fix(lidarr): unpin the ImageRepository and keep Renovate out of image-automation

Renovate (141b11a9, 2026-11-02 03:01Z) pinned a digest into ImageRepository/lidarr spec.image. image-reflector rejects that (ImageURLInvalid: "should not include a tag"), so Flux stopped scanning lidarr and FluxImageAutomationNotReady fires. Renovate touched it because dab7c10e moved the ImageRepository and the workload refs from lscr.io to ghcr.io/linuxserver/lidarr, while the renovate.json list of Flux-managed images kept lscr.io/linuxserver/lidarr. - lidarr.yaml: spec.image back to ghcr.io/linuxserver/lidarr. - renovate.json: the list names ghcr.io/linuxserver/lidarr instead of lscr.io, so Renovate also leaves the workload refs in apps/navidrome/lidarr.yaml to Flux. - renovate.json: ignorePaths gains kubernetes/infrastructure/image-automation/**. That directory holds only ImageRepository/ImagePolicy/ImageUpdateAutomation objects; no image ref in it is a deployable pin, and an ImageRepository spec.image must never carry a tag or digest. This is the second time in a week (gitea-mcp, ffd24865) a list gap let Renovate pin one. Closes #1551
chore(image-automation): bump gitea.renner.uno/gitea_admin/secret-rotator:2026-11-02
2026-11-02 13:24:54 +00:00 · 2026-11-02 11:24:03 +00:00 · 2026-11-02 11:21:19 +00:00 · 2026-11-02 11:12:43 +00:00 · 2026-11-02 11:05:13 +00:00 · 2026-11-02 11:04:56 +00:00
105 changed files with 838 additions and 208 deletions
@@ -47,7 +47,7 @@ when:

 steps:
  - name: build-ansible
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/ansible
    # Only rebuild when THIS image's source (or the pipeline file) changed, or
    # on a manual run. Without this every step ran on any matching push, so a
@@ -74,7 +74,7 @@ steps:
          --destination gitea.renner.uno/gitea_admin/ci-ansible:latest

  - name: build-k8s
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/k8s
    when:
      - event: deployment
@@ -97,7 +97,7 @@ steps:
          --destination gitea.renner.uno/gitea_admin/ci-k8s:latest

  - name: build-vmtest
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/vmtest
    when:
      - event: deployment
@@ -120,7 +120,7 @@ steps:
          --destination gitea.renner.uno/gitea_admin/ci-vmtest:latest

  - name: build-tofu
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/tofu
    when:
      - event: deployment
@@ -150,7 +150,7 @@ steps:
  # Runtime image, not CI tooling: a static musl binary in a FROM-scratch image,
  # used as the base for secret-rotation CronJobs. Replaces per-job inline Python.
  - name: build-secret-rotator
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: secret-rotator
    when:
      - event: deployment
@@ -175,7 +175,7 @@ steps:
  # review-bot: the Go service that reviews pull requests with a Mistral agent (webhook plus sweep).
  # Runs after Gitea is up, so no ghcr mirror.
  - name: build-review-bot
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: review-bot
    when:
      - event: deployment
@@ -225,7 +225,7 @@ steps:
  #
  # The gitea_admin/ copy stays until nothing references it any more.
  - name: build-alpine-jq
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/alpine-jq
    when:
      - event: deployment
@@ -276,7 +276,7 @@ steps:
  # note on build-alpine-jq. Anything an app needs while the cluster is still
  # being built cannot live only in that cluster's own registry.
  - name: build-cni-plugins
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/cni-plugins
    when:
      - event: deployment
@@ -316,7 +316,7 @@ steps:
  # gitea.renner.uno is not there to serve it. A cold-rebuild rehearsal left
  # paperless in Init:ErrImagePull on exactly this image.
  - name: build-alpine-openssl
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/alpine-openssl
    when:
      - event: deployment
@@ -351,7 +351,7 @@ steps:
  # Ansible converge. Not a ci-* image -- it is a runtime artifact -- but it
  # builds the same way and lands in the same registry so the audit sees it.
  - name: build-heating-can
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/heating-can
    when:
      - event: deployment
@@ -377,7 +377,7 @@ steps:
  # services (public Ingress hosts -> TLS passthrough -> Traefik ClusterIP).
  # Runtime artifact like heating-can; same registry so the audit tracks it.
  - name: build-netbird-service-sync
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/netbird-service-sync
    when:
      - event: deployment
@@ -402,7 +402,7 @@ steps:
  # authentik-gate-sync: the authentik-gate ingress class (Ingress -> Authentik
  # proxy gate + Traefik route). Its unit tests run as a stage of the image build.
  - name: build-authentik-gate-sync
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/authentik-gate-sync
    when:
      - event: deployment
@@ -428,7 +428,7 @@ steps:
  # kuma-sync: reconciles KumaMonitor resources into Uptime Kuma. Its unit
  # tests run as a stage of the image build.
  - name: build-kuma-sync
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/kuma-sync
    when:
      - event: deployment
@@ -454,7 +454,7 @@ steps:
  # cloudflare-lb-sync: reconciles CloudflareLoadBalancer resources into
  # Cloudflare. Its unit tests run as a stage of the image build.
  - name: build-cloudflare-lb-sync
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/cloudflare-lb-sync
    when:
      - event: deployment
@@ -480,7 +480,7 @@ steps:
  # bird: BGP daemon for the pod-network mesh over pod0 (#576). Runtime
  # artifact like heating-can; same registry so the audit tracks it.
  - name: build-bird
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/bird
    when:
      - event: deployment
@@ -504,7 +504,7 @@ steps:

  # Orchestrator for the monthly backup-verify CronJob (velero ns).
  - name: build-backup-verify
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/backup-verify
    when:
      - event: deployment
@@ -131,7 +131,7 @@ steps:
  #    --build-arg to the resolved version (not "latest") guarantees the tag and
  #    the image content agree even if a new release lands mid-run.
  - name: build
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/claude
    depends_on: [decide]
    environment:
@@ -172,7 +172,7 @@ steps:
  # whenever it trails the deployed server. If you bump the server, bump here.
  - name: woodpecker-lint
    depends_on: [] # see note above `steps:`
-    image: woodpeckerci/woodpecker-cli:v3.19.0-alpine@sha256:27a77117e38d7bbdc380f0e90ff3ee4871ab1eefa78b5d9136a2c969fbecd9f4
+    image: woodpeckerci/woodpecker-cli:v3.20.1-alpine@sha256:74c576faf49cce699825d11c7d7bd38ab5f007dd4f57cdbdd55099d2c0f2621a
    commands:
      - |
        set -eu
@@ -35,25 +35,25 @@ when:
 steps:
  - name: model-selection-tests
    depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
+    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:2.1.311
+    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:2.1.311
+    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:2.1.311
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.316
    commands:
      - sh scripts/ci/test-yaml-citations.sh

@@ -63,7 +63,7 @@ steps:
  # bridge, and the secret guard.
  - name: hermes-skill-tests
    depends_on: []
-    image: python:3.15-alpine@sha256:d44b1254cb92329418d164b22b20d86bbd3869d48e80e09e476531a409a728bb
+    image: python:3.15-alpine@sha256:20a82dbc2783112ddb91d1534603f802d222a3e63e593cd002eb2ac534e70211
    environment:
      PYTHONDONTWRITEBYTECODE: "1"
    commands:
@@ -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:2.1.311
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.316
    commands:
      - sh scripts/ci/test-model-selection.sh

@@ -10,7 +10,7 @@ when:

 steps:
  - name: build
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
    directory: ci/images/hermes
    environment:
      # registry-bot write:package PAT (konairius org secret).
@@ -6,7 +6,7 @@ when:

 steps:
  - name: go-test
-    image: golang:1.27.3-bookworm@sha256:972b4110ba0f47539a975c31e52c64765e1ff19f2d74469ae4a595c6676e80a5
+    image: golang:1.27.3-bookworm@sha256:d9b6a1beb9474adc2a1ce842573639b44b2a0dd49b6669f51d3821baf9ec37c9
    commands:
      - test -z "$(gofmt -l review-bot)"
      - go -C review-bot vet ./...
@@ -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:2.1.311
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.316
    environment:
      CLAUDE_CODE_OAUTH_TOKEN:
        from_secret: claude_code_oauth_token
@@ -30,7 +30,7 @@ when:

 steps:
  - name: update-audit-agent
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.316
    environment:
      CLAUDE_CODE_OAUTH_TOKEN:
        from_secret: claude_code_oauth_token
@@ -8,7 +8,7 @@
 # two plays over this group -- withdraw the static assignments fleet-wide, then
 # hand the address to keepalived -- and both need the same value. Duplicating a
 # service address across plays is exactly the sort of thing that drifts.
-ntp_vip6: "fd40::123/128"
+ntp_vip6: "fd02:40::123/128"

