feat(ansible): SSH CA on proxy-2

proxy-1 is verified: owner cert login as root (sk-ed25519 cert) and claude-bot cert login with the expected sudo rules both work. proxy-2 is its twin (same OpenSSH_10.6 banner). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Merge pull request 'fix(ansible): ssh-ca compares sshd -T output case-insensitively' (#1469 ) from ssh-ca-assert-case into main
2026-10-27 10:31:42 +01:00 · 2026-10-27 09:25:47 +00:00 · 2026-10-27 10:24:41 +01:00 · 2026-10-27 09:09:51 +00:00 · 2026-10-27 10:05:19 +01:00 · 2026-10-27 08:53:33 +00:00
171 changed files with 2933 additions and 1403 deletions
@@ -319,7 +319,7 @@ steps:
  # writes its stripped mirror under mktemp and never into the workspace.
  - name: promtool
    depends_on: [] # see note above `steps:`
-    image: prom/prometheus:v3.15.0@sha256:efd719c99d83b060d9daefdcf00360461adf279f45ef5391f8d111892118753e
+    image: prom/prometheus:v3.15.1@sha256:fa3302279710be2f21a8301ec17a8b4f2301fd829bd113839b3b6b02b6f191a2
    commands:
      - sh scripts/ci/promtool-rules.sh

@@ -35,25 +35,25 @@ when:
 steps:
  - name: model-selection-tests
    depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.306
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
    commands:
      - sh scripts/ci/test-model-selection.sh

  - name: pr-review-mistral-tests
    depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.306
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
    commands:
      - sh scripts/ci/test-pr-review-mistral.sh

  - name: promtool-rules-guard-tests
    depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.306
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
    commands:
      - sh scripts/ci/test-promtool-rules.sh

  - name: yaml-citations-guard-tests
    depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.306
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
    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:3.14-alpine@sha256:f6a589d43c42b9e7f7dc67a12d37132491f362859a5d750607710cc56da3bc72
+    image: python:3.15-alpine@sha256:d44b1254cb92329418d164b22b20d86bbd3869d48e80e09e476531a409a728bb
    environment:
      PYTHONDONTWRITEBYTECODE: "1"
    commands:
@@ -13,7 +13,7 @@ when:

 steps:
  - name: validate-secrets
-    image: alpine:3.24.2@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
+    image: alpine:3.24.3@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a
    environment:
      TF_VAR_proxmox_api_url:
        from_secret: proxmox_api_url
@@ -0,0 +1,34 @@
+when:
+  # Deploy only on main (merge) + manual — never auto-deploy from a branch.
+  - event: push
+    branch: main
+    path:
+      - "ansible/roles/ssh-ca/**"
+      - "ansible/plays/configure-ssh-ca.yml"
+      - "ansible/inventory/pve_hosts.yml"
+      - ".woodpecker/deploy-ssh-ca.yml"
+  - event: deployment
+    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "deploy-ssh-ca"'
+
+timeout: 30
+
+steps:
+  - name: deploy-ssh-ca
+    image: gitea.renner.uno/gitea_admin/ci-ansible:2026-04-29
+    environment:
+      ANSIBLE_FORCE_COLOR: "true"
+      ANSIBLE_HOST_KEY_CHECKING: "false"
+      ANSIBLE_ROLES_PATH: "../roles:./roles"
+      SSH_PRIVATE_KEY:
+        from_secret: ssh_private_key
+      VAULT_PASS:
+        from_secret: vault_pass
+    commands:
+      - mkdir -p ~/.ssh
+      - echo "$SSH_PRIVATE_KEY" | base64 -d > ~/.ssh/id_ed25519
+      - chmod 600 ~/.ssh/id_ed25519
+      - printf "Host *\n\tStrictHostKeyChecking no\n\tUserKnownHostsFile /dev/null\n" > ~/.ssh/config
+      - cd ansible
+      - echo "$VAULT_PASS" > .vault_pass && chmod 600 .vault_pass
+      - export ANSIBLE_VAULT_PASSWORD_FILE=.vault_pass
+      - ansible-playbook -i inventory/ plays/configure-ssh-ca.yml -v
@@ -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:2.1.306
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
    commands:
      - sh scripts/ci/test-model-selection.sh

@@ -6,7 +6,7 @@ when:

 steps:
  - name: go-test
-    image: golang:1.27.2-bookworm@sha256:5cf287a799e6b94384bad13d16b14904c531f51ba65792237e122ce42b392f61
+    image: golang:1.27.3-bookworm@sha256:972b4110ba0f47539a975c31e52c64765e1ff19f2d74469ae4a595c6676e80a5
    commands:
      - test -z "$(gofmt -l review-bot)"
      - go -C review-bot vet ./...
@@ -18,12 +18,12 @@ when:

 steps:
  - name: iac-scan
-    image: aquasec/trivy:latest@sha256:2416d1f74045b57274df1a340eee6b510cacd73c66a6ccb8da092b117eb7d222
+    image: aquasec/trivy:latest@sha256:790fd66d1697395d8693d1acaa1ea702406a20f109b6fc7bac8db623eca6c06c
    commands:
      - trivy fs --format json -o trivy-iac.json --severity CRITICAL,HIGH --ignore-unfixed .

  - name: image-scans
-    image: aquasec/trivy:latest@sha256:2416d1f74045b57274df1a340eee6b510cacd73c66a6ccb8da092b117eb7d222
+    image: aquasec/trivy:latest@sha256:790fd66d1697395d8693d1acaa1ea702406a20f109b6fc7bac8db623eca6c06c
    commands:
      - trivy image --download-db-only
      - |
@@ -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:2.1.306
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
    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:2.1.306
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
    environment:
      CLAUDE_CODE_OAUTH_TOKEN:
        from_secret: claude_code_oauth_token
@@ -72,14 +72,14 @@ none of these commands.

 ## Secrets (before first play run)

-Create `inventory/group_vars/edge_host/vault.yml` with ansible-vault; the
-current live values come straight out of the cluster:
+Create `inventory/group_vars/edge_host/vault.yml` with ansible-vault. The
+cluster broker has no `open3e` user: edge-1 logs in only as the register
+account `edge-1` (see "MQTT bridge" below), so
+`vault_edge_open3e_mqtt_password` reaches only the loopback broker, which
+allows anonymous clients; any random value works (`openssl rand -hex 24`).
+The zwave-js value comes out of the cluster:

 ```
-# sml2mqtt broker password
-kubectl -n home-assistant get secret mosquitto-sml2mqtt-credentials -o jsonpath='{.data.password}' | base64 -d
-# open3e broker password
-kubectl -n home-assistant get secret mosquitto-open3e-credentials -o jsonpath='{.data.password}' | base64 -d
 # zwave-js session secret
 kubectl -n home-assistant get secret zwave-js-session -o jsonpath='{.data.session-secret}' | base64 -d
 ```
@@ -230,15 +230,14 @@ They connect to a **local mosquitto on loopback** (`127.0.0.1:1883`,
  broker is briefly unreachable, and flushes on reconnect — edge-1 no longer
  hard-depends on cluster/network uptime for every publish.

-Two bridge `connection`s preserve the existing cluster identities, so **no
-cluster-side change was needed**: one authenticates as the `open3e` user
-(carries `open3e/#` out + `open3e/cmnd` back), one as `sml2mqtt` (`sml2mqtt/#`
-out). The local broker is `allow_anonymous` on loopback — the trust boundary
-is the host; nothing off-host can reach it.
+The local broker is `allow_anonymous` on loopback — the trust boundary is the
+host; nothing off-host can reach it.

-**Bridge credential (REN-1307).** The two vault-password bridges are being
-replaced by one bridge as the register account `edge-1`
-(`kubernetes/apps/home-assistant/mqtt-accounts.yaml`). Its password is pushed
+**Bridge credential (REN-1307).** One bridge `connection` logs in as the
+register account `edge-1` (`kubernetes/apps/home-assistant/mqtt-accounts.yaml`)
+and carries `open3e/#` out and `open3e/cmnd` back. The cluster broker does not
+accept the vault-password bridges in `bridge.d/legacy.conf`, which exists only
+until the first push. Its password is pushed
 by mqtt-account-controller to `edge-mqtt-cred` (`:8443`, the controller's
 esp32 API over HTTPS). That endpoint accepts only a client certificate from
 the MQTT CA with CN `mqtt-account-controller`; edge-1 holds the public CA and
@@ -69,3 +69,10 @@ edge_host
 # home, so it must NOT be used as ansible_host.
 [claude_workstation]
 claude-ws ansible_host=10.3.40.78 ansible_user=root
+
+# Hosts that trust the OpenBao SSH user CA (plays/configure-ssh-ca.yml).
+# Rolled out one host at a time: add the next host after the previous one
+# was verified.
+[ssh_ca]
+proxy-1.renner.uno
+proxy-2.renner.uno
@@ -0,0 +1,15 @@
+---
+# Trust the OpenBao SSH user CA (ssh-client-signer) on the hosts in [ssh_ca]:
+# owner certificates (principal k.renner) for root/ladmin, Claude's 1h
+# certificates (principal claude-bot) for its own claude-bot account with
+# limited sudo. Existing authorized_keys stay untouched.
+#
+# serial: 1 so a host whose sshd rejects the change stops the run before the
+# next host is touched.
+- name: Configure the SSH user CA
+  hosts: ssh_ca
+  become: true
+  gather_facts: true
+  serial: 1
+  roles:
+    - ssh-ca
@@ -95,9 +95,8 @@ the VM enrolled as `claude-ws-190-112.nb.renner.uno` / `100.96.190.112` (+ IPv6)
 > inventory targets the tunnel DHCP IP.

 > **DNS trap.** `claude-ws.obg.renner.uno` resolves to the VM's lease **only at
-> the off-site DNS** (`@10.3.40.1`). The home resolver catch-alls `*.renner.uno`
-> to the public proxy (`162.55.50.97`, the Netbird VPS) — so from home the FQDN
-> lands on `root@netbird`, **not** the VM. Never use it as `ansible_host`.
+> the off-site DNS** (`@10.3.40.1`). From home this FQDN does not resolve (it
+> exists only at the off-site DNS @10.3.40.1). Never use it as `ansible_host`.

 **Optional — mesh route to the k8s API (redundant read path):** to reach the API
 over the mesh too, add a Netbird dashboard **network route** advertising the
@@ -3,7 +3,7 @@
 #
 # Enforces the decisions the in-cluster CrowdSec already detects, at the point
 # where public traffic actually enters: these hosts terminate TLS for every
-# *.renner.uno name. A drop here never reaches the mesh, the relay or the
+# public renner.uno name. A drop here never reaches the mesh, the relay or the
 # cluster.
 #
 # Detection stays in the cluster. The reverse-proxy produces no parseable
@@ -0,0 +1,18 @@
+---
+# SSH user CA (OpenBao ssh-client-signer). Hosts trust certificates signed by
+# it; the public key is fetched from OpenBao on the controller at run time.
+ssh_ca_public_key_url: "https://openbao.renner.uno/v1/ssh-client-signer/public_key"
+
+# Owner certificates (role owner) carry this principal. It is accepted for
+# whichever admin login the distro has; users that do not exist are skipped.
+ssh_ca_owner_principal: k.renner
+ssh_ca_owner_users:
+  - root
+  - ladmin
+
+# Claude's own account. Certificates (role claude, 1h) carry the principal.
+ssh_ca_claude_user: claude-bot
+ssh_ca_claude_principal: claude-bot
+
+# Units claude-bot may restart/reload via sudo on this host, e.g. [netbird].
+ssh_ca_claude_sudo_units: []
@@ -0,0 +1,2 @@
+# Public keys whose certificates sshd must reject (one per line, OpenSSH format).
+# Revoking a key also revokes every certificate issued for it.
@@ -0,0 +1,139 @@
+---
+- name: Fetch the SSH CA public key from OpenBao
+  ansible.builtin.uri:
+    url: "{{ ssh_ca_public_key_url }}"
+    return_content: true
+  delegate_to: localhost
+  become: false
+  run_once: true
+  register: ssh_ca_key
+
+- name: Check the fetched CA key is an SSH public key
+  ansible.builtin.assert:
+    that:
+      - ssh_ca_key.content is match('^ssh-ed25519 AAAA')
+    fail_msg: "Unexpected CA key from {{ ssh_ca_public_key_url }}"
+  run_once: true
+
+- name: Install the trusted user CA key
+  ansible.builtin.copy:
+    content: "{{ ssh_ca_key.content | trim }}\n"
+    dest: /etc/ssh/trusted_user_ca_keys
+    owner: root
+    group: root
+    mode: "0644"
+
+# sshd refuses all public key logins when RevokedKeys is set but unreadable,
+# so the file is always deployed, even when empty.
+- name: Install the revoked keys list
+  ansible.builtin.copy:
+    src: revoked_keys
+    dest: /etc/ssh/revoked_keys
+    owner: root
+    group: root
+    mode: "0644"
+
+- name: Create the Claude account
+  ansible.builtin.user:
+    name: "{{ ssh_ca_claude_user }}"
+    shell: /bin/bash
+    create_home: true
+    password: "!"
+
+- name: Look up the owner admin logins
+  ansible.builtin.getent:
+    database: passwd
+    key: "{{ item }}"
+    fail_key: false
+  loop: "{{ ssh_ca_owner_users }}"
+  register: ssh_ca_owner_lookup
+
+- name: Create the principals directory
+  ansible.builtin.file:
+    path: /etc/ssh/auth_principals
+    state: directory
+    owner: root
+    group: root
+    mode: "0755"
+
+- name: Accept the owner principal for the existing admin logins
+  ansible.builtin.copy:
+    content: "{{ ssh_ca_owner_principal }}\n"
+    dest: "/etc/ssh/auth_principals/{{ item.item }}"
+    owner: root
+    group: root
+    mode: "0644"
+  loop: "{{ ssh_ca_owner_lookup.results }}"
+  loop_control:
+    label: "{{ item.item }}"
+  when: (item.ansible_facts.getent_passwd | default({})).get(item.item) is not none
+
+- name: Accept the Claude principal for the Claude account
+  ansible.builtin.copy:
+    content: "{{ ssh_ca_claude_principal }}\n"
+    dest: "/etc/ssh/auth_principals/{{ ssh_ca_claude_user }}"
+    owner: root
+    group: root
+    mode: "0644"
+
+- name: Install the Claude sudo rules
+  ansible.builtin.template:
+    src: sudoers-claude.j2
+    dest: "/etc/sudoers.d/{{ ssh_ca_claude_user }}"
+    owner: root
+    group: root
+    mode: "0440"
+    validate: visudo -cf %s
+
+# A broken drop-in only bites on the next sshd restart, so it is tested here
+# and removed again if the full config does not parse.
+- name: Configure sshd for the user CA
+  block:
+    - name: Install the sshd drop-in
+      ansible.builtin.template:
+        src: ssh-ca.conf.j2
+        dest: /etc/ssh/sshd_config.d/50-ssh-ca.conf
+        owner: root
+        group: root
+        mode: "0644"
+
+    - name: Test the full sshd config
+      ansible.builtin.command: sshd -t
+      changed_when: false
+  rescue:
+    - name: Remove the drop-in that broke sshd -t
+      ansible.builtin.file:
+        path: /etc/ssh/sshd_config.d/50-ssh-ca.conf
+        state: absent
+
+    - name: Fail the host
+      ansible.builtin.fail:
+        msg: "sshd -t failed with the SSH CA drop-in; it was removed again"
+
+- name: Read the effective sshd settings
+  ansible.builtin.command: sshd -T
+  changed_when: false
+  register: ssh_ca_effective
+
+# Keyword case in sshd -T output differs between OpenSSH versions (mixed case
+# on 10.6), so the lines are compared lowercased.
+- name: Check sshd uses the CA, principals and revocation list
+  vars:
+    ssh_ca_effective_lines: "{{ ssh_ca_effective.stdout_lines | map('lower') | list }}"
+  ansible.builtin.assert:
+    that:
+      - "'trustedusercakeys /etc/ssh/trusted_user_ca_keys' in ssh_ca_effective_lines"
+      - "'authorizedprincipalsfile /etc/ssh/auth_principals/%u' in ssh_ca_effective_lines"
+      - "'revokedkeys /etc/ssh/revoked_keys' in ssh_ca_effective_lines"
+    fail_msg: "sshd -T does not show the SSH CA settings; another config line takes precedence"
+
+# The unit is sshd.service on Arch and RedHat, ssh.service on Debian. sshd -T
+# only parses the files, so the running daemon is reloaded on every run; a
+# reload keeps open sessions.
+- name: Read the service list
+  ansible.builtin.service_facts:
+
+- name: Reload sshd so the running daemon uses the CA config
+  ansible.builtin.systemd:
+    name: "{{ 'sshd.service' if 'sshd.service' in ansible_facts.services else 'ssh.service' }}"
+    state: reloaded
@@ -0,0 +1,4 @@
+# {{ ansible_managed }}
+TrustedUserCAKeys /etc/ssh/trusted_user_ca_keys
+AuthorizedPrincipalsFile /etc/ssh/auth_principals/%u
+RevokedKeys /etc/ssh/revoked_keys
@@ -0,0 +1,6 @@
+# {{ ansible_managed }}
+# NOEXEC: journalctl/systemctl open a pager, which must not spawn a shell.
+{{ ssh_ca_claude_user }} ALL=(root) NOPASSWD:NOEXEC: /usr/bin/journalctl, /usr/bin/journalctl *, /usr/bin/systemctl status, /usr/bin/systemctl status *, /usr/bin/systemctl list-units, /usr/bin/systemctl list-units *, /usr/bin/ss -tulpn, /usr/sbin/sshd -T
+{% for unit in ssh_ca_claude_sudo_units %}
+{{ ssh_ca_claude_user }} ALL=(root) NOPASSWD:NOEXEC: /usr/bin/systemctl restart {{ unit }}, /usr/bin/systemctl reload {{ unit }}
+{% endfor %}
@@ -1,4 +1,4 @@
-FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
+FROM alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a

