fix(authentik): embedded outpost config lives in the blueprint

The embedded outpost's config is Authentik's own and does not depend on
authentik-gate-sync. A blueprint update of an existing outpost is partial
(importer: partial=True unless MUST_CREATED), so the entry sets config
without providers and the gates the controller attached stay.

config is replaced whole; the entry mirrors the live row
(authentik_outposts_outpost, 2026-10-23) with refresh_interval
minutes=1. kubernetes_namespace stays default: the outpost has the
Local Kubernetes Cluster connection, and the authentik namespace would
let the worker create an ak-outpost Service for it.

The controller drops embedded_config/ensure_embedded_config and only
attaches providers.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

.woodpecker/ci-manifests-test.yml

@@ -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:v3.15.1@sha256:fa3302279710be2f21a8301ec17a8b4f2301fd829bd113839b3b6b02b6f191a2
+    image: prom/prometheus:v3.15.0@sha256:efd719c99d83b060d9daefdcf00360461adf279f45ef5391f8d111892118753e
     commands:
       - sh scripts/ci/promtool-rules.sh
 

.woodpecker/ci-scripts-test.yml

@@ -35,25 +35,25 @@ when:
 steps:
   - name: model-selection-tests
     depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.306
     commands:
       - sh scripts/ci/test-model-selection.sh
 
   - name: pr-review-mistral-tests
     depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.306
     commands:
       - sh scripts/ci/test-pr-review-mistral.sh
 
   - name: promtool-rules-guard-tests
     depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.306
     commands:
       - sh scripts/ci/test-promtool-rules.sh
 
   - name: yaml-citations-guard-tests
     depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.306
     commands:
       - sh scripts/ci/test-yaml-citations.sh
 
@@ -63,7 +63,7 @@ steps:
   # bridge, and the secret guard.
   - name: hermes-skill-tests
     depends_on: []
-    image: python:3.15-alpine@sha256:d44b1254cb92329418d164b22b20d86bbd3869d48e80e09e476531a409a728bb
+    image: python:3.14-alpine@sha256:f6a589d43c42b9e7f7dc67a12d37132491f362859a5d750607710cc56da3bc72
     environment:
       PYTHONDONTWRITEBYTECODE: "1"
     commands:

.woodpecker/deploy-infrastructure.yml

@@ -13,7 +13,7 @@ when:
 
 steps:
   - name: validate-secrets
-    image: alpine:3.24.3@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a
+    image: alpine:3.24.2@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
     environment:
       TF_VAR_proxmox_api_url:
         from_secret: proxmox_api_url

.woodpecker/deploy-ssh-ca.yml

@@ -1,34 +0,0 @@
-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

.woodpecker/e2e.yml

@@ -26,7 +26,7 @@ steps:
     # fetch-models.sh response mapping. No cluster, no secrets, no network — the
     # ci-claude image just provides sh + jq. Keeps the flag-injection regression
     # test from rotting (it exercises the exact injection shapes).
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.306
     commands:
       - sh scripts/ci/test-model-selection.sh
 

.woodpecker/review-bot-test.yml

@@ -6,7 +6,7 @@ when:
 
 steps:
   - name: go-test
-    image: golang:1.27.3-bookworm@sha256:972b4110ba0f47539a975c31e52c64765e1ff19f2d74469ae4a595c6676e80a5
+    image: golang:1.27.2-bookworm@sha256:5cf287a799e6b94384bad13d16b14904c531f51ba65792237e122ce42b392f61
     commands:
       - test -z "$(gofmt -l review-bot)"
       - go -C review-bot vet ./...

.woodpecker/security-scan.yml

@@ -18,12 +18,12 @@ when:
 
 steps:
   - name: iac-scan
-    image: aquasec/trivy:latest@sha256:790fd66d1697395d8693d1acaa1ea702406a20f109b6fc7bac8db623eca6c06c
+    image: aquasec/trivy:latest@sha256:2416d1f74045b57274df1a340eee6b510cacd73c66a6ccb8da092b117eb7d222
     commands:
       - trivy fs --format json -o trivy-iac.json --severity CRITICAL,HIGH --ignore-unfixed .
 
   - name: image-scans
-    image: aquasec/trivy:latest@sha256:790fd66d1697395d8693d1acaa1ea702406a20f109b6fc7bac8db623eca6c06c
+    image: aquasec/trivy:latest@sha256:2416d1f74045b57274df1a340eee6b510cacd73c66a6ccb8da092b117eb7d222
     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:2.1.311
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.306
     environment:
       CLAUDE_CODE_OAUTH_TOKEN:
         from_secret: claude_code_oauth_token

.woodpecker/update-audit.yml

@@ -30,7 +30,7 @@ when:
 
 steps:
   - name: update-audit-agent
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.306
     environment:
       CLAUDE_CODE_OAUTH_TOKEN:
         from_secret: claude_code_oauth_token

