.Queue).Snapshot()
+	}
+	if queue == nil {
+		queue = []deployqueue.ServiceQueueState{}
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"active_deployments": active,
+		"recent_failures":    recentFailed,
+		"cron_runs":          cronRuns,
+		"backups":            backups,
+		"deploy_queue":       queue,
+	})
+}

app/backend/internal/api/routes.go

@@ -333,6 +333,9 @@ func SetupRoutes(router *gin.Engine, db *database.DB, redis *database.Redis, cfg
 			// WebSocket endpoint
 			authed.GET("/ws", handleWebSocket)
 
+			// Cross-cutting ops view — active/queued/failed work
+			authed.GET("/operations", handleGetOperations)
+
 			// Outbound webhooks — signed event delivery to user HTTP endpoints
 			authed.GET("/webhooks", handleListOutboundWebhooks)
 			authed.POST("/webhooks", handleCreateOutboundWebhook)

app/backend/internal/cli/commands/operations.go

@@ -0,0 +1,24 @@
+package commands
+
+import (
+	"github.com/spf13/cobra"
+)
+
+// OperationsCmd shows the cross-cutting operations view.
+var OperationsCmd = &cobra.Command{
+	Use:     "operations",
+	Aliases: []string{"ops"},
+	Short:   "Show active and recent platform work (deploys, cron, backups)",
+	RunE: func(cmd *cobra.Command, args []string) error {
+		c, err := client()
+		if err != nil {
+			return err
+		}
+		data, err := c.Do("GET", "/operations", nil)
+		if err != nil {
+			return err
+		}
+		PrintRaw(data)
+		return nil
+	},
+}

app/backend/internal/cli/root.go

@@ -88,6 +88,7 @@ func init() {
 	rootCmd.AddCommand(commands.AdminCmd)
 	rootCmd.AddCommand(commands.NotificationsCmd)
 	rootCmd.AddCommand(commands.WebhooksCmd)
+	rootCmd.AddCommand(commands.OperationsCmd)
 	rootCmd.AddCommand(commands.UpCmd)
 }
 

app/backend/internal/deployqueue/queue.go

@@ -129,6 +129,27 @@ func (q *Queue) Cancel(serviceID, deploymentID uuid.UUID) CancelState {
 	return NotFound
 }
 
+// ServiceQueueState reports queue depth for one service.
+type ServiceQueueState struct {
+	ServiceID uuid.UUID `json:"service_id"`
+	Running   bool      `json:"running"`
+	Queued    int       `json:"queued"`
+}
+
+// Snapshot returns per-service queue depth for observability.
+func (q *Queue) Snapshot() []ServiceQueueState {
+	q.mu.Lock()
+	defer q.mu.Unlock()
+	out := make([]ServiceQueueState, 0, len(q.states))
+	for id, st := range q.states {
+		if !st.running && len(st.pending) == 0 {
+			continue
+		}
+		out = append(out, ServiceQueueState{ServiceID: id, Running: st.running, Queued: len(st.pending)})
+	}
+	return out
+}
+
 // Do runs fn through the queue and waits for completion — for synchronous
 // endpoints (redeploy) that still must not overlap an in-flight deployment.
 // ctx bounds the wait, not the job; on timeout the job still runs to

app/backend/internal/deployqueue/queue_test.go

@@ -125,6 +125,40 @@ func TestCancelActiveCancelsContext(t *testing.T) {
 	}
 }
 
+func TestSnapshot(t *testing.T) {
+	q := New()
+	if got := q.Snapshot(); len(got) != 0 {
+		t.Fatalf("empty queue snapshot = %v, want empty", got)
+	}
+
+	svc := uuid.New()
+	release := make(chan struct{})
+	q.Enqueue(svc, Job{Run: func(ctx context.Context) { <-release }})
+	q.Enqueue(svc, Job{Run: func(ctx context.Context) {}})
+	q.Enqueue(svc, Job{Run: func(ctx context.Context) {}})
+
+	deadline := time.After(2 * time.Second)
+	for {
+		snap := q.Snapshot()
+		if len(snap) == 1 && snap[0].Running {
+			if snap[0].ServiceID != svc {
+				t.Fatalf("snapshot service = %v, want %v", snap[0].ServiceID, svc)
+			}
+			if snap[0].Queued != 2 {
+				t.Fatalf("queued = %d, want 2", snap[0].Queued)
+			}
+			close(release)
+			return
+		}
+		select {
+		case <-deadline:
+			t.Fatalf("snapshot never showed running job: %v", snap)
+		default:
+			time.Sleep(time.Millisecond)
+		}
+	}
+}
+
 func TestEnqueuePosition(t *testing.T) {
 	q := New()
 	svc := uuid.New()