 # Alpine plus jq. Nothing application-specific — a general-purpose base for any
 # workload that needs to read JSON from a shell script.
@@ -1,4 +1,4 @@
-FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
+FROM alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a

 # Alpine plus the openssl CLI. Nothing application-specific — named for what it
 # is, so anything needing `openssl s_client` / `x509` from a shell script can use
@@ -1,4 +1,4 @@
-FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
+FROM alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a

 RUN apk add --no-cache \
      ansible \
@@ -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@sha256:2da676046630d7bf14c6764ae1143dc7fa0377a53f94bf5a642f0b214aca5bce AS test
+FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51 AS test
 WORKDIR /src
 COPY controller.py test_controller.py ./
 RUN python3 -B -m unittest -v

-FROM python:3.15-slim@sha256:2da676046630d7bf14c6764ae1143dc7fa0377a53f94bf5a642f0b214aca5bce
+FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51

 RUN useradd --system --no-create-home --shell /usr/sbin/nologin controller
 COPY --from=test /src/controller.py /opt/controller.py
@@ -210,9 +210,10 @@ def resolve_backend(gate, service):


 def embedded_config(config):
-    """The embedded outpost's config with the hosts the gates depend on: the API
-    over the in-cluster Service, the browser sent to the public URL."""
-    return {**(config or {}), "authentik_host": AK_URL, "authentik_host_insecure": False,
+    """The embedded outpost's config with the host the gates depend on. The
+    embedded outpost builds the sign-in redirect from authentik_host, so it is
+    the public URL, which is also Authentik's default for it."""
+    return {**(config or {}), "authentik_host": AK_BROWSER_URL, "authentik_host_insecure": False,
            "authentik_host_browser": AK_BROWSER_URL}


@@ -167,8 +167,8 @@ class Objects(unittest.TestCase):
        self.assertEqual(c.drift({"a": 1, "b": 2}, {"a": 1, "b": 3}), {"b": 3})

    def test_embedded_config_keeps_other_keys(self):
-        cfg = c.embedded_config({"log_level": "debug", "authentik_host": "https://auth.renner.uno/"})
-        self.assertEqual(cfg, {"log_level": "debug", "authentik_host": c.AK_URL,
+        cfg = c.embedded_config({"log_level": "debug", "authentik_host": c.AK_URL})
+        self.assertEqual(cfg, {"log_level": "debug", "authentik_host": c.AK_BROWSER_URL,
                               "authentik_host_insecure": False, "authentik_host_browser": c.AK_BROWSER_URL})


@@ -303,7 +303,7 @@ class Reconcile(unittest.TestCase):
        c.ensure_embedded_config(self.ak)
        cfg = self.ak.get(f"outposts/instances/{self.embedded['pk']}/")["config"]
        self.assertEqual((cfg["log_level"], cfg["authentik_host"], cfg["authentik_host_browser"]),
-                         ("info", c.AK_URL, c.AK_BROWSER_URL))
+                         ("info", c.AK_BROWSER_URL, c.AK_BROWSER_URL))
        before = len(self.ak.calls)
        c.ensure_embedded_config(self.ak)
        self.assertEqual(self.ak.calls[before:], [])
@@ -1,6 +1,6 @@
-FROM hetznercloud/cli:v1.70.1@sha256:795ac09a5ecabd48cc13a8f1c3dc45983c8f75ae1277c70d621719e07f276ccb AS hcloud
+FROM hetznercloud/cli:v1.70.2@sha256:3b3a8f66323a5754089df7939fd9d3f350127072deed13418f3d3052b4bbeeae AS hcloud

-FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
+FROM alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a

 RUN apk add --no-cache \
      bash \
@@ -1,4 +1,4 @@
-FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
+FROM alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a

 # bird: BGP daemon for the pod-network mesh over pod0. Distro package, no build
 # step — the image is the binary plus its runtime.
@@ -1,4 +1,4 @@
-FROM node:24-alpine@sha256:44fce696f38ba8c987c4db89954051000bbd05ffd8d8659ba15ed4a8602e937f
+FROM node:24-alpine@sha256:06d7adf3e0ef61a13f1d28682726366f97a15aa1888c934d3ecec86c33918b53

 # 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@sha256:820153096fda4de6ac1b7194d12e416b7dd8f4e9a33d17e0345b111b945162d8 AS build
+FROM golang:1.27@sha256:f20d83a83e18dbd2a4714b8ffd4b30b287b6243962dd75608e86abcc63ba4efc 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:e2e927ec666bae08560abb3c55d0659eceabb657f56b6782ab500a9fc7f555e3
+FROM gcr.io/distroless/static:nonroot@sha256:18f4cc26c9ffa7f20a359298be7deadac5c607c8e03a02b8119f1a5fc2f82c99
 COPY --from=build /out/cloudflare-lb-sync /cloudflare-lb-sync
 USER 65532
 ENTRYPOINT ["/cloudflare-lb-sync"]
@@ -28,7 +28,7 @@
 # amd64 only, matching the ARCH the installer already hardcoded and the cluster's
 # node architecture. Add a second stage if a different arch is ever needed.

-FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6 AS fetch
+FROM alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a AS fetch

 ARG CNI_PLUGINS_VERSION=v1.9.1
 ARG CNI_PLUGINS_SHA256=b98f74a0f8522f0a83867178729c1aa70f2158f90c45a2ca8fa791db1c76b303
@@ -61,7 +61,7 @@ RUN set -eu; \
      [ -x "/plugins/$p" ] || { echo "FATAL: /plugins/$p missing or not executable" >&2; exit 1; }; \
    done

-FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
+FROM alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a

 # Alpine rather than scratch: the installer needs a shell to copy the binaries
 # onto the host. busybox covers cp/mv/chown/ls, so nothing is added.
@@ -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@sha256:2da676046630d7bf14c6764ae1143dc7fa0377a53f94bf5a642f0b214aca5bce AS build
+FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51 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@sha256:2da676046630d7bf14c6764ae1143dc7fa0377a53f94bf5a642f0b214aca5bce
+FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51

 ARG OPEN3E_REF=6553c10453a6bae1210908f38a5af2481a46a3e5
 ARG E3ONCAN_REF=461dcbdf97e8d72d2edb9929c63b39382af6c3a1
@@ -1,4 +1,4 @@
-FROM nousresearch/hermes-agent:v0.22.2@sha256:36099926da316742423544e055d4734777105ffe6341873af5459b957d0c2919
+FROM nousresearch/hermes-agent:v0.22.5@sha256:9c5561579f3ffdf333401797094ac3a743738d6c25d40f4331c7bf77b694238d

 USER root

@@ -6,9 +6,9 @@ RUN apt-get update \
 && apt-get install -y --no-install-recommends jq \
 && rm -rf /var/lib/apt/lists/*

-COPY --from=ghcr.io/siderolabs/talosctl:v1.13.10@sha256:3116f64c97ddffb53bd3c5bf87c8614d99f04df4326177dbbb7702b5087f0e4d /talosctl /usr/local/bin/talosctl
-COPY --from=alpine/kubectl:1.36.3@sha256:dae261106d5555008acede256b7102c8a6decde7209198434f5999f051460f57 /usr/local/bin/kubectl /usr/local/bin/kubectl
-COPY --from=ghcr.io/fluxcd/flux-cli:v2.9.5@sha256:704d5529535570a495249b643159c93a9aa88ffca07813c974a54b7ba6edbd86 /usr/local/bin/flux /usr/local/bin/flux
+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=gitea/tea:0.16.0@sha256:af50a2060ce4d8fd76b7ebe75a3d6db4bb0c615c5bc8f2bdfd8ea83207c4752d /usr/bin/tea /usr/local/bin/tea

@@ -1,4 +1,4 @@
-FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
+FROM alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a

 ARG TALOS_VERSION=v1.13.12
 ARG VELERO_VERSION=v1.16.0
@@ -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@sha256:820153096fda4de6ac1b7194d12e416b7dd8f4e9a33d17e0345b111b945162d8 AS build
+FROM golang:1.27@sha256:f20d83a83e18dbd2a4714b8ffd4b30b287b6243962dd75608e86abcc63ba4efc 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:e2e927ec666bae08560abb3c55d0659eceabb657f56b6782ab500a9fc7f555e3
+FROM gcr.io/distroless/static:nonroot@sha256:18f4cc26c9ffa7f20a359298be7deadac5c607c8e03a02b8119f1a5fc2f82c99
 COPY --from=build /out/kuma-sync /kuma-sync
 USER 65532
 ENTRYPOINT ["/kuma-sync"]
@@ -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@sha256:2da676046630d7bf14c6764ae1143dc7fa0377a53f94bf5a642f0b214aca5bce
+FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51

 RUN useradd --system --no-create-home --shell /usr/sbin/nologin controller
 COPY controller.py /opt/controller.py
@@ -1,4 +1,4 @@
-FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
+FROM alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a

 ARG TOFU_VERSION=1.11.0

@@ -1,4 +1,4 @@
-FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
+FROM alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a

 # Everything `bootstrap.sh vmtest` needs, so the rebuild test can run as a Job in
 # the cluster instead of on a workstation. The workstation has 31G and the test
@@ -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:8.22.0@sha256:58adaa4e8dca9c988bae2aba4ab3434a0bb2da16bbe3f92dec39ec7785166777
+          image: curlimages/curl:8.23.0@sha256:11e64e28c5f58c8d93ee95fcf22ac055f48b0bc440e0ce7d8013bbb5ad6aa8ac
          command:
            - sh
            - -c
@@ -70,7 +70,7 @@ spec:
              mountPath: /ca
      containers:
        - name: audiobookshelf
-          image: ghcr.io/advplyr/audiobookshelf:2.37.1 # {"$imagepolicy": "flux-system:audiobookshelf"}
+          image: ghcr.io/advplyr/audiobookshelf:2.37.2 # {"$imagepolicy": "flux-system:audiobookshelf"}
          ports:
            - name: http
              containerPort: 80
@@ -4,8 +4,8 @@ metadata:
  name: audiobookshelf
  namespace: audiobookshelf
  labels:
-    # Registered publicly (Cloudflare wildcard -> NetBird proxy); the UDM
-    # external-dns instance skips it, LAN reaches it via the hairpin NAT.
+    # Registered publicly (explicit CNAME -> NetBird proxy). No
+    # dns.renner.uno/internal label: external-dns-unifi writes no UDM record.
    dns.renner.uno/public: "true"
    netbird.renner.uno/public: "true"
  annotations:
@@ -23,7 +23,7 @@ spec:
  retryInterval: 60
  maxRetries: 1
  dns:
-    # cluster services have no own record; they resolve through the *.renner.uno wildcard
+    # public CNAME to the NetBird proxy, created by external-dns (dns.renner.uno/public)
    hostname: audiobooks.renner.uno
    resolveType: CNAME
    resolveServer: "2606:4700:4700::1111,1.1.1.1"
@@ -706,7 +706,7 @@ data:
            # return entries instead of short-circuiting. Built from
            # the samba-bridge repo at
            # gitea.renner.uno/konairius/authentik-samba-bridge .
-            container_image: gitea.renner.uno/konairius/authentik-samba-bridge-ldap-outpost:2026.8.3-9dd92dd
+            container_image: gitea.renner.uno/konairius/authentik-samba-bridge-ldap-outpost:2026.8.4-3c8f413
            object_naming_template: "ak-outpost-%(name)s"
            kubernetes_namespace: authentik
            kubernetes_replicas: 1
@@ -1034,9 +1034,19 @@ data:
          negate: false
          failure_result: false

+      # wiki.renner.uno signs in via OIDC application `wiki`; only this group may sign in.
+      # Members are managed in Authentik.
+      - id: wiki-readers-group
+        model: authentik_core.group
+        identifiers:
+          name: Wiki Readers
+        state: present
+        attrs:
+          is_superuser: false
+
      # Wiki (apps/wiki): its own OIDC login. Public client + PKCE; RS256
-      # so the service verifies the ID token against the JWKS. No policy
-      # binding: every Authentik user may sign in.
+      # so the service verifies the ID token against the JWKS. Only the
+      # Wiki Readers group passes.
      - id: wiki-provider
        model: authentik_providers_oauth2.oauth2provider
        identifiers:
@@ -1072,6 +1082,83 @@ data:
          meta_launch_url: https://wiki.renner.uno
          meta_description: "Homelab wiki"

+      - model: authentik_policies.policybinding
+        identifiers:
+          target: !Find [authentik_core.application, [slug, wiki]]
+          group: !KeyOf wiki-readers-group
+          order: 0
+        state: present
+        attrs:
+          enabled: true
+          negate: false
+          failure_result: false
+
+      # OpenBao human login (auth/oidc, role owner). Confidential client:
+      # OpenBao's OIDC method requires a secret. Authentik generates it; it
+      # lives only in OpenBao's auth/oidc/config, never in git.
+      - id: openbao-admins-group
+        model: authentik_core.group
+        identifiers:
+          name: OpenBao Admins
+        state: present
+        attrs:
+          is_superuser: false
+          # Members may log in to OpenBao via OIDC. Add/remove members HERE.
+          users:
+            - !Find [authentik_core.user, [username, k.renner]]
+
+      - id: openbao-provider
+        model: authentik_providers_oauth2.oauth2provider
+        identifiers:
+          name: OpenBao
+        state: present
+        attrs:
+          authentication_flow: null
+          authorization_flow: !Find [authentik_flows.flow, [slug, default-provider-authorization-implicit-consent]]
+          invalidation_flow: !Find [authentik_flows.flow, [slug, default-provider-invalidation-flow]]
+          client_type: confidential
+          client_id: openbao
+          # See the Matrix (MAS) provider: a blueprint-made provider starts
+          # with no grant types.
+          grant_types:
+            - authorization_code
+            - refresh_token
+          signing_key: !Find [authentik_crypto.certificatekeypair, [name, authentik Self-signed Certificate]]
+          property_mappings:
+            - !Find [authentik_providers_oauth2.scopemapping, [managed, goauthentik.io/providers/oauth2/scope-openid]]
+            - !Find [authentik_providers_oauth2.scopemapping, [managed, goauthentik.io/providers/oauth2/scope-profile]]
+            - !Find [authentik_providers_oauth2.scopemapping, [managed, goauthentik.io/providers/oauth2/scope-email]]
+          redirect_uris:
+            # bao login -method=oidc (CLI listener).
+            - url: http://localhost:8250/oidc/callback
+              matching_mode: strict
+            - url: https://openbao.renner.uno/ui/vault/auth/oidc/oidc/callback
+              matching_mode: strict
+
+      # The slug is the issuer path: https://auth.renner.uno/application/o/openbao/
+      - model: authentik_core.application
+        identifiers:
+          slug: openbao
+        state: present
+        attrs:
+          name: OpenBao
+          slug: openbao
+          provider: !KeyOf openbao-provider
+          meta_launch_url: https://openbao.renner.uno
+          meta_description: "OpenBao secrets"
+
+      # Only the OpenBao Admins group passes.
+      - model: authentik_policies.policybinding
+        identifiers:
+          target: !Find [authentik_core.application, [slug, openbao]]
+          group: !KeyOf openbao-admins-group
+          order: 0
+        state: present
+        attrs:
+          enabled: true
+          negate: false
+          failure_result: false
+
      # OpenProject, decommissioned. Application first: Application.provider
      # is on_delete=PROTECT. Its policy binding cascades with it.
      - model: authentik_core.application
@@ -105,7 +105,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: controller
-          image: gitea.renner.uno/gitea_admin/authentik-gate-sync:2026-10-22-1858 # {"$imagepolicy": "flux-system:authentik-gate-sync"}
+          image: gitea.renner.uno/gitea_admin/authentik-gate-sync:2026-10-27-0801 # {"$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: "2026.8.3"
+      version: "2026.8.4"
      sourceRef:
        kind: HelmRepository
        name: authentik
@@ -58,7 +58,7 @@ spec:
        # 2. Pinning means the deployed binary is traceable to a
        #    specific repo commit. Bump the tag whenever a new build
        #    is published from gitea.renner.uno/konairius/authentik-samba-bridge .
-        tag: "2026.8.3-9dd92dd"
+        tag: "2026.8.4-3c8f413"
      envFrom:
        # SAMBA_BRIDGE_DOMAIN_SID / _ENABLED_GROUP / _UID_OFFSET
        # consumed by the bridge module at Django app startup. Missing
@@ -161,8 +161,8 @@ spec:
        enabled: true
        ingressClassName: traefik
        labels:
-          # Registered publicly (Cloudflare wildcard -> NetBird proxy); the
-          # UDM external-dns instance skips it, LAN uses the hairpin NAT.
+          # Registered publicly (explicit CNAME -> NetBird proxy). No
+          # dns.renner.uno/internal label: external-dns-unifi writes no UDM record.
          dns.renner.uno/public: "true"
          netbird.renner.uno/public: "true"
        annotations:
@@ -23,7 +23,7 @@ spec:
  retryInterval: 60
  maxRetries: 1
  dns:
-    # cluster services have no own record; they resolve through the *.renner.uno wildcard
+    # public CNAME to the NetBird proxy, created by external-dns (dns.renner.uno/public)
    hostname: auth.renner.uno
    resolveType: CNAME
    resolveServer: "2606:4700:4700::1111,1.1.1.1"
@@ -30,7 +30,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: controller
-          image: gitea.renner.uno/gitea_admin/cloudflare-lb-sync:2026-10-22-1904 # {"$imagepolicy": "flux-system:cloudflare-lb-sync"}
+          image: gitea.renner.uno/gitea_admin/cloudflare-lb-sync:2026-10-27-0807 # {"$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:0.317.1@sha256:c50cd4f83c22b39722a76a76b8d428b69bf8ab3334209ed9ed24ec0e3c48dde5
+          image: evcc/evcc:0.318.1@sha256:2f8163ab22f04863afd86cd511c09607ba71debd9eebd65511f3d654922a80d1
          # 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.
@@ -20,7 +20,7 @@ metadata:
 #   services group                   infrastructure group
 #     Web Service 1 = Authentik        Infrastructure 1 = retired (was PBS 2)
 #     Web Service 2 = Gitea            Infrastructure 2 = retired (was Proxmox VE)
-#     Web Service 3 = Immich           Infrastructure 3 = UDM DNS (10.2.40.1)
+#     Web Service 3 = Immich           Infrastructure 3 = UDM DNS (10.2.47.1)
 #     Web Service 4 = Woodpecker CI    Infrastructure 4 = Mosquitto MQTT broker
 #     Web Service 5 = Grafana
 #     Web Service 6 = Home Assistant
@@ -290,9 +290,11 @@ data:
      # a backup server that nothing backs up to reports on nothing. Re-add
      # alongside the first host that is declared to back up to it.