 # Link-local address carried as the FIRST virtual_ipaddress of the IPv6 VRRP
 # instance. RFC 5798 gives an IPv6 virtual router a link-local primary, and
@@ -55,7 +55,7 @@ heating_can
 # THIS IS NO LONGER HIGHLY AVAILABLE. The group was jupiter (MASTER, prio 100),
 # saturn (90), neptune (80) and edge-1 (BACKUP, 70); the first three are gone.
 # A single VRRP member takes the address regardless of its configured state, so
-# fd40::123 is still served — verified answering — but by one thin client with
+# the service address is still served, but by one thin client with
 # no failover behind it. install-ntp-ha.yml still carries the four-host
 # ntp_servers priority map, which now describes hosts that do not exist.
 #
@@ -62,7 +62,7 @@
  # One node at a time. The keepalived role withdraws the statically assigned
  # IPv6 service address and restarts keepalived so the address is re-taken
  # under VRRP control; doing that across every NTP server at once would leave
-  # the whole fleet with nobody holding fd40::123 until the elections settle.
+  # the whole fleet with nobody holding the service address until the elections settle.
  # Serialised, the remaining members keep answering throughout.
  serial: 1

@@ -4,7 +4,7 @@
 # Networks allowed to use this server as NTP source.
 #
 # BOTH families are required. IPv6 is the primary address family here -- the
-# service address ntp.srv.renner.uno resolves to fd40::123 -- so an IPv4-only
+# service address ntp.srv.renner.uno resolves to fd02:40::123 -- so an IPv4-only
 # allow list refuses every client that uses the documented name.
 #
 # The hosts carried `allow fd00::/8` for a long time without it ever being in
@@ -99,7 +99,7 @@
 # quietly proceed either. install-edge-host.yml is a separate play with no
 # ordering relationship to this one, so nothing guarantees it has been re-run
 # to drop the [Address] block. If it has not, edge-1 would end up holding
-# fd40::123 statically AND running a VRRP instance for the same address:
+# the service address statically AND running a VRRP instance for the same address:
 # keepalived would believe it had withdrawn the address while networkd kept it
 # assigned, and the host would go on answering NTP with a clock the health
 # check had already rejected.
@@ -107,9 +107,9 @@
 # That is the precise failure of 2026-08-04, on the host it happened to, so it
 # fails fast rather than being left to inspection.
 # Matched on the bare address, not the full address/prefixlen, and anchored
-# with \b so it cannot also hit a longer address sharing the prefix (fd40::1234).
+# with \b so it cannot also hit a longer address sharing the prefix (fd02:40::1234).
 #
-# Searching for the literal "fd40::123/128" would fail open: a hand-written
+# Searching for the literal "fd02:40::123/128" would fail open: a hand-written
 # [Address] using any other mask -- /64, say -- would not match, the assert
 # below would pass, and keepalived would be handed an address networkd is
 # still assigning. Since this check is detect-only, with no delete afterwards
@@ -5,12 +5,12 @@

 # The unit tests gate the image: the final stage copies the controller out of
 # this stage, so a failing test fails the build.
-FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51 AS test
+FROM python:3.15-slim@sha256:94d3426f1def7db4a106a232ac121bfd975393e5dfd40a619b955fae45fe7913 AS test
 WORKDIR /src
 COPY controller.py test_controller.py ./
 RUN python3 -B -m unittest -v

-FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51
+FROM python:3.15-slim@sha256:94d3426f1def7db4a106a232ac121bfd975393e5dfd40a619b955fae45fe7913

 RUN useradd --system --no-create-home --shell /usr/sbin/nologin controller
 COPY --from=test /src/controller.py /opt/controller.py
@@ -1,4 +1,4 @@
-FROM node:24-alpine@sha256:06d7adf3e0ef61a13f1d28682726366f97a15aa1888c934d3ecec86c33918b53
+FROM node:24-alpine@sha256:8a32c8cf649a49915a66e81e7a609223c708d0adabf288ee3f4077d765542f85

 # Default to the latest Claude Code. Pinning a fixed version is the wrong
 # default here: old releases eventually stop working against the API, so a
@@ -2,7 +2,7 @@
 # Cloudflare. The unit tests (no tags, so no envtest) gate the image: the
 # final stage copies the binary out of this stage, so a failing test fails the
 # build.
-FROM golang:1.27@sha256:f20d83a83e18dbd2a4714b8ffd4b30b287b6243962dd75608e86abcc63ba4efc AS build
+FROM golang:1.27@sha256:2920bb124f1a2e12a1d39f0cab756ae0068441ee1da7655dec7f5e374944095b AS build
 WORKDIR /src
 COPY go.mod go.sum ./
 RUN go mod download
@@ -10,7 +10,7 @@ COPY . .
 RUN go test ./...
 RUN CGO_ENABLED=0 go build -trimpath -ldflags="-s -w" -o /out/cloudflare-lb-sync ./cmd/cloudflare-lb-sync

-FROM gcr.io/distroless/static:nonroot@sha256:18f4cc26c9ffa7f20a359298be7deadac5c607c8e03a02b8119f1a5fc2f82c99
+FROM gcr.io/distroless/static:nonroot@sha256:25ac8f0c3b2334a9eb05452266bd4697864a8c8ef0ef71e5e6480d7f92868329
 COPY --from=build /out/cloudflare-lb-sync /cloudflare-lb-sync
 USER 65532
 ENTRYPOINT ["/cloudflare-lb-sync"]
@@ -23,7 +23,7 @@
 # namespace, so can0 is only reachable with network_mode: host. That is also
 # how the local MQTT broker on 127.0.0.1:1883 is reached. CAN_RAW sockets need
 # no capabilities, so both run unprivileged.
-FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51 AS build
+FROM python:3.15-slim@sha256:94d3426f1def7db4a106a232ac121bfd975393e5dfd40a619b955fae45fe7913 AS build

 # Pins live here, in the artifact, rather than in Ansible variables.
 #
@@ -56,7 +56,7 @@ RUN git clone --quiet https://github.com/MyHomeMyData/E3onCAN.git /opt/e3oncan \
 && rm -rf /opt/e3oncan/.git


-FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51
+FROM python:3.15-slim@sha256:94d3426f1def7db4a106a232ac121bfd975393e5dfd40a619b955fae45fe7913

 ARG OPEN3E_REF=6553c10453a6bae1210908f38a5af2481a46a3e5
 ARG E3ONCAN_REF=461dcbdf97e8d72d2edb9929c63b39382af6c3a1
@@ -6,10 +6,10 @@ RUN apt-get update \
 && apt-get install -y --no-install-recommends jq \
 && rm -rf /var/lib/apt/lists/*

-COPY --from=ghcr.io/siderolabs/talosctl:v1.14.4@sha256:b3233234327350f20ed194f3fad83d90a64344c1940f839c7b0c0abef50c8c33 /talosctl /usr/local/bin/talosctl
-COPY --from=alpine/kubectl:1.37.1@sha256:a5d0fbecab3f7b6c2ab7398f1daa73a3e0ed6ece18556d21698233e9e3759cc7 /usr/local/bin/kubectl /usr/local/bin/kubectl
-COPY --from=ghcr.io/fluxcd/flux-cli:v2.9.6@sha256:b1ac18156f227af9a524b842a96f2c20986c7a779ef721df3ba4e4540f449d76 /usr/local/bin/flux /usr/local/bin/flux
-COPY --from=quay.io/openbao/openbao:2.7.1@sha256:6d2b93856e3fcf7b18ad855a0b51eaba474dc8b79cf554379ea32034797d2acf /usr/bin/bao /usr/local/bin/bao
+COPY --from=ghcr.io/siderolabs/talosctl:v1.14.5@sha256:0b852e35c1f513ee5eacc22183d6193486012420569fde39fcd5260c51938443 /talosctl /usr/local/bin/talosctl
+COPY --from=alpine/kubectl:1.37.2@sha256:5e2de75d37e811ba6eb92e06890b1b3263eae4f0a1c17b49269edec589b1352a /usr/local/bin/kubectl /usr/local/bin/kubectl
+COPY --from=ghcr.io/fluxcd/flux-cli:v2.10.0@sha256:1a5178b1770052d6e88ab1c7c8434c5ac9bca8a8ab984dcaf6b9df31814ce9f2 /usr/local/bin/flux /usr/local/bin/flux
+COPY --from=quay.io/openbao/openbao:2.7.2@sha256:5046911075e137e154ce49ab051502f4ec7cf367d484ae4a4dce665d9b90561f /usr/bin/bao /usr/local/bin/bao
 COPY --from=gitea/tea:0.16.0@sha256:af50a2060ce4d8fd76b7ebe75a3d6db4bb0c615c5bc8f2bdfd8ea83207c4752d /usr/bin/tea /usr/local/bin/tea