app/backend/internal/mcpserver/server.go

@@ -147,6 +147,8 @@ func init() {
 	register(spec{"containr_webhooks_deliveries", "List recent delivery attempts for a webhook. Args: id.", "GET", "/webhooks/{id}/deliveries", []string{"id"}, nil, false})
 	register(spec{"containr_webhooks_test", "Queue a test ping delivery for a webhook. Args: id.", "POST", "/webhooks/{id}/test", []string{"id"}, nil, false})
 
+	register(spec{"containr_operations_get", "Cross-cutting operations view: active deployments, deploy queue depth, recent failures, cron runs, backups.", "GET", "/operations", nil, nil, false})
+
 	// Nodes / agent tokens (admin)
 	register(spec{"containr_nodes_list", "List node agents (admin)", "GET", "/agents", nil, nil, false})
 	register(spec{"containr_nodes_get", "Get a node agent (admin)", "GET", "/agents/{id}", []string{"id"}, nil, false})

app/frontend/src/app/App.tsx

@@ -10,6 +10,7 @@ import { BuildsPage } from '@/features/builds/pages/BuildsPage';
 import { TemplatesPage } from '@/features/templates/pages/TemplatesPage';
 import { AuditLogsPage } from '@/features/audit/pages/AuditLogsPage';
 import { WebhooksPage } from '@/features/webhooks/pages/WebhooksPage';
+import { OperationsPage } from '@/features/operations/pages/OperationsPage';
 import { AdminPage } from '@/features/admin/pages/AdminPage';
 import { LandingPage } from '@/features/landing/LandingPage';
 import {
@@ -142,6 +143,7 @@ export default function App() {
           <Route path="/templates" element={<TemplatesPage />} />
           <Route path="/databases" element={<DatabasesPage />} />
           <Route path="/ha" element={<HighAvailabilityPage />} />
+          <Route path="/operations" element={<OperationsPage />} />
           <Route path="/security" element={<SecurityPage />} />
           <Route path="/usage" element={<UsagePage />} />
           <Route path="/docs" element={<DocsPage />} />

app/frontend/src/app/layout/PlatformShell.tsx

@@ -3,6 +3,7 @@ import { useEffect, useState } from 'react';
 import { useMutation, useQuery, useQueryClient } from '@tanstack/react-query';
 import * as DropdownMenu from '@radix-ui/react-dropdown-menu';
 import {
+  Activity,
   Bell,
   BookOpen,
   ChartBar,
@@ -57,6 +58,7 @@ const navSections: NavSection[] = [
   {
     title: 'Operate',
     items: [
+      { label: 'Operations', href: '/operations', icon: Activity, hint: 'Live jobs & failures' },
       { label: 'Databases', href: '/databases', icon: Database, hint: 'Managed data services' },
       { label: 'High Availability', href: '/ha', icon: ShieldCheck, hint: 'Failover & health' },
       { label: 'Security', href: '/security', icon: Shield, hint: 'Scans & compliance' },