+      # The UDM on the segment pod traffic leaves on (k8s-gateway-site in
+      # talos/patches/site-homelab.yaml).
      - name: Infrastructure 3
        group: infrastructure
-        url: 10.2.40.1
+        url: 10.2.47.1
        interval: 30s
        dns:
          query-name: udm.renner.uno
@@ -4,8 +4,8 @@ metadata:
  name: gatus
  namespace: apps
  labels:
-    # Registered publicly (Cloudflare wildcard -> NetBird proxy); the UDM
-    # external-dns instance skips it, LAN reaches it via the hairpin NAT.
+    # Registered publicly (explicit CNAME -> NetBird proxy). No
+    # dns.renner.uno/internal label: external-dns-unifi writes no UDM record.
    dns.renner.uno/public: "true"
    netbird.renner.uno/public: "true"
  annotations:
@@ -23,7 +23,7 @@ spec:
  retryInterval: 60
  maxRetries: 1
  dns:
-    # cluster services have no own record; they resolve through the *.renner.uno wildcard
+    # public CNAME to the NetBird proxy, created by external-dns (dns.renner.uno/public)
    hostname: status.renner.uno
    resolveType: CNAME
    resolveServer: "2606:4700:4700::1111,1.1.1.1"
@@ -23,7 +23,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: gitea-mcp
-          image: docker.gitea.com/gitea-mcp-server:1.10.0 # {"$imagepolicy": "flux-system:gitea-mcp"}
+          image: docker.gitea.com/gitea-mcp-server:1.11.0 # {"$imagepolicy": "flux-system:gitea-mcp"}
          # Image has no ENTRYPOINT (binary is in CMD), so args alone would replace it.
          command:
            - /app/gitea-mcp
@@ -23,7 +23,7 @@ spec:
  retryInterval: 60
  maxRetries: 1
  dns:
-    # cluster services have no own record; they resolve through the *.renner.uno wildcard
+    # public CNAME to the NetBird proxy, created by external-dns (dns.renner.uno/public)
    hostname: gitea-mcp.renner.uno
    resolveType: CNAME
    resolveServer: "2606:4700:4700::1111,1.1.1.1"
@@ -23,7 +23,7 @@ spec:
  retryInterval: 60
  maxRetries: 1
  dns:
-    # cluster services have no own record; they resolve through the *.renner.uno wildcard
+    # public CNAME to the NetBird proxy, created by external-dns (dns.renner.uno/public)
    hostname: git.renner.uno
    resolveType: CNAME
    resolveServer: "2606:4700:4700::1111,1.1.1.1"
@@ -90,7 +90,7 @@ spec:
  retryInterval: 60
  maxRetries: 1
  dns:
-    # cluster services have no own record; they resolve through the *.renner.uno wildcard
+    # public CNAME to the NetBird proxy, created by external-dns (dns.renner.uno/public)
    hostname: gitea.renner.uno
    resolveType: CNAME
    resolveServer: "2606:4700:4700::1111,1.1.1.1"
@@ -115,7 +115,7 @@ spec:
              type: RuntimeDefault
          containers:
            - name: retention
-              image: docker.io/library/python:3.14-alpine@sha256:f6a589d43c42b9e7f7dc67a12d37132491f362859a5d750607710cc56da3bc72
+              image: docker.io/library/python:3.15-alpine@sha256:d44b1254cb92329418d164b22b20d86bbd3869d48e80e09e476531a409a728bb
              command: ["python3", "/app/package-retention.py"]
              env:
                # In-cluster Service; the public name hairpins off the ingress
@@ -32,7 +32,7 @@ spec:
              type: RuntimeDefault
          containers:
            - name: sync
-              image: gitea.renner.uno/konairius/hermes:build.1792569647 # {"$imagepolicy": "flux-system:hermes"}
+              image: gitea.renner.uno/konairius/hermes:build.1793088058 # {"$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:build.1792569647 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1793088058 # {"$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:build.1792569647 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1793088058 # {"$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:build.1792569647 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1793088058 # {"$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:build.1792569647 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1793088058 # {"$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:build.1792569647 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1793088058 # {"$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:build.1792569647 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1793088058 # {"$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:build.1792569647 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1793088058 # {"$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:build.1792569647 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1793088058 # {"$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:build.1792569647 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1793088058 # {"$imagepolicy": "flux-system:hermes"}
          command:
            - sh
            - -ec
@@ -457,7 +457,7 @@ spec:
              readOnly: true
      containers:
        - name: hermes
-          image: gitea.renner.uno/konairius/hermes:build.1792569647 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1793088058 # {"$imagepolicy": "flux-system:hermes"}
          args: ["gateway", "run"]
          env:
            - name: HERMES_DASHBOARD
@@ -19,8 +19,11 @@ expert's PR goes back to the card that opened it, without a manual step.
   labels, PR reviews, PR comments, PR open/close) posts to
   `http://hermes.hermes.svc.cluster.local:8644/webhooks/gitea-issues`.
   The CronJob `gitea-webhook-sync` (namespace hermes, every 15 min) keeps that hook in
-   place, creates the domain labels and backfills, all only in repos where hermes-bot
-   has issue write (org labels for their orgs, repo labels for user-owned ones): open
+   place, creates the domain labels and backfills, all in every non-archived repo with
+   issues of the orgs hermes-bot belongs to, where an org team grants it issue write
+   (today: all repos of `konairius` through team `Bots`). Labels are org labels only.
+   User-owned repos and repos where hermes-bot is only a direct collaborator get neither
+   labels nor backfill; their new issues still become cards through the system hook. Backfill: open
   issues without a card comment are replayed to the route as signed `opened`
   deliveries, at most 10 per run, and the reviews of open hermes-bot PRs are replayed
   (step 8). Its site-admin PAT lives at OpenBao `apps/gitea-webhook-sync/admin`,
@@ -7,10 +7,10 @@
   active system hook carries the desired name, a new one is created first and every
   other hook with the prefix is deleted afterwards.
 2. Domain labels. hestia/atlas/apollo/clio/daedalus are created only where Hermes
-   works issues: repos with an issue tracker in which BOT_LOGIN (hermes-bot) has
-   issue write. They become org labels in each org owning such a repo and repo labels
-   in such user-owned repos (org labels do not reach those). Existing labels are left
-   as they are; only missing ones are created.
+   works issues: the non-archived org repos with an issue tracker in which BOT_LOGIN
+   (hermes-bot) may write issues through an org team (it labels and comments). They
+   are org labels of those orgs, never repo labels; user-owned repos are out of scope.
+   Existing labels are left as they are; only missing ones are created.
 3. Backfill. Open issues of the same repos without the bridge's card comment are
   replayed to the Hermes webhook route as signed `opened` deliveries, at most
   BACKFILL_LIMIT per run and none started after RUN_BUDGET seconds, in random order
@@ -60,9 +60,10 @@ BACKFILL_SPACING = float(os.environ.get("BACKFILL_SPACING_SECONDS", "3"))
 RUN_BUDGET = float(os.environ.get("RUN_BUDGET_SECONDS", "900"))
 DELIVER_TIMEOUT = 60
 CARD_MARKER = "<!-- hermes-kanban-card:"
-# Labels and backfill only where this account may write issues (it labels and comments).
+# Labels and backfill only in org repos this account may write issues in (it labels and comments).
 BOT_LOGIN = os.environ.get("BOT_LOGIN", "hermes-bot")
 BOT_WRITE = ("write", "admin", "owner")
+ISSUES_UNIT = "repo.issues"
 STARTED = time.monotonic()
 # Review replay (step 4): reviews by these accounts on open BOT_LOGIN PRs.
 REVIEW_BOT_LOGIN = os.environ.get("REVIEW_BOT_LOGIN", "review-bot")
@@ -110,13 +111,11 @@ def api(method: str, path: str, token: str, body: dict | None = None):


 def paged(path: str, token: str) -> list[dict]:
-    """All pages of a list endpoint; /repos/search wraps its list in {"data": [...]}."""
+    """All pages of a list endpoint."""
    out, page = [], 1
    sep = "&" if "?" in path else "?"
    while True:
        batch = api("GET", f"{path}{sep}page={page}&limit=50", token) or []
-        if isinstance(batch, dict):
-            batch = batch.get("data") or []
        out.extend(batch)
        if len(batch) < 50:
            return out
@@ -160,25 +159,56 @@ def reconcile(token: str, secret: str) -> str:

 # --- 2. domain labels --------------------------------------------------------

+def team_writes_issues(team: dict) -> bool:
+    """Issue write from the team's unit map (Gitea >= 1.20), else its team-wide mode."""
+    if team.get("permission") in ("admin", "owner"):
+        return True
+    units = team.get("units_map") or {}
+    return (units.get(ISSUES_UNIT) if units else team.get("permission")) in BOT_WRITE
+
+
 def issue_repos(token: str, errors: list[str] | None = None) -> list[dict]:
-    """Repos whose issues Hermes works: issue tracker on, not archived, and hermes-bot may
-    write issues there (it sets the labels and comments). A site admin sees every repo.
-    A repo whose permission lookup fails is skipped and named in `errors`."""
-    out = []
-    for r in paged("/repos/search", token):
-        if not r.get("has_issues", True) or r.get("archived"):
+    """Repos whose issues Hermes works: in each org BOT_LOGIN belongs to, the repos of its
+    teams that grant issue write (every org repo for an includes_all_repositories team),
+    issue tracker on, not archived. Not /collaborators/{user}/permission: that reports
+    the repo-wide access mode, which stays "none" when the write comes from a unit-based
+    team. The admin route lists private orgs too and needs only the PAT's admin scope
+    (/users/{u}/orgs also requires read:user). An org or team whose lookup fails is
+    skipped and named in `errors`."""
+    def failed(what: str, exc: RuntimeError) -> None:
+        if errors is None:
+            raise exc
+        errors.append(f"{what}: {exc}")
+
+    found: dict[str, dict] = {}
+    for org in paged(f"/admin/users/{q(BOT_LOGIN)}/orgs", token):
+        name = org.get("username") or org.get("name") or ""
+        if not name:
            continue
-        owner, _, name = r["full_name"].partition("/")
        try:
-            perm = api("GET", f"/repos/{q(owner)}/{q(name)}/collaborators/{q(BOT_LOGIN)}/permission", token)
+            teams = paged(f"/orgs/{q(name)}/teams", token)
        except RuntimeError as exc:
-            if errors is None:
-                raise
-            errors.append(f"{r['full_name']}: {exc}")
+            failed(name, exc)
            continue
-        if (perm or {}).get("permission") in BOT_WRITE:
-            out.append(r)
-    return out
+        for team in teams:
+            if not team_writes_issues(team):
+                continue
+            try:
+                try:
+                    api("GET", f"/teams/{team['id']}/members/{q(BOT_LOGIN)}", token)
+                except RuntimeError as exc:
+                    if str(exc).endswith("HTTP 404"):
+                        continue  # not a member of this team
+                    raise
+                repos = paged(f"/orgs/{q(name)}/repos" if team.get("includes_all_repositories")
+                              else f"/teams/{team['id']}/repos", token)
+            except RuntimeError as exc:
+                failed(f"{name} team {team.get('name')}", exc)
+                continue
+            for r in repos:
+                if r.get("has_issues", True) and not r.get("archived"):
+                    found.setdefault(r["full_name"], r)
+    return [found[k] for k in sorted(found)]


 def ensure_labels_at(path: str, token: str) -> list[str]:
@@ -192,18 +222,14 @@ def ensure_labels_at(path: str, token: str) -> list[str]:


 def ensure_labels(token: str, repos: list[dict]) -> str:
-    """Org labels in each org that owns one of `repos`, repo labels in the user-owned ones."""
-    orgs = {n for o in paged("/admin/orgs", token) if (n := o.get("username") or o.get("name"))}
-    owners = {(r.get("owner") or {}).get("login") for r in repos}
-    targets = [f"/orgs/{q(org)}/labels" for org in sorted(orgs & owners)]
-    targets += [f"/repos/{q(r['owner']['login'])}/{q(r['name'])}/labels" for r in repos
-                if (r.get("owner") or {}).get("login") not in orgs]
+    """Org labels in each org that owns one of `repos` (all org repos); never repo labels."""
+    orgs = sorted({o for r in repos if (o := (r.get("owner") or {}).get("login"))})
    actions = []
-    for path in targets:
-        created = ensure_labels_at(path, token)
+    for org in orgs:
+        created = ensure_labels_at(f"/orgs/{q(org)}/labels", token)
        if created:
-            actions.append(f"{path.rsplit('/labels', 1)[0]}: created {','.join(created)}")
-    return "; ".join(actions) or f"labels present in {len(targets)} orgs/repos"
+            actions.append(f"/orgs/{org}: created {','.join(created)}")
+    return "; ".join(actions) or f"labels present in {len(orgs)} orgs"


 # --- 3. backfill -------------------------------------------------------------
@@ -372,9 +398,9 @@ def main() -> int:
    def load_repos() -> str:
        errors: list[str] = []
        repos.extend(issue_repos(token, errors))
-        msg = f"{len(repos)} with issues writable by {BOT_LOGIN}"
+        msg = f"{len(repos)} org repos with issues writable by {BOT_LOGIN}"
        if errors:  # the other repos still get labels and backfill; the Job fails
-            raise RuntimeError(f"{msg}; permission lookup failed, skipped: {'; '.join(errors)}")
+            raise RuntimeError(f"{msg}; team lookup failed, skipped: {'; '.join(errors)}")
        return msg

    failures = 0
@@ -5,8 +5,12 @@
  is a TLS-passthrough service on :443 with a PROXY v2 header, going to Traefik `websecure`.
  There are no UDM port forwards and no other public L4 path. LB VIPs (`bgp-pool`,
  `fd99::/64`, `10.2.99.0/24`) are LAN/mesh-only.
+- DNS labels on an Ingress: `dns.renner.uno/internal` writes the UDM (LAN) record
+  (opt-in), `dns.renner.uno/public` writes the Cloudflare CNAME to `proxy.renner.uno`, and
+  `netbird.renner.uno/public` makes `netbird-service-sync` publish the proxy service. A
+  public host needs both public labels.
 - `netbird-service-sync` publishes **only hosts on Ingresses** labelled
-  `dns.renner.uno/public` (or `netbird.renner.uno/public`), and it reads no other kind.
+  `netbird.renner.uno/public`, and it reads no other kind.
  To publish a TLS host served by an `IngressRouteTCP` (TLS terminated by Traefik), put the
  host on its **own** labelled Ingress annotated
  `traefik.ingress.kubernetes.io/router.entrypoints: web` with **no** `tls:` section, and
@@ -16,15 +16,15 @@ monitor, and its history starts over.
  the KumaMonitor `healthCheckExprs` entry with `current: "true"` (see SKILL.md pitfalls).