ansible/docs/edge-host.md

@@ -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
-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:
+Create `inventory/group_vars/edge_host/vault.yml` with ansible-vault; the
+current live values come straight 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
 ```
@@ -230,14 +230,15 @@ 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.
 
-The local broker is `allow_anonymous` on loopback — the trust boundary is the
-host; nothing off-host can reach it.
+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.
 
-**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
+**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
 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

ansible/inventory/pve_hosts.yml

@@ -69,11 +69,3 @@ 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
-netbird.renner.uno

ansible/plays/configure-ssh-ca.yml

@@ -1,15 +0,0 @@
----
-# 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

ansible/roles/ssh-ca/defaults/main.yml

@@ -1,18 +0,0 @@
----
-# 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: []

ansible/roles/ssh-ca/files/revoked_keys

@@ -1,2 +0,0 @@
-# Public keys whose certificates sshd must reject (one per line, OpenSSH format).
-# Revoking a key also revokes every certificate issued for it.

ansible/roles/ssh-ca/tasks/main.yml

@@ -1,150 +0,0 @@
----
-- 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/Ubuntu.
-# Ubuntu also lists sshd.service as a not-found alias, so the running one is
-# picked. 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 the running sshd unit
-  vars:
-    ssh_ca_sshd_units: "{{ ansible_facts.services | dict2items | selectattr('key', 'in', ['sshd.service', 'ssh.service']) | selectattr('value.state', 'equalto', 'running') | map(attribute='key') | list }}"
-  block:
-    - name: Check exactly one sshd unit is running
-      ansible.builtin.assert:
-        that:
-          - ssh_ca_sshd_units | length == 1
-        fail_msg: "Expected one running sshd.service or ssh.service, found {{ ssh_ca_sshd_units }}"
-
-    - name: Reload sshd so the running daemon uses the CA config
-      ansible.builtin.systemd:
-        name: "{{ ssh_ca_sshd_units | first }}"
-        state: reloaded

ansible/roles/ssh-ca/templates/ssh-ca.conf.j2

@@ -1,4 +0,0 @@
-# {{ ansible_managed }}
-TrustedUserCAKeys /etc/ssh/trusted_user_ca_keys
-AuthorizedPrincipalsFile /etc/ssh/auth_principals/%u
-RevokedKeys /etc/ssh/revoked_keys

ansible/roles/ssh-ca/templates/sudoers-claude.j2

@@ -1,6 +0,0 @@
-# {{ 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 %}

ci/images/alpine-jq/Containerfile

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

ci/images/alpine-openssl/Containerfile

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

ci/images/ansible/Containerfile

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

ci/images/authentik-gate-sync/Containerfile

@@ -5,12 +5,12 @@
 
 # The unit tests gate the image: the final stage copies the controller out of
 # this stage, so a failing test fails the build.
-FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51 AS test
+FROM python:3.15-slim@sha256:2da676046630d7bf14c6764ae1143dc7fa0377a53f94bf5a642f0b214aca5bce AS test
 WORKDIR /src
 COPY controller.py test_controller.py ./
 RUN python3 -B -m unittest -v
 
-FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51
+FROM python:3.15-slim@sha256:2da676046630d7bf14c6764ae1143dc7fa0377a53f94bf5a642f0b214aca5bce
 
 RUN useradd --system --no-create-home --shell /usr/sbin/nologin controller
 COPY --from=test /src/controller.py /opt/controller.py

ci/images/authentik-gate-sync/controller.py

@@ -45,7 +45,6 @@ INGRESS_NS = os.environ.get("INGRESS_NAMESPACE", "ingress")
 DEFAULT_AUTHZ_FLOW = os.environ.get("DEFAULT_AUTHORIZATION_FLOW", "default-provider-authorization-implicit-consent")
 INVALIDATION_FLOW = os.environ.get("INVALIDATION_FLOW", "default-provider-invalidation-flow")
 COOKIE_DOMAIN = os.environ.get("COOKIE_DOMAIN", "renner.uno")
-AK_BROWSER_URL = os.environ.get("AUTHENTIK_HOST_BROWSER", "https://auth.renner.uno/")
 INTERVAL = int(os.environ.get("INTERVAL_SECONDS", "60"))
 HTTP_TIMEOUT = 20
 
@@ -209,14 +208,6 @@ def resolve_backend(gate, service):
     return sp["port"], selector, target
 
 
-def embedded_config(config):
-    """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}
-
-
 def provider_body(gate, flows):
     return {
         "name": gate["name"],
@@ -349,14 +340,6 @@ def embedded_outpost(ak):
     return found[0]
 
 
-def ensure_embedded_config(ak):
-    outpost = embedded_outpost(ak)
-    want = embedded_config(outpost.get("config"))
-    if outpost.get("config") != want:
-        ak.req("PATCH", f"outposts/instances/{outpost['pk']}/", {"config": want})
-        LOG.info("embedded outpost: updated config")
-
-
 def ensure_gate(ak, gate, flows):
     name = gate["name"]
     if gate["group"] and ak.one("core/groups/", name=gate["group"]) is None:
@@ -485,7 +468,6 @@ def reconcile():
     sources = [i for i in k8s.get("/apis/networking.k8s.io/v1/ingresses").get("items", []) if is_gated(i)]
     shared = shared_hosts(sources)
     flows = {f["slug"]: f["pk"] for f in ak.list("flows/instances/")}
-    ensure_embedded_config(ak)
 
     desired = set()  # (kind, ns, name) of every Kubernetes object some gate wants
     gates = set()    # gate names whose Authentik side should exist

ci/images/authentik-gate-sync/test_controller.py

@@ -166,11 +166,6 @@ class Objects(unittest.TestCase):
     def test_drift(self):
         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": 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})
-
 
 class FakeAuthentik:
     """In-memory stand-in for the endpoints the controller uses; records calls."""
@@ -299,15 +294,6 @@ class Reconcile(unittest.TestCase):
             c.embedded_outpost(self.ak)
         self.assertEqual(self.ak.get(f"outposts/instances/{ldap['pk']}/")["providers"], [7])
 
-    def test_embedded_config(self):
-        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_BROWSER_URL, c.AK_BROWSER_URL))
-        before = len(self.ak.calls)
-        c.ensure_embedded_config(self.ak)
-        self.assertEqual(self.ak.calls[before:], [])
-
     def test_provider_moves_from_proxy_mode(self):
         self.ak.add("providers/proxy/", {"name": self.g["name"], "mode": "proxy",
                                          "internal_host": "http://llama-server.ai.svc.cluster.local:8080",

ci/images/backup-verify/Containerfile

@@ -1,6 +1,6 @@
-FROM hetznercloud/cli:v1.70.2@sha256:3b3a8f66323a5754089df7939fd9d3f350127072deed13418f3d3052b4bbeeae AS hcloud
+FROM hetznercloud/cli:v1.70.1@sha256:795ac09a5ecabd48cc13a8f1c3dc45983c8f75ae1277c70d621719e07f276ccb AS hcloud
 
-FROM alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a
+FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
 
 RUN apk add --no-cache \
       bash \

ci/images/bird/Containerfile

@@ -1,4 +1,4 @@
-FROM alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a
+FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
 
 # bird: BGP daemon for the pod-network mesh over pod0. Distro package, no build
 # step — the image is the binary plus its runtime.

ci/images/claude/Containerfile

@@ -1,4 +1,4 @@
-FROM node:24-alpine@sha256:06d7adf3e0ef61a13f1d28682726366f97a15aa1888c934d3ecec86c33918b53
+FROM node:24-alpine@sha256:44fce696f38ba8c987c4db89954051000bbd05ffd8d8659ba15ed4a8602e937f
 
 # 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

ci/images/cloudflare-lb-sync/Containerfile

@@ -2,7 +2,7 @@
 # Cloudflare. The unit tests (no tags, so no envtest) gate the image: the
 # final stage copies the binary out of this stage, so a failing test fails the
 # build.
-FROM golang:1.27@sha256:f20d83a83e18dbd2a4714b8ffd4b30b287b6243962dd75608e86abcc63ba4efc AS build
+FROM golang:1.27@sha256:820153096fda4de6ac1b7194d12e416b7dd8f4e9a33d17e0345b111b945162d8 AS build
 WORKDIR /src
 COPY go.mod go.sum ./
 RUN go mod download
@@ -10,7 +10,7 @@ COPY . .
 RUN go test ./...
 RUN CGO_ENABLED=0 go build -trimpath -ldflags="-s -w" -o /out/cloudflare-lb-sync ./cmd/cloudflare-lb-sync
 
-FROM gcr.io/distroless/static:nonroot@sha256:18f4cc26c9ffa7f20a359298be7deadac5c607c8e03a02b8119f1a5fc2f82c99
+FROM gcr.io/distroless/static:nonroot@sha256:e2e927ec666bae08560abb3c55d0659eceabb657f56b6782ab500a9fc7f555e3
 COPY --from=build /out/cloudflare-lb-sync /cloudflare-lb-sync
 USER 65532
 ENTRYPOINT ["/cloudflare-lb-sync"]

ci/images/cni-plugins/Containerfile

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

ci/images/heating-can/Containerfile

@@ -23,7 +23,7 @@
 # namespace, so can0 is only reachable with network_mode: host. That is also
 # how the local MQTT broker on 127.0.0.1:1883 is reached. CAN_RAW sockets need
 # no capabilities, so both run unprivileged.
-FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51 AS build
+FROM python:3.15-slim@sha256:2da676046630d7bf14c6764ae1143dc7fa0377a53f94bf5a642f0b214aca5bce AS build
 
 # Pins live here, in the artifact, rather than in Ansible variables.
 #
@@ -56,7 +56,7 @@ RUN git clone --quiet https://github.com/MyHomeMyData/E3onCAN.git /opt/e3oncan \
  && rm -rf /opt/e3oncan/.git
 
 
-FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51
+FROM python:3.15-slim@sha256:2da676046630d7bf14c6764ae1143dc7fa0377a53f94bf5a642f0b214aca5bce
 
 ARG OPEN3E_REF=6553c10453a6bae1210908f38a5af2481a46a3e5
 ARG E3ONCAN_REF=461dcbdf97e8d72d2edb9929c63b39382af6c3a1

ci/images/hermes/Containerfile

@@ -1,4 +1,4 @@
-FROM nousresearch/hermes-agent:v0.22.5@sha256:9c5561579f3ffdf333401797094ac3a743738d6c25d40f4331c7bf77b694238d
+FROM nousresearch/hermes-agent:v0.22.2@sha256:36099926da316742423544e055d4734777105ffe6341873af5459b957d0c2919
 
 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:v1.14.4@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=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=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
 

ci/images/k8s/Containerfile

@@ -1,4 +1,4 @@
-FROM alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a
+FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
 
 ARG TALOS_VERSION=v1.13.12
 ARG VELERO_VERSION=v1.16.0

ci/images/kuma-sync/Containerfile

@@ -1,7 +1,7 @@
 # kuma-sync: reconciles KumaMonitor resources into Uptime Kuma. The unit tests
 # (no tags, so no Docker and no envtest) gate the image: the final stage copies
 # the binary out of this stage, so a failing test fails the build.
-FROM golang:1.27@sha256:f20d83a83e18dbd2a4714b8ffd4b30b287b6243962dd75608e86abcc63ba4efc AS build
+FROM golang:1.27@sha256:820153096fda4de6ac1b7194d12e416b7dd8f4e9a33d17e0345b111b945162d8 AS build
 WORKDIR /src
 COPY go.mod go.sum ./
 RUN go mod download
@@ -9,7 +9,7 @@ COPY . .
 RUN go test ./...
 RUN CGO_ENABLED=0 go build -trimpath -ldflags="-s -w" -o /out/kuma-sync ./cmd/kuma-sync
 
-FROM gcr.io/distroless/static:nonroot@sha256:18f4cc26c9ffa7f20a359298be7deadac5c607c8e03a02b8119f1a5fc2f82c99
+FROM gcr.io/distroless/static:nonroot@sha256:e2e927ec666bae08560abb3c55d0659eceabb657f56b6782ab500a9fc7f555e3
 COPY --from=build /out/kuma-sync /kuma-sync
 USER 65532
 ENTRYPOINT ["/kuma-sync"]

ci/images/netbird-service-sync/Containerfile

@@ -2,7 +2,7 @@
 # domains -> TLS passthrough -> Traefik ClusterIP) from Ingresses carrying the
 # public label. Standard library only, so the image is the interpreter plus one
 # file; runs unprivileged as its own user.
-FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51
+FROM python:3.15-slim@sha256:2da676046630d7bf14c6764ae1143dc7fa0377a53f94bf5a642f0b214aca5bce
 
 RUN useradd --system --no-create-home --shell /usr/sbin/nologin controller
 COPY controller.py /opt/controller.py

ci/images/tofu/Containerfile

@@ -1,4 +1,4 @@
-FROM alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a
+FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
 
 ARG TOFU_VERSION=1.11.0
 

ci/images/vmtest/Containerfile

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

kubernetes/apps/audiobookshelf/deployment.yaml

@@ -48,7 +48,7 @@ spec:
         # cert when doing server-side OIDC token exchange. Bundle both
         # roots into one PEM since NODE_EXTRA_CA_CERTS accepts one file.
         - name: fetch-le-staging-roots
-          image: curlimages/curl:8.23.0@sha256:11e64e28c5f58c8d93ee95fcf22ac055f48b0bc440e0ce7d8013bbb5ad6aa8ac
+          image: curlimages/curl:8.22.0@sha256:58adaa4e8dca9c988bae2aba4ab3434a0bb2da16bbe3f92dec39ec7785166777
           command:
             - sh
             - -c
@@ -70,7 +70,7 @@ spec:
               mountPath: /ca
       containers:
         - name: audiobookshelf
-          image: ghcr.io/advplyr/audiobookshelf:2.37.2 # {"$imagepolicy": "flux-system:audiobookshelf"}
+          image: ghcr.io/advplyr/audiobookshelf:2.37.1 # {"$imagepolicy": "flux-system:audiobookshelf"}
           ports:
             - name: http
               containerPort: 80

kubernetes/apps/authentik/blueprints-configmap.yaml

@@ -374,10 +374,39 @@ data:
           name: lidarr-gate
         state: absent
 
-      # The embedded outpost is not declared here: authentik-gate-sync owns its
-      # providers list (every gate) and the hosts in its config, and a
-      # blueprint entry must carry `providers`, which would detach the gates
-      # on every apply.
+      # No `providers`: authentik-gate-sync attaches the gates, and an update
+      # of an existing outpost is partial. `config` is replaced whole, so it
+      # carries every key, kubernetes_namespace included.
+      - model: authentik_outposts.outpost
+        identifiers:
+          name: authentik Embedded Outpost
+        state: present
+        attrs:
+          config:
+            log_level: info
+            # The embedded outpost builds the sign-in redirect from
+            # authentik_host, so it is the public URL.
+            authentik_host: "https://auth.renner.uno/"
+            authentik_host_insecure: false
+            authentik_host_browser: "https://auth.renner.uno/"
+            # A replica whose outpost websocket is down picks up gate changes
+            # only on this interval; the reconnect backoff never resets
+            # (goauthentik/authentik#26463).
+            refresh_interval: "minutes=1"
+            object_naming_template: "ak-outpost-%(name)s"
+            container_image: null
+            docker_labels: null
+            docker_network: ladmin_default
+            docker_map_ports: true
+            kubernetes_namespace: default
+            kubernetes_replicas: 1
+            kubernetes_service_type: ClusterIP
+            kubernetes_disabled_components: []
+            kubernetes_image_pull_secrets: []
+            kubernetes_ingress_annotations: {}
+            kubernetes_ingress_class_name: null
+            kubernetes_ingress_secret_name: "authentik-outpost-tls"
+            kubernetes_json_patches: null
 
       # Shared LDAPS cert for the LDAP Outpost. Authentik's data model
       # owns the cert per-LDAPProvider (no outpost-level cert field), so
@@ -706,7 +735,7 @@ 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:2026.8.4-3c8f413
+            container_image: gitea.renner.uno/konairius/authentik-samba-bridge-ldap-outpost:2026.8.3-9dd92dd
             object_naming_template: "ak-outpost-%(name)s"
             kubernetes_namespace: authentik
             kubernetes_replicas: 1
@@ -1034,19 +1063,9 @@ 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. Only the
-      # Wiki Readers group passes.
+      # so the service verifies the ID token against the JWKS. No policy
+      # binding: every Authentik user may sign in.
       - id: wiki-provider
         model: authentik_providers_oauth2.oauth2provider
         identifiers:
@@ -1082,83 +1101,6 @@ 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

kubernetes/apps/authentik/gate-sync.yaml

@@ -105,7 +105,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: controller
-          image: gitea.renner.uno/gitea_admin/authentik-gate-sync:2026-10-27-0801 # {"$imagepolicy": "flux-system:authentik-gate-sync"}
+          image: gitea.renner.uno/gitea_admin/authentik-gate-sync:2026-10-23-0757 # {"$imagepolicy": "flux-system:authentik-gate-sync"}
           securityContext:
             allowPrivilegeEscalation: false
             readOnlyRootFilesystem: true
@@ -114,8 +114,6 @@ spec:
           env:
             - name: AK_URL
               value: http://authentik-server.authentik.svc.cluster.local
-            - name: AUTHENTIK_HOST_BROWSER
-              value: https://auth.renner.uno/
             - name: DEFAULT_AUTHORIZATION_FLOW
               value: default-provider-authorization-implicit-consent
             - name: INTERVAL_SECONDS

kubernetes/apps/authentik/helmrelease.yaml

@@ -20,7 +20,7 @@ spec:
       # Pinned to match the samba-bridge fork's app image (server.Dockerfile
       # AUTHENTIK_VERSION). Bump in lockstep with the bridge rebuild — a
       # floating range drifts the chart ahead of the pinned app image.
-      version: "2026.8.4"
+      version: "2026.8.3"
       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: "2026.8.4-3c8f413"
+        tag: "2026.8.3-9dd92dd"
       envFrom:
         # SAMBA_BRIDGE_DOMAIN_SID / _ENABLED_GROUP / _UID_OFFSET
         # consumed by the bridge module at Django app startup. Missing

kubernetes/apps/cloudflare-lb-sync/deployment.yaml

@@ -30,7 +30,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: controller
-          image: gitea.renner.uno/gitea_admin/cloudflare-lb-sync:2026-10-27-0807 # {"$imagepolicy": "flux-system:cloudflare-lb-sync"}
+          image: gitea.renner.uno/gitea_admin/cloudflare-lb-sync:2026-10-22-1904 # {"$imagepolicy": "flux-system:cloudflare-lb-sync"}
           env:
             - name: CLOUDFLARE_API_TOKEN
               valueFrom:

kubernetes/apps/evcc/deployment.yaml

@@ -28,7 +28,7 @@ spec:
       enableServiceLinks: false
       containers:
         - name: evcc
-          image: evcc/evcc:0.318.1@sha256:2f8163ab22f04863afd86cd511c09607ba71debd9eebd65511f3d654922a80d1
+          image: evcc/evcc:0.317.1@sha256:c50cd4f83c22b39722a76a76b8d428b69bf8ab3334209ed9ed24ec0e3c48dde5
           # 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.

kubernetes/apps/gatus/configmap.yaml

@@ -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 (10.2.47.1)
+#     Web Service 3 = Immich           Infrastructure 3 = UDM DNS (10.2.40.1)
 #     Web Service 4 = Woodpecker CI    Infrastructure 4 = Mosquitto MQTT broker
 #     Web Service 5 = Grafana
 #     Web Service 6 = Home Assistant
@@ -290,11 +290,9 @@ 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: 10.2.47.1
+        url: 10.2.40.1
         interval: 30s
         dns:
           query-name: udm.renner.uno

kubernetes/apps/gitea/package-retention.yaml

@@ -115,7 +115,7 @@ spec:
               type: RuntimeDefault
           containers:
             - name: retention
-              image: docker.io/library/python:3.15-alpine@sha256:d44b1254cb92329418d164b22b20d86bbd3869d48e80e09e476531a409a728bb
+              image: docker.io/library/python:3.14-alpine@sha256:f6a589d43c42b9e7f7dc67a12d37132491f362859a5d750607710cc56da3bc72
               command: ["python3", "/app/package-retention.py"]
               env:
                 # In-cluster Service; the public name hairpins off the ingress

kubernetes/apps/hermes/gitea-webhook-sync.yaml

@@ -32,7 +32,7 @@ spec:
               type: RuntimeDefault
           containers:
             - name: sync
-              image: gitea.renner.uno/konairius/hermes:build.1793088058 # {"$imagepolicy": "flux-system:hermes"}
+              image: gitea.renner.uno/konairius/hermes:build.1792569647 # {"$imagepolicy": "flux-system:hermes"}
               command:
                 - /opt/hermes/.venv/bin/python
                 - /opt/hermes-skills/gitea-issues/scripts/sync_webhook.py

kubernetes/apps/hermes/hermes.yaml

@@ -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.1793088058 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1792569647 # {"$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.1793088058 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1792569647 # {"$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.1793088058 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1792569647 # {"$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.1793088058 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1792569647 # {"$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.1793088058 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1792569647 # {"$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.1793088058 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1792569647 # {"$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.1793088058 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1792569647 # {"$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.1793088058 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1792569647 # {"$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.1793088058 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1792569647 # {"$imagepolicy": "flux-system:hermes"}
           command:
             - sh
             - -ec
@@ -457,7 +457,7 @@ spec:
               readOnly: true
       containers:
         - name: hermes
-          image: gitea.renner.uno/konairius/hermes:build.1793088058 # {"$imagepolicy": "flux-system:hermes"}
+          image: gitea.renner.uno/konairius/hermes:build.1792569647 # {"$imagepolicy": "flux-system:hermes"}
           args: ["gateway", "run"]
           env:
             - name: HERMES_DASHBOARD

kubernetes/apps/home-assistant-iot/mdns-relay-deployment.yaml

@@ -88,7 +88,7 @@ spec:
         # deliver, and the ClusterIP has no backend while HA restarts. The
         # trap forwards SIGTERM so the pod still terminates promptly.
         - name: socat-ipv4
-          image: alpine/socat:1.8.1.3@sha256:603174b77eebaba25ba8f8ebb15e1234d6600409554e95d6fb203fd106150287
+          image: alpine/socat:1.8.1.3@sha256:fb3862c949af7c79996d0e514ee96128644d840835ed5368eeecb14a869de361
           imagePullPolicy: IfNotPresent
           command:
             - /bin/sh
@@ -130,7 +130,7 @@ spec:
         # depends on the kernel's bindv6only default rather than on anything
         # stated here, so the roles are made explicit instead of inherited.
         - name: socat-ipv6
-          image: alpine/socat:1.8.1.3@sha256:603174b77eebaba25ba8f8ebb15e1234d6600409554e95d6fb203fd106150287
+          image: alpine/socat:1.8.1.3@sha256:fb3862c949af7c79996d0e514ee96128644d840835ed5368eeecb14a869de361
           imagePullPolicy: IfNotPresent
           command:
             - /bin/sh

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

@@ -61,7 +61,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: shelly-manager
-          image: gitea.renner.uno/k.renner/shelly-manager:build.1792997278 # {"$imagepolicy": "flux-system:shelly-manager"}
+          image: gitea.renner.uno/k.renner/shelly-manager:build.1792387459 # {"$imagepolicy": "flux-system:shelly-manager"}
           imagePullPolicy: IfNotPresent
           ports:
             - name: http
@@ -177,7 +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:b5047b9b76845eac124358373c6852377c52e4b05834a47647e955dd91cb8f1e
+          image: nginxinc/nginx-unprivileged:1.31-alpine@sha256:b9241c6e7b8e9a862f129d8d4199ab64b10390949a78bdd5603379b32c844083
           env:
             - name: POD_IP
               valueFrom:

kubernetes/apps/home-assistant/PROPOSAL-mosquitto-credential-rotation.md

@@ -0,0 +1,179 @@
+# 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.

kubernetes/apps/home-assistant/deployment.yaml

@@ -128,7 +128,7 @@ spec:
               memory: 32Mi
       containers:
         - name: home-assistant
-          image: ghcr.io/home-assistant/home-assistant:2026.10.4 # {"$imagepolicy": "flux-system:home-assistant"}
+          image: ghcr.io/home-assistant/home-assistant:2026.10.2 # {"$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:b5047b9b76845eac124358373c6852377c52e4b05834a47647e955dd91cb8f1e
+          image: nginxinc/nginx-unprivileged:1.31-alpine@sha256:378d0c32f6562f7fd9629170797f57d2b953aa09be983b3daaf4809bb039ca00
           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:v1.11.5@sha256:65c4e34ec0ee0f30ea1f72b7411ec70a91c32fc50f067a8466ad2adb1e7420f2
+          image: ghostunnel/ghostunnel:v1.11.4@sha256:e5248233863aadd36383a11c92360f2981141881ef05e38360a6ada8630d36b1
           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:4.143.1@sha256:377b66bec5645510ed52549bb00e648c273edc604d230a3f90fd2b2433afcb97
+          image: codercom/code-server:4.141.0@sha256:72ab24b5680ee597dd647b30d82625752f40109b5f61bef90ffbf1ea1f02dbb8
           args:
             - "--auth=none"
             - "--bind-addr=0.0.0.0:8080"
@@ -337,7 +337,7 @@ spec:
         # dedicated long-lived token.
         # Runs as root to match HA's root-owned /config files. See config-sync.sh.
         - name: config-sync
-          image: alpine/git:2.54.0@sha256:e8ceedc73bd80992ae8d58a7d24c58b8322146c354f1d2e81a97db4452068ec0
+          image: alpine/git:2.54.0@sha256:03228d7ded483b0b3e55e1de7fa660d70d3e1bb432fa7021d29e192640de11aa
           command: ["/bin/sh", "/scripts/sync.sh"]
           env:
             - name: SYNC_BRANCH

kubernetes/apps/home-assistant/esphome-deployment.yaml

@@ -36,7 +36,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: esphome
-          image: ghcr.io/esphome/esphome:2026.10.0@sha256:1dff19a59070cdb523b76576cdc74d200f862d43c1407809088855920cf57145
+          image: ghcr.io/esphome/esphome:2026.9.1@sha256:776a845d508909bf426d2ee7bdd81796361ebe6a7f091807ce1d6d0b48985413
           imagePullPolicy: IfNotPresent
           # Default entrypoint runs the dashboard (Device Builder) against the
           # mounted /config — no command override needed.

kubernetes/apps/home-assistant/kustomization.yaml

@@ -12,20 +12,26 @@ resources:
   - config-sync-token-externalsecret.yaml
   - config-sync-gitea-externalsecret.yaml
   - matrix-externalsecret.yaml
-  - mosquitto-admin-password.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-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. It logs in to
-  # the broker as register account `zigbee2mqtt-bridge` (mqtt-accounts.yaml).
+  # 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).
   - zigbee2mqtt-coordinator-backup-externalsecret.yaml
   - zigbee2mqtt-config.yaml
   - zigbee2mqtt-pvc.yaml

kubernetes/apps/home-assistant/mosquitto-admin-password.yaml

@@ -1,32 +0,0 @@
-# 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

kubernetes/apps/home-assistant/mosquitto-bootstrap.yaml

@@ -0,0 +1,394 @@
+---
+# 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

kubernetes/apps/home-assistant/mosquitto-config.yaml

@@ -77,15 +77,18 @@ data:
 
     allow_anonymous false
 
-    # 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).
+    # 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).
     # 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 named `admin` therefore replaces the file login.
+    # 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.
     #
     # The acl_file check of 2.0 allows every SUBSCRIBE and checks only on
     # delivery, so the Dynamic Security default must deny publishClientReceive.

kubernetes/apps/home-assistant/mosquitto-deployment.yaml

@@ -64,15 +64,67 @@ 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 admin "$ADMIN_PASSWORD"
+              mosquitto_passwd -c -b /mosquitto/auth/passwd homeassistant "$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).
               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
@@ -91,11 +143,38 @@ spec:
               chmod 0600 /mosquitto/auth/passwd /mosquitto/auth/acl /mosquitto/auth/dynamic-security.json
               exec mosquitto -c /mosquitto/config/mosquitto.conf
           env:
-            # mosquitto-admin-password.yaml
+            - name: HA_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: mosquitto-credentials
+                  key: homeassistant-password
             - name: ADMIN_PASSWORD
               valueFrom:
                 secretKeyRef:
-                  name: mosquitto-admin-password
+                  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
                   key: password
           ports:
             - name: mqtt
@@ -152,12 +231,12 @@ 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, 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.
+          # 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.
           startupProbe:
             tcpSocket:
               port: mqtt

kubernetes/apps/home-assistant/mosquitto-evcc-credentials-externalsecret.yaml

@@ -0,0 +1,15 @@
+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

kubernetes/apps/home-assistant/mosquitto-health-credentials-externalsecret.yaml

@@ -0,0 +1,36 @@
+# 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

kubernetes/apps/home-assistant/mqtt-account-controller.yaml

@@ -5,7 +5,9 @@
 # mqtt-accounts.yaml, every INTERVAL (2m).
 #
 # Manages the production broker `mosquitto` over its mTLS listener :8884
-# (REN-802 step 2, REN-900).
+# (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.
 apiVersion: v1
 kind: ServiceAccount
 metadata:
@@ -85,9 +87,6 @@ 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:
@@ -100,11 +99,6 @@ 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:
@@ -225,7 +219,7 @@ 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-b1f294d@sha256:8081adfee171c36cfa83734e5e7ccc3aad3debf1c0154488de70143674cde85f
+          image: gitea.renner.uno/konairius/mqtt-account-controller:main-cb96b1a@sha256:9d9b9e83a9c0f9f567e57edacab11cf4c58e8c0e49e38e8d7b51421cd1242911
           env:
             - name: BROKER_URL
               value: ssl://mosquitto.home-assistant.svc.cluster.local:8884

kubernetes/apps/home-assistant/mqtt-accounts.yaml

@@ -7,50 +7,51 @@
 # configMapGenerator in kustomization.yaml). An empty list is refused, so it
 # never revokes everyone.
 #
-# The controller manages the production broker `mosquitto` (REN-900).
-# `test-cert` is the certificate test account from REN-888.
+# 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.
 #
-# A cert account needs its Secret `mqtt-<name>-tls`, a password account
-# delivered to a namespace its Secret `mqtt-<name>-password`, added to the
+# A cert account needs its Secret `mqtt-<name>-tls` added to the
 # `mqtt-account-controller-secrets-<namespace>` Role in
-# 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 #"]
+# mqtt-account-controller.yaml, or revoking it fails with 403.
 - 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 (REN-953).
+# 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).
 - name: zigbee2mqtt-bridge
   auth: cert
   deliver: {namespace: home-assistant}
   acl: ["readwrite zigbee2mqtt/#", "write homeassistant/#", "read homeassistant/status"]
-# evcc (evcc namespace, REN-953). evcc takes the certificate PEMs by env
-# (EVCC_MQTT_*), see apps/evcc/deployment.yaml.
+# 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.
 - 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, REN-953).
+# 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).
 - name: home-assistant
   auth: cert
   deliver: {namespace: home-assistant}
   acl: ["readwrite #"]
-# edge-1's local mosquitto bridge (REN-1307): one bridge for open3e/e3oncan.
-# The controller pushes
+# 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
 # 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;

kubernetes/apps/home-assistant/zigbee2mqtt-migration-runbook.md

@@ -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 mqtt-zigbee2mqtt-bridge-tls             # exists (register account zigbee2mqtt-bridge)
+kubectl -n home-assistant get secret mosquitto-zigbee2mqtt-credentials       # exists (bootstrap Job ran)
 kubectl -n home-assistant get externalsecret zigbee2mqtt-coordinator-backup  # SecretSyncedError / NotReady — EXPECTED
 kubectl -n home-assistant get deploy zigbee2mqtt                             # 0/0 — EXPECTED
 ```
 