app/frontend/src/features/operations/pages/OperationsPage.tsx

@@ -0,0 +1,218 @@
+import { useQuery } from '@tanstack/react-query';
+import { useNavigate } from 'react-router-dom';
+import { getOperations, type OperationsView } from '@/lib/api-client';
+import { useDemoMode } from '@/lib/demo-mode';
+import { formatRelative } from '@/lib/time';
+import { DemoRestricted } from '@/shared/components';
+import { Activity, AlertTriangle, Clock, Database, Loader2, Timer } from 'lucide-react';
+
+function statusClass(status: string): string {
+  switch (status) {
+    case 'deployed':
+    case 'completed':
+    case 'success':
+      return 'text-[var(--success)]';
+    case 'failed':
+    case 'cancelled':
+    case 'rolled_back':
+      return 'text-[var(--error)]';
+    case 'building':
+    case 'deploying':
+    case 'in_progress':
+    case 'running':
+      return 'text-[var(--accent-primary)]';
+    default:
+      return 'text-[var(--warning)]';
+  }
+}
+
+function Section({ title, icon: Icon, count, children }: {
+  title: string;
+  icon: typeof Activity;
+  count: number;
+  children: React.ReactNode;
+}) {
+  return (
+    <section className="panel p-5">
+      <div className="flex items-center gap-2 mb-4">
+        <Icon size={16} className="text-[var(--accent-primary)]" />
+        <h2 className="text-sm font-semibold text-[var(--text-primary)]">{title}</h2>
+        <span className="text-xs text-[var(--text-muted)] mono">({count})</span>
+      </div>
+      {children}
+    </section>
+  );
+}
+
+function EmptyLine({ text }: { text: string }) {
+  return <p className="text-xs text-[var(--text-muted)]">{text}</p>;
+}
+
+export function OperationsPage() {
+  const isDemoMode = useDemoMode();
+  const navigate = useNavigate();
+
+  const opsQuery = useQuery({
+    queryKey: ['operations'],
+    queryFn: getOperations,
+    enabled: !isDemoMode,
+    refetchInterval: (query) =>
+      (query.state.data?.active_deployments?.length ?? 0) > 0 ? 3000 : 15000,
+  });
+
+  if (isDemoMode) {
+    return <DemoRestricted feature="Operations" />;
+  }
+
+  const ops: OperationsView | undefined = opsQuery.data;
+  const active = ops?.active_deployments ?? [];
+  const failed = ops?.recent_failures ?? [];
+  const cron = ops?.cron_runs ?? [];
+  const backups = ops?.backups ?? [];
+  const queue = ops?.deploy_queue ?? [];
+  const queuedTotal = queue.reduce((sum, q) => sum + q.queued, 0);
+
+  return (
+    <div className="min-h-screen">
+      <div className="border-b border-[var(--border-subtle)]">
+        <div className="w-full px-8 py-5">
+          <h1 className="v-title">Operations<span className="v-cursor">_</span></h1>
+          <p className="v-mono mt-1.5 text-[11px] text-[var(--text-tertiary)]">
+            Live view of deploys, queues, cron runs, and backups
+          </p>
+        </div>
+      </div>
+
+      {opsQuery.isLoading ? (
+        <div className="w-full px-8 py-12 flex justify-center">
+          <Loader2 size={20} className="animate-spin text-[var(--text-muted)]" />
+        </div>
+      ) : (
+        <div className="w-full px-8 py-6 space-y-6">
+          <div className="grid grid-cols-2 md:grid-cols-4 gap-4">
+            <div className="panel-soft p-4">
+              <p className="text-xs uppercase tracking-wider text-[var(--text-muted)]">In flight</p>
+              <p className="mt-1 text-2xl font-semibold text-[var(--accent-primary)]">{active.length}</p>
+            </div>
+            <div className="panel-soft p-4">
+              <p className="text-xs uppercase tracking-wider text-[var(--text-muted)]">Queued</p>
+              <p className="mt-1 text-2xl font-semibold text-[var(--warning)]">{queuedTotal}</p>
+            </div>
+            <div className="panel-soft p-4">
+              <p className="text-xs uppercase tracking-wider text-[var(--text-muted)]">Failed 24h</p>
+              <p className="mt-1 text-2xl font-semibold text-[var(--error)]">{failed.length}</p>
+            </div>
+            <div className="panel-soft p-4">
+              <p className="text-xs uppercase tracking-wider text-[var(--text-muted)]">Backups 24h</p>
+              <p className="mt-1 text-2xl font-semibold text-[var(--text-secondary)]">{backups.length}</p>
+            </div>
+          </div>
+
+          <div className="grid grid-cols-1 xl:grid-cols-2 gap-6">
+            <Section title="Active deployments" icon={Activity} count={active.length}>
+              {active.length === 0 ? (
+                <EmptyLine text="Nothing deploying right now." />
+              ) : (
+                <div className="space-y-2">
+                  {active.map((d) => (
+                    <button
+                      key={d.id}
+                      onClick={() => navigate(`/services/${d.service_id}`)}
+                      className="w-full flex items-center gap-3 px-3 py-2 rounded-[var(--radius-md)] hover:bg-[var(--surface-muted)] text-left transition-colors"
+                    >