 ## Which hosts are public
-The public set is exactly the hosts on Ingresses labelled `dns.renner.uno/public` or
-`netbird.renner.uno/public`. To confirm it, do a TLS handshake against the proxy-1 and
+A public host needs both labels on its Ingress: `netbird.renner.uno/public` for the proxy
+service and `dns.renner.uno/public` for the Cloudflare CNAME. To confirm it, do a TLS handshake against the proxy-1 and
 proxy-2 addresses (resolved via DoH) with each candidate hostname as the SNI. Only public hosts
 return a CA-verified certificate. The proxies do not answer for their own names, so a
 handshake with `proxy-N.renner.uno` as the SNI fails.

 ## Checks per host (owner's spec: DNS + HTTP reachability + response validation)
- **DNS.** A cluster host has no record of its own and resolves through the `*.renner.uno`
-  wildcard. Check `resolveType: CNAME` with `conditions: [{operator: equals, value:
+- **DNS.** A cluster host's public record is a CNAME to `proxy.renner.uno` created by
+  external-dns from `dns.renner.uno/public`. Check `resolveType: CNAME` with `conditions: [{operator: equals, value:
  proxy.renner.uno}]`. An external host checks its own AAAA record, or A when it has no
  AAAA. Use `resolveServer: "2606:4700:4700::1111,1.1.1.1"` so IPv6 comes first; Kuma
  fails over through the list in order.
@@ -71,7 +71,7 @@ reached Kuma.
  parent exists and is a group.
 - Emulate each http/keyword/json-query check the way Kuma does it: axios, Kuma's
  `evaluateJsonQuery` logic via `jsonata`, and a custom `lookup` that resolves through DoH,
-  because this pod's DNS is split-horizon. Run each wildcard host pinned to proxy-1 and to
+  because this pod's DNS is split-horizon. Run each public host pinned to proxy-1 and to
  proxy-2.
 - DNS monitors can't be checked from the cluster, because outbound :53 to external
  resolvers is blocked. After merge, read `monitor_status` from Prometheus instead
@@ -701,62 +701,120 @@ def repo(full, has_issues=True, archived=False):
            "has_issues": has_issues, "archived": archived}


+def team(tid, name, issues="write", all_repos=True, permission="write"):
+    return {"id": tid, "name": name, "includes_all_repositories": all_repos,
+            "permission": permission, "units_map": {"repo.issues": issues, "repo.code": "write"}}
+
+
+def fake_gitea(orgs, teams, members, repos, fail=()):
+    """api() stand-in: orgs of the bot, teams per org, bot's team ids, repos per org or team."""
+    seen = []
+
+    def fake(method, path, token, body=None):
+        p = path.split("?")[0]
+        seen.append(p)
+        if p in fail:
+            raise RuntimeError(f"GET {p}: HTTP 500")
+        if p == "/admin/users/hermes-bot/orgs":
+            return [{"username": o} for o in orgs]
+        if p.startswith("/orgs/") and p.endswith("/teams"):
+            return teams.get(p.split("/")[2], [])
+        if p.startswith("/teams/") and "/members/" in p:
+            if int(p.split("/")[2]) in members:
+                return {"login": "hermes-bot"}
+            raise RuntimeError(f"GET {p}: HTTP 404")
+        if p.endswith("/repos"):
+            return repos.get(p, [])
+        raise AssertionError(f"unexpected {method} {p}")
+
+    return fake, seen
+
+
 class DomainLabels(unittest.TestCase):
-    def test_labels_only_for_orgs_and_user_repos_hermes_works(self):
+    def test_org_labels_only_never_repo_labels(self):
        calls = []

        def fake(method, path, token, body=None):
            calls.append((method, path, body))
-            if path.startswith("/admin/orgs"):
-                return [{"username": "konairius"}, {"username": "unrelated-org"}]
            if path.startswith("/orgs/konairius/labels"):
                return [{"name": "Atlas"}, {"name": "bug"}]
            return []

-        repos = [repo("konairius/homelab"), repo("k.renner/turm1388")]
+        repos = [repo("konairius/homelab"), repo("konairius/shelly-manager")]
        with mock.patch.object(sync, "api", side_effect=fake):
            msg = sync.ensure_labels("tok", repos)
        posts = [(p, b["name"]) for m, p, b in calls if m == "POST"]
        self.assertEqual(sorted(n for p, n in posts if p == "/orgs/konairius/labels"),
                         ["apollo", "clio", "daedalus", "hestia"])  # atlas exists (any case)
-        self.assertEqual(len([p for p, _ in posts if p == "/repos/k.renner/turm1388/labels"]), 5)
-        self.assertFalse([p for p, _ in posts if p.startswith("/repos/konairius/")])  # org labels reach it
-        self.assertFalse([c for c in calls if "unrelated-org" in c[1]])  # no repo of it is worked
+        self.assertFalse([c for c in calls if c[1].startswith("/repos/")])  # org labels reach them
+        self.assertFalse([c for c in calls if c[1].startswith("/admin/")])
        self.assertIn("created", msg)

-    def test_repos_without_issues_archived_or_bot_write_are_skipped(self):
-        perms = {"a/x": "write", "a/w": "admin", "gitea_admin/_cargo-index": "read", "a/n": "none"}
-        seen = []
-
-        def fake(method, path, token, body=None):
-            if path.startswith("/repos/search"):
-                return {"ok": True, "data": [
-                    repo("a/x"), repo("a/w"), repo("gitea_admin/_cargo-index"), repo("a/n"),
-                    repo("a/y", has_issues=False), repo("a/z", archived=True)]}
-            seen.append(path)
-            full = path.split("/repos/")[1].split("/collaborators/")[0]
-            return {"permission": perms[full]}
-
+    def test_team_write_covers_every_org_repo_without_collaborator(self):
+        # Live 2026-10-21: hermes-bot is only in team Bots (all repos, issues write);
+        # /collaborators/hermes-bot/permission says "none" for 9 of the 10 repos.
+        org_repos = [repo("konairius/homelab"), repo("konairius/shelly-manager"),
+                     repo("konairius/ical-proxy"), repo("konairius/off", has_issues=False),
+                     repo("konairius/old", archived=True)]
+        fake, seen = fake_gitea(
+            orgs=["konairius"],
+            teams={"konairius": [team(1, "Owners", "owner", permission="owner"), team(2, "Bots"),
+                                 team(5, "Reviewers", "read", permission="none")]},
+            members={2},
+            repos={"/orgs/konairius/repos": org_repos})
        with mock.patch.object(sync, "api", side_effect=fake):
            got = [r["full_name"] for r in sync.issue_repos("tok")]
-        self.assertEqual(got, ["a/x", "a/w"])
-        self.assertIn("/repos/a/x/collaborators/hermes-bot/permission", seen)
-        self.assertFalse([p for p in seen if p.startswith(("/repos/a/y/", "/repos/a/z/"))])
+        self.assertEqual(got, ["konairius/homelab", "konairius/ical-proxy", "konairius/shelly-manager"])
+        self.assertFalse([p for p in seen if "/collaborators/" in p or p.startswith("/repos/")])
+        self.assertNotIn("/teams/5/members/hermes-bot", seen)  # read-only team is not even checked

-    def test_failed_permission_lookup_skips_only_that_repo(self):
-        def fake(method, path, token, body=None):
-            if path.startswith("/repos/search"):
-                return {"data": [repo("a/x"), repo("a/broken"), repo("a/w")]}
-            if path.startswith("/repos/a/broken/"):
-                raise RuntimeError("GET /repos/a/broken/...: HTTP 500")
-            return {"permission": "write"}
+    def test_team_with_selected_repos_and_no_issue_write(self):
+        fake, seen = fake_gitea(
+            orgs=["a", "b"],
+            teams={"a": [team(3, "Some", all_repos=False)],
+                   "b": [team(4, "CodeOnly", issues="read")]},
+            members={3, 4},
+            repos={"/teams/3/repos": [repo("a/x"), repo("a/y")],
+                   "/orgs/a/repos": [repo("a/x"), repo("a/y"), repo("a/not-in-team")],
+                   "/orgs/b/repos": [repo("b/z")]})
+        with mock.patch.object(sync, "api", side_effect=fake):
+            got = [r["full_name"] for r in sync.issue_repos("tok")]
+        self.assertEqual(got, ["a/x", "a/y"])
+        self.assertNotIn("/orgs/b/repos", seen)

+    def test_team_issue_write_from_units_map_or_team_mode(self):
+        self.assertTrue(sync.team_writes_issues(team(2, "Bots")))
+        self.assertFalse(sync.team_writes_issues(team(5, "Reviewers", "read", permission="none")))
+        self.assertTrue(sync.team_writes_issues(team(1, "Owners", "read", permission="owner")))
+        self.assertTrue(sync.team_writes_issues({"permission": "write"}))  # no units_map
+        self.assertFalse(sync.team_writes_issues({"permission": "read", "units_map": {}}))
+
+    def test_user_repos_are_out_of_scope(self):
+        fake, seen = fake_gitea(orgs=[], teams={}, members=set(), repos={})
+        with mock.patch.object(sync, "api", side_effect=fake):
+            self.assertEqual(sync.issue_repos("tok"), [])
+        self.assertEqual(seen, ["/admin/users/hermes-bot/orgs"])  # no /repos/search over user repos
+
+    def test_failed_team_lookup_skips_only_that_team(self):
+        fake, _ = fake_gitea(
+            orgs=["a", "broken"],
+            teams={"a": [team(3, "Bots", all_repos=False), team(6, "More", all_repos=False)]},
+            members={3, 6},
+            repos={"/teams/3/repos": [repo("a/x")], "/teams/6/repos": [repo("a/w"), repo("a/x")]},
+            fail={"/orgs/broken/teams", "/teams/6/members/hermes-bot"})
        errors = []
        with mock.patch.object(sync, "api", side_effect=fake):
            got = [r["full_name"] for r in sync.issue_repos("tok", errors)]
-        self.assertEqual(got, ["a/x", "a/w"])
-        self.assertEqual(len(errors), 1)
-        self.assertIn("a/broken", errors[0])
+        self.assertEqual(got, ["a/x"])
+        self.assertEqual(len(errors), 2)
+        self.assertIn("a team More", errors[0])
+        self.assertTrue(errors[1].startswith("broken:"))
+
+    def test_failed_lookup_raises_without_error_list(self):
+        fake, _ = fake_gitea(orgs=["broken"], teams={}, members=set(), repos={},
+                             fail={"/orgs/broken/teams"})
+        with mock.patch.object(sync, "api", side_effect=fake), self.assertRaises(RuntimeError):
+            sync.issue_repos("tok")


