fix(bird): route LoadBalancer VIP replies into table 47 (#1547)

A reply from a LoadBalancer VIP reaches the kernel's routing decision
with the VIP as its source: Cilium reverses the service NAT in
from-container before the packet enters the stack. The pod-source rules
1000/1001 do not match it, so it took main's default over mgmt0 while
the request had arrived on ingress0 as the BGP next hop.

bird's DaemonSet gets a vip-rules container that reads every enabled
CiliumLoadBalancerIPPool and keeps one rule per block, priority 1002,
`from <block> lookup 47`, reconciled every minute. The pool stays the
only place the prefixes are written. Like the pod rules, a rule into an
empty table 47 (bird gone) falls through to main.

bgp-pool's blocks move from start/stop to the equivalent CIDRs so each
block maps to one rule. Cilium v1.20.4 LB-IPAM compares a modified
pool's blocks by first and last address (handlePoolModified,
LBRange.EqualCIDR), and allowFirstLastIPs unset keeps .0/.255 and
fd99::/fd99::ff allocatable, so the ranges are kept and no service is
reallocated.

Closes #1547

.woodpecker/ci-scripts-test.yml

@@ -35,25 +35,25 @@ when:
 steps:
   - name: model-selection-tests
     depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.312
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.316
     commands:
       - sh scripts/ci/test-model-selection.sh
 
   - name: pr-review-mistral-tests
     depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.312
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.316
     commands:
       - sh scripts/ci/test-pr-review-mistral.sh
 
   - name: promtool-rules-guard-tests
     depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.312
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.316
     commands:
       - sh scripts/ci/test-promtool-rules.sh
 
   - name: yaml-citations-guard-tests
     depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.312
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.316
     commands:
       - sh scripts/ci/test-yaml-citations.sh
 

.woodpecker/e2e.yml

@@ -26,7 +26,7 @@ steps:
     # fetch-models.sh response mapping. No cluster, no secrets, no network — the
     # ci-claude image just provides sh + jq. Keeps the flag-injection regression
     # test from rotting (it exercises the exact injection shapes).
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.312
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.316
     commands:
       - sh scripts/ci/test-model-selection.sh
 

.woodpecker/security-scan.yml

@@ -70,7 +70,7 @@ steps:
     # this step is skipped — otherwise we'd fork-bomb PRs.
     when:
       - branch: main
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.312
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.316
     environment:
       CLAUDE_CODE_OAUTH_TOKEN:
         from_secret: claude_code_oauth_token

.woodpecker/update-audit.yml

@@ -30,7 +30,7 @@ when:
 
 steps:
   - name: update-audit-agent
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.312
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.316
     environment:
       CLAUDE_CODE_OAUTH_TOKEN:
         from_secret: claude_code_oauth_token

ci/images/kuma-sync/api/v1alpha1/kumamonitor_types.go

@@ -97,6 +97,10 @@ type KumaMonitorSpec struct {
 	// +kubebuilder:validation:Minimum=0
 	// +kubebuilder:default=0
 	MaxRetries int32 `json:"maxRetries,omitempty"`
+	// Consecutive DOWN heartbeats after which Kuma sends the DOWN notification
+	// again, not minutes; 0 sends it once per outage.
+	// +kubebuilder:validation:Minimum=0
+	ResendInterval int32 `json:"resendInterval,omitempty"`
 	// Seconds.
 	// +kubebuilder:validation:Minimum=1
 	Timeout     *int32 `json:"timeout,omitempty"`

ci/images/kuma-sync/api/v1alpha1/validation_test.go

@@ -131,6 +131,15 @@ func TestNegativeMaxRetriesRejected(t *testing.T) {
 	expectInvalid(t, m, "spec.maxRetries")
 }
 
+func TestNegativeResendIntervalRejected(t *testing.T) {
+	m := monitor("neg-resend", KumaMonitorSpec{
+		Type:           "group",
+		DisplayName:    "g",
+		ResendInterval: -1,
+	})
+	expectInvalid(t, m, "spec.resendInterval")
+}
+
 func TestJSONQueryBadOperator(t *testing.T) {
 	m := monitor("jq-bad-op", KumaMonitorSpec{
 		Type:        "json-query",

ci/images/kuma-sync/cmd/kuma-sync/config.go

@@ -3,19 +3,25 @@ package main
 import (
 	"errors"
 	"fmt"
+	"strings"
+
+	"k8s.io/apimachinery/pkg/types"
+	"k8s.io/apimachinery/pkg/util/validation"
 )
 
 type config struct {
 	URL      string
 	Username string
 	Password string
+	// RootGroup is the zero value when KUMA_ROOT_GROUP is unset.
+	RootGroup types.NamespacedName
 }
 
 // loadConfig reads the Kuma connection settings from the environment. It
-// names every missing variable.
+// names every missing or invalid variable.
 func loadConfig(getenv func(string) string) (config, error) {
 	var cfg config
-	var missing []error
+	var errs []error
 	for _, v := range []struct {
 		name string
 		dst  *string
@@ -25,8 +31,30 @@ func loadConfig(getenv func(string) string) (config, error) {
 		{"KUMA_PASSWORD", &cfg.Password},
 	} {
 		if *v.dst = getenv(v.name); *v.dst == "" {
-			missing = append(missing, fmt.Errorf("missing required environment variable %s", v.name))
+			errs = append(errs, fmt.Errorf("missing required environment variable %s", v.name))
 		}
 	}
-	return cfg, errors.Join(missing...)
+	if raw := getenv("KUMA_ROOT_GROUP"); raw != "" {
+		root, err := parseRootGroup(raw)
+		if err != nil {
+			errs = append(errs, fmt.Errorf("KUMA_ROOT_GROUP: %w", err))
+		}
+		cfg.RootGroup = root
+	}
+	return cfg, errors.Join(errs...)
+}
+
+// parseRootGroup parses namespace/name of a KumaMonitor.
+func parseRootGroup(raw string) (types.NamespacedName, error) {
+	ns, name, ok := strings.Cut(raw, "/")
+	if !ok || strings.Contains(name, "/") {
+		return types.NamespacedName{}, fmt.Errorf("%q is not namespace/name", raw)
+	}
+	if msgs := validation.IsDNS1123Label(ns); len(msgs) > 0 {
+		return types.NamespacedName{}, fmt.Errorf("namespace %q: %s", ns, strings.Join(msgs, "; "))
+	}
+	if msgs := validation.IsDNS1123Subdomain(name); len(msgs) > 0 {
+		return types.NamespacedName{}, fmt.Errorf("name %q: %s", name, strings.Join(msgs, "; "))
+	}
+	return types.NamespacedName{Namespace: ns, Name: name}, nil
 }

ci/images/kuma-sync/cmd/kuma-sync/config_test.go

@@ -3,6 +3,8 @@ package main
 import (
 	"strings"
 	"testing"
+
+	"k8s.io/apimachinery/pkg/types"
 )
 
 func TestLoadConfig(t *testing.T) {
@@ -36,3 +38,21 @@ func TestLoadConfig(t *testing.T) {
 		}
 	}
 }
+
+func TestLoadConfigRootGroup(t *testing.T) {
+	env := func(root string) func(string) string {
+		m := map[string]string{"KUMA_URL": "http://kuma", "KUMA_USERNAME": "u", "KUMA_PASSWORD": "p", "KUMA_ROOT_GROUP": root}
+		return func(k string) string { return m[k] }
+	}
+
+	cfg, err := loadConfig(env("kuma-sync/renner-uno"))
+	if err != nil || cfg.RootGroup != (types.NamespacedName{Namespace: "kuma-sync", Name: "renner-uno"}) {
+		t.Fatalf("cfg=%+v err=%v", cfg, err)
+	}
+
+	for _, bad := range []string{"renner-uno", "/renner-uno", "kuma-sync/", "a/b/c", "Kuma/x", "ns/UPPER", " ns/x"} {
+		if _, err := loadConfig(env(bad)); err == nil || !strings.Contains(err.Error(), "KUMA_ROOT_GROUP") {
+			t.Errorf("%q: err = %v, want KUMA_ROOT_GROUP rejected", bad, err)
+		}
+	}
+}

