fix(review-bot): post a review verdict, never a comment

The bot posted COMMENT whenever the agent said comment, gave no
verdict, or approved with a red or yellow section. A COMMENT is no
review verdict, so the PR showed no approval or rejection by the bot.

Every review is now APPROVED or REQUEST_CHANGES. Only blocking findings
request changes: the verdict request-changes, a Blocking section, or an
empty change. Suggestions, nits and unverified points stay in the body
of an approval. An answer without a verdict line is not posted; the
review fails instead of guessing. The prompt offers only request-changes
and approve.

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

.woodpecker/build-ci-images.yml

@@ -454,6 +454,32 @@ steps:
           --destination gitea.renner.uno/gitea_admin/kuma-sync:$TAG \
           --destination gitea.renner.uno/gitea_admin/kuma-sync:latest
 
+  # cloudflare-lb-sync: reconciles CloudflareLoadBalancer resources into
+  # Cloudflare. Its unit tests run as a stage of the image build.
+  - name: build-cloudflare-lb-sync
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    directory: ci/images/cloudflare-lb-sync
+    when:
+      - event: deployment
+      - event: push
+        path: ["ci/images/cloudflare-lb-sync/**", ".woodpecker/build-ci-images.yml"]
+    environment:
+      GITEA_USER: gitea_admin
+      GITEA_TOKEN:
+        from_secret: ci_images_token
+    commands:
+      - mkdir -p /kaniko/.docker
+      - AUTH=$(printf '%s:%s' "$GITEA_USER" "$GITEA_TOKEN" | base64 | tr -d '\n')
+      - printf '{"auths":{"gitea.renner.uno":{"auth":"%s"}}}' "$AUTH" > /kaniko/.docker/config.json
+      # YYYY-MM-DD-HHMM: the image-automation ImagePolicy picks the newest.
+      - TAG=$(date +%Y-%m-%d-%H%M)
+      - |
+        /kaniko/executor \
+          --context . \
+          --dockerfile Containerfile \
+          --destination gitea.renner.uno/gitea_admin/cloudflare-lb-sync:$TAG \
+          --destination gitea.renner.uno/gitea_admin/cloudflare-lb-sync:latest
+
   # bird: BGP daemon for the pod-network mesh over pod0 (#576). Runtime
   # artifact like heating-can; same registry so the audit tracks it.
   - name: build-bird

.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:v3.15.0@sha256:efd719c99d83b060d9daefdcf00360461adf279f45ef5391f8d111892118753e
+    image: prom/prometheus:v3.15.1@sha256:fa3302279710be2f21a8301ec17a8b4f2301fd829bd113839b3b6b02b6f191a2
     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:2.1.303
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
     commands:
       - sh scripts/ci/test-model-selection.sh
 
   - name: pr-review-mistral-tests
     depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.303
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
     commands:
       - sh scripts/ci/test-pr-review-mistral.sh
 
   - name: promtool-rules-guard-tests
     depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.303
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
     commands:
       - sh scripts/ci/test-promtool-rules.sh
 
   - name: yaml-citations-guard-tests
     depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.303
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
     commands:
       - sh scripts/ci/test-yaml-citations.sh
 
@@ -63,7 +63,7 @@ steps:
   # bridge, and the secret guard.
   - name: hermes-skill-tests
     depends_on: []
-    image: python:3.14-alpine@sha256:f6a589d43c42b9e7f7dc67a12d37132491f362859a5d750607710cc56da3bc72
+    image: python:3.15-alpine@sha256:d44b1254cb92329418d164b22b20d86bbd3869d48e80e09e476531a409a728bb
     environment:
       PYTHONDONTWRITEBYTECODE: "1"
     commands:

.woodpecker/deploy-claude-workstation.yml

@@ -1,33 +0,0 @@
-when:
-  # Deploy only on main (merge) + manual — never auto-deploy from a branch.
-  - event: push
-    branch: main
-    path:
-      - "ansible/roles/claude-workstation/**"
-      - "ansible/plays/install-claude-workstation.yml"
-      - ".woodpecker/deploy-claude-workstation.yml"
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "deploy-claude-workstation"'
-
-timeout: 30
-
-steps:
-  - name: deploy-claude-workstation
-    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/install-claude-workstation.yml -v