 RUN talosctl version --client \
@@ -1,7 +1,7 @@
 # kuma-sync: reconciles KumaMonitor resources into Uptime Kuma. The unit tests
 # (no tags, so no Docker and no envtest) gate the image: the final stage copies
 # the binary out of this stage, so a failing test fails the build.
-FROM golang:1.27@sha256:f20d83a83e18dbd2a4714b8ffd4b30b287b6243962dd75608e86abcc63ba4efc AS build
+FROM golang:1.27@sha256:2920bb124f1a2e12a1d39f0cab756ae0068441ee1da7655dec7f5e374944095b AS build
 WORKDIR /src
 COPY go.mod go.sum ./
 RUN go mod download
@@ -9,7 +9,7 @@ COPY . .
 RUN go test ./...
 RUN CGO_ENABLED=0 go build -trimpath -ldflags="-s -w" -o /out/kuma-sync ./cmd/kuma-sync

-FROM gcr.io/distroless/static:nonroot@sha256:18f4cc26c9ffa7f20a359298be7deadac5c607c8e03a02b8119f1a5fc2f82c99
+FROM gcr.io/distroless/static:nonroot@sha256:25ac8f0c3b2334a9eb05452266bd4697864a8c8ef0ef71e5e6480d7f92868329
 COPY --from=build /out/kuma-sync /kuma-sync
 USER 65532
 ENTRYPOINT ["/kuma-sync"]
@@ -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"`
@@ -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",
@@ -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
 }
@@ -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)
+		}
+	}
+}
@@ -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
@@ -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.
@@ -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 {
@@ -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
 	}
@@ -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
@@ -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))
@@ -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")
+	}
+}
@@ -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)
 }
@@ -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")
@@ -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.
@@ -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)
+	}
+}
@@ -2,7 +2,7 @@
 # domains -> TLS passthrough -> Traefik ClusterIP) from Ingresses carrying the
 # public label. Standard library only, so the image is the interpreter plus one
 # file; runs unprivileged as its own user.
-FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51
+FROM python:3.15-slim@sha256:94d3426f1def7db4a106a232ac121bfd975393e5dfd40a619b955fae45fe7913

 RUN useradd --system --no-create-home --shell /usr/sbin/nologin controller
 COPY controller.py /opt/controller.py
@@ -22,6 +22,13 @@ Two rules, one per family, send every packet with a pod source to table 47
 (`talos/patches/site-homelab.yaml`, priorities 1000/1001, below main). The
 table decides by longest prefix; no rule carves out exceptions.

+A reply from a LoadBalancer VIP is pod traffic as well, but it reaches the
+routing decision with the VIP as its source. Two more rules (1002/1003) send
+the LoadBalancer pool to table 47, so the reply leaves over `ingress0`, where
+the request arrived as the BGP next hop. Without them main sent it out
+`mgmt0`. The pool is a site fact: the site patch's `lb-pool-site` ConfigMap,
+which `bgp-pool` takes by Flux substitution, and the rules beside it.
+
 bird (`kubernetes/infrastructure/bird/`) owns table 47 and fills it with:

 - the node's attached networks — `mgmt0`, `ingress0`, `pod0`, `node0` —
@@ -48,7 +48,7 @@ spec:
        # cert when doing server-side OIDC token exchange. Bundle both
        # roots into one PEM since NODE_EXTRA_CA_CERTS accepts one file.
        - name: fetch-le-staging-roots
-          image: curlimages/curl:8.23.0@sha256:11e64e28c5f58c8d93ee95fcf22ac055f48b0bc440e0ce7d8013bbb5ad6aa8ac
+          image: curlimages/curl:8.23.0@sha256:3fb7e13e5d179a845c97d78204f3f1064d1907037f26a3ebf91710571151fd93
          command:
            - sh
            - -c
@@ -103,6 +103,16 @@ data:
          slug: paperless-proxy
        state: absent