ci/images/kuma-sync/cmd/kuma-sync/main.go

@@ -48,6 +48,7 @@ func run() error {
 		GCInterval:  5 * time.Minute,
 		OrphanGrace: time.Hour,
 		Resync:      5 * time.Minute,
+		RootGroup:   cfg.RootGroup,
 	})
 	if err != nil {
 		return err

ci/images/kuma-sync/config/crd/uptime.renner.uno_kumamonitors.yaml

@@ -222,6 +222,13 @@ spec:
                 - hostname
                 - port
                 type: object
+              resendInterval:
+                description: |-
+                  Consecutive DOWN heartbeats after which Kuma sends the DOWN notification
+                  again, not minutes; 0 sends it once per outage.
+                format: int32
+                minimum: 0
+                type: integer
               retryInterval:
                 default: 60
                 description: Seconds.

ci/images/kuma-sync/internal/app/manager.go

@@ -10,6 +10,7 @@ import (
 	"time"
 
 	"k8s.io/apimachinery/pkg/runtime"
+	"k8s.io/apimachinery/pkg/types"
 	clientgoscheme "k8s.io/client-go/kubernetes/scheme"
 	"k8s.io/client-go/rest"
 	"k8s.io/utils/ptr"
@@ -41,6 +42,9 @@ type Options struct {
 	// Resync is how often a healthy resource is reconciled again, which is
 	// what repairs drift made in Kuma; 0 means 5 minutes.
 	Resync time.Duration
+	// RootGroup is the group KumaMonitor that monitors without a parentRef are
+	// placed under; the zero value leaves them at the top level.
+	RootGroup types.NamespacedName
 
 	// SkipNameValidation allows several managers in one process, as in tests
 	// that restart the manager.
@@ -72,7 +76,9 @@ func NewManager(o Options) (manager.Manager, error) {
 		return nil, fmt.Errorf("create manager: %w", err)
 	}
 
-	if err := (&controller.Reconciler{Client: mgr.GetClient(), Kuma: o.Kuma, Resync: o.Resync}).SetupWithManager(mgr); err != nil {
+	if err := (&controller.Reconciler{
+		Client: mgr.GetClient(), Kuma: o.Kuma, Resync: o.Resync, RootGroup: o.RootGroup,
+	}).SetupWithManager(mgr); err != nil {
 		return nil, fmt.Errorf("set up reconciler: %w", err)
 	}
 	if err := (&controller.StatusPageReconciler{Client: mgr.GetClient(), Kuma: o.Kuma, Resync: o.Resync}).SetupWithManager(mgr); err != nil {

ci/images/kuma-sync/internal/controller/kumamonitor_controller.go

@@ -58,6 +58,15 @@ type Reconciler struct {
 	// Resync is how often a healthy resource is reconciled again, which repairs
 	// drift made in Kuma. 0 means 5 minutes.
 	Resync time.Duration
+	// RootGroup is the group KumaMonitor every monitor without a parentRef is
+	// placed under in Kuma; the zero value places them at the top level.
+	RootGroup types.NamespacedName
+}
+
+func (r *Reconciler) hasRoot() bool { return r.RootGroup.Name != "" }
+
+func (r *Reconciler) isRoot(o client.Object) bool {
+	return r.hasRoot() && o.GetNamespace() == r.RootGroup.Namespace && o.GetName() == r.RootGroup.Name
 }
 
 func (r *Reconciler) resync() time.Duration {
@@ -70,14 +79,18 @@ func (r *Reconciler) resync() time.Duration {
 // SetupWithManager ignores status-only updates, which keeps failure backoff
 // intact. Deletion still reconciles: setting deletionTimestamp bumps
 // metadata.generation. A KumaNotification whose ID changes enqueues the
-// monitors referencing it.
+// monitors referencing it; a change to the root group enqueues the monitors
+// without a parentRef.
 func (r *Reconciler) SetupWithManager(mgr ctrl.Manager) error {
-	return ctrl.NewControllerManagedBy(mgr).
+	b := ctrl.NewControllerManagedBy(mgr).
 		For(&v1.KumaMonitor{}, builder.WithPredicates(predicate.GenerationChangedPredicate{})).
 		Watches(&v1.KumaNotification{}, handler.EnqueueRequestsFromMapFunc(r.referencingMonitors),
-			builder.WithPredicates(predicate.Funcs{UpdateFunc: notificationIDChanged})).
-		Named("kumamonitor").
-		Complete(r)
+			builder.WithPredicates(predicate.Funcs{UpdateFunc: notificationIDChanged}))
+	if r.hasRoot() {
+		b = b.Watches(&v1.KumaMonitor{}, handler.EnqueueRequestsFromMapFunc(r.rootChildren),
+			builder.WithPredicates(r.rootPredicate()))
+	}
+	return b.Named("kumamonitor").Complete(r)
 }
 
 // failure is a Ready=False outcome. The message is fixed per reason; the cause
@@ -99,6 +112,9 @@ const (
 	msgParentNotGroup      = "parent must be of type group"
 	msgParentCycle         = "parentRef forms a cycle"
 	msgParentTooDeep       = "parentRef chain is too deep"
+	msgRootPending         = "root group has no monitor ID yet"
+	msgRootNotGroup        = "root group must be of type group"
+	msgRootHasParent       = "root group must not have a parentRef"
 	msgNotificationPending = "a referenced notification has no notification ID yet"
 	msgSynced              = "monitor in sync"
 	msgNotOwned            = "previous monitor exists without our ownership tag; restore the tag or delete it in Kuma"
@@ -119,17 +135,24 @@ func (r *Reconciler) Reconcile(ctx context.Context, req ctrl.Request) (ctrl.Resu
 	}
 
 	desired := Desired(km)
-	if km.Spec.ParentRef != nil {
-		p, err := r.resolveParent(ctx, km)
-		if err != nil {
+	var p parentOutcome
+	var err error
+	switch {
+	case km.Spec.ParentRef != nil:
+		p, err = r.resolveParent(ctx, km)
+	case r.hasRoot() && !r.isRoot(km):
+		p, err = r.resolveRoot(ctx)
+	}
+	if err != nil {
+		return ctrl.Result{}, err
+	}
+	if p.reason != "" {
+		if err := r.setReady(ctx, km, metav1.ConditionFalse, p.reason, p.message, nil); err != nil {
 			return ctrl.Result{}, err
 		}
-		if p.reason != "" {
-			if err := r.setReady(ctx, km, metav1.ConditionFalse, p.reason, p.message, nil); err != nil {
-				return ctrl.Result{}, err
-			}
-			return ctrl.Result{RequeueAfter: p.requeue}, nil
-		}
+		return ctrl.Result{RequeueAfter: p.requeue}, nil
+	}
+	if p.id != 0 {
 		desired.Parent = &p.id
 	}
 