.woodpecker/deploy-edge-mqtt-bridge.yml

@@ -1,36 +0,0 @@
-when:
-  # Deploy only on main (merge) + manual — never auto-deploy from a branch.
-  - event: push
-    branch: main
-    path:
-      - "ansible/roles/mqtt-bridge/**"
-      - "ansible/plays/edge-mqtt-bridge.yml"
-      - "ansible/inventory/group_vars/edge_host/**"
-      - ".woodpecker/deploy-edge-mqtt-bridge.yml"
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "deploy-edge-mqtt-bridge"'
-
-timeout: 30
-
-steps:
-  - name: deploy-edge-mqtt-bridge
-    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
-      # Local MQTT bridge on the edge hosts only (REN-1307); restarts only the
-      # local mosquitto on edge-1, never the cluster broker.
-      - ansible-playbook -i inventory/ plays/edge-mqtt-bridge.yml -v

.woodpecker/deploy-infrastructure.yml

@@ -13,7 +13,7 @@ when:
 
 steps:
   - name: validate-secrets
-    image: alpine:3.24.2@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
+    image: alpine:3.24.3@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a
     environment:
       TF_VAR_proxmox_api_url:
         from_secret: proxmox_api_url
@@ -109,8 +109,6 @@ steps:
         from_secret: hetzner_s3_access_key
       TF_VAR_hetzner_s3_secret_key:
         from_secret: hetzner_s3_secret_key
-      SSH_PRIVATE_KEY:
-        from_secret: ssh_private_key
       PROXMOX_TOKEN_ID:
         from_secret: proxmox_token_id
       PROXMOX_TOKEN_SECRET:
@@ -121,11 +119,6 @@ steps:
       ANSIBLE_ROLES_PATH: "../roles:./roles"
       ANSIBLE_FORCE_COLOR: "true"
     commands:
-      - mkdir -p ~/.ssh
-      - echo "$SSH_PRIVATE_KEY" | base64 -d > ~/.ssh/id_ed25519
-      - chmod 600 ~/.ssh/id_ed25519
-      - export TF_VAR_ssh_private_key="$(cat ~/.ssh/id_ed25519)"
-      - printf "Host *\n\tStrictHostKeyChecking no\n" > ~/.ssh/config
       - echo "$VAULT_PASS" > /tmp/.vault_pass && chmod 600 /tmp/.vault_pass
       - export ANSIBLE_VAULT_PASSWORD_FILE=/tmp/.vault_pass
       - tofu init -upgrade -backend-config="access_key=$AWS_ACCESS_KEY_ID" -backend-config="secret_key=$AWS_SECRET_ACCESS_KEY"

.woodpecker/deploy-netbird-client.yml

@@ -1,35 +0,0 @@
-when:
-  # Deploy only on main (merge) + manual — never auto-deploy from a branch.
-  - event: push
-    branch: main
-    path:
-      - "ansible/roles/netbird-client/**"
-      - "ansible/plays/install-netbird-client.yml"
-      - "ansible/inventory/group_vars/claude_workstation/**"
-      - ".woodpecker/deploy-netbird-client.yml"
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "deploy-netbird-client"'
-
-timeout: 30
-
-steps:
-  - name: deploy-netbird-client
-    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
-      # Enrol only the off-site Claude workstation into the Netbird mesh.
-      - ansible-playbook -i inventory/ plays/install-netbird-client.yml --limit claude_workstation -v