+      # syncthing.paperless.renner.uno is gated by authentik-gate-sync
+      # (kubernetes/apps/paperless/syncthing.yaml), which admits this group.
+      # Members are managed in Authentik.
+      - model: authentik_core.group
+        identifiers:
+          name: Paperless Admins
+        state: present
+        attrs:
+          is_superuser: false
+
      # vscode.home.renner.uno is gated by authentik-gate-sync
      # (kubernetes/apps/home-assistant/vscode-ingress.yaml), which admits this
      # group. Members are managed in Authentik.
@@ -105,7 +105,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: controller
-          image: gitea.renner.uno/gitea_admin/authentik-gate-sync:2026-10-28-0712 # {"$imagepolicy": "flux-system:authentik-gate-sync"}
+          image: gitea.renner.uno/gitea_admin/authentik-gate-sync:2026-11-01-1059 # {"$imagepolicy": "flux-system:authentik-gate-sync"}
          securityContext:
            allowPrivilegeEscalation: false
            readOnlyRootFilesystem: true
@@ -20,7 +20,7 @@ spec:
      # Pinned to match the samba-bridge fork's app image (server.Dockerfile
      # AUTHENTIK_VERSION). Bump in lockstep with the bridge rebuild — a
      # floating range drifts the chart ahead of the pinned app image.
-      version: "2026.8.4"
+      version: "2026.8.5"
      sourceRef:
        kind: HelmRepository
        name: authentik
@@ -30,7 +30,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: controller
-          image: gitea.renner.uno/gitea_admin/cloudflare-lb-sync:2026-10-28-0718 # {"$imagepolicy": "flux-system:cloudflare-lb-sync"}
+          image: gitea.renner.uno/gitea_admin/cloudflare-lb-sync:2026-10-29-1355 # {"$imagepolicy": "flux-system:cloudflare-lb-sync"}
          env:
            - name: CLOUDFLARE_API_TOKEN
              valueFrom:
@@ -28,7 +28,7 @@ spec:
      enableServiceLinks: false
      containers:
        - name: evcc
-          image: evcc/evcc:0.318.1@sha256:2f8163ab22f04863afd86cd511c09607ba71debd9eebd65511f3d654922a80d1
+          image: evcc/evcc:0.318.2@sha256:7ef9bcb15a4fdbfe3bf75d7a0857c40b6272b8783ea833fcbb22f8f134b336c7
          # evcc auto-discovers /etc/evcc.yaml on its default search path;
          # the file is delivered (with the MQTT password) via the
          # sops-encrypted evcc-config Secret mounted below.
@@ -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
@@ -32,7 +32,7 @@ spec:
              type: RuntimeDefault
          containers:
            - name: sync
-              image: gitea.renner.uno/konairius/hermes:2026-10-28-0704 # {"$imagepolicy": "flux-system:hermes"}
+              image: gitea.renner.uno/konairius/hermes:2026-10-29-1342 # {"$imagepolicy": "flux-system:hermes"}
              command:
                - /opt/hermes/.venv/bin/python
                - /opt/hermes-skills/gitea-issues/scripts/sync_webhook.py
@@ -51,7 +51,7 @@ spec:
        # connects from the pod network. No env equivalent exists, so it is
        # set in config.yaml on every start (idempotent).
        - name: config
-          image: gitea.renner.uno/konairius/hermes:2026-10-28-0704 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:2026-10-29-1342 # {"$imagepolicy": "flux-system:hermes"}
          command:
            - /opt/hermes/.venv/bin/hermes
            - config
@@ -75,7 +75,7 @@ spec:
              mountPath: /opt/data
        # WebSocket keepalive ping interval in seconds (default 20).
        - name: config-ws-ping
-          image: gitea.renner.uno/konairius/hermes:2026-10-28-0704 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:2026-10-29-1342 # {"$imagepolicy": "flux-system:hermes"}
          command:
            - /opt/hermes/.venv/bin/hermes
            - config
@@ -99,7 +99,7 @@ spec:
              mountPath: /opt/data
        # Skills from git (ConfigMap hermes-skills) beside the PVC's skills/.
        - name: skills-config
-          image: gitea.renner.uno/konairius/hermes:2026-10-28-0704 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:2026-10-29-1342 # {"$imagepolicy": "flux-system:hermes"}
          command:
            - /opt/hermes/.venv/bin/hermes
            - config
@@ -130,7 +130,7 @@ spec:
        # - alert-monitor: hourly; the script wakes the agent only for
        #   untriaged alerts.
        - name: cron-jobs
-          image: gitea.renner.uno/konairius/hermes:2026-10-28-0704 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:2026-10-29-1342 # {"$imagepolicy": "flux-system:hermes"}
          # Non-fatal: a broken jobs.json or a changed cron CLI after an image
          # bump logs a warning instead of keeping Hermes from starting.
          command:
@@ -187,7 +187,7 @@ spec:
              readOnly: true
        # Home Assistant MCP server; token resolved from HA_TOKEN at connect, writes need approval.
        - name: config-mcp-homeassistant
-          image: gitea.renner.uno/konairius/hermes:2026-10-28-0704 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:2026-10-29-1342 # {"$imagepolicy": "flux-system:hermes"}
          command:
            - /opt/hermes/.venv/bin/hermes
            - config
@@ -214,7 +214,7 @@ spec:
        # skills, the Home Assistant MCP and the tea login are re-applied on
        # every start. default gets the kanban toolset to hand cards to them.
        - name: experts
-          image: gitea.renner.uno/konairius/hermes:2026-10-28-0704 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:2026-10-29-1342 # {"$imagepolicy": "flux-system:hermes"}
          # Non-fatal like cron-jobs: a broken expert logs a warning.
          command:
            - sh
@@ -305,7 +305,7 @@ spec:
        # Gitea issues -> kanban (skills/gitea-issues): route script, webhook route on default,
        # completion shell hook plus its allowlist entry on every profile.
        - name: gitea-issues
-          image: gitea.renner.uno/konairius/hermes:2026-10-28-0704 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:2026-10-29-1342 # {"$imagepolicy": "flux-system:hermes"}
          # Non-fatal like cron-jobs: a failure logs a warning.
          command:
            - sh
@@ -368,7 +368,7 @@ spec:
              readOnly: true
        # Multiplexed default reads platform credentials only from .env (rationale: commit message).
        - name: default-env
-          image: gitea.renner.uno/konairius/hermes:2026-10-28-0704 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:2026-10-29-1342 # {"$imagepolicy": "flux-system:hermes"}
          # Fatal on a writer failure: without these Matrix and the API server stay down.
          command:
            - /opt/hermes/.venv/bin/python
@@ -428,7 +428,7 @@ spec:
        # tea login hermes-bot, written from the mounted token into an
        # emptyDir at the agent's ~/.config/tea.
        - name: tea-login
-          image: gitea.renner.uno/konairius/hermes:2026-10-28-0704 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:2026-10-29-1342 # {"$imagepolicy": "flux-system:hermes"}
          command:
            - sh
            - -ec
@@ -457,7 +457,7 @@ spec:
              readOnly: true
      containers:
        - name: hermes
-          image: gitea.renner.uno/konairius/hermes:2026-10-28-0704 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:2026-10-29-1342 # {"$imagepolicy": "flux-system:hermes"}
          args: ["gateway", "run"]
          env:
            - name: HERMES_DASHBOARD
@@ -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).