@@ -323,8 +346,75 @@ type parentOutcome struct {
 	requeue time.Duration
 }
 
+// rootChanged reports changes to the root group that alter what the monitors
+// without a parentRef resolve to.
+func rootChanged(e event.UpdateEvent) bool {
+	o, ok1 := e.ObjectOld.(*v1.KumaMonitor)
+	n, ok2 := e.ObjectNew.(*v1.KumaMonitor)
+	if !ok1 || !ok2 {
+		return true
+	}
+	return o.Status.MonitorID != n.Status.MonitorID ||
+		o.Spec.Type != n.Spec.Type ||
+		(o.Spec.ParentRef == nil) != (n.Spec.ParentRef == nil) ||
+		o.DeletionTimestamp.IsZero() != n.DeletionTimestamp.IsZero()
+}
+
+// rootPredicate passes events of the root group only.
+func (r *Reconciler) rootPredicate() predicate.Funcs {
+	return predicate.Funcs{
+		CreateFunc:  func(e event.CreateEvent) bool { return r.isRoot(e.Object) },
+		DeleteFunc:  func(e event.DeleteEvent) bool { return r.isRoot(e.Object) },
+		GenericFunc: func(e event.GenericEvent) bool { return r.isRoot(e.Object) },
+		UpdateFunc:  func(e event.UpdateEvent) bool { return r.isRoot(e.ObjectNew) && rootChanged(e) },
+	}
+}
+
+// rootChildren enqueues the KumaMonitors of all namespaces that have no
+// parentRef, except the root group itself.
+func (r *Reconciler) rootChildren(ctx context.Context, _ client.Object) []reconcile.Request {
+	var list v1.KumaMonitorList
+	if err := r.Client.List(ctx, &list); err != nil {
+		log.FromContext(ctx).Error(err, "list KumaMonitors to enqueue")
+		return nil
+	}
+	var reqs []reconcile.Request
+	for i := range list.Items {
+		km := &list.Items[i]
+		if km.Spec.ParentRef == nil && !r.isRoot(km) {
+			reqs = append(reqs, reconcile.Request{NamespacedName: types.NamespacedName{Namespace: km.Namespace, Name: km.Name}})
+		}
+	}
+	return reqs
+}
+
+// resolveRoot returns the Kuma ID of the root group for a monitor without a
+// parentRef. The root must be a group without a parentRef: under one of its
+// own ancestors it would close a cycle in Kuma.
+func (r *Reconciler) resolveRoot(ctx context.Context) (parentOutcome, error) {
+	pending := parentOutcome{reason: ReasonParentPending, message: msgRootPending, requeue: parentRetry}
+	root := &v1.KumaMonitor{}
+	err := r.Client.Get(ctx, r.RootGroup, root)
+	if apierrors.IsNotFound(err) {
+		return pending, nil
+	}
+	if err != nil {
+		return parentOutcome{}, err
+	}
+	switch {
+	case root.Spec.Type != "group":
+		return parentOutcome{reason: ReasonInvalidParent, message: msgRootNotGroup, requeue: r.resync()}, nil
+	case root.Spec.ParentRef != nil:
+		return parentOutcome{reason: ReasonInvalidParent, message: msgRootHasParent, requeue: r.resync()}, nil
+	case root.Status.MonitorID == 0 || !root.DeletionTimestamp.IsZero():
+		return pending, nil
+	}
+	return parentOutcome{id: root.Status.MonitorID}, nil
+}
+
 // resolveParent checks the whole parentRef chain: every ancestor must exist
-// and be a group, without cycles or more than maxParentDepth levels.
+// and be a group, without cycles or more than maxParentDepth levels. The root
+// group, which the topmost ancestor is placed under, counts as a level.
 func (r *Reconciler) resolveParent(ctx context.Context, km *v1.KumaMonitor) (parentOutcome, error) {
 	invalid := func(msg string) (parentOutcome, error) {
 		return parentOutcome{reason: ReasonInvalidParent, message: msg, requeue: r.resync()}, nil
@@ -334,7 +424,8 @@ func (r *Reconciler) resolveParent(ctx context.Context, km *v1.KumaMonitor) (par
 	visited := map[string]bool{km.Name: true}
 	cur := km
 	var directID int64
-	for depth := 0; cur.Spec.ParentRef != nil; depth++ {
+	depth := 0
+	for ; cur.Spec.ParentRef != nil; depth++ {
 		if depth >= maxParentDepth {
 			return invalid(msgParentTooDeep)
 		}
@@ -359,6 +450,9 @@ func (r *Reconciler) resolveParent(ctx context.Context, km *v1.KumaMonitor) (par
 		}
 		cur = parent
 	}
+	if r.hasRoot() && !r.isRoot(cur) && depth >= maxParentDepth {
+		return invalid(msgParentTooDeep)
+	}
 	if directID == 0 {
 		return pending, nil
 	}

ci/images/kuma-sync/internal/controller/mapping.go

@@ -24,14 +24,15 @@ func OwnerKey(km *v1.KumaMonitor) string {
 func Desired(km *v1.KumaMonitor) kumaclient.Monitor {
 	s := km.Spec
 	m := kumaclient.Monitor{
-		Type:          s.Type,
-		Name:          s.DisplayName,
-		Description:   s.Description,
-		Active:        !s.Paused,
-		Interval:      s.Interval,
-		RetryInterval: s.RetryInterval,
-		MaxRetries:    s.MaxRetries,
-		OwnerKey:      OwnerKey(km),
+		Type:           s.Type,
+		Name:           s.DisplayName,
+		Description:    s.Description,
+		Active:         !s.Paused,
+		Interval:       s.Interval,
+		RetryInterval:  s.RetryInterval,
+		MaxRetries:     s.MaxRetries,
+		ResendInterval: s.ResendInterval,
+		OwnerKey:       OwnerKey(km),
 	}
 	if s.Timeout != nil {
 		m.Timeout = *s.Timeout

ci/images/kuma-sync/internal/controller/mapping_test.go

@@ -57,6 +57,8 @@ func TestMappingAllTypes(t *testing.T) {
 	port.Port = &v1.PortSpec{Hostname: "p.com", Port: 443}
 	paused := base("group")
 	paused.Paused = true
+	resend := base("group")
+	resend.ResendInterval = 60
 
 	wantKW := withHTTP(common("keyword"))
 	wantKW.Keyword, wantKW.InvertKeyword = "ok", true
@@ -74,6 +76,8 @@ func TestMappingAllTypes(t *testing.T) {
 	wantPort.Hostname, wantPort.Port = "p.com", 443
 	wantPaused := common("group")
 	wantPaused.Active = false
+	wantResend := common("group")
+	wantResend.ResendInterval = 60
 
 	cases := []struct {
 		name string
@@ -88,6 +92,7 @@ func TestMappingAllTypes(t *testing.T) {
 		{"dns with conditions", dnsCond, wantDNSCond},
 		{"port", port, wantPort},
 		{"paused maps to inactive", paused, wantPaused},
+		{"resend interval", resend, wantResend},
 	}
 	for _, c := range cases {
 		got := Desired(mk(c.spec))