.woodpecker/deploy-netbird-proxy.yml

@@ -1,54 +0,0 @@
-when:
-  # Deploy only on main (merge) + manual — never auto-deploy from a branch.
-  - event: push
-    branch: main
-    path:
-      - "ansible/roles/netbird-proxy/**"
-      # install-netbird-proxy.yml also applies the netbird-proxy-watchdog role,
-      # so changes to it must redeploy this host too.
-      - "ansible/roles/netbird-proxy-watchdog/**"
-      # install-netbird-proxy.yml also applies the edge bouncer.
-      - "ansible/roles/crowdsec-edge-bouncer/**"
-      - "ansible/plays/install-netbird-proxy.yml"
-      # The variables that steer those roles, not just the roles themselves.
-      # Without these two, a change that only touches inventory never deploys
-      # and nothing says so: arming the bouncer lives in host_vars, and its
-      # LAPI key lives in group_vars, so both would sit in git looking applied
-      # while the hosts kept running the previous configuration.
-      #
-      # pve_hosts.yml is deliberately NOT listed. It is the single inventory
-      # file for the whole fleet, so listing it would redeploy the proxies for
-      # any unrelated host edit. The cost is that a change to [netbird_proxy]
-      # group membership needs a manual deployment run.
-      - "ansible/inventory/host_vars/proxy-*.yml"
-      - "ansible/inventory/group_vars/netbird_proxy/**"
-      - ".woodpecker/deploy-netbird-proxy.yml"
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "deploy-netbird-proxy"'
-
-timeout: 30
-
-steps:
-  - name: deploy-netbird-proxy
-    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
-      PROXMOX_TOKEN_ID:
-        from_secret: proxmox_token_id
-      PROXMOX_TOKEN_SECRET:
-        from_secret: proxmox_token_secret
-    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/install-netbird-proxy.yml -v

.woodpecker/deploy-netbird-server.yml

@@ -1,37 +0,0 @@
-when:
-  # Deploy only on main (merge) + manual — never auto-deploy from a branch.
-  - event: push
-    branch: main
-    path:
-      - "ansible/roles/netbird-server/**"
-      - "ansible/plays/install-netbird-server.yml"
-      - ".woodpecker/deploy-netbird-server.yml"
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "deploy-netbird-server"'
-
-timeout: 30
-
-steps:
-  - name: deploy-netbird-server
-    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
-      PROXMOX_TOKEN_ID:
-        from_secret: proxmox_token_id
-      PROXMOX_TOKEN_SECRET:
-        from_secret: proxmox_token_secret
-    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/install-netbird-server.yml -v

.woodpecker/deploy-uptime-kuma.yml

@@ -1,47 +0,0 @@
-when:
-  # Deploy only on main (merge) + manual — never auto-deploy from a branch.
-  - event: push
-    branch: main
-    path:
-      - "ansible/roles/uptime-kuma/**"
-      - "ansible/plays/install-uptime-kuma.yml"
-      - ".woodpecker/deploy-uptime-kuma.yml"
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "deploy-uptime-kuma"'
-  - event: cron
-    cron: uptime-kuma-token-renew
-
-timeout: 30
-
-steps:
-  - name: renew-openbao-token
-    image: gitea.renner.uno/gitea_admin/ci-ansible:2026-10-18
-    environment:
-      VAULT_TOKEN:
-        from_secret: openbao_uptime_kuma_token
-    commands:
-      - 'curl -sSf -X POST -H "X-Vault-Token: $VAULT_TOKEN" https://openbao.renner.uno/v1/auth/token/renew-self -o /dev/null'
-
-  - name: deploy-uptime-kuma
-    image: gitea.renner.uno/gitea_admin/ci-ansible:2026-10-18
-    when:
-      - event: [push, deployment]
-    environment:
-      ANSIBLE_FORCE_COLOR: "true"
-      ANSIBLE_HOST_KEY_CHECKING: "false"
-      ANSIBLE_ROLES_PATH: "../roles:./roles"
-      SSH_PRIVATE_KEY:
-        from_secret: ssh_private_key
-      VAULT_PASS:
-        from_secret: vault_pass
-      VAULT_TOKEN:
-        from_secret: openbao_uptime_kuma_token
-    commands:
-      - mkdir -p ~/.ssh
-      - echo "$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/install-uptime-kuma.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:2.1.303
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
     commands:
       - sh scripts/ci/test-model-selection.sh
 

.woodpecker/review-bot-test.yml

@@ -6,7 +6,7 @@ when:
 
 steps:
   - name: go-test
-    image: golang:1.27.2-bookworm@sha256:5cf287a799e6b94384bad13d16b14904c531f51ba65792237e122ce42b392f61
+    image: golang:1.27.3-bookworm@sha256:972b4110ba0f47539a975c31e52c64765e1ff19f2d74469ae4a595c6676e80a5
     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@sha256:2416d1f74045b57274df1a340eee6b510cacd73c66a6ccb8da092b117eb7d222
+    image: aquasec/trivy:latest@sha256:790fd66d1697395d8693d1acaa1ea702406a20f109b6fc7bac8db623eca6c06c
     commands:
       - trivy fs --format json -o trivy-iac.json --severity CRITICAL,HIGH --ignore-unfixed .
 