-Z2M logs in to the broker by certificate on `:8884` as the register account
-`zigbee2mqtt-bridge` (`mqtt-accounts.yaml`).
+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).
 
 ## Step 1 — export the Open Coordinator Backup (non-disruptive)
 

kubernetes/apps/immich/redis.yaml

@@ -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:7.4.12-alpine # {"$imagepolicy": "flux-system:redis-immich"}
+          image: redis:7.4.11-alpine # {"$imagepolicy": "flux-system:redis-immich"}
           args:
             - redis-server
             - --save

kubernetes/apps/immich/server.yaml

@@ -66,7 +66,7 @@ spec:
         # The library PVC is populated by the seed phase before this
         # Deployment reconciles, so no rsync init is needed here.
         - name: fetch-le-staging-roots
-          image: curlimages/curl:8.23.0@sha256:11e64e28c5f58c8d93ee95fcf22ac055f48b0bc440e0ce7d8013bbb5ad6aa8ac
+          image: curlimages/curl:8.22.0@sha256:58adaa4e8dca9c988bae2aba4ab3434a0bb2da16bbe3f92dec39ec7785166777
           command:
             - sh
             - -c

kubernetes/apps/influxdb/grafana-token-job.yaml

@@ -57,7 +57,7 @@ spec:
         runAsNonRoot: false
       initContainers:
         - name: wait-for-influxd
-          image: influxdb:2.9.1@sha256:8f106f7ff12659c5e367b99f8a0e7d14cbd4e6ca1f2914094062db6a9813d9c2
+          image: influxdb:2.9.1@sha256:cdd3dbdea45c2f43513abd06ee9644b6e05d2354a2b93ca829c9f07d716eaaac
           env:
             - { name: INFLUX_HOST, value: http://influxdb-influxdb2.influxdb.svc.cluster.local:8086 }
             - { name: INFLUX_ORG, value: renner }
@@ -80,7 +80,7 @@ spec:
               echo "[$(date -u +%H:%M:%S)] $INFLUX_HOST ready and authenticated"
       containers:
         - name: create
-          image: influxdb:2.9.1@sha256:8f106f7ff12659c5e367b99f8a0e7d14cbd4e6ca1f2914094062db6a9813d9c2
+          image: influxdb:2.9.1@sha256:cdd3dbdea45c2f43513abd06ee9644b6e05d2354a2b93ca829c9f07d716eaaac
           env:
             - { name: INFLUX_HOST, value: http://influxdb-influxdb2.influxdb.svc.cluster.local:8086 }
             - { name: INFLUX_ORG, value: renner }

kubernetes/apps/influxdb/ha-token-job.yaml

@@ -88,7 +88,7 @@ spec:
         # state). Two-stage so we don't try to create an auth before
         # the chart's `influx setup` has finished.
         - name: wait-for-influxd
-          image: influxdb:2.9.1@sha256:8f106f7ff12659c5e367b99f8a0e7d14cbd4e6ca1f2914094062db6a9813d9c2
+          image: influxdb:2.9.1@sha256:cdd3dbdea45c2f43513abd06ee9644b6e05d2354a2b93ca829c9f07d716eaaac
           env:
             - { name: INFLUX_HOST, value: http://influxdb-influxdb2.influxdb.svc.cluster.local:8086 }
             - { name: INFLUX_ORG, value: renner }
@@ -111,7 +111,7 @@ spec:
               echo "[$(date -u +%H:%M:%S)] $INFLUX_HOST ready and authenticated"
       containers:
         - name: create
-          image: influxdb:2.9.1@sha256:8f106f7ff12659c5e367b99f8a0e7d14cbd4e6ca1f2914094062db6a9813d9c2
+          image: influxdb:2.9.1@sha256:cdd3dbdea45c2f43513abd06ee9644b6e05d2354a2b93ca829c9f07d716eaaac
           env:
             - { name: INFLUX_HOST, value: http://influxdb-influxdb2.influxdb.svc.cluster.local:8086 }
             - { name: INFLUX_ORG, value: renner }

kubernetes/apps/influxdb/helmrelease.yaml

@@ -55,7 +55,7 @@ spec:
       repository: influxdb
       # Was pinned to VM 108's 2.7.4 for the one-time `influx restore`; that
       # migration is done. No downgrade below 2.9 without `influxd downgrade`.
-      tag: "2.9.1@sha256:8f106f7ff12659c5e367b99f8a0e7d14cbd4e6ca1f2914094062db6a9813d9c2"
+      tag: "2.9.1@sha256:cdd3dbdea45c2f43513abd06ee9644b6e05d2354a2b93ca829c9f07d716eaaac"
     # Single replica — InfluxDB OSS doesn't cluster. RWO Ceph-block + Velero
     # backups (pending) is the durability story.
     persistence:

kubernetes/apps/kuma-sync/deployment.yaml

@@ -30,7 +30,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: controller
-          image: gitea.renner.uno/gitea_admin/kuma-sync:2026-10-27-0801 # {"$imagepolicy": "flux-system:kuma-sync"}
+          image: gitea.renner.uno/gitea_admin/kuma-sync:2026-10-22-1858 # {"$imagepolicy": "flux-system:kuma-sync"}
           env:
             - name: KUMA_URL
               value: https://kuma.renner.uno

kubernetes/apps/matrix/element.yaml

@@ -72,7 +72,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: element-web
-          image: ghcr.io/element-hq/element-web:v1.12.32@sha256:f8700633d4336258af7a05b53865a4f479e0d628cf2d9ca83d28b5939314d4ce
+          image: ghcr.io/element-hq/element-web:v1.12.30@sha256:3e7dbd4424de9e11c812bc740acf2725b2abe66ea0d0802023b56fd85d3fa09a
           securityContext:
             allowPrivilegeEscalation: false
             readOnlyRootFilesystem: true

kubernetes/apps/matrix/mas.yaml

@@ -137,7 +137,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: mas
-          image: ghcr.io/element-hq/matrix-authentication-service:1.27.1@sha256:02712e68c90f3743fedbd5e3343517481b2b4f246a9fd9e2f050dc2553033847
+          image: ghcr.io/element-hq/matrix-authentication-service:1.26.0@sha256:e089f1048a1d4a9a492ed17b9fe759100f1bd619407b001f5927928d88b780c4
           # The server applies database migrations and syncs the upstream
           # providers from the config on start.
           args: ["server", "--config", "/config/config.yaml"]

kubernetes/apps/matrix/rtc.yaml

@@ -124,7 +124,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: livekit
-          image: livekit/livekit-server:v1.13.11@sha256:25cd902de7cacbd5f1f779f6a6ac1eae20ba8f56b0935934ce6b0ab80d1e3d20
+          image: livekit/livekit-server:v1.13.10@sha256:89ca9ce0791e18d6e03bf6e2c49ceb27e1c754eae8bd50c989386c1a5963791a
           args:
             - --config
             - /config/livekit.yaml

kubernetes/apps/matrix/synapse.yaml

@@ -179,7 +179,7 @@ spec:
         # first. The marker on the data PVC makes later starts skip it.
         # Debug image: the plain one has no shell for the marker check.
         - name: migrate-to-mas
-          image: ghcr.io/element-hq/matrix-authentication-service:1.27.1-debug@sha256:75f369b206785f1480f4a9f8dd81d7f9f3c6793c40fd184358ecd5d7acae17d4
+          image: ghcr.io/element-hq/matrix-authentication-service:1.26.0-debug@sha256:46f7480f5ea4243ccb6fd2c447ea859e0230c8b3c0e676ee285d4ae6ca344ee3
           command:
             - /busybox/sh
             - -ec
@@ -234,7 +234,7 @@ spec:
               mountPath: /data
       containers:
         - name: synapse
-          image: ghcr.io/element-hq/synapse:v1.163.2@sha256:c3c21919a322f74d177a43bce8031adc81ef839ddd117a8dd03cfec350e76e02
+          image: ghcr.io/element-hq/synapse:v1.162.0@sha256:6b84a7bbac36f080b2d2e51e0289cf1b08b349598ea44a558df38d558f2c2311
           # 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.