ci/images/kuma-sync/internal/controller/rootgroup_test.go

@@ -0,0 +1,209 @@
+package controller
+
+import (
+	"fmt"
+	"slices"
+	"testing"
+	"time"
+
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+	"k8s.io/apimachinery/pkg/types"
+	"sigs.k8s.io/controller-runtime/pkg/client"
+	"sigs.k8s.io/controller-runtime/pkg/event"
+
+	v1 "gitea.renner.uno/konairius/homelab/kuma-sync/api/v1alpha1"
+)
+
+const rootID = 7
+
+var rootName = types.NamespacedName{Namespace: "default", Name: "root"}
+
+func rootGroup() *v1.KumaMonitor {
+	g := group("root", "")
+	g.Status.MonitorID = rootID
+	return g
+}
+
+func newRootEnv(t *testing.T, objs ...client.Object) *env {
+	t.Helper()
+	e := newEnv(t, objs...)
+	e.r.RootGroup = rootName
+	return e
+}
+
+func (e *env) parentOf(t *testing.T, name string) *int64 {
+	t.Helper()
+	got := e.kuma.Get(e.get(t, name).Status.MonitorID)
+	if got == nil {
+		t.Fatalf("%s: no Kuma monitor", name)
+	}
+	return got.Parent
+}
+
+func TestRootGroupParentsParentless(t *testing.T) {
+	e := newRootEnv(t, rootGroup(), httpMonitor("a"))
+	if _, err := e.reconcile(t, "a"); err != nil {
+		t.Fatal(err)
+	}
+	if p := e.parentOf(t, "a"); p == nil || *p != rootID {
+		t.Errorf("parent = %v, want %d", p, rootID)
+	}
+}
+
+func TestRootGroupKeepsParentRef(t *testing.T) {
+	grp := group("grp", "")
+	grp.Status.MonitorID = 42
+	child := httpMonitor("child")
+	child.Spec.ParentRef = &v1.LocalRef{Name: "grp"}
+	e := newRootEnv(t, rootGroup(), grp, child)
+	if _, err := e.reconcile(t, "child"); err != nil {
+		t.Fatal(err)
+	}
+	if p := e.parentOf(t, "child"); p == nil || *p != 42 {
+		t.Errorf("parent = %v, want 42", p)
+	}
+}
+
+func TestRootGroupItselfHasNoParent(t *testing.T) {
+	root := rootGroup()
+	root.Status.MonitorID = 0
+	e := newRootEnv(t, root)
+	if _, err := e.reconcile(t, "root"); err != nil {
+		t.Fatal(err)
+	}
+	if p := e.parentOf(t, "root"); p != nil {
+		t.Errorf("parent = %d, want none", *p)
+	}
+}
+
+func TestRootGroupUnsetLeavesTopLevel(t *testing.T) {
+	e := newEnv(t, rootGroup(), httpMonitor("a"))
+	if _, err := e.reconcile(t, "a"); err != nil {
+		t.Fatal(err)
+	}
+	if p := e.parentOf(t, "a"); p != nil {
+		t.Errorf("parent = %d, want none", *p)
+	}
+}
+
+func TestRootGroupPending(t *testing.T) {
+	noID := rootGroup()
+	noID.Status.MonitorID = 0
+	deletingRoot := deleting(rootGroup())
+	cases := map[string][]client.Object{
+		"missing":   nil,
+		"no ID":     {noID},
+		"deleting":  {deletingRoot},
+		"not group": {func() *v1.KumaMonitor { m := httpMonitor("root"); m.Status.MonitorID = rootID; return m }()},
+		"has parent": {func() *v1.KumaMonitor {
+			m := rootGroup()
+			m.Spec.ParentRef = &v1.LocalRef{Name: "x"}
+			return m
+		}()},
+	}
+	want := map[string]struct {
+		reason  string
+		requeue time.Duration
+	}{
+		"missing":    {ReasonParentPending, 10 * time.Second},
+		"no ID":      {ReasonParentPending, 10 * time.Second},
+		"deleting":   {ReasonParentPending, 10 * time.Second},
+		"not group":  {ReasonInvalidParent, 5 * time.Minute},
+		"has parent": {ReasonInvalidParent, 5 * time.Minute},
+	}
+	for name, objs := range cases {
+		e := newRootEnv(t, append(objs, httpMonitor("a"))...)
+		res, err := e.reconcile(t, "a")
+		if err != nil {
+			t.Fatalf("%s: %v", name, err)
+		}
+		if res.RequeueAfter != want[name].requeue {
+			t.Errorf("%s: RequeueAfter = %v, want %v", name, res.RequeueAfter, want[name].requeue)
+		}
+		if c := ready(t, e.get(t, "a")); c.Status != metav1.ConditionFalse || c.Reason != want[name].reason {
+			t.Errorf("%s: Ready = %+v", name, c)
+		}
+		if e.cnt.creates != 0 {
+			t.Errorf("%s: creates = %d", name, e.cnt.creates)
+		}
+	}
+}
+
+// A chain of maxParentDepth groups is allowed on its own, but the root group
+// adds one more level above it.
+func TestRootGroupCountsTowardsDepth(t *testing.T) {
+	var objs []client.Object
+	for i := range maxParentDepth {
+		parent := ""
+		if i < maxParentDepth-1 {
+			parent = fmt.Sprintf("c%d", i+1)
+		}
+		objs = append(objs, group(fmt.Sprintf("c%d", i), parent))
+	}
+	deep := httpMonitor("deep")
+	deep.Spec.ParentRef = &v1.LocalRef{Name: "c0"}
+	objs = append(objs, deep)
+
+	if _, err := newEnv(t, objs...).reconcile(t, "deep"); err != nil {
+		t.Fatal(err)
+	}
+
+	e := newRootEnv(t, append(objs, rootGroup())...)
+	if _, err := e.reconcile(t, "deep"); err != nil {
+		t.Fatal(err)
+	}
+	if c := ready(t, e.get(t, "deep")); c.Reason != ReasonInvalidParent || c.Message != msgParentTooDeep {
+		t.Errorf("Ready = %+v", c)
+	}
+
+	// A chain ending in the root itself gets no extra level.
+	objs[maxParentDepth-1] = func() *v1.KumaMonitor { g := rootGroup(); g.Name = "c9"; return g }()
+	e = newEnv(t, objs...)
+	e.r.RootGroup = types.NamespacedName{Namespace: "default", Name: "c9"}
+	if _, err := e.reconcile(t, "deep"); err != nil {
+		t.Fatal(err)
+	}
+	if c := ready(t, e.get(t, "deep")); c.Status != metav1.ConditionTrue {
+		t.Errorf("chain ending in root: Ready = %+v", c)
+	}
+}
+
+func TestRootChildrenEnqueuesParentless(t *testing.T) {
+	child := httpMonitor("child")
+	child.Spec.ParentRef = &v1.LocalRef{Name: "grp"}
+	other := httpMonitor("other")
+	other.Namespace = "elsewhere"
+	e := newRootEnv(t, rootGroup(), group("grp", ""), child, httpMonitor("a"), other)
+
+	var got []string
+	for _, req := range e.r.rootChildren(t.Context(), rootGroup()) {
+		got = append(got, req.String())
+	}
+	slices.Sort(got)
+	want := []string{"default/a", "default/grp", "elsewhere/other"}
+	if !slices.Equal(got, want) {
+		t.Errorf("enqueued %v, want %v", got, want)
+	}
+}
+
+func TestRootPredicate(t *testing.T) {
+	r := &Reconciler{RootGroup: rootName}
+	p := r.rootPredicate()
+	old := rootGroup()
+	old.Status.MonitorID = 0
+	withID := rootGroup()
+	other := group("other", "")
+
+	if !p.Update(event.UpdateEvent{ObjectOld: old, ObjectNew: withID}) {
+		t.Error("root ID change must pass")
+	}
+	if p.Update(event.UpdateEvent{ObjectOld: withID, ObjectNew: withID.DeepCopy()}) {
+		t.Error("unchanged root must not pass")
+	}
+	if p.Update(event.UpdateEvent{ObjectOld: other, ObjectNew: other.DeepCopy()}) || p.Create(event.CreateEvent{Object: other}) {
+		t.Error("other monitors must not pass")
+	}
+	if !p.Create(event.CreateEvent{Object: withID}) || !p.Delete(event.DeleteEvent{Object: withID}) {
+		t.Error("root create and delete must pass")
+	}
+}