@@ -88,7 +88,7 @@ spec:
        # deliver, and the ClusterIP has no backend while HA restarts. The
        # trap forwards SIGTERM so the pod still terminates promptly.
        - name: socat-ipv4
-          image: alpine/socat:1.8.1.3@sha256:603174b77eebaba25ba8f8ebb15e1234d6600409554e95d6fb203fd106150287
+          image: alpine/socat:1.8.1.3@sha256:466c8a0383e16463fabdb7df01008292fb78d07da60224a46cb5d3142ce122ed
          imagePullPolicy: IfNotPresent
          command:
            - /bin/sh
@@ -130,7 +130,7 @@ spec:
        # depends on the kernel's bindv6only default rather than on anything
        # stated here, so the roles are made explicit instead of inherited.
        - name: socat-ipv6
-          image: alpine/socat:1.8.1.3@sha256:603174b77eebaba25ba8f8ebb15e1234d6600409554e95d6fb203fd106150287
+          image: alpine/socat:1.8.1.3@sha256:466c8a0383e16463fabdb7df01008292fb78d07da60224a46cb5d3142ce122ed
          imagePullPolicy: IfNotPresent
          command:
            - /bin/sh
@@ -46,7 +46,7 @@ spec:
        k8s.v1.cni.cncf.io/networks: shelly-manager-iot
        # Changing this rolls the pod, which is the only way a change to the
        # shelly-manager-iot attachment takes effect.
-        net.renner.uno/iot-attachment-config: "tuning-no-ra"
+        net.renner.uno/iot-attachment-config: "tuning-no-ra-no-mtu-probing"
    spec:
      # eth0 (Cilium-managed pod network) is still the primary — it
      # carries the ingress, mosquitto LB return path, etc. The macvlan
@@ -64,7 +64,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: shelly-manager
-          image: gitea.renner.uno/konairius/shelly-manager:2026-10-29-0949 # {"$imagepolicy": "flux-system:shelly-manager"}
+          image: gitea.renner.uno/konairius/shelly-manager:2026-11-02-1051 # {"$imagepolicy": "flux-system:shelly-manager"}
          imagePullPolicy: IfNotPresent
          ports:
            - name: http
@@ -106,6 +106,9 @@ spec:
            # The URL devices download firmware from: Service shelly-manager-firmware.
            - name: Firmware__PublicBaseUrl
              value: http://firmware.shelly-manager.renner.uno
+            # Battery devices get their update when they call in.
+            - name: Firmware__SleepyRollout
+              value: "true"
            - name: ShellyManager__DnsSuffix
              value: iot.renner.uno
            # BLE radios: ESP32 esphome bluetooth_proxy nodes (e.g. the M5 Atom
@@ -50,6 +50,9 @@ spec:
  # to IPv6 clients on v30iot leave via net1, bypassing Cilium's LoadBalancer
  # reverse NAT. tuning turns RA processing off on net1; the link-local
  # address mDNS uses stays.
+  #
+  # tcp_mtu_probing (pod-wide; Cilium sets 1): Shelly flash-write stalls
+  # trip black-hole detection, which cuts firmware downloads to 48-byte MSS.
  config: |
    {
      "cniVersion": "0.3.1",
@@ -67,7 +70,8 @@ spec:
          "type": "tuning",
          "sysctl": {
            "net.ipv6.conf.IFNAME.accept_ra": "0",
-            "net.ipv6.conf.IFNAME.autoconf": "0"
+            "net.ipv6.conf.IFNAME.autoconf": "0",
+            "net.ipv4.tcp_mtu_probing": "0"
          }
        },
        {
@@ -60,7 +60,7 @@ spec:
        # repo's configuration.yaml reads this key, so HA does not start
        # without it. Removing this init container takes the recorder down.
        - name: render-db-url
-          image: busybox:1.38@sha256:fd7dc98638c8e305f4dc34e979f1c0fdfdcaeb0fbf8fcff77ae834b6da3d7e6e
+          image: busybox:1.38@sha256:a46257e06c82ad85242d0d38077d0a52d9896389ca60a1a59d3463db586e5fa4
          command:
            - sh
            - -c
@@ -97,7 +97,7 @@ spec:
        # (homeassistant repo packages/matrix_assist.yaml), same filter-then-append
        # render as recorder_db_url above. Value is hex, nothing to escape.
        - name: render-matrix-password
-          image: busybox:1.38@sha256:fd7dc98638c8e305f4dc34e979f1c0fdfdcaeb0fbf8fcff77ae834b6da3d7e6e
+          image: busybox:1.38@sha256:a46257e06c82ad85242d0d38077d0a52d9896389ca60a1a59d3463db586e5fa4
          command:
            - sh
            - -c
@@ -275,7 +275,7 @@ spec:
        # any LAN client can edit, matching the user's trust-the-network
        # model. Runs as root so its writes match HA's root-owned files.
        - name: code-server
-          image: codercom/code-server:4.143.1@sha256:377b66bec5645510ed52549bb00e648c273edc604d230a3f90fd2b2433afcb97
+          image: codercom/code-server:4.144.0@sha256:b9e8056bb74bd0c4f90284c7559eddeccd38400cfedc28e64c9d3ca50fef1f83
          args:
            - "--auth=none"
            - "--bind-addr=0.0.0.0:8080"
@@ -337,7 +337,7 @@ spec:
        # dedicated long-lived token.
        # Runs as root to match HA's root-owned /config files. See config-sync.sh.
        - name: config-sync
-          image: alpine/git:2.54.0@sha256:e8ceedc73bd80992ae8d58a7d24c58b8322146c354f1d2e81a97db4452068ec0
+          image: alpine/git:2.54.0@sha256:ac6c828f15d82775d204d3d75112e1d34af8945da80ccf922713c9891ba68e7a
          command: ["/bin/sh", "/scripts/sync.sh"]
          env:
            - name: SYNC_BRANCH
@@ -36,7 +36,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: esphome
-          image: ghcr.io/esphome/esphome:2026.10.0@sha256:1dff19a59070cdb523b76576cdc74d200f862d43c1407809088855920cf57145
+          image: ghcr.io/esphome/esphome:2026.10.1@sha256:eab8cd6b4f51077c3883af4cedc058280ddc34a94f3b2ffee23e9d2cd5f1db64
          imagePullPolicy: IfNotPresent
          # Default entrypoint runs the dashboard (Device Builder) against the
          # mounted /config — no command override needed.
@@ -223,7 +223,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: controller
-          image: gitea.renner.uno/konairius/mqtt-account-controller:2026-10-28-0657 # {"$imagepolicy": "flux-system:mqtt-account-controller"}
+          image: gitea.renner.uno/konairius/mqtt-account-controller:2026-11-02-1058 # {"$imagepolicy": "flux-system:mqtt-account-controller"}
          env:
            - name: BROKER_URL
              value: ssl://mosquitto.home-assistant.svc.cluster.local:8884
@@ -66,7 +66,7 @@ spec:
          # (machine.registries.mirrors, applied by bootstrap.sh), and containerd
          # keeps the repository path when it falls through — so the path has to
          # exist on both registries. Steady state still pulls from Gitea.
-          image: gitea.renner.uno/konairius/alpine-jq:2026-10-28-0711 # {"$imagepolicy": "flux-system:alpine-jq"}
+          image: gitea.renner.uno/konairius/alpine-jq:2026-10-29-1348 # {"$imagepolicy": "flux-system:alpine-jq"}
          command:
            - sh
            - -c
@@ -163,7 +163,7 @@ spec:
          # Pinned tag. No Flux image-automation marker yet (unlike mosquitto) —
          # add an infrastructure/image-automation/zigbee2mqtt.yaml policy as a
          # follow-up if desired; pinned-and-manual is fine for the initial cutover.
-          image: ghcr.io/koenkk/zigbee2mqtt:2.14.2@sha256:addbfb08fcef2e4477de1535636118241e10d13e898fbe4d9faba8a4d7396311
+          image: ghcr.io/koenkk/zigbee2mqtt:2.14.3@sha256:fb4a6b0f6868ad1cd6a9996479802b2420e599c3463b62bbff8c8cd9a908f43a
          imagePullPolicy: IfNotPresent
          env:
            - name: TZ
@@ -17,7 +17,7 @@ spec:
    spec:
      containers:
        - name: ical-proxy
-          image: gitea.renner.uno/konairius/ical-proxy:2026-10-28-0651 # {"$imagepolicy": "flux-system:ical-proxy"}
+          image: gitea.renner.uno/konairius/ical-proxy:2026-11-02-1055 # {"$imagepolicy": "flux-system:ical-proxy"}
          ports:
            - containerPort: 8080
              name: http
@@ -66,7 +66,7 @@ spec:
        # The library PVC is populated by the seed phase before this
        # Deployment reconciles, so no rsync init is needed here.
        - name: fetch-le-staging-roots
-          image: curlimages/curl:8.23.0@sha256:11e64e28c5f58c8d93ee95fcf22ac055f48b0bc440e0ce7d8013bbb5ad6aa8ac
+          image: curlimages/curl:8.23.0@sha256:3fb7e13e5d179a845c97d78204f3f1064d1907037f26a3ebf91710571151fd93
          command:
            - sh
            - -c
@@ -57,7 +57,7 @@ spec:
        runAsNonRoot: false
      initContainers:
        - name: wait-for-influxd
-          image: influxdb:2.9.1@sha256:8f106f7ff12659c5e367b99f8a0e7d14cbd4e6ca1f2914094062db6a9813d9c2