kubernetes/apps/monitoring-rules/probes-dns.yaml

@@ -5,9 +5,7 @@
 #
 # 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. 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).
+# a deleted record green for an hour.
 #
 # `release` is load-bearing — probeSelector matches on it.
 apiVersion: monitoring.coreos.com/v1
@@ -27,8 +25,8 @@ spec:
   targets:
     staticConfig:
       static:
-        - "[fd02:47::1]:53"
-        - "10.2.47.1:53"
+        - "[fd00::1]:53"
+        - "10.2.40.1:53"
       # instance is the resolver and identical across these Probes, so the
       # queried name has to come from a label.
       labels:
@@ -51,8 +49,8 @@ spec:
   targets:
     staticConfig:
       static:
-        - "[fd02:47::1]:53"
-        - "10.2.47.1:53"
+        - "[fd00::1]:53"
+        - "10.2.40.1:53"
       labels:
         dns_name: mqtt.renner.uno
 ---
@@ -73,8 +71,8 @@ spec:
   targets:
     staticConfig:
       static:
-        - "[fd02:47::1]:53"
-        - "10.2.47.1:53"
+        - "[fd00::1]:53"
+        - "10.2.40.1:53"
       labels:
         dns_name: ldap.renner.uno
 ---
@@ -95,8 +93,8 @@ spec:
   targets:
     staticConfig:
       static:
-        - "[fd02:47::1]:53"
-        - "10.2.47.1:53"
+        - "[fd00::1]:53"
+        - "10.2.40.1:53"
       labels:
         dns_name: syslog.renner.uno
 ---
@@ -117,8 +115,8 @@ spec:
   targets:
     staticConfig:
       static:
-        - "[fd02:47::1]:53"
-        - "10.2.47.1:53"
+        - "[fd00::1]:53"
+        - "10.2.40.1:53"
       labels:
         dns_name: ftp.paperless.renner.uno
 ---
@@ -139,7 +137,7 @@ spec:
   targets:
     staticConfig:
       static:
-        - "[fd02:47::1]:53"
-        - "10.2.47.1:53"
+        - "[fd00::1]:53"
+        - "10.2.40.1:53"
       labels:
         dns_name: syncthing.paperless.renner.uno

kubernetes/apps/monitoring-rules/prometheusrule-home-assistant.yaml

@@ -82,9 +82,9 @@ spec:
           #
           # The pod regex is the Deployment's name shape
           # (mosquitto-<replicaset hash>-<suffix>) and not `mosquitto-.*` on
-          # purpose: other pods in the namespace start with `mosquitto-`
-          # (mosquitto-dynsec-test), and a Ready one must not hide a broker
-          # that is down.
+          # 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.
           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

kubernetes/apps/monitoring-rules/tests/home-assistant_test.yaml

@@ -137,13 +137,13 @@ tests:
         exp_alerts: []
 
   # --- MosquittoDown ------------------------------------------------------
-  # The broker goes not-Ready at t=10m while the mosquitto-dynsec-test pod is
-  # Ready. That pod must not mask the broker.
+  # The broker goes not-Ready at t=10m while a credentials-bootstrap Job pod is
+  # Ready. The Job 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-dynsec-test-6d9f8b7c5-r4t8w",condition="true"}'
+      - series: 'kube_pod_status_ready{namespace="home-assistant",pod="mosquitto-credentials-bootstrap-q7w2e",condition="true"}'
         values: '1x30'
     alert_rule_test:
       - eval_time: 14m

kubernetes/apps/monitoring/helmrelease-loki.yaml

@@ -32,9 +32,6 @@ 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:

kubernetes/apps/monitoring/helmrelease-prometheus.yaml

@@ -17,7 +17,7 @@ spec:
   chart:
     spec:
       chart: kube-prometheus-stack
-      version: "92.13.1"
+      version: "92.3.0"
       sourceRef:
         kind: HelmRepository
         name: prometheus-community

kubernetes/apps/music-assistant/configmap-net-reconcile.yaml

@@ -21,13 +21,10 @@ data:
       the pod's default route — which players on the IoT VLAN cannot route to.
       The v30iot address lives on the net1 macvlan child (see
       network-attachment.yaml).
-    - bind_ip must be the same live v30iot address. aiosendspin starts its
-      zeroconf on [bind_ip], or on InterfaceChoice.Default for 0.0.0.0; Default
-      sends mDNS queries via the main-table default route (eth0, net1 routes
-      live in the sbr table), so MA never queries the IoT VLAN for
-      _sendspin._tcp and Voice PEs are only rediscovered when they announce
-      on their own. The Sendspin server has no all-interfaces bind fallback, so
-      bind_ip must be local at start; it is, because it is read from net1 here.
+    - bind_ip must be 0.0.0.0. The Sendspin server (aiosendspin, port 8927) has
+      NO all-interfaces fallback: if bind_ip is a specific IP that is not local
+      it fails to bind and the server never starts, and its proxy then targets
+      that dead IP instead of 127.0.0.1. Binding 0.0.0.0 avoids both.
 
     The v30iot IP is DHCP and node-dependent (MA is not node-pinned), so a stored
     IP is a stale assumption the moment MA reschedules or the lease changes -
@@ -94,15 +91,15 @@ data:
             .setdefault("values", {})
         )
         old_pub, old_bind = values.get("publish_ip"), values.get("bind_ip")
-        if (old_pub, old_bind) == (ip, ip):
+        if (old_pub, old_bind) == (ip, "0.0.0.0"):
             print("[reconcile] publish_ip/bind_ip already correct; no change")
             return 0
 
         values["publish_ip"] = ip
-        values["bind_ip"] = ip
+        values["bind_ip"] = "0.0.0.0"
         print(
             f"[reconcile] publish_ip {old_pub!r} -> {ip!r}, "
-            f"bind_ip {old_bind!r} -> {ip!r}"
+            f"bind_ip {old_bind!r} -> '0.0.0.0'"
         )
 
         tmp = SETTINGS + ".reconcile.tmp"

kubernetes/apps/music-assistant/deployment.yaml

@@ -44,9 +44,7 @@ spec:
         #     which IoT players can't reach; and
         #   - net1 is DHCP and MA is not node-pinned, so any hard-coded IP goes
         #     stale on the next reschedule or lease change (the Sendspin server
-        #     then fails to bind and dies, with no fallback); and
-        #   - a 0.0.0.0 bind_ip makes Sendspin's mDNS browse query via eth0, so
-        #     Voice PEs on the IoT VLAN are not rediscovered after a restart.
+        #     then fails to bind and dies, with no fallback).
         # So we recompute the v30iot IP from the live interface every boot and
         # write it into /data/settings.json before MA reads it. Multus attaches
         # net1 (with its DHCP lease) before any container runs, so this sees the
@@ -54,7 +52,7 @@ spec:
         # stdlib only; Flux keeps the tag in lockstep via the shared image
         # policy) — no extra dependency.
         - name: reconcile-publish-ip
-          image: ghcr.io/music-assistant/server:2.10.8 # {"$imagepolicy": "flux-system:music-assistant"}
+          image: ghcr.io/music-assistant/server:2.10.7 # {"$imagepolicy": "flux-system:music-assistant"}
           command: ["/app/venv/bin/python", "/scripts/reconcile.py"]
           volumeMounts:
             - name: data
@@ -62,33 +60,9 @@ spec:
             - name: net-reconcile
               mountPath: /scripts
               readOnly: true
-        # Pocket Casts Up Next as a library playlist, pending upstream. Copies
-        # the image's provider and swaps in the patched __init__.py only while
-        # the stock file is the one it was written against (2.10.7 = 2.10.8);
-        # any other version keeps the stock provider.
-        - name: pocketcasts-overlay
-          image: ghcr.io/music-assistant/server:2.10.8 # {"$imagepolicy": "flux-system:music-assistant"}
-          command:
-            - /bin/sh
-            - -euc
-            - |
-              src=$(echo /app/venv/lib/python3*/site-packages/music_assistant/providers/pocketcasts)
-              cp -a "$src/." /overlay/
-              if echo "c88377d887148faf912ff217e021df3cd42bb7071dece0998b07c7bb12eb323e  $src/__init__.py" | sha256sum -c --status; then
-                cp /patch/__init__.py /overlay/__init__.py
-                echo "pocketcasts: Up Next playlist patch applied"
-              else
-                echo "pocketcasts: stock provider changed upstream, patch skipped"
-              fi
-          volumeMounts:
-            - name: pocketcasts-overlay
-              mountPath: /overlay
-            - name: pocketcasts-patch
-              mountPath: /patch
-              readOnly: true
       containers:
         - name: music-assistant
-          image: ghcr.io/music-assistant/server:2.10.8 # {"$imagepolicy": "flux-system:music-assistant"}
+          image: ghcr.io/music-assistant/server:2.10.7 # {"$imagepolicy": "flux-system:music-assistant"}
           env:
             - name: LOG_LEVEL
               value: info
@@ -107,8 +81,6 @@ spec:
           volumeMounts:
             - name: data
               mountPath: /data
-            - name: pocketcasts-overlay
-              mountPath: /app/venv/lib/python3.14/site-packages/music_assistant/providers/pocketcasts
           livenessProbe:
             httpGet:
               path: /
@@ -153,11 +125,6 @@ spec:
           configMap:
             name: music-assistant-net-reconcile
             defaultMode: 0555
-        - name: pocketcasts-overlay
-          emptyDir: {}
-        - name: pocketcasts-patch
-          configMap:
-            name: music-assistant-pocketcasts-up-next
 ---
 apiVersion: v1
 kind: Service

kubernetes/apps/music-assistant/kustomization.yaml

@@ -7,10 +7,3 @@ resources:
   - deployment.yaml
   - ingress.yaml
   - kumamonitors.yaml
-configMapGenerator:
-  # Pocket Casts provider with the Up Next playlist, applied by the
-  # pocketcasts-overlay initContainer. Hashed name: an edit rolls the pod.
-  - name: music-assistant-pocketcasts-up-next
-    namespace: music-assistant
-    files:
-      - __init__.py=pocketcasts-up-next/__init__.py

kubernetes/apps/music-assistant/network-attachment.yaml

@@ -13,9 +13,9 @@
 # initContainer (configmap-net-reconcile.yaml) discovers net1's leased
 # address the same way it used to discover the host's ens19 address —
 # scanning the pod's own interfaces for a 10.2.30.0/24 address — and
-# writes it as MA's publish_ip and bind_ip; players reach the
-# stream/sendspin servers on net1. Requires the cni-dhcp-daemon DaemonSet
-# in infrastructure/multus.
+# writes it as MA's publish_ip. bind_ip stays 0.0.0.0, which now binds
+# eth0 (pod) + net1; players reach the stream/slimproto/sendspin servers
+# on net1. Requires the cni-dhcp-daemon DaemonSet in infrastructure/multus.
 #
 # Mirrors matter-server-iot; the only difference is MA does not speak
 # Thread, so the matter NAD's accept_ra_rt_info_max_plen tuning (for the