 class Backfill(unittest.TestCase):
@@ -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:fb3862c949af7c79996d0e514ee96128644d840835ed5368eeecb14a869de361
+          image: alpine/socat:1.8.1.3@sha256:603174b77eebaba25ba8f8ebb15e1234d6600409554e95d6fb203fd106150287
          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:fb3862c949af7c79996d0e514ee96128644d840835ed5368eeecb14a869de361
+          image: alpine/socat:1.8.1.3@sha256:603174b77eebaba25ba8f8ebb15e1234d6600409554e95d6fb203fd106150287
          imagePullPolicy: IfNotPresent
          command:
            - /bin/sh
@@ -61,7 +61,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: shelly-manager
-          image: gitea.renner.uno/k.renner/shelly-manager:build.1792387459 # {"$imagepolicy": "flux-system:shelly-manager"}
+          image: gitea.renner.uno/k.renner/shelly-manager:build.1792997278 # {"$imagepolicy": "flux-system:shelly-manager"}
          imagePullPolicy: IfNotPresent
          ports:
            - name: http
@@ -90,8 +90,7 @@ spec:
            # BLE radios: ESP32 esphome bluetooth_proxy nodes (e.g. the M5 Atom
            # Echo) are AUTO-DISCOVERED on the IoT VLAN via mDNS
            # (_esphomelib._tcp) over the same net1 macvlan route as the Shellys —
-            # no static hostname/DNS (which the *.renner.uno wildcard would poison
-            # over IPv6). The shared fleet Noise key (= the dashboard's
+            # no static hostname/DNS. The shared fleet Noise key (= the dashboard's
            # shelly_ble_proxy_api_key) lets shelly-manager complete the encrypted
            # native-API handshake to each discovered proxy: DeviceInfo on
            # /ble-radios today, the BLE scan/GATT provisioning path next.
@@ -178,7 +177,7 @@ spec:
        # No probes: it only serves the API-key path, and a probe failure would
        # also pull the pod out of the shelly-manager Service.
        - name: api-proxy
-          image: nginxinc/nginx-unprivileged:1.31-alpine@sha256:b9241c6e7b8e9a862f129d8d4199ab64b10390949a78bdd5603379b32c844083
+          image: nginxinc/nginx-unprivileged:1.31-alpine@sha256:b5047b9b76845eac124358373c6852377c52e4b05834a47647e955dd91cb8f1e
          env:
            - name: POD_IP
              valueFrom:
@@ -1,179 +0,0 @@
-# Proposal: enrol the mosquitto broker credentials in Class-A rotation
-
-**Status:** proposal, nothing implemented.
-**Scope:** the 8 MQTT broker users and the credentials behind them.
-
-## Problem
-
-Every self-generated secret in this cluster rotates automatically except these.
-`kubernetes/infrastructure/openbao/rotation/` holds 13 manifests defining 15
-rotator CronJobs (`home-assistant.yaml` alone defines three). Five are **Class-A**
-— authentik, crowdsec, paperless, shelly-manager and woodpecker — meaning
-"self-generated random secret", which is exactly what a broker password is.
-The mosquitto credentials are the only Class-A-shaped secrets not enrolled.
-
-They are currently minted once by seven near-identical bootstrap Jobs
-(`mosquitto-bootstrap.yaml`, 508 lines — the ServiceAccount, Role and RoleBinding
-are inside that same file) which generate a password, hand-build Secret JSON with
-`jq` and POST it to the Kubernetes API with `curl`. Once created they never
-change again.
-
-Three consequences:
-
-1. **They never rotate.** Not on a schedule, not on compromise, not ever.
-2. **They exist only in the Secret object** — not in OpenBao, so not covered by
-   the OpenBao snapshot CronJob, and unrecoverable if lost.
-3. **The Jobs cannot be modified.** A Job's `spec.template` is immutable, so
-   changing even the container image makes the whole `home-assistant`
-   Kustomization fail to reconcile with `field is immutable`. Any edit requires
-   deleting or renaming the Jobs.
-
-## Why the obvious fixes do not work
-
-Recorded because each was tried and rejected on evidence, and the reasons are
-not obvious from the code.
-
-| Approach | Why it fails |
-| --- | --- |
-| ExternalSecrets reading hand-seeded OpenBao paths | Depends on content copied in by hand. Git cannot recreate it; a fresh OpenBao leaves the paths empty and ESO then overwrites live broker credentials with nothing. |
-| ESO `Password` generator | **Overwrites pre-existing Secrets.** Verified: a Secret holding `KNOWN-PREEXISTING-VALUE` was replaced with a freshly generated password on first sync. Adopting it rotates the 7 Job-minted credentials at once, uncoordinated (`evcc` is already ESO-extract-backed and so unaffected). |
-| Keep the Jobs, fix only the image | Blocked by `spec.template` immutability. Renaming the Jobs works but is a hack that recurs on every future edit. |
-
-The common thread: each treats the credential as something to *place*, when the
-real requirement is a credential that can be *replaced*.
-
-## How rotation actually has to work here
-
-The broker rebuilds its password file from scratch on **every pod start**
-(`mosquitto-deployment.yaml`): `rm -f /mosquitto/auth/passwd` followed by
-`mosquitto_passwd -c -b …` for each of the 8 users, sourced from env vars backed
-by the 8 Secrets.
-
-Two things follow, and they shape the whole design:
-
- **A Secret change has no effect until the broker restarts.** There is no
-  Reloader annotation on the mosquitto Deployment today, unlike the consumers of
-  the existing Class-A rotators.
- **There is no make-before-break.** A mosquitto user has exactly one password.
-  The LLAT rotators can mint a second token and revoke the first afterwards; a
-  broker user cannot hold old and new simultaneously. Unless a transitional
-  second user is created, broker and client must cut over together.
-
-### Who holds each credential
-
-This is the part that determines cutover cost, and it is not visible from the
-manifests alone.
-
-| Broker user | Held by | Cutover |
-| --- | --- | --- |
-| `health` | the broker's own liveness/readiness probes | in-cluster, same pod restart |
-| `zigbee2mqtt` | zigbee2mqtt Deployment (`secretKeyRef`) | in-cluster, pod restart |
-| `evcc` | evcc app; already OpenBao-backed via ESO | in-cluster, pod restart |
-| `sml2mqtt` | edge host, from `vault_edge_sml2mqtt_mqtt_password` | re-run the edge-host play |
-| `open3e` | edge host, from `vault_edge_open3e_mqtt_password` | re-run the edge-host play |
-| `homeassistant` | HA MQTT integration — a config entry created in the UI | needs an API/WebSocket update, or a manual re-entry |
-| `shellies` | Shelly device firmware | pushed per-device; `shelly-manager` is deployed and is the natural mechanism |
-| `admin` | a workstation client, held by a human | read the new value from OpenBao |
-
-Note `sml2mqtt` and `open3e` currently keep **the same password in two unlinked
-places** — the Kubernetes Secret for the broker, and `ansible-vault` for the
-client — synchronised by hand. That duplication, not any client limitation, is
-what makes rotation feel impossible today.
-
-## Proposed design
-
-Follow the existing Class-A pattern exactly (`rotation/paperless.yaml` is the
-closest model): *generate random bytes → merge-patch into OpenBao → ESO syncs the
-Secret → restart the consumer*.
-
-1. **One rotator CronJob per broker user**, running the existing `secret-rotator`
-   binary in random mode, writing `apps/home-assistant/mosquitto-<user>-credentials`
-   in OpenBao. Reuses the established policy/role/SA pattern; no new machinery.
-2. **ExternalSecrets** project each OpenBao entry to the existing Secret name and
-   key, so `mosquitto-deployment.yaml` and the in-cluster consumers are unchanged.
-   Key names stay as they are (`homeassistant-password` on one, `password` on the
-   rest) — consumers reference them, so normalising is a separate change.
-3. **Add a Reloader annotation to the mosquitto Deployment** so a Secret change
-   restarts the broker, instead of silently taking effect at some unrelated future
-   restart.
-4. **Move the edge host off `ansible-vault` for these two values**, reading the
-   same OpenBao entry instead, so there is one source of truth per credential.
-5. **Rotate one user at a time.** Each rotation then affects exactly one client,
-   not all eight.
-
-### The cutover window
-
-With no make-before-break, each rotation has a window where broker and client
-disagree. Two options:
-
- **Accept a brief window** (recommended for most users). Order: rotator writes
-  OpenBao → client picks up the new value → broker restarts. MQTT clients
-  reconnect automatically; the window is seconds. Because rotation is per-user,
-  only that one client is affected.
-
-  One failure mode to expect rather than be alarmed by: the broker rolls with
-  `maxUnavailable: 0` / `maxSurge: 1`, so mid-rollout **two broker pods with
-  different passwd files sit behind the LB**. A client reconnecting during that
-  window can land on the old pod and fail auth until the rollout completes. It is
-  self-healing and lasts seconds to a minute, but it will look alarming in logs
-  during the first `health` / `zigbee2mqtt` rotation, so it is worth knowing in
-  advance.
- **Transitional dual user** (`<user>` and `<user>-next` in the passwd file and
-  ACL) for any credential where even a brief outage is unacceptable. More moving
-  parts; probably only worth it for `homeassistant`, which carries everything.
-
-## Suggested phasing
-
-Ordered so the risky work happens after the pattern is proven, and so each phase
-is independently valuable.
-
-1. **`health` and `zigbee2mqtt` first.** Both are entirely in-cluster and pick up
-   a new password on pod restart with no external coordination. Proves rotator →
-   OpenBao → ESO → Reloader end to end with the smallest blast radius. `health`
-   is the safest possible start: only the broker's own probes consume it.
-2. **`evcc`.** Already OpenBao-backed via ESO; only the rotator is missing.
-3. **`sml2mqtt` and `open3e`**, together with switching the edge host to read from
-   OpenBao. This is where the duplicate-source-of-truth problem gets fixed.
-4. **`shellies`**, via shelly-manager pushing to devices. Needs investigation:
-   shelly-manager has its own Class-A rotator today, but that rotates
-   shelly-manager's own secret and does not touch device MQTT credentials.
-5. **`homeassistant`** last. Highest blast radius, and the config entry is UI-created,
-   so it needs an API/WebSocket update path — the HA LLAT rotators
-   (`rotation/home-assistant.yaml`) already talk to HA over WebSocket and are the
-   obvious precedent.
-6. **`admin`** whenever convenient; a human reads the new value from OpenBao.
-
-Only once a user is enrolled does its bootstrap Job become dead code. Delete the
-Jobs incrementally as their users migrate, rather than in one step — that also
-avoids the immutability problem entirely, since the Jobs are deleted, never
-patched.
-
-## Open questions
-
- **Does `secret-rotator` random mode fit unchanged?** The existing rotators write
-  a field into an OpenBao entry; here the entry holds a single password field, so
-  it should, but this needs confirming against the binary rather than assumed.
- **Can shelly-manager push MQTT credentials to devices**, and does it cover both
-  Gen1 (`/settings/mqtt`) and Gen2+ (`Mqtt.SetConfig`) firmwares? If not, the
-  `shellies` user may need a different mechanism or stay manual longest.
- **How is the HA MQTT config entry updated programmatically?** Reusing the
-  WebSocket approach from the LLAT rotator is plausible but unverified.
- **Rotation cadence.** The existing rotators' schedules should be the reference
-  rather than inventing a new one.
- **ESO refresh latency.** Rotator-writes-OpenBao → Secret-updates →
-  Reloader-restarts is delayed by up to one `refreshInterval`; the `evcc`
-  ExternalSecret uses `1h`. That does not widen the outage window — broker and
-  client still move together — but it does stretch how long a rotation takes to
-  land, which matters for verifying one completed and for the cold-rebuild
-  ordering question above. Worth deciding whether these ExternalSecrets want a
-  shorter interval than 1h, or whether the rotator should trigger the sync
-  directly.
- **Bootstrap on a cold rebuild.** On a fresh cluster the rotator must create the
-  OpenBao entry before ESO can sync it; check this against
-  `kubernetes/RUNBOOK-cold-rebuild.md` so broker bring-up is not blocked.
-
-## What this does not change
-
- Secret names, key names and every `secretKeyRef` in `mosquitto-deployment.yaml`.
- The ACL model and the per-user topic scoping.
- The `evcc` ExternalSecret, which already follows the target pattern.
@@ -128,7 +128,7 @@ spec:
              memory: 32Mi
      containers:
        - name: home-assistant
-          image: ghcr.io/home-assistant/home-assistant:2026.10.2 # {"$imagepolicy": "flux-system:home-assistant"}
+          image: ghcr.io/home-assistant/home-assistant:2026.10.4 # {"$imagepolicy": "flux-system:home-assistant"}
          env:
            - name: TZ
              value: Europe/Berlin
@@ -192,7 +192,7 @@ spec:
        # substitution to POD_IP so nginx-runtime variables like $host
        # / $http_x_forwarded_for in the template stay intact.
        - name: proxy
-          image: nginxinc/nginx-unprivileged:1.31-alpine@sha256:378d0c32f6562f7fd9629170797f57d2b953aa09be983b3daaf4809bb039ca00
+          image: nginxinc/nginx-unprivileged:1.31-alpine@sha256:b5047b9b76845eac124358373c6852377c52e4b05834a47647e955dd91cb8f1e
          env:
            - name: POD_IP
              valueFrom:
@@ -236,7 +236,7 @@ spec:
        # readiness probe on purpose: a broker outage must not take HA out of
        # its Service endpoints.
        - name: mqtt-tls
-          image: ghostunnel/ghostunnel:v1.11.4@sha256:e5248233863aadd36383a11c92360f2981141881ef05e38360a6ada8630d36b1
+          image: ghostunnel/ghostunnel:v1.11.5@sha256:65c4e34ec0ee0f30ea1f72b7411ec70a91c32fc50f067a8466ad2adb1e7420f2
          args:
            - client
            - --listen=127.0.0.1:11883
@@ -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:4.141.0@sha256:72ab24b5680ee597dd647b30d82625752f40109b5f61bef90ffbf1ea1f02dbb8
+          image: codercom/code-server:4.143.1@sha256:377b66bec5645510ed52549bb00e648c273edc604d230a3f90fd2b2433afcb97
          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@sha256:03228d7ded483b0b3e55e1de7fa660d70d3e1bb432fa7021d29e192640de11aa
+          image: alpine/git:2.54.0@sha256:e8ceedc73bd80992ae8d58a7d24c58b8322146c354f1d2e81a97db4452068ec0
          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:2026.9.1@sha256:776a845d508909bf426d2ee7bdd81796361ebe6a7f091807ce1d6d0b48985413
+          image: ghcr.io/esphome/esphome:2026.10.0@sha256:1dff19a59070cdb523b76576cdc74d200f862d43c1407809088855920cf57145
          imagePullPolicy: IfNotPresent
          # Default entrypoint runs the dashboard (Device Builder) against the
          # mounted /config — no command override needed.
@@ -12,26 +12,20 @@ resources:
  - config-sync-token-externalsecret.yaml
  - config-sync-gitea-externalsecret.yaml
  - matrix-externalsecret.yaml
-  - mosquitto-bootstrap.yaml
-  # Former `health` probe credential. The broker no longer reads it (the
-  # probes use the cert account mosquitto-probe, REN-953); removed with its
-  # rotator in the REN-802 cleanup step.
-  - mosquitto-health-credentials-externalsecret.yaml
+  - mosquitto-admin-password.yaml
  - mosquitto-config.yaml
  - mosquitto-certificate.yaml
  - mosquitto-service.yaml
  - mosquitto-iot-service.yaml
  - mosquitto-deployment.yaml
-  - mosquitto-evcc-credentials-externalsecret.yaml
  # shelly-manager and the mDNS relay sit on the IoT VLAN: ../home-assistant-iot.
  - esphome-pvc.yaml
  - esphome-deployment.yaml
  - esphome-service.yaml