+          image: influxdb:2.9.1@sha256:a450f6faf9573e6c2e96a0f575885ae8b7387cc87e4de94599e247ebfa3ac417
          env:
            - { name: INFLUX_HOST, value: http://influxdb-influxdb2.influxdb.svc.cluster.local:8086 }
            - { name: INFLUX_ORG, value: renner }
@@ -80,7 +80,7 @@ spec:
              echo "[$(date -u +%H:%M:%S)] $INFLUX_HOST ready and authenticated"
      containers:
        - name: create
-          image: influxdb:2.9.1@sha256:8f106f7ff12659c5e367b99f8a0e7d14cbd4e6ca1f2914094062db6a9813d9c2
+          image: influxdb:2.9.1@sha256:a450f6faf9573e6c2e96a0f575885ae8b7387cc87e4de94599e247ebfa3ac417
          env:
            - { name: INFLUX_HOST, value: http://influxdb-influxdb2.influxdb.svc.cluster.local:8086 }
            - { name: INFLUX_ORG, value: renner }
@@ -88,7 +88,7 @@ spec:
        # state). Two-stage so we don't try to create an auth before
        # the chart's `influx setup` has finished.
        - name: wait-for-influxd
-          image: influxdb:2.9.1@sha256:8f106f7ff12659c5e367b99f8a0e7d14cbd4e6ca1f2914094062db6a9813d9c2
+          image: influxdb:2.9.1@sha256:a450f6faf9573e6c2e96a0f575885ae8b7387cc87e4de94599e247ebfa3ac417
          env:
            - { name: INFLUX_HOST, value: http://influxdb-influxdb2.influxdb.svc.cluster.local:8086 }
            - { name: INFLUX_ORG, value: renner }
@@ -111,7 +111,7 @@ spec:
              echo "[$(date -u +%H:%M:%S)] $INFLUX_HOST ready and authenticated"
      containers:
        - name: create
-          image: influxdb:2.9.1@sha256:8f106f7ff12659c5e367b99f8a0e7d14cbd4e6ca1f2914094062db6a9813d9c2
+          image: influxdb:2.9.1@sha256:a450f6faf9573e6c2e96a0f575885ae8b7387cc87e4de94599e247ebfa3ac417
          env:
            - { name: INFLUX_HOST, value: http://influxdb-influxdb2.influxdb.svc.cluster.local:8086 }
            - { name: INFLUX_ORG, value: renner }
@@ -55,7 +55,7 @@ spec:
      repository: influxdb
      # Was pinned to VM 108's 2.7.4 for the one-time `influx restore`; that
      # migration is done. No downgrade below 2.9 without `influxd downgrade`.
-      tag: "2.9.1@sha256:8f106f7ff12659c5e367b99f8a0e7d14cbd4e6ca1f2914094062db6a9813d9c2"
+      tag: "2.9.1@sha256:a450f6faf9573e6c2e96a0f575885ae8b7387cc87e4de94599e247ebfa3ac417"
    # Single replica — InfluxDB OSS doesn't cluster. RWO Ceph-block + Velero
    # backups (pending) is the durability story.
    persistence:
@@ -30,7 +30,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: controller
-          image: gitea.renner.uno/gitea_admin/kuma-sync:2026-10-28-0712 # {"$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
@@ -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
@@ -6,3 +6,4 @@ resources:
  - deployment.yaml
  - statuspage-renner.yaml
  - notification-email.yaml
+  - kumamonitor-root.yaml
@@ -48,7 +48,7 @@ spec:
            # this sentinel: the entrypoint copies AccountsSettings.json
            # into ephemeral /config-internal rather than symlinking it.
            - name: seed-config
-              image: busybox:1.38.0@sha256:fd7dc98638c8e305f4dc34e979f1c0fdfdcaeb0fbf8fcff77ae834b6da3d7e6e
+              image: busybox:1.38.0@sha256:a46257e06c82ad85242d0d38077d0a52d9896389ca60a1a59d3463db586e5fa4
              command: ["/bin/sh", "-eu", "-c"]
              args:
                - |
@@ -94,7 +94,7 @@ spec:
            - name: libation
              # Pinned by digest: Spegel caches mutable tag resolutions, so
              # :latest stayed on 13.7.11 despite imagePullPolicy Always.
-              image: docker.io/rmcrackan/libation:14.2.2@sha256:fe188ac3c4ce63cc305971c76e648748341427e16bcf884011da8a384fd3908c
+              image: docker.io/rmcrackan/libation:14.2.5@sha256:7bb47a417311d154c6691747320d0b62ce15527280ad99f0e2a85ac9a6b07e40
              # The entrypoint stages config into ephemeral /config-internal
              # by copy (only the DB is symlinked to the PVC), so Audible
              # tokens refreshed during a run are lost at container exit.
@@ -72,7 +72,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: element-web
-          image: ghcr.io/element-hq/element-web:v1.12.32@sha256:f8700633d4336258af7a05b53865a4f479e0d628cf2d9ca83d28b5939314d4ce
+          image: ghcr.io/element-hq/element-web:v1.12.33@sha256:b0aa4b5a4fc1afaaff62e2dbd0c92d57e2b20724f3ccb2fef53aae949088c3d2
          securityContext:
            allowPrivilegeEscalation: false
            readOnlyRootFilesystem: true
@@ -137,7 +137,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: mas
-          image: ghcr.io/element-hq/matrix-authentication-service:1.27.1@sha256:02712e68c90f3743fedbd5e3343517481b2b4f246a9fd9e2f050dc2553033847
+          image: ghcr.io/element-hq/matrix-authentication-service:1.28.0@sha256:494c67f08ee8344368f4ed336611dea02b26c4e058bf37a212d090d50b612659
          # The server applies database migrations and syncs the upstream
          # providers from the config on start.
          args: ["server", "--config", "/config/config.yaml"]
@@ -179,7 +179,7 @@ spec:
        # first. The marker on the data PVC makes later starts skip it.
        # Debug image: the plain one has no shell for the marker check.
        - name: migrate-to-mas
-          image: ghcr.io/element-hq/matrix-authentication-service:1.27.1-debug@sha256:75f369b206785f1480f4a9f8dd81d7f9f3c6793c40fd184358ecd5d7acae17d4
+          image: ghcr.io/element-hq/matrix-authentication-service:1.28.0-debug@sha256:362b8cc6b1176aec059f3539da2d47c8b47587d1584431bf1aca285146d42b08
          command:
            - /busybox/sh
            - -ec
@@ -234,7 +234,7 @@ spec:
              mountPath: /data
      containers:
        - name: synapse
-          image: ghcr.io/element-hq/synapse:v1.163.2@sha256:c3c21919a322f74d177a43bce8031adc81ef839ddd117a8dd03cfec350e76e02
+          image: ghcr.io/element-hq/synapse:v1.164.1@sha256:fa4aa980f279bcf26d4e7ecc2a2c9a701c73f2ebe8841da9bdcf3b2fdf693d75
          # Bypass /start.py: it expects to run as root and template a config
          # from env. Default mode is generate-missing-and-run, which creates
          # the signing key on first start.
@@ -142,4 +142,4 @@ spec:
        - "[fd02:47::1]:53"
        - "10.2.47.1:53"
      labels:
-        dns_name: syncthing.paperless.renner.uno
+        dns_name: sync.paperless.renner.uno
@@ -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",
+                }
              }
            }
          }
@@ -136,7 +136,7 @@ spec:
          prober: dns
          timeout: 5s
          dns:
-            query_name: syncthing.paperless.renner.uno
+            query_name: sync.paperless.renner.uno
            query_type: A
            valid_rcodes: [NOERROR]
            validate_answer_rrs:
@@ -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
@@ -17,7 +17,7 @@ spec:
  chart:
    spec:
      chart: kube-prometheus-stack
-      version: "92.13.1"
+      version: "92.17.0"
      sourceRef:
        kind: HelmRepository
        name: prometheus-community
@@ -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
@@ -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
@@ -74,7 +74,7 @@ spec:
          # alpine/kubectl is the maintained replacement. Pin the tag
          # to the cluster's server version so kubectl is in lock-step
          # (mismatched skew can break exec streaming).
-          image: docker.io/alpine/kubectl:1.37.1@sha256:a5d0fbecab3f7b6c2ab7398f1daa73a3e0ed6ece18556d21698233e9e3759cc7
+          image: docker.io/alpine/kubectl:1.37.2@sha256:5e2de75d37e811ba6eb92e06890b1b3263eae4f0a1c17b49269edec589b1352a
          env:
            - name: DATASET_TLV
              valueFrom:
@@ -47,7 +47,7 @@ spec:
        #
        # Hence socat is installed at startup and run inside this container.
        - name: otbr
-          image: openthread/otbr:latest@sha256:f3e43ccd86d6da87323873efa0c9b6f92a2a8cc75a804ea50e34c96680363e2e
+          image: openthread/otbr:latest@sha256:51f9af250252f4faae85d0197574a7c17ada873c78799854461a93e3e42cf324
          command:
            - bash
            - -c
@@ -155,7 +155,7 @@ spec:
          # exist on both registries — hence konairius/, which matches the ghcr
          # namespace. Steady state still pulls from Gitea and never leaves the
          # network.
-          image: gitea.renner.uno/konairius/alpine-openssl:2026-10-28-0711 # {"$imagepolicy": "flux-system:alpine-openssl"}