kubernetes/apps/music-assistant/pocketcasts-up-next/__init__.py

@@ -1,817 +0,0 @@
-"""Pocket Casts music provider for Music Assistant."""
-
-from __future__ import annotations
-
-import asyncio
-import logging
-from collections.abc import AsyncGenerator
-from typing import TYPE_CHECKING, Any
-
-from music_assistant_models.enums import (
-    ContentType,
-    ImageType,
-    MediaType,
-    ProviderFeature,
-    StreamType,
-)
-from music_assistant_models.errors import (
-    LoginFailed,
-    MediaNotFoundError,
-    ProviderUnavailableError,
-    ResourceTemporarilyUnavailable,
-    RetriesExhausted,
-)
-from music_assistant_models.media_items import (
-    AudioFormat,
-    BrowseFolder,
-    ItemMapping,
-    MediaItemImage,
-    MediaItemMetadata,
-    MediaItemType,
-    Playlist,
-    Podcast,
-    PodcastEpisode,
-    ProviderMapping,
-    SearchResults,
-    UniqueList,
-)
-from music_assistant_models.streamdetails import StreamDetails
-
-from music_assistant import MusicAssistant
-from music_assistant.constants import CONF_PASSWORD, CONF_USERNAME
-from music_assistant.controllers.cache import use_cache
-from music_assistant.helpers.podcast_parsers import rank_episodes_by_date
-from music_assistant.models.music_provider import MusicProvider
-
-from .api_client import PocketCastsClient
-
-if TYPE_CHECKING:
-    from datetime import datetime
-
-    from music_assistant_models.config_entries import ConfigEntry, ProviderConfig
-    from music_assistant_models.provider import ProviderManifest
-
-    from music_assistant.models import ProviderInstanceType
-
-LOGGER = logging.getLogger(__name__)
-
-FULLY_PLAYED_THRESHOLD = 0.9
-SPECIAL_FOLDERS = ("up_next", "new_releases", "in_progress", "starred", "history")
-UP_NEXT_PLAYLIST_ID = "up_next"
-
-SUPPORTED_FEATURES = {
-    ProviderFeature.LIBRARY_PODCASTS,
-    ProviderFeature.LIBRARY_PLAYLISTS,
-    ProviderFeature.BROWSE,
-    ProviderFeature.SEARCH,
-    ProviderFeature.LIBRARY_PODCASTS_EDIT,
-}
-
-BROWSE_FOLDER_ICONS: dict[str, str] = {
-    "up_next": (
-        "data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIH"
-        "ZpZXdCb3g9IjAgMCAyNCAyNCIgd2lkdGg9IjI0MCIgaGVpZ2h0PSIyNDAiPgogICAgPHBhdGggZmls"
-        "bD0iIzhGOTdBNCIgZD0iTTMgMi45NzE1OUMzIDIuNTY0OSAzLjQ1OTY4IDIuMzI4MzQgMy43OTA2Mi"
-        "AyLjU2NDcyTDkuNDMwMzkgNi41OTMxM0M5LjcwOTU2IDYuNzkyNTQgOS43MDk1NiA3LjIwNzQ1IDku"
-        "NDMwMzkgNy40MDY4NkwzLjc5MDYyIDExLjQzNTNDMy40NTk2OSAxMS42NzE2IDMgMTEuNDM1MSAzID"
-        "ExLjAyODRWMi45NzE1OVoiLz4KICAgIDxwYXRoIGZpbGw9IiM4Rjk3QTQiIG9wYWNpdHk9IjAuNS"
-        "IgZD0iTTEyIDdDMTIgNi40NDc3MiAxMi40NDc3IDYgMTMgNkgyMUMyMS41NTIzIDYgMjIgNi40NDc3"
-        "MiAyMiA3QzIyIDcuNTUyMjggMjEuNTUyMyA4IDIxIDhIMTNDMTIuNDQ3NyA4IDEyIDcuNTUyMjggMT"
-        "IgN1pNOSAxMkM5IDExLjQ0NzcgOS40NDc3MiAxMSAxMCAxMUgyMUMyMS41NTIzIDExIDIyIDExLjQ0Nz"
-        "cgMjIgMTJDMjIgMTIuNTUyMyAyMS41NTIzIDEzIDIxIDEzSDEwQzkuNDQ3NzIgMTMgOSAxMi41NTIz"
-        "IDkgMTJaTTEwIDE2QzkuNDQ3NzIgMTYgOSAxNi40NDc3IDkgMTdDOSAxNy41NTIzIDkuNDQ3NzIgMT"
-        "ggMTAgMThIMjFDMjEuNTUyMyAxOCAyMiAxNy41NTIzIDIyIDE3QzIyIDE2LjQ0NzcgMjEuNTUyMyAx"
-        "NiAyMSAxNkgxMFoiLz4KPC9zdmc+Cg=="
-    ),
-    "new_releases": (
-        "data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIH"
-        "ZpZXdCb3g9IjAgMCAyNCAyNCIgd2lkdGg9IjI0MCIgaGVpZ2h0PSIyNDAiPgogICAgPGcgZmlsbD0i"
-        "IzhGOTdBNCIgdHJhbnNmb3JtPSJ0cmFuc2xhdGUoMCwgMSkiPgogICAgICAgIDxwYXRoIGQ9Ik0xNC"
-        "43OTM1IDQuNTU3MzVMMTUuNzc0MSAwLjc4OTIwOUMxNS45Njg4IDAuMDQxMDUwOSAxNy4wMzExIDAu"
-        "MDQxMDcxOSAxNy4yMjU4IDAuNzg5MjM3TDE4LjIwNjIgNC41NTczMkMxOC4yNzcgNC44MjkxNSAxOC"
-        "40OTM3IDUuMDM4NjggMTguNzY3NyA1LjEwMDIzTDIxLjc0MTkgNS43NjgyM0MyMi41MjI4IDUuOTQz"
-        "NjIgMjIuNTIyOCA3LjA1NjM5IDIxLjc0MTkgNy4yMzE3N0wxOC43Njc3IDcuODk5NzdDMTguNDkzNy"
-        "A3Ljk2MTMyIDE4LjI3NyA4LjE3MDg1IDE4LjIwNjIgOC40NDI2OEwxNy4yMjU4IDEyLjIxMDhDMTcu"
-        "MDMxMSAxMi45NTg5IDE1Ljk2ODggMTIuOTU4OSAxNS43NzQxIDEyLjIxMDhMMTQuNzkzNSA4LjQ0Mj"
-        "Y1QzE0LjcyMjcgOC4xNzA4MyAxNC41MDYxIDcuOTYxMzIgMTQuMjMyIDcuODk5NzdMMTEuMjU4IDcu"
-        "MjMxNzdDMTAuNDc3MSA3LjA1NjM5IDEwLjQ3NzEgNS45NDM2MiAxMS4yNTggNS43NjgyNEwxNC4yMz"
-        "IgNS4xMDAyM0MxNC41MDYxIDUuMDM4NjggMTQuNzIyNyA0LjgyOTE3IDE0Ljc5MzUgNC41NTczNVoi"
-        "Lz4KICAgICAgICA8cGF0aCBvcGFjaXR5PSIwLjgiIGQ9Ik01LjI5OTQgOS4yNjgzTDYuMDMwNjYgNy"
-        "4yNzc2M0M2LjE5MTEyIDYuODQwODUgNi44MDg4OCA2Ljg0MDg1IDYuOTY5MzQgNy4yNzc2M0w3Ljcw"
-        "MDYgOS4yNjgzQzcuNzU0MjUgOS40MTQzNSA3Ljg3Mjg0IDkuNTI3MSA4LjAyMTQxIDkuNTczMzJMOS"
-        "40NjU0MSAxMC4wMjI2QzkuOTM0MDMgMTAuMTY4MyA5LjkzNDAzIDEwLjgzMTYgOS40NjU0MSAxMC45"
-        "Nzc0TDguMDIxNCAxMS40MjY3QzcuODcyODMgMTEuNDcyOSA3Ljc1NDI1IDExLjU4NTYgNy43MDA2ID"
-        "ExLjczMTdMNi45NjkzMyAxMy43MjI0QzYuODA4ODggMTQuMTU5MiA2LjE5MTEyIDE0LjE1OTIgNi4w"
-        "MzA2NiAxMy43MjI0TDUuMjk5NCAxMS43MzE3QzUuMjQ1NzUgMTEuNTg1NiA1LjEyNzE3IDExLjQ3Mj"
-        "kgNC45Nzg2IDExLjQyNjdMMy41MzQ1OSAxMC45Nzc0QzMuMDY1OTcgMTAuODMxNiAzLjA2NTk3IDEw"
-        "LjE2ODMgMy41MzQ1OSAxMC4wMjI2TDQuOTc4NTkgOS41NzMzMkM1LjEyNzE2IDkuNTI3MSA1LjI0NT"
-        "c1IDkuNDE0MzUgNS4yOTk0IDkuMjY4M1oiLz4KICAgICAgICA8cGF0aCBvcGFjaXR5PSIwLjYiIGQ9"
-        "Ik0xMC42ODgyIDE2LjAxNEwxMS41MjQ3IDEzLjQ1NDNDMTEuNjc0OSAxMi45OTQ3IDEyLjMyNTEgMT"
-        "IuOTk0NyAxMi40NzUzIDEzLjQ1NDNMMTMuMzExOCAxNi4wMTRDMTMuMzYwNCAxNi4xNjI3IDEzLjQ3"
-        "NTcgMTYuMjggMTMuNjIzNSAxNi4zMzEyTDE1LjYzNSAxNy4wMjc1QzE2LjA4MzYgMTcuMTgyOCAxNi"
-        "4wODM2IDE3LjgxNzIgMTUuNjM1IDE3Ljk3MjVMMTMuNjIzNSAxOC42Njg4QzEzLjQ3NTcgMTguNzIg"
-        "MTMuMzYwNCAxOC44MzczIDEzLjMxMTggMTguOTg2TDEyLjQ3NTMgMjEuNTQ1N0MxMi4zMjUxIDIyLj"
-        "AwNTMgMTEuNjc0OSAyMi4wMDUzIDExLjUyNDcgMjEuNTQ1N0wxMC42ODgyIDE4Ljk4NkMxMC42Mzk2"
-        "IDE4LjgzNzMgMTAuNTI0MyAxOC43MiAxMC4zNzY1IDE4LjY2ODhMOC4zNjQ5OCAxNy45NzI1QzcuOT"
-        "E2MzggMTcuODE3MiA3LjkxNjM5IDE3LjE4MjggOC4zNjQ5OCAxNy4wMjc1TDEwLjM3NjUgMTYuMzMx"
-        "MkMxMC41MjQzIDE2LjI4IDEwLjYzOTYgMTYuMTYyNyAxMC42ODgyIDE2LjAxNFoiLz4KICAgIDwvZz"
-        "4KPC9zdmc+Cg=="
-    ),
-    "in_progress": (
-        "data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIH"
-        "ZpZXdCb3g9IjAgMCAyNCAyNCIgd2lkdGg9IjI0MCIgaGVpZ2h0PSIyNDAiPgogICAgPHBhdGggZmls"
-        "bD0iIzhGOTdBNCIgb3BhY2l0eT0iMC41IiBkPSJNNCAxMkM0IDE2LjQxODMgNy41ODE3MiAyMCAxMi"
-        "AyMEMxNi40MTgzIDIwIDIwIDE2LjQxODMgMjAgMTJDMjAgNy41ODE3MiAxNi40MTgzIDQgMTIgNEM3"
-        "LjU4MTcyIDQgNCA3LjU4MTcyIDQgMTJaTTE4IDEyQzE4IDE1LjMxMzcgMTUuMzEzNyAxOCAxMiAxOE"
-        "M4LjY4NjI5IDE4IDYgMTUuMzEzNyA2IDEyQzYgOC42ODYyOSA4LjY4NjI5IDYgMTIgNkMxNS4zMTM3"
-        "IDYgMTggOC42ODYyOSAxOCAxMloiLz4KICAgIDxwYXRoIGZpbGw9IiM4Rjk3QTQiIGQ9Ik0xNi45Mj"
-        "UzIDE4LjMwNDFDMjAuNDA2OSAxNS41ODM5IDIxLjAyNDMgMTAuNTU2NCAxOC4zMDQxIDcuMDc0NzJD"
-        "MTYuODI2OSA1LjE4Mzk0IDE0LjYxNjcgNC4wODMyNyAxMi4yNjUgNC4wMDQyNEMxMS43MTMxIDMuOT"
-        "g1NjkgMTEuMjUwNiA0LjQxODExIDExLjIzMiA0Ljk3MDA4QzExLjIxMzUgNS41MjIwNiAxMS42NDU5"
-        "IDUuOTg0NTYgMTIuMTk3OSA2LjAwMzExQzEzLjk2MzkgNi4wNjI0NiAxNS42MTkzIDYuODg2ODYgMT"
-        "YuNzI4MSA4LjMwNjA1QzE4Ljc2ODIgMTAuOTE3MyAxOC4zMDUyIDE0LjY4OCAxNS42OTQgMTYuNzI4"
-        "MUMxNS4yNTg4IDE3LjA2ODEgMTUuMTgxNiAxNy42OTY1IDE1LjUyMTYgMTguMTMxOEMxNS44NjE2ID"
-        "E4LjU2NyAxNi40OTAxIDE4LjY0NDEgMTYuOTI1MyAxOC4zMDQxWiIvPgo8L3N2Zz4K"
-    ),
-    "starred": (
-        "data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIH"
-        "ZpZXdCb3g9IjAgMCAyNCAyNCIgd2lkdGg9IjI0MCIgaGVpZ2h0PSIyNDAiPgogICAgPHBhdGggZmls"
-        "bD0iIzhGOTdBNCIgdHJhbnNmb3JtPSJ0cmFuc2xhdGUoMSwgLTAuNSkiIGQ9Ik0xMS41ODMxIDE3Lj"
-        "Q3NzZMOC4wNzM4NCAxOS4yOTMzQzcuMDk0MTMgMTkuODAwMiA2LjQ0NjgxIDE5LjMxOTcgNi42MjQ2"
-        "NiAxOC4yNDA0TDcuMjY3MDcgMTQuMzQxOEw0LjQ1NTgxIDExLjU2NTRDMy42NzA5NyAxMC43OTAzID"
-        "MuOTI3OTEgMTAuMDI2MiA1LjAwOTM1IDkuODYxNzdMOC45MTU2NSA5LjI2ODAxTDEwLjY4NzUgNS43"
-        "MzYzOEMxMS4xODIxIDQuNzUwNDIgMTEuOTg4MiA0Ljc1ODY3IDEyLjQ3ODggNS43MzYzOEwxNC4yNT"
-        "A2IDkuMjY4MDFMMTguMTU2OSA5Ljg2MTc3QzE5LjI0NzQgMTAuMDI3NSAxOS40ODg3IDEwLjc5Njgg"
-        "MTguNzEwNCAxMS41NjU0TDE1Ljg5OTIgMTQuMzQxOEwxNi41NDE2IDE4LjI0MDRDMTYuNzIwOSAxOS"
-        "4zMjg4IDE2LjA2MzkgMTkuNzk2IDE1LjA5MjQgMTkuMjkzM0wxMS41ODMxIDE3LjQ3NzZaIi8+Cjwv"
-        "c3ZnPgo="
-    ),
-    "history": (
-        "data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIH"
-        "ZpZXdCb3g9IjAgMCAyNCAyNCIgd2lkdGg9IjI0MCIgaGVpZ2h0PSIyNDAiPgogICAgPHBhdGggZmls"
-        "bD0iIzhGOTdBNCIgb3BhY2l0eT0iMC41IiBjbGlwLXJ1bGU9ImV2ZW5vZGQiIGQ9Ik0xMC41IDEzQz"
-        "EwLjUgMTMuNTUyMyAxMC45NDc3IDE0IDExLjUgMTRIMTQuNUMxNS4wNTIzIDE0IDE1LjUgMTMuNTUy"
-        "MyAxNS41IDEzQzE1LjUgMTIuNDQ3NyAxNS4wNTIzIDEyIDE0LjUgMTJIMTIuNUwxMi41IDEwQzEyLj"
-        "UgOS40NDc3MiAxMi4wNTIzIDkgMTEuNSA5QzEwLjk0NzcgOSAxMC41IDkuNDQ3NzIgMTAuNSAxMFYx"
-        "M1oiLz4KICAgIDxwYXRoIGZpbGw9IiM4Rjk3QTQiIGZpbGwtcnVsZT0iZXZlbm9kZCIgY2xpcC1y"
-        "dWxlPSJldmVub2RkIiBkPSJNMTIgMThDMTUuMzEzNyAxOCAxOCAxNS4zMTM3IDE4IDEyQzE4IDguNj"
-        "g2MjkgMTUuMzEzNyA2IDEyIDZDOC42ODYyOSA2IDYgOC42ODYyOSA2IDEyQzYgMTUuMzEzNyA4LjY4"
-        "NjI5IDE4IDEyIDE4Wk0xMiAyMEMxNi40MTgzIDIwIDIwIDE2LjQxODMgMjAgMTJDMjAgNy41ODE3Mi"
-        "AxNi40MTgzIDQgMTIgNEM3LjU4MTcyIDQgNCA3LjU4MTcyIDQgMTJDNCAxNi40MTgzIDcuNTgxNzIg"
-        "MjAgMTIgMjBaIi8+Cjwvc3ZnPgo="
-    ),
-}
-
-
-async def setup(
-    mass: MusicAssistant, manifest: ProviderManifest, config: ProviderConfig
-) -> ProviderInstanceType:
-    """Initialize provider(instance) with given configuration."""
-    return PocketCastsProvider(mass, manifest, config, SUPPORTED_FEATURES)
-
-
-class PocketCastsProvider(MusicProvider):
-    """Provider for Pocket Casts podcast service."""
-
-    _client: PocketCastsClient
-    # episode uuids already mirrored to Pocket Casts Up Next/history this session, keyed as a
-    # set since multi-room playback can have several episodes in progress on one instance
-    _announced_episodes: set[str]
-
-    async def get_config_entries(self) -> tuple[ConfigEntry, ...]:
-        """Return Config entries to configure this provider."""
-        return ()
-
-    async def handle_async_init(self) -> None:
-        """Handle async initialization of the provider."""
-        email = self.get_setup_value(CONF_USERNAME)
-        password = self.get_setup_value(CONF_PASSWORD)
-        if not email or not password:
-            raise LoginFailed("Email and password are required for Pocket Casts")
-        self._announced_episodes = set()
-        self._client = PocketCastsClient(self.mass.http_session, self.logger)
-        await self._client.login(str(email), str(password))
-
-    async def get_library_podcasts(self) -> AsyncGenerator[Podcast]:
-        """Get all podcasts from the user's library."""
-        for podcast_data in await self._client.get_subscribed_podcasts():
-            yield self._convert_podcast(podcast_data)
-
-    async def library_add(self, item: MediaItemType) -> bool:
-        """
-        Subscribe to a podcast.
-
-        :param item: The media item to add to the library.
-        """
-        if not isinstance(item, Podcast):
-            return await super().library_add(item)
-        await self._client.subscribe_podcast(item.item_id)
-        return True
-
-    async def library_remove(self, prov_item_id: str, media_type: MediaType) -> bool:
-        """
-        Unsubscribe from a podcast.
-
-        :param prov_item_id: The provider item ID to remove from the library.
-        :param media_type: The media type of the item.
-        """
-        if media_type != MediaType.PODCAST:
-            return await super().library_remove(prov_item_id, media_type)
-        await self._client.unsubscribe_podcast(prov_item_id)
-        return True
-
-    @use_cache(3600 * 24)
-    async def get_podcast(self, prov_podcast_id: str) -> Podcast:
-        """
-        Get full details for a podcast.
-
-        :param prov_podcast_id: The provider podcast id.
-        """
-        podcast_data = await self._client.get_podcast(prov_podcast_id)
-        if not podcast_data:
-            raise MediaNotFoundError(
-                f"podcast://{prov_podcast_id} not found on provider {self.domain}"
-            )
-        return self._convert_podcast(podcast_data)
-
-    async def get_podcast_episodes(self, prov_podcast_id: str) -> AsyncGenerator[PodcastEpisode]:
-        """
-        Get all episodes for a podcast, enriched with playback status.
-
-        :param prov_podcast_id: The provider podcast id.
-        """
-        # fetch episode metadata, user status and show notes in parallel
-        (podcast_name, episodes), in_progress, history, show_notes = await asyncio.gather(
-            self._client.get_podcast_episodes(prov_podcast_id),
-            self._client.get_in_progress_episodes(),
-            self._client.get_history(),
-            self._get_show_notes(prov_podcast_id),
-        )
-        in_progress_map = {ep.get("uuid"): ep for ep in in_progress}
-        history_map = {ep.get("uuid"): ep for ep in history}
-
-        # the full-podcast payload carries no episode number, so rank on the publication date
-        positions = rank_episodes_by_date([ep.get("published") or None for ep in episodes])
-        for position, episode_data in zip(positions, episodes, strict=True):
-            episode_item = self._convert_episode(
-                episode_data,
-                prov_podcast_id,
-                show_notes.get(episode_data.get("uuid", "")),
-                podcast_name,
-                position=position,
-            )
-            if episode_item:
-                self._enrich_episode_with_status(
-                    episode_item, episode_data, in_progress_map, history_map
-                )
-                yield episode_item
-
-    async def get_library_playlists(self) -> AsyncGenerator[Playlist]:
-        """Get the user's Up Next queue as a playlist."""
-        yield self._get_up_next_playlist()
-
-    async def get_playlist(self, prov_playlist_id: str) -> Playlist:
-        """
-        Get full details for a playlist.
-
-        :param prov_playlist_id: The provider playlist id.
-        """
-        if prov_playlist_id != UP_NEXT_PLAYLIST_ID:
-            raise MediaNotFoundError(
-                f"playlist://{prov_playlist_id} not found on provider {self.domain}"
-            )
-        return self._get_up_next_playlist()
-
-    async def get_playlist_tracks(
-        self, prov_playlist_id: str, page: int = 0
-    ) -> list[PodcastEpisode]:
-        """
-        Get the episodes of a playlist, in Up Next order.
-
-        :param prov_playlist_id: The provider playlist id.
-        :param page: Zero-based page index; Up Next is returned whole on the first page.
-        """
-        if prov_playlist_id != UP_NEXT_PLAYLIST_ID:
-            raise MediaNotFoundError(
-                f"playlist://{prov_playlist_id} not found on provider {self.domain}"
-            )
-        if page > 0:
-            return []
-        episodes = await self._get_special_folder_episodes(UP_NEXT_PLAYLIST_ID)
-        # the Up Next payload carries no duration or playback status, and marking an episode
-        # played reports its duration as the position, so take both from the episode details
-        details = await asyncio.gather(
-            *(self.get_podcast_episode(episode.item_id) for episode in episodes),
-            return_exceptions=True,
-        )
-        items: list[PodcastEpisode] = []
-        for episode, detail in zip(episodes, details, strict=True):
-            if isinstance(detail, PodcastEpisode):
-                items.append(detail)
-            elif isinstance(
-                detail,
-                MediaNotFoundError
-                | LoginFailed
-                | ProviderUnavailableError
-                | ResourceTemporarilyUnavailable
-                | RetriesExhausted,
-            ):
-                self.logger.debug("Could not retrieve details for %s: %s", episode.name, detail)
-                items.append(episode)
-            else:
-                raise detail
-        return items
-
-    async def browse(self, path: str) -> list[MediaItemType | BrowseFolder]:
-        """
-        Browse this provider's items.
-
-        :param path: The browse path to resolve.
-        """
-        item_path = path.split("://", 1)[1] if "://" in path else path
-
-        if not item_path:
-            # root level - special folders followed by subscribed podcasts
-            items: list[MediaItemType | BrowseFolder] = list(self._create_browse_folders())
-            for podcast_data in await self._client.get_subscribed_podcasts():
-                items.append(self._convert_podcast(podcast_data))
-            return items
-
-        if item_path in SPECIAL_FOLDERS:
-            return list(await self._get_special_folder_episodes(item_path))
-
-        return [episode async for episode in self.get_podcast_episodes(item_path)]
-
-    async def get_stream_details(self, item_id: str, media_type: MediaType) -> StreamDetails:
-        """
-        Get streamable URL and details for the given media item.
-
-        :param item_id: The episode item id (format: podcast_uuid:episode_uuid).
-        :param media_type: The media type of the item.
-        """
-        _, episode_uuid = item_id.split(":", 1)
-        episode_data = await self._client.get_episode_details(episode_uuid)
-
-        url = episode_data.get("url", "")
-        if not url:
-            raise MediaNotFoundError(f"No URL found for episode {item_id}")
-
-        return StreamDetails(
-            item_id=item_id,
-            provider=self.instance_id,
-            audio_format=AudioFormat(
-                content_type=ContentType.try_parse(episode_data.get("fileType", "audio/mpeg")),
-            ),
-            media_type=MediaType.PODCAST_EPISODE,
-            stream_type=StreamType.HTTP,
-            path=url,
-            duration=episode_data.get("duration"),
-            can_seek=True,
-            allow_seek=True,
-        )
-
-    @use_cache(3600 * 24)
-    async def search(
-        self, search_query: str, media_types: list[MediaType], limit: int = 5
-    ) -> SearchResults:
-        """
-        Search for podcasts.
-
-        :param search_query: The search query.
-        :param media_types: The media types to include in the search.
-        :param limit: The maximum number of items to return per type.
-        """
-        results = SearchResults()
-        if media_types and MediaType.PODCAST not in media_types:
-            return results
-        podcasts = await self._client.search_podcasts(search_query)
-        results.podcasts = [self._convert_podcast(podcast) for podcast in podcasts[:limit]]
-        return results
-
-    @use_cache(3600)
-    async def get_podcast_episode(self, prov_item_id: str) -> PodcastEpisode:
-        """
-        Get full details for a podcast episode.
-
-        :param prov_item_id: The episode item id (format: podcast_uuid:episode_uuid).
-        """
-        podcast_uuid, episode_uuid = prov_item_id.split(":", 1)