+                      <Loader2 size={13} className="animate-spin text-[var(--accent-primary)] shrink-0" />
+                      <div className="min-w-0 flex-1">
+                        <span className="text-sm text-[var(--text-primary)]">{d.service_name}</span>
+                        <span className="text-xs text-[var(--text-muted)]"> · {d.project_name}</span>
+                      </div>
+                      <span className={`text-xs mono ${statusClass(d.status)}`}>{d.status}</span>
+                      <span className="text-xs text-[var(--text-muted)]">{formatRelative(d.created_at)}</span>
+                    </button>
+                  ))}
+                </div>
+              )}
+            </Section>
+
+            <Section title="Failed — last 24h" icon={AlertTriangle} count={failed.length}>
+              {failed.length === 0 ? (
+                <EmptyLine text="No recent failures." />
+              ) : (
+                <div className="space-y-2">
+                  {failed.map((d) => (
+                    <button
+                      key={d.id}
+                      onClick={() => navigate(`/services/${d.service_id}`)}
+                      className="w-full flex items-center gap-3 px-3 py-2 rounded-[var(--radius-md)] hover:bg-[var(--surface-muted)] text-left transition-colors"
+                    >
+                      <AlertTriangle size={13} className="text-[var(--error)] shrink-0" />
+                      <div className="min-w-0 flex-1">
+                        <span className="text-sm text-[var(--text-primary)]">{d.service_name}</span>
+                        <span className="text-xs text-[var(--text-muted)]"> · {d.project_name}</span>
+                        {d.error && (
+                          <p className="text-[11px] text-[var(--error)]/80 truncate">{d.error}</p>
+                        )}
+                      </div>
+                      <span className={`text-xs mono ${statusClass(d.status)}`}>{d.status}</span>
+                      <span className="text-xs text-[var(--text-muted)]">{formatRelative(d.created_at)}</span>
+                    </button>
+                  ))}
+                </div>
+              )}
+            </Section>
+
+            <Section title="Cron — last 24h" icon={Timer} count={cron.length}>
+              {cron.length === 0 ? (
+                <EmptyLine text="No cron runs in the last day." />
+              ) : (
+                <div className="space-y-1.5">
+                  {cron.map((r) => (
+                    <div key={r.id} className="flex items-center gap-3 px-3 py-1.5 text-xs">
+                      <span className={`mono ${statusClass(r.status)}`}>{r.status}</span>
+                      <span className="text-[var(--text-primary)]">{r.job_name}</span>
+                      <span className="mono text-[var(--text-muted)]">{r.schedule}</span>
+                      {r.error && <span className="text-[var(--error)]/80 truncate">{r.error}</span>}
+                      <span className="ml-auto text-[var(--text-muted)]">{formatRelative(r.started_at)}</span>
+                    </div>
+                  ))}
+                </div>
+              )}
+            </Section>
+
+            <Section title="Backups — last 24h" icon={Database} count={backups.length}>
+              {backups.length === 0 ? (
+                <EmptyLine text="No backups in the last day." />
+              ) : (
+                <div className="space-y-1.5">
+                  {backups.map((b) => (
+                    <div key={b.id} className="flex items-center gap-3 px-3 py-1.5 text-xs">
+                      <span className={`mono ${statusClass(b.status)}`}>{b.status}</span>
+                      <span className="text-[var(--text-primary)]">{b.database_name}</span>
+                      <span className="text-[var(--text-muted)]">{b.size}</span>
+                      <span className="ml-auto text-[var(--text-muted)]">{formatRelative(b.created_at)}</span>
+                    </div>
+                  ))}
+                </div>
+              )}
+            </Section>
+          </div>
+
+          {queue.length > 0 && (
+            <Section title="Deploy queue depth" icon={Clock} count={queue.length}>
+              <div className="space-y-1.5">
+                {queue.map((q) => (
+                  <div key={q.service_id} className="flex items-center gap-3 px-3 py-1.5 text-xs mono">
+                    <span className="text-[var(--text-secondary)]">{q.service_id.slice(0, 8)}</span>
+                    <span className={q.running ? 'text-[var(--accent-primary)]' : 'text-[var(--text-muted)]'}>
+                      {q.running ? 'running' : 'idle'}
+                    </span>
+                    <span className="text-[var(--warning)]">{q.queued} queued</span>
+                  </div>
+                ))}
+              </div>
+            </Section>
+          )}
+        </div>
+      )}
+    </div>
+  );
+}