   - name: image-scans
-    image: aquasec/trivy:latest@sha256:2416d1f74045b57274df1a340eee6b510cacd73c66a6ccb8da092b117eb7d222
+    image: aquasec/trivy:latest@sha256:790fd66d1697395d8693d1acaa1ea702406a20f109b6fc7bac8db623eca6c06c
     commands:
       - trivy image --download-db-only
       - |
@@ -70,7 +70,7 @@ steps:
     # this step is skipped — otherwise we'd fork-bomb PRs.
     when:
       - branch: main
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.303
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
     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:2.1.303
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
     environment:
       CLAUDE_CODE_OAUTH_TOKEN:
         from_secret: claude_code_oauth_token

ansible/ansible.cfg

@@ -112,7 +112,7 @@
 
 # (string) This setting controls the default policy of fact gathering (facts discovered about remote systems).
 # This option can be useful for those wishing to save fact gathering time. Both 'smart' and 'explicit' will use the cache plugin.
-;gathering=implicit
+gathering=smart
 
 # (list) Set the `gather_subset` option for the :ref:`ansible_collections.ansible.builtin.setup_module` task in the implicit fact gathering. See the module documentation for specifics.
 # It does **not** apply to user defined ``ansible.builtin.setup`` tasks.
@@ -134,7 +134,7 @@
 ;hash_behaviour=replace
 
 # (pathlist) Comma separated list of Ansible inventory sources
-inventory=~/source/homelab/ansible/inventory
+inventory=inventory
 
 # (pathspec) Colon separated paths in which Ansible will search for HttpApi Plugins.
 ;httpapi_plugins={{ ANSIBLE_HOME ~ "/plugins/httpapi:/usr/share/ansible/plugins/httpapi" }}
@@ -206,7 +206,7 @@ inventory=~/source/homelab/ansible/inventory
 ;poll_interval=15
 
 # (path) Option for connections using a certificate or key file to authenticate, rather than an agent or passwords, you can set the default value here to avoid re-specifying --private-key with every invocation.
-private_key_file=~/.ssh/id_ed25519
+;private_key_file=
 
 # (boolean) By default, imported roles publish their variables to the play and other roles, this setting can avoid that.
 # This was introduced as a way to reset role variables to default values if a role is used more than once in a playbook.
@@ -274,7 +274,7 @@ roles_path=../roles:./roles
 
 # (path) The vault password file to use. Equivalent to --vault-password-file or --vault-id
 # If executable, it will be run and the resulting stdout will be used as the password.
-vault_password_file=~/source/homelab/ansible/vault-password.sh
+vault_password_file=vault-password.sh
 
 # (integer) Sets the default verbosity, equivalent to the number of ``-v`` passed in the command line.
 ;verbosity=0
@@ -484,7 +484,7 @@ vault_password_file=~/source/homelab/ansible/vault-password.sh
 # It can result in a very significant performance improvement when enabled.
 # However this conflicts with privilege escalation (become). For example, when using 'sudo:' operations you must first disable 'requiretty' in /etc/sudoers on all managed hosts, which is why it is disabled by default.
 # This setting will be disabled if ``ANSIBLE_KEEP_REMOTE_FILES`` is enabled.
-;pipelining=False
+pipelining=True
 
 
 [colors]
@@ -694,3 +694,8 @@ vault_password_file=~/source/homelab/ansible/vault-password.sh
 # (list) default list of tags to skip in your plays, has precedence over Run Tags
 ;skip=
 