-        episode_data, show_notes, podcast_name = await asyncio.gather(
-            self._client.get_episode_details(episode_uuid),
-            self._get_show_notes(podcast_uuid),
-            self._get_podcast_name(podcast_uuid),
-        )
-        episode_item = self._convert_episode(
-            episode_data, podcast_uuid, show_notes.get(episode_uuid), podcast_name
-        )
-        if episode_item is None:
-            raise MediaNotFoundError(f"Episode {episode_uuid} not found in podcast {podcast_uuid}")
-
-        # the API sends explicit nulls for these fields, so a dict default is not enough
-        played_up_to = episode_data.get("playedUpTo") or 0
-        duration = episode_data.get("duration") or 0
-        playing_status = episode_data.get("playingStatus", 1)  # 1=unplayed, 2=in_progress, 3=played
-        if duration > 0:
-            episode_item.duration = duration
-        completed = playing_status == 3 or (
-            duration > 0 and (played_up_to / duration) > FULLY_PLAYED_THRESHOLD
-        )
-        episode_item.fully_played = completed
-        episode_item.resume_position_ms = 0 if completed else played_up_to * 1000
-
-        return episode_item
-
-    async def get_resume_position(
-        self, item_id: str, media_type: MediaType
-    ) -> tuple[bool, int, datetime | None]:
-        """
-        Return the (fully_played, position_ms, timestamp) resume point for an episode.
-
-        PocketCasts does not expose a reliable last-played timestamp, so the timestamp
-        is always None.
-
-        :param item_id: The episode item id (format: podcast_uuid:episode_uuid).
-        :param media_type: The media type (should be PODCAST_EPISODE).
-        """
-        _, episode_uuid = item_id.split(":", 1)
-
-        try:
-            in_progress = await self._client.get_in_progress_episodes()
-        except (ProviderUnavailableError, ResourceTemporarilyUnavailable, RetriesExhausted) as err:
-            # resume is best-effort; a transient failure should not break playback
-            LOGGER.warning("Could not fetch resume position for %s: %s", episode_uuid, err)
-            return (False, 0, None)
-
-        for ep in in_progress:
-            if ep.get("uuid") == episode_uuid:
-                played_up_to = int(ep.get("playedUpTo") or 0)  # seconds from API
-                duration = int(ep.get("duration") or 0)
-                fully_played = duration > 0 and (played_up_to / duration) > FULLY_PLAYED_THRESHOLD
-                LOGGER.debug(
-                    "Resume position for %s: %d ms (fully_played=%s)",
-                    episode_uuid,
-                    played_up_to * 1000,
-                    fully_played,
-                )
-                return (fully_played, played_up_to * 1000, None)
-
-        LOGGER.debug("No in-progress entry for %s; resuming from start", episode_uuid)
-        return (False, 0, None)
-
-    async def on_played(
-        self,
-        media_type: MediaType,
-        prov_item_id: str,
-        fully_played: bool,
-        position: int,
-        media_item: MediaItemType,
-        is_playing: bool = False,
-    ) -> None:
-        """
-        Sync playback progress for a podcast episode back to Pocket Casts.
-
-        Called by the Queue controller when a track is played, stopped/skipped, and
-        periodically while playing.
-
-        :param media_type: The media type of the played item.
-        :param prov_item_id: The provider item id (format: podcast_uuid:episode_uuid).
-        :param fully_played: Whether the episode was played to the end.
-        :param position: Last known position in seconds.
-        :param media_item: The full media item details.
-        :param is_playing: Whether the episode is currently playing.
-        """
-        if media_type != MediaType.PODCAST_EPISODE or not isinstance(media_item, PodcastEpisode):
-            return
-        podcast_uuid, episode_uuid = prov_item_id.split(":", 1)
-
-        # MA reports fully_played=True when an episode is skipped/stopped, not only when it
-        # truly ends, so confirm completion against the real position before marking it played.
-        duration = media_item.duration or 0
-        completed = fully_played and duration > 0 and position >= duration * FULLY_PLAYED_THRESHOLD
-        if completed:
-            self._announced_episodes.discard(episode_uuid)
-            await self._client.mark_episode_played(podcast_uuid, episode_uuid)
-            await self._client.remove_from_up_next(episode_uuid)
-            await self._client.archive_episode(podcast_uuid, episode_uuid, archive=True)
-        elif position == 0 and not is_playing:
-            # the user explicitly marked the episode as unplayed
-            self._announced_episodes.discard(episode_uuid)
-            await self._client.mark_episode_unplayed(podcast_uuid, episode_uuid)
-            await self._client.archive_episode(podcast_uuid, episode_uuid, archive=False)
-        else:
-            # on_played fires every progress tick, so mirror the start to Up Next/history only
-            # once per session - re-announcing each tick would re-bump Up Next and spam the API.
-            # A resume within the same session is intentionally not re-announced.
-            if is_playing and episode_uuid not in self._announced_episodes:
-                self._announced_episodes.add(episode_uuid)
-                await self._announce_playback_start(podcast_uuid, episode_uuid, media_item)
-            await self._client.update_episode_progress(podcast_uuid, episode_uuid, position)
-
-    def _convert_podcast(self, podcast_data: dict[str, Any]) -> Podcast:
-        """
-        Convert raw Pocket Casts podcast data to a Podcast object.
-
-        :param podcast_data: Raw podcast data from the subscribed-list or full-podcast endpoint.
-        """
-        uuid = podcast_data["uuid"]
-        return Podcast(
-            item_id=uuid,
-            provider=self.instance_id,
-            name=podcast_data.get("title", ""),
-            publisher=podcast_data.get("author"),
-            provider_mappings={
-                ProviderMapping(
-                    item_id=uuid,
-                    provider_domain=self.domain,
-                    provider_instance=self.instance_id,
-                )
-            },
-            metadata=MediaItemMetadata(
-                description=podcast_data.get("description"),
-                images=UniqueList(
-                    [
-                        MediaItemImage(
-                            type=ImageType.THUMB,
-                            path=f"https://static.pocketcasts.com/discover/images/280/{uuid}.jpg",
-                            provider=self.instance_id,
-                            remotely_accessible=True,
-                        )
-                    ]
-                ),
-            ),
-        )
-
-    async def _get_podcast_name(self, prov_podcast_id: str) -> str:
-        """Return a podcast's name, empty when it cannot be looked up."""
-        # the podcast lookup is cached, so this is one call per podcast per day at most
-        try:
-            return (await self.get_podcast(prov_podcast_id)).name
-        except (
-            MediaNotFoundError,
-            LoginFailed,
-            ProviderUnavailableError,
-            ResourceTemporarilyUnavailable,
-            RetriesExhausted,
-        ) as err:
-            self.logger.debug("Could not retrieve podcast name for %s: %s", prov_podcast_id, err)
-            return ""
-
-    async def _get_show_notes(self, prov_podcast_id: str) -> dict[str, dict[str, Any]]:
-        """Return show notes per episode uuid, empty when they cannot be read."""
-        # show notes are supplementary, so a failure here must never break episode
-        # resolution. The failure itself is not cached, so the next call tries again.
-        try:
-            return await self._fetch_show_notes(prov_podcast_id)
-        except (
-            LoginFailed,
-            ProviderUnavailableError,
-            ResourceTemporarilyUnavailable,
-            RetriesExhausted,
-        ) as err:
-            self.logger.debug("Could not retrieve show notes for %s: %s", prov_podcast_id, err)
-            return {}
-
-    @use_cache(3600 * 24)
-    async def _fetch_show_notes(self, prov_podcast_id: str) -> dict[str, dict[str, Any]]:
-        """Return show notes per episode uuid for the given podcast."""
-        return await self._client.get_show_notes(prov_podcast_id)
-
-    def _convert_episode(
-        self,
-        episode_data: dict[str, Any],
-        podcast_uuid: str,
-        show_notes: dict[str, Any] | None = None,
-        podcast_name: str = "",
-        position: int = 0,
-    ) -> PodcastEpisode | None:
-        """
-        Convert episode data to a PodcastEpisode, or None when it carries no episode uuid.
-
-        :param position: The episode's listing position. Defaults to 0 (unknown).
-        """
-        episode_uuid = episode_data.get("uuid")
-        if not episode_uuid:
-            return None
-
-        # this is fed by two endpoints with different field schemas: the full-podcast JSON
-        # uses snake_case (file_type) while /user/episode uses camelCase (fileType,
-        # episodeNumber). Neither carries the description or artwork, which is what the
-        # separate show notes lookup is for.
-        item_id = f"{podcast_uuid}:{episode_uuid}"
-        file_type = episode_data.get("fileType") or episode_data.get("file_type", "audio/mpeg")
-        episode_item = PodcastEpisode(
-            item_id=item_id,
-            provider=self.instance_id,
-            name=episode_data.get("title", "Unknown Episode"),
-            podcast=ItemMapping(
-                media_type=MediaType.PODCAST,
-                item_id=podcast_uuid,
-                provider=self.instance_id,
-                name=podcast_name,
-            ),
-            position=position,
-            provider_mappings={
-                ProviderMapping(
-                    item_id=item_id,
-                    provider_domain=self.domain,
-                    provider_instance=self.instance_id,
-                    audio_format=AudioFormat(content_type=ContentType.try_parse(file_type)),
-                    url=episode_data.get("url", ""),
-                )
-            },
-        )
-        if episode_data.get("duration"):
-            episode_item.duration = int(episode_data["duration"])
-        if title := episode_data.get("title"):
-            episode_item.metadata.label = title
-        details = show_notes or {}
-        if description := details.get("description"):
-            episode_item.metadata.description = description
-        # only about half the episodes have their own artwork, the rest keep the podcast cover
-        image_url = details.get("image") or (
-            f"https://static.pocketcasts.com/discover/images/280/{podcast_uuid}.jpg"
-        )
-        episode_item.metadata.images = UniqueList(
-            [
-                MediaItemImage(
-                    type=ImageType.THUMB,
-                    path=image_url,
-                    provider=self.instance_id,
-                    remotely_accessible=True,
-                )
-            ]
-        )
-        return episode_item
-
-    def _enrich_episode_with_status(
-        self,
-        episode_item: PodcastEpisode,
-        episode_data: dict[str, Any],
-        in_progress_map: dict[str | None, dict[str, Any]],
-        history_map: dict[str | None, dict[str, Any]],
-    ) -> None:
-        """
-        Apply playback status to a PodcastEpisode from the in-progress/history data.
-
-        :param episode_item: The episode object to enrich in place.
-        :param episode_data: Raw episode data dict from the API.
-        :param in_progress_map: UUID-keyed map of in-progress episode data.
-        :param history_map: UUID-keyed map of listen-history episode data.
-        """
-        episode_uuid = episode_data.get("uuid")
-        # history is "recently played", not "completed" - rely on the entry's real progress,
-        # never on mere history membership. Both fields are always set so the library sync can
-        # clear a stale completed/resume value (it only updates when both are non-None).
-        status_data = in_progress_map.get(episode_uuid) or history_map.get(episode_uuid) or {}
-        # feeds that omit a duration yield an explicit null rather than a missing key, so
-        # coerce instead of relying on a dict default
-        played_up_to = status_data.get("playedUpTo") or 0
-        duration = status_data.get("duration") or episode_data.get("duration") or 0
-        completed = status_data.get("playingStatus") == 3 or (
-            duration > 0 and (played_up_to / duration) > FULLY_PLAYED_THRESHOLD
-        )
-        episode_item.fully_played = completed
-        episode_item.resume_position_ms = 0 if completed else played_up_to * 1000
-
-    async def _get_special_folder_episodes(self, folder_name: str) -> list[PodcastEpisode]:
-        """
-        Get episodes for a special browse folder.
-
-        :param folder_name: Name of the special folder (up_next, new_releases, etc.)
-        """
-        folder_getters = {
-            "up_next": self._client.get_up_next_episodes,
-            "new_releases": self._client.get_new_releases,
-            "in_progress": self._client.get_in_progress_episodes,
-            "starred": self._client.get_starred_episodes,
-            "history": self._client.get_history,
-        }
-        episode_list = await folder_getters[folder_name]()
-
-        # (episode, podcast uuid, podcast name) per episode, the name empty when the folder
-        # payload does not carry it
-        resolved: list[tuple[dict[str, Any], str, str]] = []
-        for episode_data in episode_list:
-            # the podcast reference is a string on some endpoints and an object on others
-            podcast_field = episode_data.get("podcast")
-            podcast_uuid: str | None
-            if isinstance(podcast_field, str):
-                podcast_uuid = podcast_field
-            elif isinstance(podcast_field, dict):
-                podcast_uuid = podcast_field.get("uuid")
-            else:
-                podcast_uuid = episode_data.get("podcastUuid")
-
-            if not podcast_uuid:
-                continue
-            # these folders mix podcasts, so the name is not known up front. Take it from the
-            # payload where that carries it, in either of the two shapes
-            payload_name = podcast_field.get("title") if isinstance(podcast_field, dict) else None
-            resolved.append(
-                (
-                    episode_data,
-                    podcast_uuid,
-                    payload_name or episode_data.get("podcastTitle") or "",
-                )
-            )
-
-        # every remaining name costs a full-podcast fetch, so look them up once per podcast and
-        # all at once: serialising them would stall the browse for as long as the folder is deep
-        missing = list({uuid for _, uuid, name in resolved if not name})
-        looked_up = await asyncio.gather(*(self._get_podcast_name(uuid) for uuid in missing))
-        names = dict(zip(missing, looked_up, strict=True))
-
-        items: list[PodcastEpisode] = []
-        for episode_data, podcast_uuid, podcast_name in resolved:
-            if episode_item := self._convert_episode(
-                episode_data,
-                podcast_uuid,
-                show_notes=None,
-                podcast_name=podcast_name or names.get(podcast_uuid, ""),
-            ):
-                items.append(episode_item)
-        return items
-
-    def _create_browse_folders(self) -> list[BrowseFolder]:
-        """Create special browse folders for root level."""
-        folders = [
-            ("up_next", "Up Next"),
-            ("new_releases", "New Releases"),
-            ("in_progress", "In Progress"),
-            ("starred", "Starred"),
-            ("history", "History"),
-        ]
-        return [
-            BrowseFolder(
-                item_id=folder_id,
-                provider=self.instance_id,
-                path=f"{self.instance_id}://{folder_id}",
-                name=name,
-                image=MediaItemImage(
-                    type=ImageType.THUMB,
-                    path=BROWSE_FOLDER_ICONS[folder_id],
-                    provider=self.instance_id,
-                    remotely_accessible=True,
-                ),
-            )
-            for folder_id, name in folders
-        ]
-
-    def _get_up_next_playlist(self) -> Playlist:
-        """Return the playlist that mirrors the user's Up Next queue."""
-        return Playlist(
-            item_id=UP_NEXT_PLAYLIST_ID,
-            provider=self.instance_id,
-            name="Up Next",
-            owner="Pocket Casts",
-            is_editable=False,
-            supported_mediatypes={MediaType.PODCAST_EPISODE},
-            provider_mappings={
-                ProviderMapping(
-                    item_id=UP_NEXT_PLAYLIST_ID,
-                    provider_domain=self.domain,
-                    provider_instance=self.instance_id,
-                    # every account has its own Up Next queue
-                    is_unique=True,
-                )
-            },
-            metadata=MediaItemMetadata(
-                images=UniqueList(
-                    [
-                        MediaItemImage(
-                            type=ImageType.THUMB,
-                            path=BROWSE_FOLDER_ICONS[UP_NEXT_PLAYLIST_ID],
-                            provider=self.instance_id,
-                            remotely_accessible=True,
-                        )
-                    ]
-                ),
-            ),
-        )
-
-    async def _announce_playback_start(
-        self, podcast_uuid: str, episode_uuid: str, episode: PodcastEpisode
-    ) -> None:
-        """
-        Mirror a playback start to Pocket Casts by adding the episode to Up Next and history.
-
-        :param podcast_uuid: The podcast UUID.
-        :param episode_uuid: The episode UUID.
-        :param episode: The episode that started playing.
-        """
-        # source the url from the already-loaded item so no extra API call is needed; filtered
-        # to our own mapping since merged library items can carry other providers' mappings
-        url = next(
-            (
-                mapping.url
-                for mapping in episode.provider_mappings
-                if mapping.provider_instance == self.instance_id and mapping.url
-            ),
-            "",
-        )
-        await self._client.play_now(
-            episode_uuid=episode_uuid, podcast_uuid=podcast_uuid, title=episode.name, url=url
-        )
-        await self._client.add_to_history(
-            episode_uuid=episode_uuid, podcast_uuid=podcast_uuid, title=episode.name, url=url
-        )