app/frontend/src/generated/api-types.ts

@@ -3757,6 +3757,58 @@ export interface paths {
         patch?: never;
         trace?: never;
     };
+    "/operations": {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        /**
+         * Cross-cutting operations view
+         * @description Single snapshot of platform work scoped to the caller's projects
+         *     (admins see all): active deployments, in-memory deploy-queue
+         *     depth per service, deployments that failed in the last 24h,
+         *     cron executions and database backups from the last 24h.
+         */
+        get: {
+            parameters: {
+                query?: never;
+                header?: never;
+                path?: never;
+                cookie?: never;
+            };
+            requestBody?: never;
+            responses: {
+                /** @description Operations snapshot */
+                200: {
+                    headers: {
+                        [name: string]: unknown;
+                    };
+                    content: {
+                        "application/json": {
+                            active_deployments?: Record<string, never>[];
+                            deploy_queue?: {
+                                service_id?: string;
+                                running?: boolean;
+                                queued?: number;
+                            }[];
+                            recent_failures?: Record<string, never>[];
+                            cron_runs?: Record<string, never>[];
+                            backups?: Record<string, never>[];
+                        };
+                    };
+                };
+            };
+        };
+        put?: never;
+        post?: never;
+        delete?: never;
+        options?: never;
+        head?: never;
+        patch?: never;
+        trace?: never;
+    };
     "/audit-logs": {
         parameters: {
             query?: never;