ci/images/kuma-sync/internal/kumaclient/breml.go

@@ -378,7 +378,7 @@ func (b *Breml) update(ctx context.Context, m Monitor) error {
 		return fmt.Errorf("update %d: monitor carries owner key %q, not %q: %w", m.ID, key, m.OwnerKey, ErrNotOwned)
 	}
 	// Start from the full current object, also across a type change, so
-	// fields we do not manage (proxy, resend interval, upside down, auth)
+	// fields we do not manage (proxy, upside down, auth)
 	// survive the overwrite.
 	wire, err := toWire(m, &cur)
 	if err != nil {
@@ -420,6 +420,7 @@ func toDomain(base monitor.Base, ownerKey string) (Monitor, error) {
 		Interval:        int32(base.Interval),
 		RetryInterval:   int32(base.RetryInterval),
 		MaxRetries:      int32(base.MaxRetries),
+		ResendInterval:  int32(base.ResendInterval),
 		NotificationIDs: slices.Clone(base.NotificationIDs),
 		OwnerKey:        ownerKey,
 	}
@@ -581,6 +582,7 @@ func writeBase(b *monitor.Base, m Monitor) {
 	b.Interval = int64(m.Interval)
 	b.RetryInterval = int64(m.RetryInterval)
 	b.MaxRetries = int64(m.MaxRetries)
+	b.ResendInterval = int64(m.ResendInterval)
 	b.IsActive = m.Active
 	b.NotificationIDs = slices.Clone(m.NotificationIDs)
 }

ci/images/kuma-sync/internal/kumaclient/breml_integration_test.go

@@ -127,7 +127,7 @@ func TestCreateFieldsIntact(t *testing.T) {
 
 	group := Monitor{
 		Type: "group", Name: "grp", Description: "a group", Active: true,
-		Interval: 60, RetryInterval: 60, MaxRetries: 0, OwnerKey: "default/grp",
+		Interval: 60, RetryInterval: 60, MaxRetries: 0, ResendInterval: 60, OwnerKey: "default/grp",
 	}
 	gid, err := b.Create(ctx, group)
 	if err != nil {
@@ -313,7 +313,6 @@ func setUnmanaged(t *testing.T, b *Breml, id int64) (notificationID int64) {
 		t.Fatal(err)
 	}
 	kw.UpsideDown = true
-	kw.ResendInterval = 7
 	kw.NotificationIDs = []int64{nid}
 	if err := b.c.UpdateMonitor(ctx, &kw); err != nil {
 		t.Fatal(err)
@@ -328,8 +327,8 @@ func assertUnmanaged(t *testing.T, c *Breml, id int64, when string) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	if !base.UpsideDown || base.ResendInterval != 7 {
-		t.Errorf("%s: unmanaged state lost: upsideDown=%v resend=%d", when, base.UpsideDown, base.ResendInterval)
+	if !base.UpsideDown {
+		t.Errorf("%s: unmanaged state lost: upsideDown=%v", when, base.UpsideDown)
 	}
 }
 
@@ -344,7 +343,7 @@ func TestUpdatePreservesUnmanagedAndClearsManaged(t *testing.T) {
 	}
 	orig := Monitor{
 		Type: "keyword", Name: "kw", Active: true, Parent: &gid,
-		Interval: 60, RetryInterval: 60, URL: "https://example.com",
+		Interval: 60, RetryInterval: 60, ResendInterval: 7, URL: "https://example.com",
 		Headers: map[string]string{"A": "1"}, Keyword: "up", OwnerKey: "default/kw",
 	}
 	id, err := b.Create(ctx, orig)
@@ -360,6 +359,7 @@ func TestUpdatePreservesUnmanagedAndClearsManaged(t *testing.T) {
 	cleared.Headers = nil
 	cleared.Keyword = ""
 	cleared.Interval = 90
+	cleared.ResendInterval = 0
 	if err := b.Update(ctx, cleared); err != nil {
 		t.Fatal(err)
 	}
@@ -369,7 +369,7 @@ func TestUpdatePreservesUnmanagedAndClearsManaged(t *testing.T) {
 		t.Fatal(err)
 	}
 	m := byID(got)[id]
-	if m.Parent != nil || m.Headers != nil || m.Keyword != "" || m.Interval != 90 || m.NotificationIDs != nil {
+	if m.Parent != nil || m.Headers != nil || m.Keyword != "" || m.Interval != 90 || m.ResendInterval != 0 || m.NotificationIDs != nil {
 		t.Errorf("managed fields not cleared: %+v", m)
 	}
 	assertUnmanaged(t, fresh, id, "after plain update")

ci/images/kuma-sync/internal/kumaclient/client.go

@@ -141,6 +141,9 @@ type Monitor struct {
 	Interval      int32
 	RetryInterval int32
 	MaxRetries    int32
+	// ResendInterval counts consecutive DOWN heartbeats between repeated DOWN
+	// notifications; 0 disables resending.
+	ResendInterval int32
 	// Timeout is in seconds and only applies to http, keyword and json-query.
 	// 0 is written as round(0.8*Interval), because Kuma treats a stored 0 as a
 	// huge request timeout. For other types it is ignored and reads back as 0.

ci/images/kuma-sync/internal/kumaclient/resend_test.go

@@ -0,0 +1,61 @@
+package kumaclient
+
+import (
+	"encoding/json"
+	"testing"
+
+	"github.com/breml/go-uptime-kuma-client/monitor"
+)
+
+// resendOnWire writes m over existing (nil for a create) and returns the wire
+// resendInterval and the value read back from it.
+func resendOnWire(t *testing.T, m Monitor, existing *monitor.Base) (wire, back int64) {
+	t.Helper()
+	w, err := toWire(m, existing)
+	if err != nil {
+		t.Fatal(err)
+	}
+	raw, err := json.Marshal(w)
+	if err != nil {
+		t.Fatal(err)
+	}
+	var f struct {
+		ResendInterval int64 `json:"resendInterval"`
+	}
+	if err := json.Unmarshal(raw, &f); err != nil {
+		t.Fatal(err)
+	}
+	var base monitor.Base
+	if err := json.Unmarshal(raw, &base); err != nil {
+		t.Fatal(err)
+	}
+	got, err := toDomain(base, m.OwnerKey)
+	if err != nil {
+		t.Fatal(err)
+	}
+	return f.ResendInterval, int64(got.ResendInterval)
+}
+
+func TestResendIntervalRoundTrip(t *testing.T) {
+	for _, m := range []Monitor{
+		{ID: 1, Type: "group", Name: "g", Active: true, Interval: 60, RetryInterval: 60, ResendInterval: 60, OwnerKey: "ns/g"},
+		{ID: 2, Type: "http", Name: "h", Active: true, Interval: 60, RetryInterval: 60, ResendInterval: 3, URL: "https://e.com", OwnerKey: "ns/h"},
+	} {
+		wire, back := resendOnWire(t, m, nil)
+		if wire != int64(m.ResendInterval) || back != int64(m.ResendInterval) {
+			t.Errorf("%s: wire=%d read back=%d, want %d", m.Type, wire, back, m.ResendInterval)
+		}
+	}
+}
+
+// 0 must overwrite a resend interval stored in Kuma, not keep it.
+func TestResendIntervalClearedOnUpdate(t *testing.T) {
+	var existing monitor.Base
+	if err := json.Unmarshal([]byte(`{"id":1,"type":"group","name":"g","resendInterval":7}`), &existing); err != nil {
+		t.Fatal(err)
+	}
+	m := Monitor{ID: 1, Type: "group", Name: "g", Active: true, Interval: 60, RetryInterval: 60, OwnerKey: "ns/g"}
+	if wire, back := resendOnWire(t, m, &existing); wire != 0 || back != 0 {
+		t.Errorf("wire=%d read back=%d, want 0", wire, back)
+	}
+}

kubernetes/NETWORK-traffic-classes.md

@@ -8,7 +8,7 @@ Issue #576. Five classes, each on its own VLAN.
 |---|---|---|
 | Ceph replication | `ceph-san`, VLAN 49 | the whole link is handed to the OSD pod (Multus `host-device`) |
 | pod↔pod | `pod0`, VLAN 48 | pod-sourced traffic is routed from table 47; bird puts the peers' pod CIDRs there via `pod0` |
-| world↔pod | `ingress0`, VLAN 47 | BGP session sourced there (next hop of every LoadBalancer VIP); pod egress takes table 47's default |
+| world↔pod | `ingress0`, VLAN 47 | BGP session sourced there (next hop of every LoadBalancer VIP); pod egress and VIP replies take table 47's default |
 | node↔node | `node0`, VLAN 46 | the node InternalIP and etcd live there; so do apiserver↔kubelet, cilium-health and host→remote-pod traffic |
 | world↔node | `mgmt0`, VLAN 40 | API VIP for kubectl, talosctl from outside, node egress (DNS, NTP, image pulls) |
 