kubernetes/apps/navidrome/lidarr.yaml

@@ -93,7 +93,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: lidarr
-          image: lscr.io/linuxserver/lidarr:3.1.6.5079-ls46 # {"$imagepolicy": "flux-system:lidarr"}
+          image: lscr.io/linuxserver/lidarr:3.1.0.4875-ls45 # {"$imagepolicy": "flux-system:lidarr"}
           env:
             - name: PUID
               value: "1000"
@@ -140,7 +140,7 @@ spec:
               drop: ["ALL"]
               add: ["CHOWN", "DAC_OVERRIDE", "FOWNER", "SETGID", "SETUID"]
         - name: reconcile
-          image: lscr.io/linuxserver/lidarr:3.1.6.5079-ls46 # {"$imagepolicy": "flux-system:lidarr"}
+          image: lscr.io/linuxserver/lidarr:3.1.0.4875-ls45 # {"$imagepolicy": "flux-system:lidarr"}
           command: ["sh", "/scripts/reconcile.sh"]
           volumeMounts:
             - name: config

kubernetes/apps/otbr/dataset-bootstrap.yaml

@@ -74,7 +74,7 @@ spec:
           # alpine/kubectl is the maintained replacement. Pin the tag
           # to the cluster's server version so kubectl is in lock-step
           # (mismatched skew can break exec streaming).
-          image: docker.io/alpine/kubectl:1.37.1@sha256:a5d0fbecab3f7b6c2ab7398f1daa73a3e0ed6ece18556d21698233e9e3759cc7
+          image: docker.io/alpine/kubectl:1.37.1@sha256:b568e8beb6a79aee269c142343078a278b85e7710f1c0e7d8d6b21d1eb566a48
           env:
             - name: DATASET_TLV
               valueFrom:

kubernetes/apps/otbr/deployment.yaml

@@ -47,7 +47,7 @@ spec:
         #
         # Hence socat is installed at startup and run inside this container.
         - name: otbr
-          image: openthread/otbr:latest@sha256:f3e43ccd86d6da87323873efa0c9b6f92a2a8cc75a804ea50e34c96680363e2e
+          image: openthread/otbr:latest@sha256:a1ccea58241c2e0c2e16a55590cdd5651336462c3b4fa26e24a59607e155ef72
           command:
             - bash
             - -c

kubernetes/apps/paperless/ftp-scanner.yaml

@@ -22,7 +22,7 @@ spec:
           type: RuntimeDefault
       initContainers:
         - name: prepare-dirs
-          image: alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a
+          image: alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
           command:
             - sh
             - -c

kubernetes/apps/paperless/gotenberg.yaml

@@ -22,7 +22,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: gotenberg
-          image: gotenberg/gotenberg:8.39.0 # {"$imagepolicy": "flux-system:gotenberg"}
+          image: gotenberg/gotenberg:8.38.1 # {"$imagepolicy": "flux-system:gotenberg"}
           args:
             - "gotenberg"
             - "--chromium-disable-javascript=true"

kubernetes/apps/paperless/paperless.yaml

@@ -287,7 +287,7 @@ spec:
               add: ["CHOWN", "DAC_OVERRIDE", "FOWNER", "SETGID", "SETUID"]
         # anchor: bridge-tls-proxy
         - name: bridge-tls-proxy
-          image: alpine/socat:1.8.1.3@sha256:603174b77eebaba25ba8f8ebb15e1234d6600409554e95d6fb203fd106150287
+          image: alpine/socat:1.8.1.3@sha256:fb3862c949af7c79996d0e514ee96128644d840835ed5368eeecb14a869de361
           args:
             - "-d"
             - "TCP-LISTEN:11143,fork,reuseaddr,bind=127.0.0.1"

kubernetes/apps/paperless/redis.yaml

@@ -25,7 +25,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: redis
-          image: redis:8.10.3-alpine # {"$imagepolicy": "flux-system:redis-paperless"}
+          image: redis:8.10.2-alpine # {"$imagepolicy": "flux-system:redis-paperless"}
           args:
             - redis-server
             - --save

kubernetes/apps/paperless/syncthing.yaml

@@ -50,7 +50,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: syncthing
-          image: syncthing/syncthing:2.1.7@sha256:2b71da7c0d0a91a6ae5285ad079226fecc0a365d08b27720e1f7037b018f7546
+          image: syncthing/syncthing:2.1.6@sha256:4d0281bdcb4ed9baf503d251d0544ddd856f49fce3f114056257ae172b7fb670
           env:
             # UI bind: any-interface so the ClusterIP Service can reach
             # it. Network exposure is gated by the absence of an Ingress

kubernetes/apps/renovate/cronjob.yaml

@@ -59,7 +59,7 @@ spec:
             - name: renovate
               # Pinned by tag and digest. Renovate updates itself through
               # homelab's renovate.json, like any other image here.
-              image: docker.io/renovate/renovate:44.181.8@sha256:b28b2de1dfd35de7e8198756d7f7cdd84ebc28c3f25e80f5b09e598d3faefb2a
+              image: docker.io/renovate/renovate:44.151.2@sha256:9ea828b38867af0ca5f269e6c5feace9e74e7f035da150bb16f8c5f70bf2e6e8
               env:
                 - name: RENOVATE_CONFIG_FILE
                   value: /config/config.json

kubernetes/apps/review-bot/deployment.yaml

@@ -32,7 +32,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: review-bot
-          image: gitea.renner.uno/gitea_admin/review-bot:2026-10-27-0757 # {"$imagepolicy": "flux-system:review-bot"}
+          image: gitea.renner.uno/gitea_admin/review-bot:2026-10-22-1854 # {"$imagepolicy": "flux-system:review-bot"}
           env:
             - name: REPOS
               value: konairius/homelab,konairius/homeassistant,konairius/authentik-samba-bridge,konairius/shelly-manager

kubernetes/apps/trmnl/valkey.yaml

@@ -27,7 +27,7 @@ spec:
         # Valkey major version tracks upstream's compose.yml (9.x). Sidekiq
         # is the only consumer; a major bump is a separate migration.
         - name: valkey
-          image: valkey/valkey:9.1.3-alpine # {"$imagepolicy": "flux-system:valkey-trmnl"}
+          image: valkey/valkey:9.1.2-alpine # {"$imagepolicy": "flux-system:valkey-trmnl"}
           args:
             - valkey-server
             - --save