app/frontend/src/generated/docs-snapshot.ts

@@ -40,7 +40,7 @@ export const bundledDocs: BundledDoc[] = [
     "path": "guides/CLI.md",
     "section": "guides",
     "title": "Containr CLI",
-    "markdown": "# Containr CLI\n\nThe CLI controls every part of a Containr instance — the same API surface\nthe web UI uses. Build it with `scripts/build-cli.sh` or\n`go build ./cmd/cli` from `app/backend`.\n\n## Authentication\n\nCreate a personal access token in the web UI under\n**Settings → Personal Access Tokens** (or `containr tokens create`), then:\n\n```bash\ncontainr auth login cnp_...                      # verify + store\ncontainr auth login cnp_... --url https://containr.example.com\ncontainr auth login cnp_... --name production    # named profile\ncontainr auth status                             # show active profile + identity\ncontainr auth logout\n```\n\nResolution order for every command: `--token`/`--api-url` flags >\n`CONTAINR_TOKEN`/`CONTAINR_API_URL` env > active profile >\n`http://localhost:8080/api/v1`. The active profile is `--profile` >\n`CONTAINR_PROFILE` > `current_profile` in `~/.containr.yaml`.\n\n## Output and scripting\n\n- `--json` prints the raw API response — safe to pipe and parse.\n- `--yes` / `-y` skips confirmation on destructive commands (delete,\n  revoke, restore, failover). Non-interactive shells refuse destructive\n  commands without it.\n- Exit codes are stable: `0` ok, `1` error, `2` auth/permission,\n  `3` not found, `4` validation, `5` unreachable.\n\n## Commands\n\n```\nauth login|logout|status         token auth and profiles\ntokens list|create|revoke        personal access tokens\nprojects list|get|create|delete\nservices list|get|create|update|delete|start|stop|restart|redeploy\nservices clone|move              duplicate config or re-parent a service\nservices domains list|add|remove|default|check   multi-domain + DNS preflight\nregistries list|add|update|remove  private-image pull credentials\nvolumes list|delete              docker volume inventory + cleanup (admin)\ndeploy <service-id>              trigger a deployment (--no-cache, --commit-hash, --branch)\ndeployments list|get|logs|rollback|cancel\nlogs <service-id> [--follow]     runtime logs (SSE follow)\nexec <service-id> -- <cmd>       one-off container command\nvariables list|set|unset         env vars (secrets masked; --redeploy applies them)\nvariables shared list|set|unset  project shared vars — referenced as ${{shared.KEY}}\ndatabases list|get|create|update|delete|action|backup|restore|download-backup|import-backup\n                               import-backup <id> <file.tar.gz|-> uploads an archive as a restore\n                               point; ships offsite too when a backup target is assigned\ndatabases list|get|create|update|delete|action|backup|restore|download-backup\n                               create --public exposes the port on all interfaces;\n                               update <id> --public/--public=false toggles it (container recreates, data persists)\ndatabases register <name>      register an external database (--type --host --port --database --username --password --ssl; probed before storing)\ndatabases test-connection      probe a connection — by id, or ad-hoc flags\nbackup-targets list|add|update|remove|test\n                               S3-compatible archive destinations; add/update probe the bucket\n                               first, empty --access-key/--secret-key on update keep stored keys;\n                               update <db-id> --backup-target assigns a target (\"\" clears it)\ncron list|get|create|delete|trigger|executions\ntemplates list|get|create|delete|deploy|plan|import-compose|deploy-graph\n                               deploy --name --var K=V; plan dry-resolves expressions;\n                               import-compose <compose.yml|-> converts a compose file into\n                               a v2 graph config; deploy-graph <project-id> <config.json|->\n                               deploys an ad-hoc service graph\nimport compose <project-id> <compose.yml|->\n                               deploys a docker-compose file straight into a project —\n                               no template row. DB images become managed databases\n                               attached under their service name; --var K=V overrides\n                               template variables\nnodes list|get|delete|tokens     node agents + onboarding tokens (admin)\nscaling status|policies|services|scale\nha status|alerts|health|policies|enable|disable|failover\nsecurity scan|vulnerabilities|metrics\ngateway services|keys|analytics  (admin)\nadmin overview|users|settings|audit-logs\nnotifications list|read\nwebhooks list|create|update|delete|deliveries|test\n                               outbound signed webhooks — create <name> <url>\n                               --event 'service.*' (repeatable, '*' = all);\n                               deliveries are HMAC-signed (X-Containr-Signature)\nup                               deploy the current directory\n```\n\n## containr up\n\nRun inside a git checkout: uses `remote.origin.url` + the current branch\Line truncated
+    "markdown": "# Containr CLI\n\nThe CLI controls every part of a Containr instance — the same API surface\nthe web UI uses. Build it with `scripts/build-cli.sh` or\n`go build ./cmd/cli` from `app/backend`.\n\n## Authentication\n\nCreate a personal access token in the web UI under\n**Settings → Personal Access Tokens** (or `containr tokens create`), then:\n\n```bash\ncontainr auth login cnp_...                      # verify + store\ncontainr auth login cnp_... --url https://containr.example.com\ncontainr auth login cnp_... --name production    # named profile\ncontainr auth status                             # show active profile + identity\ncontainr auth logout\n```\n\nResolution order for every command: `--token`/`--api-url` flags >\n`CONTAINR_TOKEN`/`CONTAINR_API_URL` env > active profile >\n`http://localhost:8080/api/v1`. The active profile is `--profile` >\n`CONTAINR_PROFILE` > `current_profile` in `~/.containr.yaml`.\n\n## Output and scripting\n\n- `--json` prints the raw API response — safe to pipe and parse.\n- `--yes` / `-y` skips confirmation on destructive commands (delete,\n  revoke, restore, failover). Non-interactive shells refuse destructive\n  commands without it.\n- Exit codes are stable: `0` ok, `1` error, `2` auth/permission,\n  `3` not found, `4` validation, `5` unreachable.\n\n## Commands\n\n```\nauth login|logout|status         token auth and profiles\ntokens list|create|revoke        personal access tokens\nprojects list|get|create|delete\nservices list|get|create|update|delete|start|stop|restart|redeploy\nservices clone|move              duplicate config or re-parent a service\nservices domains list|add|remove|default|check   multi-domain + DNS preflight\nregistries list|add|update|remove  private-image pull credentials\nvolumes list|delete              docker volume inventory + cleanup (admin)\ndeploy <service-id>              trigger a deployment (--no-cache, --commit-hash, --branch)\ndeployments list|get|logs|rollback|cancel\nlogs <service-id> [--follow]     runtime logs (SSE follow)\nexec <service-id> -- <cmd>       one-off container command\nvariables list|set|unset         env vars (secrets masked; --redeploy applies them)\nvariables shared list|set|unset  project shared vars — referenced as ${{shared.KEY}}\ndatabases list|get|create|update|delete|action|backup|restore|download-backup|import-backup\n                               import-backup <id> <file.tar.gz|-> uploads an archive as a restore\n                               point; ships offsite too when a backup target is assigned\ndatabases list|get|create|update|delete|action|backup|restore|download-backup\n                               create --public exposes the port on all interfaces;\n                               update <id> --public/--public=false toggles it (container recreates, data persists)\ndatabases register <name>      register an external database (--type --host --port --database --username --password --ssl; probed before storing)\ndatabases test-connection      probe a connection — by id, or ad-hoc flags\nbackup-targets list|add|update|remove|test\n                               S3-compatible archive destinations; add/update probe the bucket\n                               first, empty --access-key/--secret-key on update keep stored keys;\n                               update <db-id> --backup-target assigns a target (\"\" clears it)\ncron list|get|create|delete|trigger|executions\ntemplates list|get|create|delete|deploy|plan|import-compose|deploy-graph\n                               deploy --name --var K=V; plan dry-resolves expressions;\n                               import-compose <compose.yml|-> converts a compose file into\n                               a v2 graph config; deploy-graph <project-id> <config.json|->\n                               deploys an ad-hoc service graph\nimport compose <project-id> <compose.yml|->\n                               deploys a docker-compose file straight into a project —\n                               no template row. DB images become managed databases\n                               attached under their service name; --var K=V overrides\n                               template variables\nnodes list|get|delete|tokens     node agents + onboarding tokens (admin)\nscaling status|policies|services|scale\nha status|alerts|health|policies|enable|disable|failover\nsecurity scan|vulnerabilities|metrics\ngateway services|keys|analytics  (admin)\nadmin overview|users|settings|audit-logs\nnotifications list|read\nwebhooks list|create|update|delete|deliveries|test\n                               outbound signed webhooks — create <name> <url>\n                               --event 'service.*' (repeatable, '*' = all);\n                               deliveries are HMAC-signed (X-Containr-Signature)\noperations                       live ops view: active deploys, queue depth,\n                               24h failures, cron runs, backups\nup                
Line truncated
   },
   {
     "path": "guides/CLOUDFLARE_SETUP.md",