  - esphome-ingress.yaml
  # Zigbee2MQTT — ZHA replacement bridge. Ships scaled to 0; the cutover
-  # runbook (zigbee2mqtt-migration-runbook.md) scales it up. The MQTT
-  # `zigbee2mqtt` broker user is provisioned by mosquitto-bootstrap.yaml
-  # (above) and wired into mosquitto-deployment.yaml (passwd + ACL).
+  # runbook (zigbee2mqtt-migration-runbook.md) scales it up. It logs in to
+  # the broker as register account `zigbee2mqtt-bridge` (mqtt-accounts.yaml).
  - zigbee2mqtt-coordinator-backup-externalsecret.yaml
  - zigbee2mqtt-config.yaml
  - zigbee2mqtt-pvc.yaml
@@ -0,0 +1,32 @@
+# Password of the broker's `admin` workstation login (mosquitto-deployment.yaml).
+# Generated once in-cluster, nothing in OpenBao. Read it with
+#   kubectl -n home-assistant get secret mosquitto-admin-password -o jsonpath='{.data.password}' | base64 -d
+apiVersion: generators.external-secrets.io/v1alpha1
+kind: Password
+metadata:
+  name: mosquitto-admin-password
+  namespace: home-assistant
+spec:
+  length: 32
+  digits: 8
+  symbols: 0
+  allowRepeat: true
+  noUpper: false
+  secretKeys:
+    - password
+---
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: mosquitto-admin-password
+  namespace: home-assistant
+spec:
+  refreshPolicy: CreatedOnce
+  target:
+    name: mosquitto-admin-password
+  dataFrom:
+    - sourceRef:
+        generatorRef:
+          apiVersion: generators.external-secrets.io/v1alpha1
+          kind: Password
+          name: mosquitto-admin-password
@@ -1,394 +0,0 @@
---
-# Generates mosquitto-credentials on first deploy. The password is created
-# in-cluster, lives only in the Secret object, and is never written to git
-# or seen by a human. The Mosquitto broker hashes it via mosquitto_passwd
-# -U at startup; HA reads the same value from this Secret (configured
-# manually in the HA MQTT integration UI).
-#
-# Idempotent: if the Secret already exists, the Job exits 0 without
-# regenerating, so subsequent Flux reconciles don't rotate the password.
-# To rotate, delete both the Secret and this Job; Flux will re-create
-# the Job and a fresh password.
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: mosquitto-bootstrap
-  namespace: home-assistant
---
-apiVersion: rbac.authorization.k8s.io/v1
-kind: Role
-metadata:
-  name: mosquitto-bootstrap
-  namespace: home-assistant
-rules:
-  - apiGroups: [""]
-    resources: ["secrets"]
-    verbs: ["get", "create"]
---
-apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
-metadata:
-  name: mosquitto-bootstrap
-  namespace: home-assistant
-subjects:
-  - kind: ServiceAccount
-    name: mosquitto-bootstrap
-    namespace: home-assistant
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: Role
-  name: mosquitto-bootstrap
---
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: mosquitto-credentials-bootstrap
-  namespace: home-assistant
-  annotations:
-    # Job pod templates are immutable; force-recreate so image bumps
-    # apply on Flux re-reconcile. Safe: the Job is idempotent (see above).
-    kustomize.toolkit.fluxcd.io/force: enabled
-spec:
-  backoffLimit: 4
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: mosquitto-bootstrap
-    spec:
-      serviceAccountName: mosquitto-bootstrap
-      restartPolicy: OnFailure
-      containers:
-        - name: bootstrap
-          image: alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
-          command:
-            - sh
-            - -c
-            - |
-              set -eu
-              apk add --no-cache curl jq >/dev/null
-
-              NS=home-assistant
-              NAME=mosquitto-credentials
-              TOKEN=$(cat /var/run/secrets/kubernetes.io/serviceaccount/token)
-              CA=/var/run/secrets/kubernetes.io/serviceaccount/ca.crt
-              API=https://kubernetes.default.svc
-
-              if curl -fsSL --cacert "$CA" -H "Authorization: Bearer $TOKEN" \
-                   "$API/api/v1/namespaces/$NS/secrets/$NAME" >/dev/null 2>&1; then
-                echo "$NAME already exists; nothing to do."
-                exit 0
-              fi
-
-              PW=$(tr -dc 'A-Za-z0-9' </dev/urandom | head -c 32)
-              PW_B64=$(printf '%s' "$PW" | base64 | tr -d '\n')
-
-              body=$(jq -nc \
-                --arg name "$NAME" \
-                --arg ns "$NS" \
-                --arg pw "$PW_B64" \
-                '{apiVersion: "v1",
-                  kind: "Secret",
-                  metadata: {name: $name, namespace: $ns},
-                  type: "Opaque",
-                  data: {"homeassistant-password": $pw}}')
-
-              curl -fsSL --cacert "$CA" -H "Authorization: Bearer $TOKEN" \
-                   -H "Content-Type: application/json" -X POST \
-                   --data "$body" \
-                   "$API/api/v1/namespaces/$NS/secrets" >/dev/null
-
-              echo "generated $NAME"
-          resources:
-            requests:
-              cpu: 10m
-              memory: 32Mi
-            limits:
-              memory: 64Mi
---
-# Third broker user: `admin`. Full readwrite (same as HA) but kept on
-# its own credential so a workstation client can hold a password the
-# in-cluster HA config never sees, and rotating one doesn't affect the
-# other. Retrieve with:
-#   kubectl -n home-assistant get secret mosquitto-admin-credentials \
-#     -o jsonpath='{.data.password}' | base64 -d
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: mosquitto-admin-credentials-bootstrap
-  namespace: home-assistant
-  annotations:
-    # Job pod templates are immutable; force-recreate so image bumps
-    # apply on Flux re-reconcile. Safe: the Job is idempotent (see above).
-    kustomize.toolkit.fluxcd.io/force: enabled
-spec:
-  backoffLimit: 4
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: mosquitto-bootstrap
-    spec:
-      serviceAccountName: mosquitto-bootstrap
-      restartPolicy: OnFailure
-      containers:
-        - name: bootstrap
-          image: alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
-          command:
-            - sh
-            - -c
-            - |
-              set -eu
-              apk add --no-cache curl jq >/dev/null
-
-              NS=home-assistant
-              NAME=mosquitto-admin-credentials
-              TOKEN=$(cat /var/run/secrets/kubernetes.io/serviceaccount/token)
-              CA=/var/run/secrets/kubernetes.io/serviceaccount/ca.crt
-              API=https://kubernetes.default.svc
-
-              if curl -fsSL --cacert "$CA" -H "Authorization: Bearer $TOKEN" \
-                   "$API/api/v1/namespaces/$NS/secrets/$NAME" >/dev/null 2>&1; then
-                echo "$NAME already exists; nothing to do."
-                exit 0
-              fi
-
-              PW=$(tr -dc 'A-Za-z0-9' </dev/urandom | head -c 32)
-              PW_B64=$(printf '%s' "$PW" | base64 | tr -d '\n')
-
-              body=$(jq -nc \
-                --arg name "$NAME" \
-                --arg ns "$NS" \
-                --arg pw "$PW_B64" \
-                '{apiVersion: "v1",
-                  kind: "Secret",
-                  metadata: {name: $name, namespace: $ns},
-                  type: "Opaque",
-                  data: {password: $pw}}')
-
-              curl -fsSL --cacert "$CA" -H "Authorization: Bearer $TOKEN" \
-                   -H "Content-Type: application/json" -X POST \
-                   --data "$body" \
-                   "$API/api/v1/namespaces/$NS/secrets" >/dev/null
-
-              echo "generated $NAME"
-          resources:
-            requests:
-              cpu: 10m
-              memory: 32Mi
-            limits:
-              memory: 64Mi
---
-# Fourth broker user: `sml2mqtt` — the power-meter bridge. Publish-only
-# under `sml2mqtt/#` (ACL in mosquitto-deployment.yaml). Own credential so
-# its lifecycle is independent of the others. The sml2mqtt pod reads this
-# password via its init container and renders it into config.yml.
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: mosquitto-sml2mqtt-credentials-bootstrap
-  namespace: home-assistant
-  annotations:
-    # Job pod templates are immutable; force-recreate so image bumps
-    # apply on Flux re-reconcile. Safe: the Job is idempotent (see above).
-    kustomize.toolkit.fluxcd.io/force: enabled
-spec:
-  backoffLimit: 4
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: mosquitto-bootstrap
-    spec:
-      serviceAccountName: mosquitto-bootstrap
-      restartPolicy: OnFailure
-      containers:
-        - name: bootstrap
-          image: alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
-          command:
-            - sh
-            - -c
-            - |
-              set -eu
-              apk add --no-cache curl jq >/dev/null
-
-              NS=home-assistant
-              NAME=mosquitto-sml2mqtt-credentials
-              TOKEN=$(cat /var/run/secrets/kubernetes.io/serviceaccount/token)
-              CA=/var/run/secrets/kubernetes.io/serviceaccount/ca.crt
-              API=https://kubernetes.default.svc
-
-              if curl -fsSL --cacert "$CA" -H "Authorization: Bearer $TOKEN" \
-                   "$API/api/v1/namespaces/$NS/secrets/$NAME" >/dev/null 2>&1; then
-                echo "$NAME already exists; nothing to do."
-                exit 0
-              fi
-
-              PW=$(tr -dc 'A-Za-z0-9' </dev/urandom | head -c 32)
-              PW_B64=$(printf '%s' "$PW" | base64 | tr -d '\n')
-
-              body=$(jq -nc \
-                --arg name "$NAME" \
-                --arg ns "$NS" \
-                --arg pw "$PW_B64" \
-                '{apiVersion: "v1",
-                  kind: "Secret",
-                  metadata: {name: $name, namespace: $ns},
-                  type: "Opaque",
-                  data: {password: $pw}}')
-
-              curl -fsSL --cacert "$CA" -H "Authorization: Bearer $TOKEN" \
-                   -H "Content-Type: application/json" -X POST \
-                   --data "$body" \
-                   "$API/api/v1/namespaces/$NS/secrets" >/dev/null
-
-              echo "generated $NAME"
-          resources:
-            requests:
-              cpu: 10m
-              memory: 32Mi
-            limits:
-              memory: 64Mi
---
-# Fifth broker user: `open3e` — the Viessmann E3 CAN bridge (Vitocal 250-A
-# + Vitocharge VX3 via open3e). Scoped to `open3e/#` (ACL in
-# mosquitto-deployment.yaml). Own credential so its lifecycle is
-# independent of the others. Retrieve with:
-#   kubectl -n home-assistant get secret mosquitto-open3e-credentials \
-#     -o jsonpath='{.data.password}' | base64 -d
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: mosquitto-open3e-credentials-bootstrap
-  namespace: home-assistant
-  annotations:
-    # Job pod templates are immutable; force-recreate so image bumps
-    # apply on Flux re-reconcile. Safe: the Job is idempotent (see above).
-    kustomize.toolkit.fluxcd.io/force: enabled
-spec:
-  backoffLimit: 4
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: mosquitto-bootstrap
-    spec:
-      serviceAccountName: mosquitto-bootstrap
-      restartPolicy: OnFailure
-      containers:
-        - name: bootstrap
-          image: alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
-          command:
-            - sh
-            - -c
-            - |
-              set -eu
-              apk add --no-cache curl jq >/dev/null
-
-              NS=home-assistant
-              NAME=mosquitto-open3e-credentials
-              TOKEN=$(cat /var/run/secrets/kubernetes.io/serviceaccount/token)
-              CA=/var/run/secrets/kubernetes.io/serviceaccount/ca.crt
-              API=https://kubernetes.default.svc
-
-              if curl -fsSL --cacert "$CA" -H "Authorization: Bearer $TOKEN" \
-                   "$API/api/v1/namespaces/$NS/secrets/$NAME" >/dev/null 2>&1; then
-                echo "$NAME already exists; nothing to do."
-                exit 0
-              fi
-
-              PW=$(tr -dc 'A-Za-z0-9' </dev/urandom | head -c 32)
-              PW_B64=$(printf '%s' "$PW" | base64 | tr -d '\n')
-
-              body=$(jq -nc \
-                --arg name "$NAME" \
-                --arg ns "$NS" \
-                --arg pw "$PW_B64" \
-                '{apiVersion: "v1",
-                  kind: "Secret",
-                  metadata: {name: $name, namespace: $ns},
-                  type: "Opaque",
-                  data: {password: $pw}}')
-
-              curl -fsSL --cacert "$CA" -H "Authorization: Bearer $TOKEN" \
-                   -H "Content-Type: application/json" -X POST \
-                   --data "$body" \
-                   "$API/api/v1/namespaces/$NS/secrets" >/dev/null
-
-              echo "generated $NAME"
-          resources:
-            requests:
-              cpu: 10m
-              memory: 32Mi
-            limits:
-              memory: 64Mi
---
-# Broker user `zigbee2mqtt` — the Zigbee2MQTT bridge (ZHA replacement). Scoped
-# to its own `zigbee2mqtt/#` subtree plus `write homeassistant/#` (so it can
-# publish HA MQTT-discovery configs) and
-# `read homeassistant/status` (HA's birth/will topic; on `online` Z2M
-# republishes cached device states, NOT discovery configs — ACL and the full
-# reasoning in mosquitto-deployment.yaml). Own credential so its lifecycle is
-# independent of the others. The Z2M init container reads this password and
-# renders it into /app/data/secret.yaml.
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: mosquitto-zigbee2mqtt-credentials-bootstrap
-  namespace: home-assistant
-  annotations:
-    # Job pod templates are immutable; force-recreate so image bumps
-    # apply on Flux re-reconcile. Safe: the Job is idempotent (see above).
-    kustomize.toolkit.fluxcd.io/force: enabled
-spec:
-  backoffLimit: 4
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: mosquitto-bootstrap
-    spec:
-      serviceAccountName: mosquitto-bootstrap
-      restartPolicy: OnFailure
-      containers:
-        - name: bootstrap
-          image: alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
-          command:
-            - sh
-            - -c
-            - |
-              set -eu
-              apk add --no-cache curl jq >/dev/null
-
-              NS=home-assistant
-              NAME=mosquitto-zigbee2mqtt-credentials
-              TOKEN=$(cat /var/run/secrets/kubernetes.io/serviceaccount/token)
-              CA=/var/run/secrets/kubernetes.io/serviceaccount/ca.crt
-              API=https://kubernetes.default.svc
-
-              if curl -fsSL --cacert "$CA" -H "Authorization: Bearer $TOKEN" \
-                   "$API/api/v1/namespaces/$NS/secrets/$NAME" >/dev/null 2>&1; then
-                echo "$NAME already exists; nothing to do."
-                exit 0
-              fi
-
-              PW=$(tr -dc 'A-Za-z0-9' </dev/urandom | head -c 32)
-              PW_B64=$(printf '%s' "$PW" | base64 | tr -d '\n')
-
-              body=$(jq -nc \
-                --arg name "$NAME" \
-                --arg ns "$NS" \
-                --arg pw "$PW_B64" \
-                '{apiVersion: "v1",
-                  kind: "Secret",
-                  metadata: {name: $name, namespace: $ns},
-                  type: "Opaque",
-                  data: {password: $pw}}')
-
-              curl -fsSL --cacert "$CA" -H "Authorization: Bearer $TOKEN" \
-                   -H "Content-Type: application/json" -X POST \
-                   --data "$body" \
-                   "$API/api/v1/namespaces/$NS/secrets" >/dev/null
-
-              echo "generated $NAME"
-          resources:
-            requests:
-              cpu: 10m
-              memory: 32Mi
-            limits:
-              memory: 64Mi
@@ -77,18 +77,15 @@ data:

    allow_anonymous false

-    # Two account sources side by side (REN-802 step 2, tested on 2.0.22 in
-    # REN-900, document `coexistence`):
-    #   Dynamic Security: accounts from the register mqtt-accounts.yaml,
-    #     managed live by mqtt-account-controller over $CONTROL.
-    #   password_file/acl_file: the legacy users, unchanged until each client
-    #     moves to the register (step 3).
+    # Accounts (tested on 2.0.22 in REN-900, document `coexistence`):
+    #   Dynamic Security: every client account, from the register
+    #     mqtt-accounts.yaml, managed live by mqtt-account-controller over
+    #     $CONTROL. Applies to all listeners (per_listener_settings false).
+    #   password_file/acl_file: the owner's workstation login `admin` only
+    #     (mosquitto-deployment.yaml).
    # Dynamic Security is asked first. For a username it does not know, and
    # for a request none of its roles match, it defers to the files. A
-    # register entry with the same name as a legacy user therefore replaces
-    # that user's password, while its acl_file block still applies to
-    # whatever the entry's roles do not cover. Delete the legacy user when
-    # its client moves.
+    # register entry named `admin` therefore replaces the file login.
    #
    # The acl_file check of 2.0 allows every SUBSCRIBE and checks only on
    # delivery, so the Dynamic Security default must deny publishClientReceive.
@@ -64,67 +64,15 @@ spec:
            - -c
            - |
              set -eu
+              # `admin` is the owner's workstation login over the LoadBalancer
+              # (1883/8883), full readwrite. The only password_file user: the
+              # controller cannot deliver a password account to a Secret, and
+              # the cert listener :8884 is in-cluster only.
              rm -f /mosquitto/auth/passwd
-              mosquitto_passwd -c -b /mosquitto/auth/passwd homeassistant "$HA_PASSWORD"
-              mosquitto_passwd -b /mosquitto/auth/passwd admin "$ADMIN_PASSWORD"
-              mosquitto_passwd -b /mosquitto/auth/passwd sml2mqtt "$SML2MQTT_PASSWORD"
-              mosquitto_passwd -b /mosquitto/auth/passwd open3e "$OPEN3E_PASSWORD"
-              mosquitto_passwd -b /mosquitto/auth/passwd evcc "$EVCC_PASSWORD"
-              mosquitto_passwd -b /mosquitto/auth/passwd zigbee2mqtt "$ZIGBEE2MQTT_PASSWORD"
-              # ACL: HA keeps full access (subscribes to everything). Shellies
-              # are not legacy users any more: each has its own Dynamic Security
-              # account from mqtt-accounts.yaml (REN-802, REN-1017).
-              # `admin` is a workstation/debugging credential — full
-              # readwrite, kept on its own credential so its password can
-              # be rotated independently of the HA session.
-              # `sml2mqtt` is the power-meter bridge — WRITE-only under its own
-              # `sml2mqtt/#` subtree (it only publishes; HA reads it via the
-              # full-access homeassistant user).
-              # `open3e` is the Viessmann E3 CAN bridge (Vitocal/VX3) —
-              # scoped to its own `open3e/#` subtree: publishes datapoints
-              # and later subscribes to `open3e/cmnd` in listener mode (HA
-              # reads via the full-access homeassistant user).
-              # `evcc` is the (cross-namespace) EV charge controller — reads
-              # `open3e/#` (VX3 grid/PV/battery/SoC datapoints), publishes its
-              # own state under `evcc/#`, and reads the grid price from
-              # `energy/#` (HA republishes input_number.strompreis to
-              # energy/tariff/grid; kept OUTSIDE evcc/# so evcc's own retained-
-              # topic management can't wipe it).
+              mosquitto_passwd -c -b /mosquitto/auth/passwd admin "$ADMIN_PASSWORD"
              cat > /mosquitto/auth/acl <<'EOF'
-              user homeassistant
-              topic readwrite #
-
              user admin
              topic readwrite #
-
-              user sml2mqtt
-              topic write sml2mqtt/#
-
-              user open3e
-              topic readwrite open3e/#
-
-              user evcc
-              topic read open3e/#
-              topic readwrite evcc/#
-              topic read energy/#
-
-              # `zigbee2mqtt` is the Zigbee2MQTT bridge (the ZHA replacement).
-              # Owns its own `zigbee2mqtt/#` subtree; may WRITE `homeassistant/#`
-              # to publish HA MQTT-discovery configs (write-only there, to deny
-              # discovery-tree recon from a compromised bridge); and READs `homeassistant/status`, HA's birth/will topic.
-              #
-              # That read grant does NOT buy a discovery re-publish: on
-              # `online`, Z2M 2.12.1 republishes bridge/state and cached device
-              # states only (lib/extension/homeassistant.ts onMQTTMessage) —
-              # discover() runs solely from start(). The grant is still correct,
-              # because the cached-state republish is what makes HA show current
-              # values right after an HA restart. Restoring discovery after a
-              # BROKER restart is handled by the discovery-guard sidecar in
-              # zigbee2mqtt-deployment.yaml.
-              user zigbee2mqtt
-              topic readwrite zigbee2mqtt/#
-              topic write homeassistant/#
-              topic read homeassistant/status
              EOF
              # Dynamic Security start file (REN-802): the controller's seed
              # if it exists, else the static base file. The seed carries
@@ -143,38 +91,11 @@ spec:
              chmod 0600 /mosquitto/auth/passwd /mosquitto/auth/acl /mosquitto/auth/dynamic-security.json
              exec mosquitto -c /mosquitto/config/mosquitto.conf
          env:
-            - name: HA_PASSWORD
-              valueFrom:
-                secretKeyRef:
-                  name: mosquitto-credentials
-                  key: homeassistant-password
+            # mosquitto-admin-password.yaml
            - name: ADMIN_PASSWORD
              valueFrom:
                secretKeyRef:
-                  name: mosquitto-admin-credentials
-                  key: password
-            - name: SML2MQTT_PASSWORD
-              valueFrom:
-                secretKeyRef:
-                  name: mosquitto-sml2mqtt-credentials
-                  key: password
-            - name: OPEN3E_PASSWORD
-              valueFrom:
-                secretKeyRef:
-                  name: mosquitto-open3e-credentials
-                  key: password
-            - name: EVCC_PASSWORD
-              valueFrom:
-                secretKeyRef:
-                  name: mosquitto-evcc-credentials
-                  key: password
-            # Zigbee2MQTT bridge credential (mosquitto-zigbee2mqtt-credentials-
-            # bootstrap). Hashed into the passwd file here; Z2M reads the same
-            # Secret via its init container to authenticate to the broker.
-            - name: ZIGBEE2MQTT_PASSWORD
-              valueFrom:
-                secretKeyRef:
-                  name: mosquitto-zigbee2mqtt-credentials
+                  name: mosquitto-admin-password
                  key: password
          ports:
            - name: mqtt
@@ -231,12 +152,12 @@ spec:
          # Service and the probe dials 127.0.0.1; the chain is still checked
          # against mqtt-ca.
          #
-          # mosquitto is a single-replica SPOF (HA, Shelly, sml2mqtt, open3e,
-          # evcc). Liveness is deliberately slow to fire — failureThreshold 6
-          # x 30s = 3 min of sustained failure before a restart — so a
-          # transient hiccup never bounces the broker every client depends
-          # on. The startupProbe (tcpSocket) suspends both while the
-          # container builds the passwd/acl files and mosquitto binds :1883.
+          # mosquitto is a single-replica SPOF (HA, Shelly, Zigbee2MQTT,
+          # edge-1, evcc). Liveness is deliberately slow to fire —
+          # failureThreshold 6 x 30s = 3 min of sustained failure before a
+          # restart — so a transient hiccup never bounces the broker every
+          # client depends on. The startupProbe (tcpSocket) suspends both while
+          # the container prepares /mosquitto/auth and mosquitto binds :1883.
          startupProbe:
            tcpSocket:
              port: mqtt
@@ -1,15 +0,0 @@
-apiVersion: external-secrets.io/v1
-kind: ExternalSecret
-metadata:
-  name: mosquitto-evcc-credentials
-  namespace: home-assistant
-spec:
-  refreshInterval: 1h
-  secretStoreRef:
-    kind: ClusterSecretStore
-    name: openbao
-  target:
-    name: mosquitto-evcc-credentials # keeps the old Secret's name — consumers unchanged
-  dataFrom:
-    - extract:
-        key: apps/home-assistant/mosquitto-evcc-credentials
@@ -1,36 +0,0 @@
-# Projects the mosquitto `health` broker credential from OpenBao into the Secret
-# the broker already consumes. FIRST of the eight broker users to move off the
-# bootstrap Jobs and onto Class-A rotation (see
-# PROPOSAL-mosquitto-credential-rotation.md (PR #453 — not yet merged; this
-# file lands with it)); the rotator lives at
-# kubernetes/infrastructure/openbao/rotation/mosquitto-health.yaml.
-#
-# Secret name and key are UNCHANGED (`password`), so mosquitto-deployment.yaml's
-# secretKeyRef and the exec probes that read $HEALTH_PASSWORD need no edit.
-#
-# refreshInterval is 10m rather than the 1h used by mosquitto-evcc-credentials:
-# a rotation only lands once ESO re-reads, so 1h would mean up to an hour between
-# the rotator running and the broker actually using the new password, with the
-# old one still valid in the meantime. 10m keeps that window short without
-# polling OpenBao pointlessly hard.
-#
-# ⚠️ OWNERSHIP: creationPolicy is implicitly Owner, so ESO sets an ownerReference
-# on the Secret. Deleting this ExternalSecret therefore DELETES the live Secret
-# and with it the broker's probe credential — the bootstrap Job it replaces had
-# no such coupling. To detach without destroying, set creationPolicy: Orphan
-# before removing it.
-apiVersion: external-secrets.io/v1
-kind: ExternalSecret
-metadata:
-  name: mosquitto-health-credentials
-  namespace: home-assistant
-spec:
-  refreshInterval: 10m
-  secretStoreRef:
-    kind: ClusterSecretStore
-    name: openbao
-  target:
-    name: mosquitto-health-credentials
-  dataFrom:
-    - extract:
-        key: apps/home-assistant/mosquitto-health-credentials
@@ -5,9 +5,7 @@
 # mqtt-accounts.yaml, every INTERVAL (2m).
 #
 # Manages the production broker `mosquitto` over its mTLS listener :8884
-# (REN-802 step 2, REN-900). The legacy users in that broker's password_file
-# are not Dynamic Security clients, so the controller never sees or touches
-# them.
+# (REN-802 step 2, REN-900).
 apiVersion: v1
 kind: ServiceAccount
 metadata:
@@ -87,6 +85,9 @@ subjects:
 #     delivered to this namespace. Add the name with the register entry.
 #   mqtt-ha-cert-sync: sha256 of the client certificate last accepted by
 #     Home Assistant's MQTT config entry (HA cert sync, REN-953/REN-1284).
+#   mqtt-<name>-password: the login of a password account delivered to this
+#     namespace, written, rewritten and deleted on revocation. One entry per
+#     account.
 apiVersion: rbac.authorization.k8s.io/v1
 kind: Role
 metadata:
@@ -99,6 +100,11 @@ rules:
    resources: ["secrets"]
    resourceNames: ["mqtt-account-hashes", "mqtt-dynsec-seed", "mqtt-ha-cert-sync"]
    verbs: ["get", "create", "patch"]
+  - apiGroups: [""]
+    resources: ["secrets"]
+    resourceNames:
+      - mqtt-admin-password
+    verbs: ["get", "create", "patch", "delete"]
  - apiGroups: [""]
    resources: ["secrets"]
    resourceNames:
@@ -219,7 +225,7 @@ spec:
        - name: controller
          # Woodpecker builds main-<sha> on every merge to main; no sortable
          # tag, so bumps are manual (same as ical-proxy).
-          image: gitea.renner.uno/konairius/mqtt-account-controller:main-cb96b1a@sha256:9d9b9e83a9c0f9f567e57edacab11cf4c58e8c0e49e38e8d7b51421cd1242911
+          image: gitea.renner.uno/konairius/mqtt-account-controller:main-b1f294d@sha256:8081adfee171c36cfa83734e5e7ccc3aad3debf1c0154488de70143674cde85f
          env:
            - name: BROKER_URL
              value: ssl://mosquitto.home-assistant.svc.cluster.local:8884
@@ -7,51 +7,50 @@
 # configMapGenerator in kustomization.yaml). An empty list is refused, so it
 # never revokes everyone.
 #
-# The controller manages the production broker `mosquitto` (REN-900). Its
-# legacy users (password_file in mosquitto-deployment.yaml) are not listed
-# here; each moves here with its client (REN-802 step 3). `test-cert` is the
-# certificate test account from REN-888.
+# The controller manages the production broker `mosquitto` (REN-900).
+# `test-cert` is the certificate test account from REN-888.
 #
-# A cert account needs its Secret `mqtt-<name>-tls` added to the
+# A cert account needs its Secret `mqtt-<name>-tls`, a password account
+# delivered to a namespace its Secret `mqtt-<name>-password`, added to the
 # `mqtt-account-controller-secrets-<namespace>` Role in
-# mqtt-account-controller.yaml, or revoking it fails with 403.
+# mqtt-account-controller.yaml, or writing or revoking it fails with 403.
+# The owner's workstation login over the LoadBalancer (1883/8883). Password in
+# the Secret mqtt-admin-password (home-assistant); deleting the Secret makes a
+# new one.
+- name: admin
+  auth: password
+  deliver: {namespace: home-assistant}
+  acl: ["readwrite #"]
 - name: test-cert
  auth: cert
  deliver: {namespace: home-assistant}
  acl: ["readwrite test/cert/#"]
 # The broker's own liveness/readiness probe (mosquitto-deployment.yaml).
-# Not named `health`: a Dynamic Security client of that name would shadow the
-# legacy password user while the old broker pod still probes with it.
 - name: mosquitto-probe
  auth: cert
  deliver: {namespace: home-assistant}
  acl: ["readwrite health/#"]
 # Zigbee2MQTT and its two sidecars (discovery-guard, interview-watch), one
-# certificate for the pod. Same ACL as the legacy user `zigbee2mqtt`; not
-# named like it, so this entry cannot shadow the password login of a running
-# Z2M (REN-953).
+# certificate for the pod (REN-953).
 - name: zigbee2mqtt-bridge
  auth: cert
  deliver: {namespace: home-assistant}
  acl: ["readwrite zigbee2mqtt/#", "write homeassistant/#", "read homeassistant/status"]
-# evcc (evcc namespace). Same ACL as the legacy user `evcc`, different name
-# so it cannot shadow the running password login (REN-953). evcc takes the
-# certificate PEMs by env (EVCC_MQTT_*), see apps/evcc/deployment.yaml.
+# evcc (evcc namespace, REN-953). evcc takes the certificate PEMs by env
+# (EVCC_MQTT_*), see apps/evcc/deployment.yaml.
 - name: evcc-client
  auth: cert
  deliver: {namespace: evcc}
  acl: ["read open3e/#", "readwrite evcc/#", "read energy/#"]
 # Home Assistant, via the ghostunnel sidecar `mqtt-tls` in its pod (HA keeps
 # client certificates only as uploaded PEMs in its config entry, so a renewal
-# could not reach it without a reconfigure). Same ACL as the legacy user
-# `homeassistant`; not named like it, so it cannot shadow that login (REN-953).
+# could not reach it without a reconfigure, REN-953).
 - name: home-assistant
  auth: cert
  deliver: {namespace: home-assistant}
  acl: ["readwrite #"]
-# edge-1's local mosquitto bridge (REN-1307): one bridge for open3e/e3oncan
-# and sml2mqtt, replacing the legacy password users `open3e` and `sml2mqtt`
-# (different name, so it cannot shadow their logins). The controller pushes
+# edge-1's local mosquitto bridge (REN-1307): one bridge for open3e/e3oncan.
+# The controller pushes
 # the password to edge-mqtt-cred on edge-1 (ansible role mqtt-bridge) over
 # HTTPS with its own client certificate, and pins edge-1's self-generated
 # server certificate on first contact (key edge-1.pin in mqtt-account-hashes;
@@ -50,13 +50,13 @@ release it before Z2M connects (step 3).
 Confirm the standing pieces are in place (nothing is running yet):

 ```
-kubectl -n home-assistant get secret mosquitto-zigbee2mqtt-credentials       # exists (bootstrap Job ran)
+kubectl -n home-assistant get secret mqtt-zigbee2mqtt-bridge-tls             # exists (register account zigbee2mqtt-bridge)
 kubectl -n home-assistant get externalsecret zigbee2mqtt-coordinator-backup  # SecretSyncedError / NotReady — EXPECTED
 kubectl -n home-assistant get deploy zigbee2mqtt                             # 0/0 — EXPECTED
 ```

-The `mosquitto` pod will have rolled to pick up the new `zigbee2mqtt` passwd/ACL
-entry. Verify the broker still serves HA (it will — the change is additive).
+Z2M logs in to the broker by certificate on `:8884` as the register account
+`zigbee2mqtt-bridge` (`mqtt-accounts.yaml`).