@@ -41,6 +41,15 @@ address, or a hostNetwork pod — would otherwise take the default to the UDM.
 The routing decision runs before Cilium's masquerade hook, so the rule sees the
 pod address and the masquerade then rewrites it to the egress link's.
 
+A reply from a LoadBalancer VIP is the exception: Cilium reverses the service
+NAT before the packet reaches the routing decision, so its source is the VIP
+and the pod rules miss it. bird's `vip-rules` container adds one rule per
+block of every `CiliumLoadBalancerIPPool` (priority 1002, `from <block>
+lookup 47`) and keeps them in sync with the pools every minute. The blocks
+must be CIDRs; a start/stop block stops the container. Without these rules
+the reply takes main's default over `mgmt0` while the request arrived on
+`ingress0` (#1547).
+
 Node-originated traffic does not match the rules and uses main, where Cilium
 routes each peer's pod CIDR via the peer's InternalIP — on `node0`.
 

kubernetes/apps/authentik/gate-sync.yaml

@@ -105,7 +105,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: controller
-          image: gitea.renner.uno/gitea_admin/authentik-gate-sync:2026-10-29-1349 # {"$imagepolicy": "flux-system:authentik-gate-sync"}
+          image: gitea.renner.uno/gitea_admin/authentik-gate-sync:2026-11-01-1059 # {"$imagepolicy": "flux-system:authentik-gate-sync"}
           securityContext:
             allowPrivilegeEscalation: false
             readOnlyRootFilesystem: true

kubernetes/apps/gitea-mcp/deployment.yaml

@@ -23,7 +23,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: gitea-mcp
-          image: docker.gitea.com/gitea-mcp-server:1.11.0 # {"$imagepolicy": "flux-system:gitea-mcp"}
+          image: docker.gitea.com/gitea-mcp-server:1.12.0 # {"$imagepolicy": "flux-system:gitea-mcp"}
           # Image has no ENTRYPOINT (binary is in CMD), so args alone would replace it.
           command:
             - /app/gitea-mcp

kubernetes/apps/hermes/skills/homelab-gitea-pr/references/uptime-monitoring.md

@@ -14,6 +14,9 @@ monitor, and its history starts over.
   proxies, the Cloudflare-served apex `renner.uno` and third-party sites.
 - A monitor alerts only through its `notificationRefs` to cluster-scoped `KumaNotification`
   objects (`kubernetes/apps/kuma-sync/notification-*.yaml`). Without refs it sends nothing.
+- Parentless monitors hang under the root group `kuma-sync/renner-uno` (controller env
+  `KUMA_ROOT_GROUP`). Only the root carries `notificationRefs`; don't add `notificationRefs`
+  to service monitors.
 - The CRD lives in `infrastructure/kuma-sync-crds`. Every consuming Flux Kustomization needs
   the KumaMonitor `healthCheckExprs` entry with `current: "true"` (see SKILL.md pitfalls).
 

kubernetes/apps/home-assistant-iot/shelly-manager-deployment.yaml

@@ -64,7 +64,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: shelly-manager
-          image: gitea.renner.uno/konairius/shelly-manager:2026-10-30-0913 # {"$imagepolicy": "flux-system:shelly-manager"}
+          image: gitea.renner.uno/konairius/shelly-manager:2026-10-30-1343 # {"$imagepolicy": "flux-system:shelly-manager"}
           imagePullPolicy: IfNotPresent
           ports:
             - name: http

kubernetes/apps/kuma-sync/deployment.yaml

@@ -30,7 +30,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: controller
-          image: gitea.renner.uno/gitea_admin/kuma-sync:2026-10-29-1349 # {"$imagepolicy": "flux-system:kuma-sync"}
+          image: gitea.renner.uno/gitea_admin/kuma-sync:2026-10-30-1314 # {"$imagepolicy": "flux-system:kuma-sync"}
           env:
             - name: KUMA_URL
               value: https://kuma.renner.uno
@@ -44,6 +44,8 @@ spec:
                 secretKeyRef:
                   name: kuma-sync-kuma
                   key: password
+            - name: KUMA_ROOT_GROUP
+              value: kuma-sync/renner-uno
           ports:
             - name: metrics
               containerPort: 8080

kubernetes/apps/kuma-sync/kumamonitor-root.yaml

@@ -0,0 +1,14 @@
+# Root group (KUMA_ROOT_GROUP): parent of every monitor without a parentRef; the only one with notificationRefs.
+apiVersion: uptime.renner.uno/v1alpha1
+kind: KumaMonitor
+metadata:
+  name: renner-uno
+  namespace: kuma-sync
+spec:
+  type: group
+  displayName: renner.uno
+  interval: 60
+  # heartbeats, not minutes: 60 x 60s = hourly reminder while down
+  resendInterval: 60
+  notificationRefs:
+    - name: email

kubernetes/apps/kuma-sync/kustomization.yaml

@@ -6,3 +6,4 @@ resources:
   - deployment.yaml
   - statuspage-renner.yaml
   - notification-email.yaml
+  - kumamonitor-root.yaml

kubernetes/apps/monitoring/helmrelease-alloy-syslog.yaml

@@ -158,43 +158,69 @@ spec:
             relabel_rules = loki.relabel.syslog.rules
           }
 
-          // UniFi UDM SIEM Server (Network app) — UDP/5514. UDM emits CEF
-          // (Common Event Format), not RFC syslog: payload starts with
-          // "<bsd-ts> <iso-ts> <device-name> CEF:0|Vendor|Product|...".
-          // raw listener captures verbatim; loki.process.udm_cef extracts
-          // CEF header + UNIFI* extension fields and promotes a curated
-          // low-cardinality set to labels.
+          // UniFi activity logging — UDP/5514, one target for two payloads:
+          // the UDM SIEM events in CEF ("<bsd-ts> <device-name> CEF:0|...")
+          // and plain syslog from the UDM (log_all_contents) and from every
+          // adopted AP/switch (debug). raw listener captures verbatim;
+          // loki.process.udm_cef sets `source` per payload type.
           loki.source.syslog "udp_5514" {
             listener {
               address       = "0.0.0.0:5514"
               protocol      = "udp"
               syslog_format = "raw"
-              labels        = { job = "syslog", listener = "udp-5514", source = "udm-siem" }
+              labels        = { job = "syslog", listener = "udp-5514" }
             }
             forward_to = [loki.process.udm_cef.receiver]
           }
 
-          // CEF parser for UDM SIEM payload. The listener also receives the
-          // UDM's plain syslog (log_all_contents), which does not match and
-          // passes through unlabelled. CEF extension keys differ per event
-          // type, so the regex anchors only on the header
-          // (vendor|product|product_version|sig_id|name|sev), UNIFIcategory,
-          // UNIFIhost and the trailing msg. The full raw line stays the log
-          // content.
           loki.process "udm_cef" {
             forward_to = [loki.write.default.receiver]
 