+          image: gitea.renner.uno/konairius/alpine-openssl:2026-10-29-1348 # {"$imagepolicy": "flux-system:alpine-openssl"}
          command:
            - sh
            - -c
@@ -182,7 +182,7 @@ spec:
              drop: ["ALL"]
      containers:
        - name: paperless
-          image: ghcr.io/paperless-ngx/paperless-ngx:3.3.4 # {"$imagepolicy": "flux-system:paperless-ngx"}
+          image: ghcr.io/paperless-ngx/paperless-ngx:3.4.1 # {"$imagepolicy": "flux-system:paperless-ngx"}
          ports:
            - name: http
              containerPort: 8000
@@ -287,7 +287,7 @@ spec:
              add: ["CHOWN", "DAC_OVERRIDE", "FOWNER", "SETGID", "SETUID"]
        # anchor: bridge-tls-proxy
        - name: bridge-tls-proxy
-          image: alpine/socat:1.8.1.3@sha256:603174b77eebaba25ba8f8ebb15e1234d6600409554e95d6fb203fd106150287
+          image: alpine/socat:1.8.1.3@sha256:466c8a0383e16463fabdb7df01008292fb78d07da60224a46cb5d3142ce122ed
          args:
            - "-d"
            - "TCP-LISTEN:11143,fork,reuseaddr,bind=127.0.0.1"
@@ -52,11 +52,8 @@ spec:
        - name: syncthing
          image: syncthing/syncthing:2.1.7@sha256:2b71da7c0d0a91a6ae5285ad079226fecc0a365d08b27720e1f7037b018f7546
          env:
-            # UI bind: any-interface so the ClusterIP Service can reach
-            # it. Network exposure is gated by the absence of an Ingress
-            # and the namespace default-deny CNP — set a UI password in
-            # the Syncthing UI on first port-forward access before
-            # publishing it.
+            # UI bind: any-interface so the ClusterIP Service can reach it.
+            # External access goes through the syncthing-ui Ingress only.
            - name: STGUIADDRESS
              value: "0.0.0.0:8384"
            - name: PUID
@@ -115,10 +112,6 @@ spec:
          persistentVolumeClaim:
            claimName: paperless-consume
 ---
-# UI Service — ClusterIP only. Access via `kubectl -n paperless
-# port-forward svc/syncthing-ui 8384:8384` for first-time setup
-# (set admin password). Future Ingress + Authentik gate is a
-# separate change once auth is configured.
 apiVersion: v1
 kind: Service
 metadata:
@@ -132,6 +125,36 @@ spec:
      port: 8384
      targetPort: ui
 ---
+# LAN-only UI: Paperless Admins through the Authentik gate.
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: syncthing-ui
+  namespace: paperless
+  labels:
+    dns.renner.uno/internal: "true"
+  annotations:
+    traefik.ingress.kubernetes.io/router.middlewares: authentik-gate@kubernetescrd
+    cert-manager.io/cluster-issuer: letsencrypt-cluster
+    auth.renner.uno/group: Paperless Admins
+spec:
+  ingressClassName: traefik
+  rules:
+    - host: syncthing.paperless.renner.uno
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: syncthing-ui
+                port:
+                  number: 8384
+  tls:
+    - secretName: syncthing-ui-tls
+      hosts:
+        - syncthing.paperless.renner.uno
+---
 # Sync ports — LAN-reachable LoadBalancer. Peers (phones, laptops)
 # connect here for the dropbox sync. external-dns publishes the
 # hostname into UniFi DNS only (no cloudflare label); off-LAN peers
@@ -146,7 +169,7 @@ metadata:
    dns.renner.uno/internal: "true"
  annotations:
    io.cilium/lb-ipam-ips: "10.2.99.85,fd99::85"
-    external-dns.kubernetes.io/hostname: syncthing.paperless.renner.uno
+    external-dns.kubernetes.io/hostname: sync.paperless.renner.uno
 spec:
  type: LoadBalancer
  externalTrafficPolicy: Local
@@ -59,7 +59,7 @@ spec:
            - name: renovate
              # Pinned by tag and digest. Renovate updates itself through
              # homelab's renovate.json, like any other image here.
-              image: docker.io/renovate/renovate:44.181.8@sha256:b28b2de1dfd35de7e8198756d7f7cdd84ebc28c3f25e80f5b09e598d3faefb2a
+              image: docker.io/renovate/renovate:44.199.2@sha256:0538f498be1b074e2434f8449cab7b2be30f8c0d0baf3b72814010f19db5bcfb
              env:
                - name: RENOVATE_CONFIG_FILE
                  value: /config/config.json
@@ -32,7 +32,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: review-bot
-          image: gitea.renner.uno/gitea_admin/review-bot:2026-10-28-0709 # {"$imagepolicy": "flux-system:review-bot"}
+          image: gitea.renner.uno/gitea_admin/review-bot:2026-11-02-1054 # {"$imagepolicy": "flux-system:review-bot"}
          env:
            - name: GITEA_URL
              value: https://gitea.renner.uno
@@ -184,7 +184,7 @@ spec:
          # (machine.registries.mirrors, applied by bootstrap.sh), and containerd
          # keeps the repository path, so it has to exist on both registries.
          # Steady state still pulls from Gitea.
-          image: gitea.renner.uno/konairius/alpine-jq:2026-10-28-0711 # {"$imagepolicy": "flux-system:alpine-jq"}
+          image: gitea.renner.uno/konairius/alpine-jq:2026-10-29-1348 # {"$imagepolicy": "flux-system:alpine-jq"}
          command:
            - sh
            - -c
@@ -57,7 +57,7 @@ spec:
          # Pinned, and deliberately NOT under Flux image automation. rbac.yaml
          # is derived from what this exact version calls; an automatic bump
          # could add a call the Role does not cover, silently.
-          image: ghcr.io/stakater/ingressmonitorcontroller:v2.2.13@sha256:3301afb61c10abc4e334deab9cd8601cef069e352b4d7f4dd0897787fca32eac
+          image: ghcr.io/stakater/ingressmonitorcontroller:v2.2.14@sha256:6d7b7fcb39d72296b6b6c0301b443fb31e12d86c55e706adcc7e4f92a887a3ba
          command: ["/manager"]
          args:
            - --health-probe-bind-address=:8081
@@ -68,7 +68,7 @@ spec:
              type: RuntimeDefault
          containers:
            - name: sync
-              image: curlimages/curl:8.22.0@sha256:58adaa4e8dca9c988bae2aba4ab3434a0bb2da16bbe3f92dec39ec7785166777
+              image: curlimages/curl:8.23.0@sha256:3fb7e13e5d179a845c97d78204f3f1064d1907037f26a3ebf91710571151fd93
              command:
                - sh
                - -c
@@ -128,7 +128,7 @@ spec:
              type: RuntimeDefault
          containers:
            - name: run
-              image: curlimages/curl:8.22.0@sha256:58adaa4e8dca9c988bae2aba4ab3434a0bb2da16bbe3f92dec39ec7785166777
+              image: curlimages/curl:8.23.0@sha256:3fb7e13e5d179a845c97d78204f3f1064d1907037f26a3ebf91710571151fd93
              command:
                - sh
                - -c
@@ -34,7 +34,7 @@ spec:
          # Image automation, range 3.x (see image-automation/woodpecker.yaml).
          # MUST stay version-matched with woodpecker-server (gRPC parity) — both
          # track the same range/filter so they bump together on each release.
-          image: woodpeckerci/woodpecker-agent:v3.20.0 # {"$imagepolicy": "flux-system:woodpecker-agent"}
+          image: woodpeckerci/woodpecker-agent:v3.20.1 # {"$imagepolicy": "flux-system:woodpecker-agent"}
          env:
            - name: WOODPECKER_SERVER
              value: woodpecker.woodpecker.svc.cluster.local:9000 # in-cluster gRPC, replaces LXC :9000
@@ -40,7 +40,7 @@ spec:
          # minor + patch auto-update within 3.x; only the 4.0 major is held for
          # a reviewed bump. Safe now the DB is postgres (the old sqlite-surprise
          # -bump hazard is gone). Stays in lockstep with the agent.
-          image: woodpeckerci/woodpecker-server:v3.20.0 # {"$imagepolicy": "flux-system:woodpecker-server"}
+          image: woodpeckerci/woodpecker-server:v3.20.1 # {"$imagepolicy": "flux-system:woodpecker-server"}
          env:
            - name: WOODPECKER_HOST
              value: https://ci.renner.uno
@@ -25,7 +25,7 @@ spec:
        fsGroup: 33
      containers:
        - name: wordpress
-          image: wordpress:7.1.3-php8.5-apache@sha256:ce31904fa1e51b73543fa2e35cc8f1747589b2abf48dc747b422749b88b77e9e
+          image: wordpress:7.1.4-php8.5-apache@sha256:131532d893b5dc4fdf4312a878b7e5e4e4d1d40eb54c854c78eddf6282457dfb
          ports:
            - name: http
              containerPort: 80
@@ -89,6 +89,9 @@ spec:
    substituteFrom:
      - kind: ConfigMap
        name: cluster-settings
+      # The LoadBalancer pool, from the site's Talos patch (site-*.yaml).
+      - kind: ConfigMap
+        name: lb-pool-site
  dependsOn:
    - name: infrastructure
 ---
@@ -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
@@ -69,7 +69,7 @@ spec:
          # first build of that day — imagePullPolicy: Always does not help,
          # because the tag itself resolves stale. Update this when the image
          # is rebuilt.
-          image: gitea.renner.uno/gitea_admin/bird@sha256:65fc93efead1e9b065d2c78e748f6c3c1ad7216e28b757d9fa4e204fa2ffe9a9
+          image: gitea.renner.uno/gitea_admin/bird@sha256:fee5645ad0d718661fb90da6ea9090d30fe47597bebeecb246c01c2adc6df585
          command: ["/bin/sh", "-c"]
          args:
            - |
@@ -95,7 +95,7 @@ spec:
              mountPath: /etc/bird
      containers:
        - name: bird
-          image: gitea.renner.uno/gitea_admin/bird@sha256:65fc93efead1e9b065d2c78e748f6c3c1ad7216e28b757d9fa4e204fa2ffe9a9
+          image: gitea.renner.uno/gitea_admin/bird@sha256:fee5645ad0d718661fb90da6ea9090d30fe47597bebeecb246c01c2adc6df585
          resources:
            requests:
              cpu: "50m"
@@ -4,7 +4,7 @@ metadata:
  name: lidarr
  namespace: flux-system
 spec:
-  image: lscr.io/linuxserver/lidarr
+  image: ghcr.io/linuxserver/lidarr
  interval: 1h
 ---
 # Tags are <maj>.<min>.<patch>.<build>-ls<n>. Two numbers move, and BOTH
@@ -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.
@@ -73,7 +73,7 @@ spec:
          # No imagePullSecret: the ghcr namespace is private and its credential
          # is in machine.registries too, because a Secret would have to come
          # from OpenBao, which needs Ceph, which needs these binaries.
-          image: gitea.renner.uno/konairius/cni-plugins:2026-10-28-0711 # {"$imagepolicy": "flux-system:cni-plugins"}
+          image: gitea.renner.uno/konairius/cni-plugins:2026-10-29-1348 # {"$imagepolicy": "flux-system:cni-plugins"}
          command:
            - sh
            - -c
@@ -401,6 +401,13 @@ spec:
        - ports:
            - port: "80"
              protocol: TCP
+    # v30iot global addresses: the delegated prefix is not fixed.
+    - toCIDR:
+        - ::/0
+      toPorts:
+        - ports:
+            - port: "80"
+              protocol: TCP
    - toCIDR:
        - 224.0.0.251/32
      toPorts:
@@ -145,8 +145,8 @@ spec:
 # Allow Syncthing peer-to-peer sync from the LAN/world.
 # - 22000 TCP+QUIC: actual sync traffic between peers.
 # - 21027 UDP: local-discovery broadcast packets from peers on the LAN.
-# UI (8384) is intentionally NOT listed — accessed via port-forward
-# until an Ingress + Authentik gate is added.
+# UI (8384) is intentionally NOT listed — authentik-gate-sync generates the
+# CNP syncthing-ui-gate that admits traefik.
 apiVersion: cilium.io/v2
 kind: CiliumNetworkPolicy
 metadata:
@@ -24,7 +24,7 @@ spec:
      # window. The StatefulSet rolls one pod at a time (updateStrategyType
      # below). Undo after a pod has run the new server = restore the
      # snapshot, not a git revert.
-      version: ">=0.30.4 <0.31.0"
+      version: ">=0.30.6 <0.31.0"
      sourceRef:
        kind: HelmRepository
        name: openbao
@@ -71,7 +71,7 @@ spec:
              type: RuntimeDefault
          containers:
            - name: rotate
-              image: gitea.renner.uno/gitea_admin/secret-rotator:2026-10-28 # {"$imagepolicy": "flux-system:secret-rotator"}
+              image: gitea.renner.uno/gitea_admin/secret-rotator:2026-11-02 # {"$imagepolicy": "flux-system:secret-rotator"}
              args: ["ha-token"]
              securityContext:
                allowPrivilegeEscalation: false
@@ -133,7 +133,7 @@ spec:
              type: RuntimeDefault
          containers:
            - name: rotate
-              image: gitea.renner.uno/gitea_admin/secret-rotator:2026-10-28 # {"$imagepolicy": "flux-system:secret-rotator"}
+              image: gitea.renner.uno/gitea_admin/secret-rotator:2026-11-02 # {"$imagepolicy": "flux-system:secret-rotator"}
              args: ["ha-token"]
              securityContext:
                allowPrivilegeEscalation: false
@@ -195,7 +195,7 @@ spec:
              type: RuntimeDefault
          containers:
            - name: rotate
-              image: gitea.renner.uno/gitea_admin/secret-rotator:2026-10-28 # {"$imagepolicy": "flux-system:secret-rotator"}
+              image: gitea.renner.uno/gitea_admin/secret-rotator:2026-11-02 # {"$imagepolicy": "flux-system:secret-rotator"}
              args: ["ha-token"]
              securityContext:
                allowPrivilegeEscalation: false
@@ -45,7 +45,7 @@ spec:
              type: RuntimeDefault
          containers:
            - name: snapshot
-              image: quay.io/openbao/openbao:2.7.1@sha256:6d2b93856e3fcf7b18ad855a0b51eaba474dc8b79cf554379ea32034797d2acf # same image as the server — bao CLI included
+              image: quay.io/openbao/openbao:2.7.2@sha256:5046911075e137e154ce49ab051502f4ec7cf367d484ae4a4dce665d9b90561f # same image as the server — bao CLI included
              securityContext:
                allowPrivilegeEscalation: false
                capabilities:
@@ -8,6 +8,10 @@
 # Selector is opt-in via `lb-pool: bgp`. There is no default pool —
 # Services without this label do not get a LoadBalancer IP.
 #
+# The ranges are a site fact: lb-pool-site from the site's Talos patch
+# (talos/patches/site-*.yaml), by Flux substitution. A CIDR block uses all its
+# addresses (allowFirstLastIPs defaults to Yes).
+#
 # IPv4 + IPv6 ranges keep matching last bytes (10.2.99.x ↔ fd99::x)
 # so each LB has the same "tail" in both families.
 apiVersion: cilium.io/v2alpha1
@@ -19,10 +23,8 @@ spec:
    matchLabels:
      lb-pool: bgp
  blocks:
-    - start: "10.2.99.0"
-      stop: "10.2.99.255"
-    - start: "fd99::"
-      stop: "fd99::ff"
+    - cidr: "${LB_POOL_V4}"
+    - cidr: "${LB_POOL_V6}"
 ---
 # 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.
@@ -32,7 +32,7 @@ spec:
              type: RuntimeDefault
          containers:
            - name: backup-verify
-              image: gitea.renner.uno/gitea_admin/ci-backup-verify:2026-10-28 # {"$imagepolicy": "flux-system:backup-verify"}
+              image: gitea.renner.uno/gitea_admin/ci-backup-verify:2026-10-29 # {"$imagepolicy": "flux-system:backup-verify"}
              command: ["bash", "/script/backup-verify.sh"]
              env:
                - name: HOME
@@ -67,6 +67,18 @@ cluster:
                nameservers:
                  - 185.12.64.1
                  - 185.12.64.2
+    # The LoadBalancer pool (see site-homelab.yaml). Services pin their
+    # addresses from the production pool, so a test run carries the same one.
+    - name: lb-pool-site
+      contents: |
+        apiVersion: v1
+        kind: ConfigMap
+        metadata:
+          name: lb-pool-site
+          namespace: flux-system
+        data:
+          LB_POOL_V4: 10.2.99.0/24
+          LB_POOL_V6: fd99::/120
 ---
 # Host DNS asks k8s-gateway first, so containerd resolves in-cluster names
 # (gitea.renner.uno) in the cluster; bootstrap.sh installs k8s-gateway right
@@ -85,6 +85,18 @@ cluster:
                nameservers:
                  - fd02:47::1
                  - 10.2.47.1
+    # The LoadBalancer pool (bgp-pool, infrastructure/post-crds/cilium-bgp.yaml,
+    # by Flux substitution). The routing rules 1002/1003 below name it too.
+    - name: lb-pool-site
+      contents: |
+        apiVersion: v1
+        kind: ConfigMap
+        metadata:
+          name: lb-pool-site
+          namespace: flux-system
+        data:
+          LB_POOL_V4: 10.2.99.0/24
+          LB_POOL_V6: fd99::/120
 ---
 # All pod traffic goes to table 47, and the table decides — longest prefix
 # match, no exceptions to carve out. bird fills it with the node's attached
@@ -115,6 +127,21 @@ name: "1001"
 src: 10.244.0.0/16
 table: "47"
 ---
+# A LoadBalancer reply is pod traffic too, but it reaches the routing decision
+# with the VIP as its source, so the rules above miss it and main sends it out
+# mgmt0 while the request came in over ingress0. The pool is lb-pool-site above.
+apiVersion: v1alpha1
+kind: RoutingRuleConfig
+name: "1002"
+src: fd99::/120
+table: "47"
+---
+apiVersion: v1alpha1
+kind: RoutingRuleConfig
+name: "1003"
+src: 10.2.99.0/24
+table: "47"
+---
 # Host DNS asks k8s-gateway first, so containerd resolves in-cluster names
 # (gitea.renner.uno) in the cluster; bootstrap.sh installs k8s-gateway right
 # after the CNI, before anything else needs DNS. The UDM is the site's
--- a/Show More
+++ b/Show More