app/frontend/src/lib/api-client.ts

@@ -1827,6 +1827,45 @@ export async function testWebhook(id: string): Promise<void> {
   await requestJson(`/webhooks/${id}/test`, { method: 'POST', body: JSON.stringify({}) });
 }
 
+export type OperationsView = {
+  active_deployments: Array<{
+    id: string;
+    service_id: string;
+    service_name: string;
+    project_name: string;
+    status: string;
+    image: string;
+    error?: string | null;
+    started_at?: string | null;
+    completed_at?: string | null;
+    created_at: string;
+  }>;
+  deploy_queue: Array<{ service_id: string; running: boolean; queued: number }>;
+  recent_failures: OperationsView['active_deployments'];
+  cron_runs: Array<{
+    id: string;
+    job_name: string;
+    schedule: string;
+    status: string;
+    started_at: string;
+    finished_at?: string | null;
+    error?: string | null;
+  }>;
+  backups: Array<{
+    id: string;
+    database_id: string;
+    database_name: string;
+    status: string;
+    size: string;
+    created_at: string;
+    completed_at?: string | null;
+  }>;
+};
+
+export async function getOperations(): Promise<OperationsView> {
+  return requestJson<OperationsView>('/operations');
+}
+
 export function serviceStatusClass(status: ServiceStatus): string {
   switch (status) {
     case 'running':

docs/api/openapi.yaml

@@ -2533,6 +2533,54 @@ paths:
               schema:
                 $ref: '#/components/schemas/MessageResponse'
 
+  /operations:
+    get:
+      tags:
+        - Operations
+      summary: Cross-cutting operations view
+      description: |
+        Single snapshot of platform work scoped to the caller's projects
+        (admins see all): active deployments, in-memory deploy-queue
+        depth per service, deployments that failed in the last 24h,
+        cron executions and database backups from the last 24h.
+      security:
+        - bearerAuth: []
+      responses:
+        '200':
+          description: Operations snapshot
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  active_deployments:
+                    type: array
+                    items:
+                      type: object
+                  deploy_queue:
+                    type: array
+                    items:
+                      type: object
+                      properties:
+                        service_id:
+                          type: string
+                        running:
+                          type: boolean
+                        queued:
+                          type: integer
+                  recent_failures:
+                    type: array
+                    items:
+                      type: object
+                  cron_runs:
+                    type: array
+                    items:
+                      type: object
+                  backups:
+                    type: array
+                    items:
+                      type: object
+
   # Audit Logs
   /audit-logs:
     get:

docs/guides/CLI.md

@@ -82,6 +82,8 @@ webhooks list|create|update|delete|deliveries|test
                                outbound signed webhooks — create <name> <url>
                                --event 'service.*' (repeatable, '*' = all);
                                deliveries are HMAC-signed (X-Containr-Signature)
+operations                       live ops view: active deploys, queue depth,
+                               24h failures, cron runs, backups
 up                               deploy the current directory
 ```