-            stage.regex {
-              expression = "CEF:\\d+\\|(?P<vendor>[^|]*)\\|(?P<product>[^|]*)\\|(?P<product_version>[^|]*)\\|(?P<signature_id>[^|]*)\\|(?P<event_name>[^|]*)\\|(?P<cef_severity>[^|]*)\\|UNIFIcategory=(?P<category>.+?) UNIFIhost=(?P<unifi_host>.+?) \\S+=.* msg=(?P<msg>.+)$"
+            // CEF: extension keys differ per event type, so the regex
+            // anchors only on the header
+            // (vendor|product|product_version|sig_id|name|sev),
+            // UNIFIcategory, UNIFIhost and the trailing msg. The full raw
+            // line stays the log content.
+            stage.match {
+              selector = "{listener=\"udp-5514\"} |= \"CEF:\""
+
+              stage.static_labels {
+                values = { source = "udm-siem" }
+              }
+
+              stage.regex {
+                expression = "CEF:\\d+\\|(?P<vendor>[^|]*)\\|(?P<product>[^|]*)\\|(?P<product_version>[^|]*)\\|(?P<signature_id>[^|]*)\\|(?P<event_name>[^|]*)\\|(?P<cef_severity>[^|]*)\\|UNIFIcategory=(?P<category>.+?) UNIFIhost=(?P<unifi_host>.+?) \\S+=.* msg=(?P<msg>.+)$"
+              }
+
+              stage.labels {
+                values = {
+                  vendor       = "vendor",
+                  product      = "product",
+                  signature_id = "signature_id",
+                  event_name   = "event_name",
+                  category     = "category",
+                }
+              }
             }
 
-            stage.labels {
-              values = {
-                vendor       = "vendor",
-                product      = "product",
-                signature_id = "signature_id",
-                event_name   = "event_name",
-                category     = "category",
+            // Plain syslog. UDM: "<ts> <host> <host> <app>[pid]: ...";
+            // AP/switch: "<ts> <host> <mac>,<model>-<fw>: [: ]<app>[pid]: ...".
+            stage.match {
+              selector = "{listener=\"udp-5514\"} != \"CEF:\""
+
+              stage.static_labels {
+                values = { source = "unifi-syslog" }
+              }
+
+              stage.regex {
+                expression = "^\\S+ +\\d+ \\S+ (?P<host>\\S+) (?:[0-9a-f]{12},\\S+:(?: :)? |\\S+ )(?P<app>[A-Za-z0-9_./+-]+)"
+              }
+
+              stage.labels {
+                values = {
+                  host = "host",
+                  app  = "app",
+                }
               }
             }
           }

kubernetes/apps/monitoring/helmrelease-loki.yaml

@@ -39,8 +39,14 @@ spec:
         replication_factor: 1
       storage:
         type: filesystem
+      # retention_period is only enforced by the compactor with
+      # retention_enabled; Loki keeps logs forever otherwise.
+      compactor:
+        working_directory: /var/loki/compactor
+        retention_enabled: true
+        delete_request_store: filesystem
       limits_config:
-        retention_period: 2160h
+        retention_period: 8760h
         ingestion_rate_mb: 10
         ingestion_burst_size_mb: 20
         max_streams_per_user: 10000

kubernetes/apps/music-assistant/deployment.yaml

@@ -54,7 +54,7 @@ spec:
         # stdlib only; Flux keeps the tag in lockstep via the shared image
         # policy) — no extra dependency.
         - name: reconcile-publish-ip
-          image: ghcr.io/music-assistant/server:2.10.8 # {"$imagepolicy": "flux-system:music-assistant"}
+          image: ghcr.io/music-assistant/server:2.10.9 # {"$imagepolicy": "flux-system:music-assistant"}
           command: ["/app/venv/bin/python", "/scripts/reconcile.py"]
           volumeMounts:
             - name: data
@@ -67,7 +67,7 @@ spec:
         # the stock file is the one it was written against (2.10.7 = 2.10.8);
         # any other version keeps the stock provider.
         - name: pocketcasts-overlay
-          image: ghcr.io/music-assistant/server:2.10.8 # {"$imagepolicy": "flux-system:music-assistant"}
+          image: ghcr.io/music-assistant/server:2.10.9 # {"$imagepolicy": "flux-system:music-assistant"}
           command:
             - /bin/sh
             - -euc
@@ -88,7 +88,7 @@ spec:
               readOnly: true
       containers:
         - name: music-assistant
-          image: ghcr.io/music-assistant/server:2.10.8 # {"$imagepolicy": "flux-system:music-assistant"}
+          image: ghcr.io/music-assistant/server:2.10.9 # {"$imagepolicy": "flux-system:music-assistant"}
           env:
             - name: LOG_LEVEL
               value: info

kubernetes/apps/navidrome/lidarr.yaml

@@ -93,7 +93,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: lidarr
-          image: lscr.io/linuxserver/lidarr:3.1.6.5079-ls46 # {"$imagepolicy": "flux-system:lidarr"}
+          image: ghcr.io/linuxserver/lidarr:3.1.6.5079-ls46 # {"$imagepolicy": "flux-system:lidarr"}
           env:
             - name: PUID
               value: "1000"
@@ -140,7 +140,7 @@ spec:
               drop: ["ALL"]
               add: ["CHOWN", "DAC_OVERRIDE", "FOWNER", "SETGID", "SETUID"]
         - name: reconcile
-          image: lscr.io/linuxserver/lidarr:3.1.6.5079-ls46 # {"$imagepolicy": "flux-system:lidarr"}
+          image: ghcr.io/linuxserver/lidarr:3.1.6.5079-ls46 # {"$imagepolicy": "flux-system:lidarr"}
           command: ["sh", "/scripts/reconcile.sh"]
           volumeMounts:
             - name: config

kubernetes/apps/paperless/kumamonitors.yaml

@@ -138,25 +138,3 @@ spec:
     expiryNotification: true
   keyword:
     keyword: "<title>authentik</title>"
----
-apiVersion: uptime.renner.uno/v1alpha1
-kind: KumaMonitor
-metadata:
-  name: syncthing-ui-gate
-  namespace: paperless
-spec:
-  type: keyword
-  displayName: Syncthing Login
-  parentRef:
-    name: docs
-  interval: 60
-  retryInterval: 60
-  maxRetries: 1
-  timeout: 20
-  http:
-    # behind the Authentik gate; asserts the login page the redirect chain ends on
-    url: https://syncthing.paperless.renner.uno/
-    acceptedStatusCodes: ["200-299"]
-    expiryNotification: true
-  keyword:
-    keyword: "<title>authentik</title>"

kubernetes/apps/paperless/paperless.yaml

@@ -182,7 +182,7 @@ spec:
               drop: ["ALL"]
       containers:
         - name: paperless
-          image: ghcr.io/paperless-ngx/paperless-ngx:3.4.0 # {"$imagepolicy": "flux-system:paperless-ngx"}
+          image: ghcr.io/paperless-ngx/paperless-ngx:3.4.1 # {"$imagepolicy": "flux-system:paperless-ngx"}
           ports:
             - name: http
               containerPort: 8000