kubernetes/apps/wiki/cronjobs.yaml

@@ -1,152 +0,0 @@
-# The wiki's schedules. The service runs nothing on its own clock; these jobs
-# call its API with the `scheduler` key. Run one now:
-#   kubectl -n ai create job --from=cronjob/wiki-encyclopedia wiki-encyclopedia-now
-# Generated once in-cluster, nothing in OpenBao.
-apiVersion: generators.external-secrets.io/v1alpha1
-kind: Password
-metadata:
-  name: wiki-scheduler-key
-  namespace: ai
-spec:
-  length: 64
-  digits: 16
-  symbols: 0
-  allowRepeat: true
-  noUpper: false
-  secretKeys:
-    - Auth__ApiKeys__scheduler
----
-apiVersion: external-secrets.io/v1
-kind: ExternalSecret
-metadata:
-  name: wiki-scheduler-key
-  namespace: ai
-spec:
-  refreshPolicy: CreatedOnce
-  target:
-    name: wiki-scheduler-key
-  dataFrom:
-    - sourceRef:
-        generatorRef:
-          apiVersion: generators.external-secrets.io/v1alpha1
-          kind: Password
-          name: wiki-scheduler-key
----
-# Interval sync; the Gitea push webhook is the fast path.
-apiVersion: batch/v1
-kind: CronJob
-metadata:
-  name: wiki-sync
-  namespace: ai
-  labels:
-    app.kubernetes.io/name: wiki-sync
-spec:
-  schedule: "*/30 * * * *"
-  timeZone: Etc/UTC
-  concurrencyPolicy: Forbid
-  successfulJobsHistoryLimit: 1
-  failedJobsHistoryLimit: 3
-  startingDeadlineSeconds: 600
-  jobTemplate:
-    spec:
-      backoffLimit: 0
-      activeDeadlineSeconds: 1800
-      ttlSecondsAfterFinished: 86400
-      template:
-        metadata:
-          labels:
-            app.kubernetes.io/name: wiki-sync
-        spec:
-          restartPolicy: Never
-          enableServiceLinks: false
-          automountServiceAccountToken: false
-          securityContext:
-            runAsNonRoot: true
-            runAsUser: 65534
-            runAsGroup: 65534
-            seccompProfile:
-              type: RuntimeDefault
-          containers:
-            - name: sync
-              image: curlimages/curl:8.22.0@sha256:58adaa4e8dca9c988bae2aba4ab3434a0bb2da16bbe3f92dec39ec7785166777
-              command:
-                - sh
-                - -c
-                - 'curl -fsS --retry 12 --retry-delay 10 --retry-connrefused --retry-max-time 120 --max-time 1700 -X POST -H "X-Api-Key: $API_KEY" http://wiki.ai.svc.cluster.local:8080/api/v1/sync'
-              env:
-                - name: API_KEY
-                  valueFrom:
-                    secretKeyRef:
-                      name: wiki-scheduler-key
-                      key: Auth__ApiKeys__scheduler
-              resources:
-                requests:
-                  cpu: 5m
-                  memory: 16Mi
-                limits:
-                  memory: 64Mi
-              securityContext:
-                allowPrivilegeEscalation: false
-                readOnlyRootFilesystem: true
-                capabilities:
-                  drop: ["ALL"]
----
-# Plans and writes the house encyclopedia (/house). The endpoint syncs first and
-# answers 502 when the run fails or the Anthropic API stopped it.
-apiVersion: batch/v1
-kind: CronJob
-metadata:
-  name: wiki-encyclopedia
-  namespace: ai
-  labels:
-    app.kubernetes.io/name: wiki-encyclopedia
-spec:
-  schedule: "0 6 * * *"
-  timeZone: Europe/Berlin
-  concurrencyPolicy: Forbid
-  successfulJobsHistoryLimit: 3
-  failedJobsHistoryLimit: 3
-  startingDeadlineSeconds: 3600
-  jobTemplate:
-    spec:
-      backoffLimit: 0
-      activeDeadlineSeconds: 11400
-      ttlSecondsAfterFinished: 604800
-      template:
-        metadata:
-          labels:
-            app.kubernetes.io/name: wiki-encyclopedia
-        spec:
-          restartPolicy: Never
-          enableServiceLinks: false
-          automountServiceAccountToken: false
-          securityContext:
-            runAsNonRoot: true
-            runAsUser: 65534
-            runAsGroup: 65534
-            seccompProfile:
-              type: RuntimeDefault
-          containers:
-            - name: run
-              image: curlimages/curl:8.22.0@sha256:58adaa4e8dca9c988bae2aba4ab3434a0bb2da16bbe3f92dec39ec7785166777
-              command:
-                - sh
-                - -c
-                - 'curl -fsS --max-time 10800 -X POST -H "X-Api-Key: $API_KEY" http://wiki.ai.svc.cluster.local:8080/api/v1/encyclopedia/run'
-              env:
-                - name: API_KEY
-                  valueFrom:
-                    secretKeyRef:
-                      name: wiki-scheduler-key
-                      key: Auth__ApiKeys__scheduler
-              resources:
-                requests:
-                  cpu: 5m
-                  memory: 16Mi
-                limits:
-                  memory: 64Mi
-              securityContext:
-                allowPrivilegeEscalation: false
-                readOnlyRootFilesystem: true
-                capabilities:
-                  drop: ["ALL"]

kubernetes/apps/wiki/deployment.yaml

@@ -24,7 +24,7 @@ metadata:
   namespace: ai
   annotations:
     # Keys, tokens and the Anthropic key arrive via envFrom; a rotated Secret rolls the pod.
-    secret.reloader.stakater.com/reload: wiki-gitea,wiki-api-keys,wiki-scheduler-key,wiki-typesafe,wiki-anthropic,wiki-api-basic-auth
+    secret.reloader.stakater.com/reload: wiki-gitea,wiki-api-keys,wiki-typesafe,wiki-anthropic,wiki-api-basic-auth
   labels:
     app.kubernetes.io/name: wiki
 spec:
@@ -53,7 +53,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: wiki
-          image: gitea.renner.uno/konairius/wiki:build.1793086240 # {"$imagepolicy": "flux-system:wiki"}
+          image: gitea.renner.uno/konairius/wiki:build.1792419299 # {"$imagepolicy": "flux-system:wiki"}
           securityContext:
             allowPrivilegeEscalation: false
             readOnlyRootFilesystem: true
@@ -77,10 +77,6 @@ spec:
               value: https://auth.renner.uno/application/o/wiki/
             - name: Auth__Oidc__ClientId
               value: wiki
-            - name: Wiki__Encyclopedia__Enabled
-              value: "true"
-            - name: Wiki__Encyclopedia__MaxArticles
-              value: "0"
             # wiki-index BasicAuth users (htpasswd), checked by the service for the read API.
             - name: Auth__Basic__UsersPath
               value: /var/run/secrets/wiki-basic-auth
@@ -89,9 +85,6 @@ spec:
                 name: wiki-gitea
             - secretRef:
                 name: wiki-api-keys
-            # The key the wiki-sync and wiki-encyclopedia CronJobs call with (cronjobs.yaml).
-            - secretRef:
-                name: wiki-scheduler-key
             - secretRef:
                 name: wiki-typesafe
             - secretRef:

kubernetes/apps/wiki/kustomization.yaml

@@ -4,4 +4,3 @@ resources:
   - externalsecrets.yaml
   - deployment.yaml
   - ingress.yaml
-  - cronjobs.yaml

kubernetes/infrastructure-inhouse/bird/daemonset.yaml

@@ -69,7 +69,7 @@ spec:
           # first build of that day — imagePullPolicy: Always does not help,
           # because the tag itself resolves stale. Update this when the image
           # is rebuilt.
-          image: gitea.renner.uno/gitea_admin/bird@sha256:65fc93efead1e9b065d2c78e748f6c3c1ad7216e28b757d9fa4e204fa2ffe9a9
+          image: gitea.renner.uno/gitea_admin/bird@sha256:afd8c3a1fc21a9f2c67af366b3bf77ca9b948f07f66a4977821e4972c8fa6ae4
           command: ["/bin/sh", "-c"]
           args:
             - |
@@ -95,7 +95,7 @@ spec:
               mountPath: /etc/bird
       containers:
         - name: bird
-          image: gitea.renner.uno/gitea_admin/bird@sha256:65fc93efead1e9b065d2c78e748f6c3c1ad7216e28b757d9fa4e204fa2ffe9a9
+          image: gitea.renner.uno/gitea_admin/bird@sha256:afd8c3a1fc21a9f2c67af366b3bf77ca9b948f07f66a4977821e4972c8fa6ae4
           resources:
             requests:
               cpu: "50m"

kubernetes/infrastructure/coredns-config/configmap.yaml

@@ -0,0 +1,74 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: coredns
+  namespace: kube-system
+data:
+  Corefile: |
+    # Delegate renner.uno to the in-cluster k8s_gateway resolver. It
+    # watches Ingress resources and synthesises A/AAAA records that
+    # point at the ingress-nginx LB, so pods resolving `auth.renner.uno`,
+    # `audiobooks.renner.uno`, … stay inside the cluster. Names not
+    # backed by an in-cluster Ingress fall through inside k8s_gateway
+    # itself to the UDM (10.2.40.1 / fd00::1), which serves the split-horizon
+    # renner.uno zone, preserving resolution of LXC/VM + physical services.
+    # (The old Proxmox DNS VIP 10.2.40.53 is DECOMMISSIONED.) 10.96.0.11 is a
+    # pinned ClusterIP of the k8s-gateway Service — avoids DNS-name
+    # resolution during CoreDNS startup.
+    # Cache tuning mirrors k8s-gateway's (issue #393): the UDM's dnsmasq
+    # refuses connections in bursts, and because the public renner.uno zone
+    # has a *.renner.uno wildcard CNAME that matches at every depth, a local
+    # failure never returns NXDOMAIN — it resolves to the WAN proxy instead.
+    # Correct answers carry TTL 5 (dnsmasq lease records) while the wrong
+    # wildcard answer carries TTL 300, so one brief blip pins a wrong answer
+    # for minutes. `success ... 60` raises the 5s TTL to a 60s floor and
+    # `serve_stale 1h immediate` keeps serving through an upstream outage.
+    # NOTE: only cache/serve_stale — the `template` plugin is deliberately NOT
+    # reintroduced here (it broke cluster DNS in 7a09bad5).
+    renner.uno:53 {
+        errors
+        cache 300 {
+            success 9984 300 60
+            denial 9984 300 30
+            serve_stale 1h immediate
+        }
+        forward . 10.96.0.11
+        loop
+        reload
+    }
+
+    .:53 {
+        errors
+        health {
+            lameduck 5s
+        }
+        ready
+        log . {
+            class error
+        }
+        prometheus :9153
+
+        kubernetes cluster.local in-addr.arpa ip6.arpa {
+            pods insecure
+            fallthrough in-addr.arpa ip6.arpa
+            ttl 30
+        }
+        forward . /etc/resolv.conf {
+           max_concurrent 1000
+        }
+        # serve_stale mirrors the renner.uno:53 block (issue #393): when the
+        # upstream resolver browns out, keep answering from expired cache
+        # instead of SERVFAILing every public name cluster-wide. Seen on
+        # 2026-07-30 01:22-01:26Z (~1150 SERVFAILs) — it killed a Velero Kopia
+        # maintenance job, which runs with backoffLimit 0, on the Hetzner S3
+        # endpoint (issue #439). cluster.local is exempt from the cache above,
+        # so in-cluster Service records are never served stale.
+        cache 30 {
+           disable success cluster.local
+           disable denial cluster.local
+           serve_stale 1h immediate
+        }
+        loop
+        reload
+        loadbalance
+    }

kubernetes/infrastructure/coredns-config/kustomization.yaml

@@ -1,6 +1,5 @@
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
-# CoreDNS itself (Deployment, Corefile) is a Talos bootstrap manifest; only
-# its LoadBalancer Service lives here.
 resources:
+  - configmap.yaml
   - service.yaml

kubernetes/infrastructure/k8s-gateway/helmrelease.yaml

@@ -85,11 +85,10 @@ spec:
             parameters: "0.0.0.0:9153"
     serviceType: ClusterIP
     service:
-      # Pinned because the nodes' resolver names it by address
-      # (ResolverConfig in the Talos site patches); CoreDNS forwards to the
-      # node, so every name reaches k8s-gateway that way. Chosen from the
-      # low, sparsely populated end of the service CIDR (kube-dns is
-      # 10.96.0.10).
+      # Pinned so the main CoreDNS Corefile can forward renner.uno
+      # here without depending on DNS-based Service resolution during
+      # CoreDNS startup (chicken-and-egg). Chosen from the low, sparsely
+      # populated end of the service CIDR (kube-dns is 10.96.0.10).
       clusterIP: 10.96.0.11
       ipFamilyPolicy: PreferDualStack
   # The site's upstream resolvers (deployment.dnsPolicy/dnsConfig), from the

kubernetes/infrastructure/multus/cni-dhcp-daemon.yaml

@@ -71,7 +71,7 @@ spec:
         # socket's parent, and refuses to start if the socket file is left
         # over from an unclean shutdown (bind: address already in use).
         - name: clean-socket
-          image: alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a
+          image: alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
           command: ["sh", "-c", "rm -f /run/cni/dhcp.sock"]
           volumeMounts:
             - name: run-cni
@@ -83,7 +83,7 @@ spec:
           # Any image with a shell works: the binary executed here is the
           # host's, bind-mounted from /opt/cni/bin. Pinned to the same
           # alpine tag the sibling installer uses.
-          image: alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a
+          image: alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
           command:
             - /opt/cni/bin/dhcp
             - daemon

kubernetes/infrastructure/network-policies/ai-ns.yaml

@@ -87,9 +87,11 @@ spec:
             - port: "53"
               protocol: UDP
     # host/remote-node: kubelet probes + node-local reach (Ceph mons on host net)
+    # world: image pulls and llama-server's Hugging Face model download
     - toEntities:
         - host
         - remote-node
+        - world
     # ICMP — egress mirror; see ingress block above.
     - toEndpoints:
         - matchExpressions:
@@ -164,76 +166,3 @@ spec:
         - ports:
             - port: "8080"
               protocol: TCP
----
-# Hugging Face model download on cold cache (llama-server, llama-embed, wiki-embed).
-apiVersion: cilium.io/v2
-kind: CiliumNetworkPolicy
-metadata:
-  name: models-egress-huggingface
-  namespace: ai
-spec:
-  endpointSelector:
-    matchExpressions:
-      - key: app.kubernetes.io/name
-        operator: In
-        values:
-          - llama-server
-          - llama-embed
-          - wiki-embed
-  egress:
-    # rules.dns lets Cilium learn the toFQDNs mapping
-    - toEndpoints:
-        - matchLabels:
-            "k8s:io.kubernetes.pod.namespace": kube-system
-            k8s-app: kube-dns
-      toPorts:
-        - ports:
-            - port: "53"
-              protocol: UDP
-            - port: "53"
-              protocol: TCP
-          rules:
-            dns:
-              - matchPattern: "*"
-    - toFQDNs:
-        - matchName: "huggingface.co"
-        - matchName: "hf.co"
-        - matchPattern: "*.huggingface.co"
-        - matchPattern: "*.hf.co"
-      toPorts:
-        - ports:
-            - port: "443"
-              protocol: TCP
----
-# wiki: Anthropic API (distillation) and TypeSafe API (typed judgements).
-apiVersion: cilium.io/v2
-kind: CiliumNetworkPolicy
-metadata:
-  name: wiki-egress-apis
-  namespace: ai
-spec:
-  endpointSelector:
-    matchLabels:
-      app.kubernetes.io/name: wiki
-  egress:
-    # rules.dns lets Cilium learn the toFQDNs mapping
-    - toEndpoints:
-        - matchLabels:
-            "k8s:io.kubernetes.pod.namespace": kube-system
-            k8s-app: kube-dns
-      toPorts:
-        - ports:
-            - port: "53"
-              protocol: UDP
-            - port: "53"
-              protocol: TCP
-          rules:
-            dns:
-              - matchPattern: "*"
-    - toFQDNs:
-        - matchName: "api.anthropic.com"
-        - matchName: "api.typesafe.ai"
-      toPorts:
-        - ports:
-            - port: "443"
-              protocol: TCP

kubernetes/infrastructure/network-policies/audiobookshelf-ns.yaml

@@ -66,9 +66,11 @@ spec:
             - port: "53"
               protocol: UDP
     # host/remote-node: kubelet probes + node-local reach (Ceph mons on host net)
+    # world: image pulls, OBC S3 endpoint reachable via the cluster's LB IP, migration pipeline API
     - toEntities:
         - host
         - remote-node
+        - world
     # ICMP — egress mirror; see ingress block above.
     - toEndpoints:
         - matchExpressions:
@@ -92,19 +94,3 @@ spec:
             - { type: 135, family: IPv6 }
             - { type: 136, family: IPv6 }
             - { type: 143, family: IPv6 }
----
-# audiobookshelf (metadata providers) and libation (Audible): HTTPS to the internet.
-apiVersion: cilium.io/v2
-kind: CiliumNetworkPolicy
-metadata:
-  name: audiobookshelf-egress-https
-  namespace: audiobookshelf
-spec:
-  endpointSelector: {}
-  egress:
-    - toEntities:
-        - world
-      toPorts:
-        - ports:
-            - port: "443"
-              protocol: TCP