 ## Step 1 — export the Open Coordinator Backup (non-disruptive)

@@ -4,8 +4,8 @@ metadata:
  name: immich
  namespace: immich
  labels:
-    # Registered publicly (Cloudflare wildcard -> NetBird proxy); the UDM
-    # external-dns instance skips it, LAN reaches it via the hairpin NAT.
+    # Registered publicly (explicit CNAME -> NetBird proxy). No
+    # dns.renner.uno/internal label: external-dns-unifi writes no UDM record.
    dns.renner.uno/public: "true"
    netbird.renner.uno/public: "true"
  annotations:
@@ -23,7 +23,7 @@ spec:
  retryInterval: 60
  maxRetries: 1
  dns:
-    # cluster services have no own record; they resolve through the *.renner.uno wildcard
+    # public CNAME to the NetBird proxy, created by external-dns (dns.renner.uno/public)
    hostname: immich.renner.uno
    resolveType: CNAME
    resolveServer: "2606:4700:4700::1111,1.1.1.1"
@@ -27,7 +27,7 @@ spec:
        # Pinned to 7.4-alpine to match the LXC 225 compose exactly.
        # Any redis major-version bump is a separate migration.
        - name: redis
-          image: redis:7.4.11-alpine # {"$imagepolicy": "flux-system:redis-immich"}
+          image: redis:7.4.12-alpine # {"$imagepolicy": "flux-system:redis-immich"}
          args:
            - redis-server
            - --save
@@ -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:8.22.0@sha256:58adaa4e8dca9c988bae2aba4ab3434a0bb2da16bbe3f92dec39ec7785166777
+          image: curlimages/curl:8.23.0@sha256:11e64e28c5f58c8d93ee95fcf22ac055f48b0bc440e0ce7d8013bbb5ad6aa8ac
          command:
            - sh
            - -c
@@ -57,7 +57,7 @@ spec:
        runAsNonRoot: false
      initContainers:
        - name: wait-for-influxd
-          image: influxdb:2.9.1@sha256:cdd3dbdea45c2f43513abd06ee9644b6e05d2354a2b93ca829c9f07d716eaaac
+          image: influxdb:2.9.1@sha256:8f106f7ff12659c5e367b99f8a0e7d14cbd4e6ca1f2914094062db6a9813d9c2
          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)] $INFLUX_HOST ready and authenticated"
      containers:
        - name: create
-          image: influxdb:2.9.1@sha256:cdd3dbdea45c2f43513abd06ee9644b6e05d2354a2b93ca829c9f07d716eaaac
+          image: influxdb:2.9.1@sha256:8f106f7ff12659c5e367b99f8a0e7d14cbd4e6ca1f2914094062db6a9813d9c2
          env:
            - { name: INFLUX_HOST, value: http://influxdb-influxdb2.influxdb.svc.cluster.local:8086 }
            - { name: INFLUX_ORG, value: renner }
@@ -88,7 +88,7 @@ spec:
        # state). Two-stage so we don't try to create an auth before
        # the chart's `influx setup` has finished.
        - name: wait-for-influxd
-          image: influxdb:2.9.1@sha256:cdd3dbdea45c2f43513abd06ee9644b6e05d2354a2b93ca829c9f07d716eaaac
+          image: influxdb:2.9.1@sha256:8f106f7ff12659c5e367b99f8a0e7d14cbd4e6ca1f2914094062db6a9813d9c2
          env:
            - { name: INFLUX_HOST, value: http://influxdb-influxdb2.influxdb.svc.cluster.local:8086 }
            - { name: INFLUX_ORG, value: renner }
@@ -111,7 +111,7 @@ spec:
              echo "[$(date -u +%H:%M:%S)] $INFLUX_HOST ready and authenticated"
      containers:
        - name: create
-          image: influxdb:2.9.1@sha256:cdd3dbdea45c2f43513abd06ee9644b6e05d2354a2b93ca829c9f07d716eaaac
+          image: influxdb:2.9.1@sha256:8f106f7ff12659c5e367b99f8a0e7d14cbd4e6ca1f2914094062db6a9813d9c2
          env:
            - { name: INFLUX_HOST, value: http://influxdb-influxdb2.influxdb.svc.cluster.local:8086 }
            - { name: INFLUX_ORG, value: renner }
@@ -55,7 +55,7 @@ spec:
      repository: influxdb
      # Was pinned to VM 108's 2.7.4 for the one-time `influx restore`; that
      # migration is done. No downgrade below 2.9 without `influxd downgrade`.
-      tag: "2.9.1@sha256:cdd3dbdea45c2f43513abd06ee9644b6e05d2354a2b93ca829c9f07d716eaaac"
+      tag: "2.9.1@sha256:8f106f7ff12659c5e367b99f8a0e7d14cbd4e6ca1f2914094062db6a9813d9c2"
    # Single replica — InfluxDB OSS doesn't cluster. RWO Ceph-block + Velero
    # backups (pending) is the durability story.
    persistence:
@@ -30,7 +30,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: controller
-          image: gitea.renner.uno/gitea_admin/kuma-sync:2026-10-22-1858 # {"$imagepolicy": "flux-system:kuma-sync"}
+          image: gitea.renner.uno/gitea_admin/kuma-sync:2026-10-27-0801 # {"$imagepolicy": "flux-system:kuma-sync"}
          env:
            - name: KUMA_URL
              value: https://kuma.renner.uno
@@ -15,9 +15,8 @@ metadata:
  name: llama-server
  namespace: ai
  labels:
-    # Public: Cloudflare wildcard → tunnel → NetBird proxy → Traefik. The UDM
-    # external-dns instance skips anything carrying this, and LAN clients reach
-    # the same hostname through the hairpin NAT.
+    # Public: Cloudflare CNAME → NetBird proxy → Traefik. No
+    # dns.renner.uno/internal label: external-dns-unifi writes no UDM record.
    dns.renner.uno/public: "true"
    netbird.renner.uno/public: "true"
  annotations:
@@ -23,7 +23,7 @@ spec:
  retryInterval: 60
  maxRetries: 1
  dns:
-    # cluster services have no own record; they resolve through the *.renner.uno wildcard
+    # public CNAME to the NetBird proxy, created by external-dns (dns.renner.uno/public)
    hostname: llm.renner.uno
    resolveType: CNAME
    resolveServer: "2606:4700:4700::1111,1.1.1.1"
@@ -72,7 +72,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: element-web
-          image: ghcr.io/element-hq/element-web:v1.12.30@sha256:3e7dbd4424de9e11c812bc740acf2725b2abe66ea0d0802023b56fd85d3fa09a
+          image: ghcr.io/element-hq/element-web:v1.12.32@sha256:f8700633d4336258af7a05b53865a4f479e0d628cf2d9ca83d28b5939314d4ce
          securityContext:
            allowPrivilegeEscalation: false
            readOnlyRootFilesystem: true
@@ -1,8 +1,9 @@
 # Public (REN-663): each Ingress carries dns.renner.uno/public, so
 # netbird-service-sync publishes its host through the NetBird proxy
-# (Cloudflare wildcard -> proxy.renner.uno -> TLS passthrough to Traefik) and
-# external-dns-unifi skips it; LAN clients follow the public answer and the UDM
-# hairpins back in. Same path as audiobooks/immich. Federation stays off.
+# (explicit Cloudflare CNAME -> proxy.renner.uno -> TLS passthrough to Traefik)
+# and there is no dns.renner.uno/internal label, so external-dns-unifi writes
+# no UDM record; LAN clients follow the public answer and the UDM hairpins
+# back in. Same path as audiobooks/immich. Federation stays off.
 #
 # Synapse: only the client-facing paths. /_synapse/admin stays off the
 # Ingress (in-cluster only); /_matrix/federation and /_matrix/key are not
@@ -13,8 +14,8 @@ metadata:
  name: synapse
  namespace: matrix
  labels:
-    # Registered publicly (Cloudflare wildcard -> NetBird proxy); the UDM
-    # external-dns instance skips it, LAN reaches it via the hairpin NAT.
+    # Registered publicly (explicit CNAME -> NetBird proxy). No
+    # dns.renner.uno/internal label: external-dns-unifi writes no UDM record.
    dns.renner.uno/public: "true"
    netbird.renner.uno/public: "true"
  annotations:
@@ -123,8 +124,8 @@ metadata:
  name: element-web
  namespace: matrix
  labels:
-    # Registered publicly (Cloudflare wildcard -> NetBird proxy); the UDM
-    # external-dns instance skips it, LAN reaches it via the hairpin NAT.
+    # Registered publicly (explicit CNAME -> NetBird proxy). No
+    # dns.renner.uno/internal label: external-dns-unifi writes no UDM record.
    dns.renner.uno/public: "true"
    netbird.renner.uno/public: "true"
  annotations:
@@ -154,8 +155,8 @@ metadata:
  name: mas
  namespace: matrix
  labels:
-    # Registered publicly (Cloudflare wildcard -> NetBird proxy); the UDM
-    # external-dns instance skips it, LAN reaches it via the hairpin NAT.
+    # Registered publicly (explicit CNAME -> NetBird proxy). No
+    # dns.renner.uno/internal label: external-dns-unifi writes no UDM record.
    dns.renner.uno/public: "true"
    netbird.renner.uno/public: "true"
  annotations:
@@ -23,7 +23,7 @@ spec:
  retryInterval: 60
  maxRetries: 1
  dns:
-    # cluster services have no own record; they resolve through the *.renner.uno wildcard
+    # public CNAME to the NetBird proxy, created by external-dns (dns.renner.uno/public)
    hostname: matrix.renner.uno
    resolveType: CNAME
    resolveServer: "2606:4700:4700::1111,1.1.1.1"
@@ -136,7 +136,7 @@ spec:
  retryInterval: 60
  maxRetries: 1
  dns:
-    # cluster services have no own record; they resolve through the *.renner.uno wildcard
+    # public CNAME to the NetBird proxy, created by external-dns (dns.renner.uno/public)
    hostname: account.matrix.renner.uno
    resolveType: CNAME
    resolveServer: "2606:4700:4700::1111,1.1.1.1"
@@ -202,7 +202,7 @@ spec:
  retryInterval: 60
  maxRetries: 1
  dns:
-    # cluster services have no own record; they resolve through the *.renner.uno wildcard
+    # public CNAME to the NetBird proxy, created by external-dns (dns.renner.uno/public)
    hostname: element.renner.uno
    resolveType: CNAME
    resolveServer: "2606:4700:4700::1111,1.1.1.1"
@@ -289,7 +289,7 @@ spec:
  retryInterval: 60
  maxRetries: 1
  dns:
-    # cluster services have no own record; they resolve through the *.renner.uno wildcard
+    # public CNAME to the NetBird proxy, created by external-dns (dns.renner.uno/public)
    hostname: rtc.matrix.renner.uno
    resolveType: CNAME
    resolveServer: "2606:4700:4700::1111,1.1.1.1"
@@ -354,7 +354,7 @@ spec:
  retryInterval: 60
  maxRetries: 1
  dns:
-    # cluster services have no own record; they resolve through the *.renner.uno wildcard
+    # public CNAME to the NetBird proxy, created by external-dns (dns.renner.uno/public)
    hostname: turn.matrix.renner.uno
    resolveType: CNAME
    resolveServer: "2606:4700:4700::1111,1.1.1.1"
@@ -137,7 +137,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: mas
-          image: ghcr.io/element-hq/matrix-authentication-service:1.26.0@sha256:e089f1048a1d4a9a492ed17b9fe759100f1bd619407b001f5927928d88b780c4
+          image: ghcr.io/element-hq/matrix-authentication-service:1.27.1@sha256:02712e68c90f3743fedbd5e3343517481b2b4f246a9fd9e2f050dc2553033847
          # The server applies database migrations and syncs the upstream
          # providers from the config on start.
          args: ["server", "--config", "/config/config.yaml"]
@@ -124,7 +124,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: livekit
-          image: livekit/livekit-server:v1.13.10@sha256:89ca9ce0791e18d6e03bf6e2c49ceb27e1c754eae8bd50c989386c1a5963791a
+          image: livekit/livekit-server:v1.13.11@sha256:25cd902de7cacbd5f1f779f6a6ac1eae20ba8f56b0935934ce6b0ab80d1e3d20
          args:
            - --config
            - /config/livekit.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:1.26.0-debug@sha256:46f7480f5ea4243ccb6fd2c447ea859e0230c8b3c0e676ee285d4ae6ca344ee3
+          image: ghcr.io/element-hq/matrix-authentication-service:1.27.1-debug@sha256:75f369b206785f1480f4a9f8dd81d7f9f3c6793c40fd184358ecd5d7acae17d4
          command:
            - /busybox/sh
            - -ec
@@ -234,7 +234,7 @@ spec:
              mountPath: /data
      containers:
        - name: synapse
-          image: ghcr.io/element-hq/synapse:v1.162.0@sha256:6b84a7bbac36f080b2d2e51e0289cf1b08b349598ea44a558df38d558f2c2311
+          image: ghcr.io/element-hq/synapse:v1.163.2@sha256:c3c21919a322f74d177a43bce8031adc81ef839ddd117a8dd03cfec350e76e02
          # 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.
@@ -5,7 +5,9 @@
 #
 # The UDM is queried directly rather than through the cluster resolver:
 # k8s-gateway caches these with `serve_stale 1h immediate`, which would keep
-# a deleted record green for an hour.
+# a deleted record green for an hour. The addresses are the UDM on the segment
+# pod traffic leaves on, the same upstream k8s-gateway uses (k8s-gateway-site
+# in talos/patches/site-homelab.yaml).
 #
 # `release` is load-bearing — probeSelector matches on it.
 apiVersion: monitoring.coreos.com/v1
@@ -25,8 +27,8 @@ spec:
  targets:
    staticConfig:
      static:
-        - "[fd00::1]:53"
-        - "10.2.40.1:53"
+        - "[fd02:47::1]:53"
+        - "10.2.47.1:53"
      # instance is the resolver and identical across these Probes, so the
      # queried name has to come from a label.
      labels:
@@ -49,8 +51,8 @@ spec:
  targets:
    staticConfig:
      static:
-        - "[fd00::1]:53"
-        - "10.2.40.1:53"
+        - "[fd02:47::1]:53"
+        - "10.2.47.1:53"
      labels:
        dns_name: mqtt.renner.uno
 ---
@@ -71,8 +73,8 @@ spec:
  targets:
    staticConfig:
      static:
-        - "[fd00::1]:53"
-        - "10.2.40.1:53"
+        - "[fd02:47::1]:53"
+        - "10.2.47.1:53"
      labels:
        dns_name: ldap.renner.uno
 ---
@@ -93,8 +95,8 @@ spec:
  targets:
    staticConfig:
      static:
-        - "[fd00::1]:53"
-        - "10.2.40.1:53"
+        - "[fd02:47::1]:53"
+        - "10.2.47.1:53"
      labels:
        dns_name: syslog.renner.uno
 ---
@@ -115,8 +117,8 @@ spec:
  targets:
    staticConfig:
      static:
-        - "[fd00::1]:53"
-        - "10.2.40.1:53"
+        - "[fd02:47::1]:53"
+        - "10.2.47.1:53"
      labels:
        dns_name: ftp.paperless.renner.uno
 ---
@@ -137,7 +139,7 @@ spec:
  targets:
    staticConfig:
      static:
-        - "[fd00::1]:53"
-        - "10.2.40.1:53"
+        - "[fd02:47::1]:53"
+        - "10.2.47.1:53"
      labels:
        dns_name: syncthing.paperless.renner.uno
@@ -25,8 +25,8 @@ spec:
            summary: "{{ $labels.dns_name }} no longer resolves to its LAN address"
            description: >-
              The UDM stopped answering for a name external-dns publishes from
-              a LoadBalancer Service, or answered with the public
-              *.renner.uno wildcard instead of the record. Clients that use
+              a LoadBalancer Service, or answered without the
+              record (no answer, or a public CNAME). Clients that use
              the name rather than the address lose the service while
              everything in the cluster stays healthy — nothing else in the
              stack reports this. Check the external-dns alerts first, then
@@ -82,9 +82,9 @@ spec:
          #
          # The pod regex is the Deployment's name shape
          # (mosquitto-<replicaset hash>-<suffix>) and not `mosquitto-.*` on
-          # purpose: mosquitto-bootstrap.yaml runs six Jobs named
-          # mosquitto-*-credentials-bootstrap, and a bootstrap pod that is
-          # briefly Ready must not hide a broker that is down.
+          # purpose: other pods in the namespace start with `mosquitto-`
+          # (mosquitto-dynsec-test), and a Ready one must not hide a broker
+          # that is down.
          expr: |
            absent(kube_pod_status_ready{namespace="home-assistant", pod=~"mosquitto-[a-z0-9]{6,10}-[a-z0-9]{5}", condition="true"} == 1)
          for: 5m
@@ -31,8 +31,9 @@ spec:
              {{ $value | humanizePercentage }} of probes in the last 10m got
              the Ingress address for {{ $labels.dns_name }} ({{ $labels.record }})
              from k8s-gateway. Pods then resolve Ingress names through the UDM
-              and the public wildcard (CNAME proxy.renner.uno) and leave the
-              cluster. Check the rendered Corefile in the k8s-gateway ConfigMap
+              and the public zone (CNAME proxy.renner.uno for public hosts)
+              and leave the cluster. Check the rendered Corefile in the
+              k8s-gateway ConfigMap
              (kube-system) for the renner.uno zone, the k8s-gateway logs, and
              whether the Traefik VIP in infrastructure/traefik/helmrelease.yaml
              still matches the dns_k8s_gateway_auth_* modules in
@@ -137,13 +137,13 @@ tests:
        exp_alerts: []

  # --- MosquittoDown ------------------------------------------------------
-  # The broker goes not-Ready at t=10m while a credentials-bootstrap Job pod is
-  # Ready. The Job pod must not mask the broker.
+  # The broker goes not-Ready at t=10m while the mosquitto-dynsec-test pod is
+  # Ready. That pod must not mask the broker.
  - interval: 1m
    input_series:
      - series: 'kube_pod_status_ready{namespace="home-assistant",pod="mosquitto-7f8b9c6d5-x2k9q",condition="true"}'
        values: '1x9 0x20'
-      - series: 'kube_pod_status_ready{namespace="home-assistant",pod="mosquitto-credentials-bootstrap-q7w2e",condition="true"}'
+      - series: 'kube_pod_status_ready{namespace="home-assistant",pod="mosquitto-dynsec-test-6d9f8b7c5-r4t8w",condition="true"}'
        values: '1x30'
    alert_rule_test:
      - eval_time: 14m
@@ -30,7 +30,7 @@ tests:
              record: A
            exp_annotations:
              summary: "k8s-gateway does not answer auth.renner.uno A with the Traefik VIP"
-              description: "20% of probes in the last 10m got the Ingress address for auth.renner.uno (A) from k8s-gateway. Pods then resolve Ingress names through the UDM and the public wildcard (CNAME proxy.renner.uno) and leave the cluster. Check the rendered Corefile in the k8s-gateway ConfigMap (kube-system) for the renner.uno zone, the k8s-gateway logs, and whether the Traefik VIP in infrastructure/traefik/helmrelease.yaml still matches the dns_k8s_gateway_auth_* modules in apps/monitoring/helmrelease-blackbox-exporter.yaml. It also fails when the auth.renner.uno Ingress (authentik) is gone."
+              description: "20% of probes in the last 10m got the Ingress address for auth.renner.uno (A) from k8s-gateway. Pods then resolve Ingress names through the UDM and the public zone (CNAME proxy.renner.uno for public hosts) and leave the cluster. Check the rendered Corefile in the k8s-gateway ConfigMap (kube-system) for the renner.uno zone, the k8s-gateway logs, and whether the Traefik VIP in infrastructure/traefik/helmrelease.yaml still matches the dns_k8s_gateway_auth_* modules in apps/monitoring/helmrelease-blackbox-exporter.yaml. It also fails when the auth.renner.uno Ingress (authentik) is gone."
      - eval_time: 17m
        alertname: K8sGatewayProbesAbsent
        exp_alerts: []
@@ -53,7 +53,7 @@ tests:
              record: AAAA
            exp_annotations:
              summary: "k8s-gateway does not answer auth.renner.uno AAAA with the Traefik VIP"
-              description: "50% of probes in the last 10m got the Ingress address for auth.renner.uno (AAAA) from k8s-gateway. Pods then resolve Ingress names through the UDM and the public wildcard (CNAME proxy.renner.uno) and leave the cluster. Check the rendered Corefile in the k8s-gateway ConfigMap (kube-system) for the renner.uno zone, the k8s-gateway logs, and whether the Traefik VIP in infrastructure/traefik/helmrelease.yaml still matches the dns_k8s_gateway_auth_* modules in apps/monitoring/helmrelease-blackbox-exporter.yaml. It also fails when the auth.renner.uno Ingress (authentik) is gone."
+              description: "50% of probes in the last 10m got the Ingress address for auth.renner.uno (AAAA) from k8s-gateway. Pods then resolve Ingress names through the UDM and the public zone (CNAME proxy.renner.uno for public hosts) and leave the cluster. Check the rendered Corefile in the k8s-gateway ConfigMap (kube-system) for the renner.uno zone, the k8s-gateway logs, and whether the Traefik VIP in infrastructure/traefik/helmrelease.yaml still matches the dns_k8s_gateway_auth_* modules in apps/monitoring/helmrelease-blackbox-exporter.yaml. It also fails when the auth.renner.uno Ingress (authentik) is gone."

  # Two consecutive failures in an otherwise healthy hour stay silent
  # (average exactly 0.8).
@@ -78,11 +78,10 @@ spec:
        # passed per scrape. The Probes in monitoring-rules/probes-dns.yaml
        # point these at the UDM.
        #
-        # Both answer checks are load-bearing. valid_rcodes alone passes a
-        # deleted record two labels deep (NOERROR, no answer), and the public
-        # *.renner.uno wildcard answers one label deep with a CNAME to
-        # proxy.renner.uno — NOERROR with the WAN proxy behind it. Requiring
-        # an A and rejecting a CNAME separates a real record from both.
+        # Both answer checks are load-bearing: valid_rcodes alone passes a
+        # deleted record (NOERROR, no answer, any depth). Requiring an A
+        # separates a real record from that; a CNAME means the UDM answered with a
+        # public-zone target instead of the LAN address.
        dns_lan_ha:
          prober: dns
          timeout: 5s
@@ -32,6 +32,9 @@ spec:
    deploymentMode: SingleBinary
    loki:
      auth_enabled: false
+      # No usage reports to stats.grafana.org (egress is not allowed anyway).
+      analytics:
+        reporting_enabled: false
      commonConfig:
        replication_factor: 1
      storage:
@@ -17,7 +17,7 @@ spec:
  chart:
    spec:
      chart: kube-prometheus-stack
-      version: "92.3.0"
+      version: "92.13.1"
      sourceRef:
        kind: HelmRepository
        name: prometheus-community
@@ -23,7 +23,7 @@ spec:
  retryInterval: 60
  maxRetries: 1
  dns:
-    # target of the *.renner.uno wildcard
+    # target of every public CNAME (NetBird proxy load balancer)
    hostname: proxy.renner.uno
    resolveType: AAAA
    resolveServer: "2606:4700:4700::1111,1.1.1.1"
@@ -228,7 +228,7 @@ spec:
  retryInterval: 60
  maxRetries: 1
  dns:
-    # Cloudflare-proxied apex, not the wildcard
+    # Cloudflare-proxied apex
    hostname: renner.uno
    resolveType: AAAA
    resolveServer: "2606:4700:4700::1111,1.1.1.1"
--- a/Show More
+++ b/Show More