kubernetes/clusters/homelab/kuma-sync.yaml

@@ -1,5 +1,5 @@
-# kuma-sync controller: KumaMonitor -> Uptime Kuma monitors. Ships no KumaMonitor objects;
-# they live with their app, the CRD in infrastructure/kuma-sync-crds.
+# kuma-sync controller: KumaMonitor -> Uptime Kuma monitors. Ships only the root group KumaMonitor;
+# service monitors live with their app, the CRD in infrastructure/kuma-sync-crds.
 # healthCheckExprs: Flux has no status reader for ExternalSecret; fail only on the non-retrying reasons.
 apiVersion: kustomize.toolkit.fluxcd.io/v1
 kind: Kustomization
@@ -21,6 +21,10 @@ spec:
       kind: ExternalSecret
       failed: "has(status.conditions) && status.conditions.exists(c, c.type == 'Ready' && c.status == 'False' && (c.reason == 'SecretOwnedByOther' || c.reason == 'SecretImmutable'))"
       current: "has(status.conditions) && status.conditions.exists(c, c.type == 'Ready' && c.status == 'True')"
+    # KumaMonitor Ready tracks Uptime Kuma on the VPS, not this apply.
+    - apiVersion: uptime.renner.uno/v1alpha1
+      kind: KumaMonitor
+      current: "true"
   dependsOn:
     - name: infrastructure
     - name: infrastructure-crds

kubernetes/infrastructure-inhouse/bird/daemonset.yaml

@@ -14,6 +14,10 @@ rules:
   - apiGroups: [""]
     resources: ["nodes"]
     verbs: ["get", "list"]
+  # vip-rules reads the LoadBalancer pool blocks it routes into table 47.
+  - apiGroups: ["cilium.io"]
+    resources: ["ciliumloadbalancerippools"]
+    verbs: ["get", "list"]
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding
@@ -111,6 +115,24 @@ spec:
           volumeMounts:
             - name: etc-bird
               mountPath: /etc/bird
+        # Routes replies from LoadBalancer VIPs into table 47 (vip-rules.sh).
+        - name: vip-rules
+          image: gitea.renner.uno/gitea_admin/bird@sha256:65fc93efead1e9b065d2c78e748f6c3c1ad7216e28b757d9fa4e204fa2ffe9a9
+          command: ["/bin/sh", "/config/vip-rules.sh"]
+          resources:
+            requests:
+              cpu: "5m"
+              memory: "16Mi"
+            limits:
+              cpu: "100m"
+              memory: "64Mi"
+          securityContext:
+            capabilities:
+              drop: ["ALL"]
+              add: ["NET_ADMIN"]
+          volumeMounts:
+            - name: config
+              mountPath: /config
       volumes:
         - name: config
           configMap:

kubernetes/infrastructure-inhouse/bird/kustomization.yaml

@@ -10,3 +10,5 @@ configMapGenerator:
       - bird.conf
       - defines.tmpl
       - peers.tmpl
+      - vip-rules.sh
+      - vip-rules.tmpl

kubernetes/infrastructure-inhouse/bird/vip-rules.sh

@@ -0,0 +1,66 @@
+#!/bin/sh
+# Keeps one routing rule per LoadBalancer pool block: from <block> lookup 47.
+#
+# A reply from a VIP reaches the routing decision with the VIP as its source:
+# Cilium reverses the service NAT before the packet enters the stack. The pod
+# rules (1000/1001, talos/patches/site-homelab.yaml) do not match it, so
+# without these rules it takes main's default over mgmt0 while its request
+# arrived on ingress0. The blocks are read from the pools, so the prefix is
+# written only there.
+#
+# Rules are left in place on exit: if bird is gone, table 47 is empty and the
+# lookup falls through to main, as it does for the pod rules.
+set -eu
+
+PRIO=1002
+TABLE=47
+
+family_of() {
+	case $1 in *:*) echo 6 ;; *) echo 4 ;; esac
+}
+
+reconcile() {
+	# An API error skips this round; the rules in place stay.
+	if ! blocks=$(kubectl get ciliumloadbalancerippools.cilium.io \
+		-o go-template-file=/config/vip-rules.tmpl); then
+		echo "reading the pools failed; retrying" >&2
+		return 0
+	fi
+	for b in $blocks; do
+		case $b in
+		range:*)
+			echo "pool block ${b#range:} is a range; only cidr blocks map to a rule" >&2
+			return 1
+			;;
+		esac
+	done
+
+	for fam in 4 6; do
+		want=$(for b in $blocks; do
+			if [ "$(family_of "$b")" = "$fam" ]; then echo "$b"; fi
+		done | sort -u)
+		have=$(ip -"$fam" rule show |
+			awk -v p="$PRIO:" -v t="$TABLE" '$1 == p && $2 == "from" && $4 == "lookup" && $5 == t { print $3 }' |
+			sort -u)
+
+		for b in $have; do
+			if ! echo "$want" | grep -qxF "$b"; then
+				ip -"$fam" rule del priority "$PRIO" from "$b" table "$TABLE"
+				echo "removed: priority $PRIO from $b table $TABLE"
+			fi
+		done
+		for b in $want; do
+			if ! echo "$have" | grep -qxF "$b"; then
+				ip -"$fam" rule add priority "$PRIO" from "$b" table "$TABLE"
+				echo "added: priority $PRIO from $b table $TABLE"
+			fi
+		done
+	done
+}
+
+trap 'exit 0' TERM INT
+while :; do
+	reconcile
+	sleep 60 &
+	wait $!
+done

kubernetes/infrastructure-inhouse/bird/vip-rules.tmpl

@@ -0,0 +1,5 @@
+{{- /* One line per block of every enabled CiliumLoadBalancerIPPool. A start/stop
+     block renders as range:<start>-<stop>, which vip-rules.sh refuses. */ -}}
+{{- range .items }}{{ if not .spec.disabled }}{{ range .spec.blocks }}
+{{- if .cidr }}{{ .cidr }}{{ else }}range:{{ .start }}-{{ .stop }}{{ end }}
+{{ end }}{{ end }}{{ end -}}

kubernetes/infrastructure/kuma-sync-crds/crd-kumamonitors.yaml

@@ -223,6 +223,13 @@ spec:
                 - hostname
                 - port
                 type: object
+              resendInterval:
+                description: |-
+                  Consecutive DOWN heartbeats after which Kuma sends the DOWN notification
+                  again, not minutes; 0 sends it once per outage.
+                format: int32
+                minimum: 0
+                type: integer
               retryInterval:
                 default: 60
                 description: Seconds.

kubernetes/infrastructure/post-crds/cilium-bgp.yaml

@@ -10,6 +10,9 @@
 #
 # IPv4 + IPv6 ranges keep matching last bytes (10.2.99.x ↔ fd99::x)
 # so each LB has the same "tail" in both families.
+#
+# Blocks are CIDRs: bird's vip-rules turns each into a routing rule into
+# table 47, so VIP replies leave on ingress0 (infrastructure-inhouse/bird).
 apiVersion: cilium.io/v2alpha1
 kind: CiliumLoadBalancerIPPool
 metadata:
@@ -19,10 +22,8 @@ spec:
     matchLabels:
       lb-pool: bgp
   blocks:
-    - start: "10.2.99.0"
-      stop: "10.2.99.255"
-    - start: "fd99::"
-      stop: "fd99::ff"
+    - cidr: "10.2.99.0/24"
+    - cidr: "fd99::/120"
 ---
 # Cilium BGPv2 control-plane config peering each node with the UDM over the
 # ingress VLAN 47 — never over v30iot, which is the untrusted IoT segment.

kubernetes/talos/patches/site-homelab.yaml

@@ -102,7 +102,8 @@ cluster:
 #
 # Priorities are below main (32766) and clear of the rule Cilium installs at 9.
 # The two families are separate rule tables, so the priorities need not match;
-# the document name is the priority and must be unique.
+# the document name is the priority and must be unique. 1002 is taken by bird's
+# vip-rules: replies from LoadBalancer VIPs, whose source is the VIP.
 apiVersion: v1alpha1
 kind: RoutingRuleConfig
 name: "1000"