+
+[ssh_connection]
+# Connections stay open across the plays of a run, so each host costs one
+# YubiKey PIN; plays/close-connections.yml closes them at the end of a run.
+ssh_args=-C -o ControlMaster=auto -o ControlPersist=30m

ansible/docs/edge-host.md

@@ -41,13 +41,11 @@ Build and boot the dedicated installer image — see
 4. Add the host to `[edge_host]` in `inventory/pve_hosts.yml`, by name.
    That group is the base: every edge thin client belongs to it, and it
    assumes no peripherals.
-5. From the workstation:
+5. From the workstation, in `ansible/`:
    ```
-   ansible-playbook -i inventory/pve_hosts.yml plays/install-edge-host.yml
+   ansible-playbook site.yml
    ```
-   One unrestricted run over the whole group. The play is self-contained --
-   it carries `certificates` and `common` itself, so there is no second
-   command and no `--limit`. Running it converges every edge host, which is
+   One unrestricted run, no `--limit`. It converges every host, which is
    the point: a run that touches only the new box tells you nothing about
    the others.
 
@@ -72,14 +70,14 @@ none of these commands.
 
 ## Secrets (before first play run)
 
-Create `inventory/group_vars/edge_host/vault.yml` with ansible-vault; the
-current live values come straight out of the cluster:
+Create `inventory/group_vars/edge_host/vault.yml` with ansible-vault. The
+cluster broker has no `open3e` user: edge-1 logs in only as the register
+account `edge-1` (see "MQTT bridge" below), so
+`vault_edge_open3e_mqtt_password` reaches only the loopback broker, which
+allows anonymous clients; any random value works (`openssl rand -hex 24`).
+The zwave-js value comes out of the cluster:
 
 ```
-# sml2mqtt broker password
-kubectl -n home-assistant get secret mosquitto-sml2mqtt-credentials -o jsonpath='{.data.password}' | base64 -d
-# open3e broker password
-kubectl -n home-assistant get secret mosquitto-open3e-credentials -o jsonpath='{.data.password}' | base64 -d
 # zwave-js session secret
 kubectl -n home-assistant get secret zwave-js-session -o jsonpath='{.data.session-secret}' | base64 -d
 ```
@@ -230,15 +228,14 @@ They connect to a **local mosquitto on loopback** (`127.0.0.1:1883`,
   broker is briefly unreachable, and flushes on reconnect — edge-1 no longer
   hard-depends on cluster/network uptime for every publish.
 
-Two bridge `connection`s preserve the existing cluster identities, so **no
-cluster-side change was needed**: one authenticates as the `open3e` user
-(carries `open3e/#` out + `open3e/cmnd` back), one as `sml2mqtt` (`sml2mqtt/#`
-out). The local broker is `allow_anonymous` on loopback — the trust boundary
-is the host; nothing off-host can reach it.
+The local broker is `allow_anonymous` on loopback — the trust boundary is the
+host; nothing off-host can reach it.
 
-**Bridge credential (REN-1307).** The two vault-password bridges are being
-replaced by one bridge as the register account `edge-1`
-(`kubernetes/apps/home-assistant/mqtt-accounts.yaml`). Its password is pushed
+**Bridge credential (REN-1307).** One bridge `connection` logs in as the
+register account `edge-1` (`kubernetes/apps/home-assistant/mqtt-accounts.yaml`)
+and carries `open3e/#` out and `open3e/cmnd` back. The cluster broker does not
+accept the vault-password bridges in `bridge.d/legacy.conf`, which exists only
+until the first push. Its password is pushed
 by mqtt-account-controller to `edge-mqtt-cred` (`:8443`, the controller's
 esp32 API over HTTPS). That endpoint accepts only a client certificate from
 the MQTT CA with CN `mqtt-account-controller`; edge-1 holds the public CA and
@@ -246,8 +243,7 @@ its own server key, nothing else. On a push it writes
 `/etc/mosquitto/bridge.d/edge-1.conf`, deletes `bridge.d/legacy.conf` and
 restarts the local mosquitto. The controller sets a new password whenever the
 bridge reports "not connected" (also after a reinstall), so no play run is
-needed for a rotation. `.woodpecker/deploy-edge-mqtt-bridge.yml` runs
-`plays/edge-mqtt-bridge.yml` on merge. Diagnosis: `journalctl -u
+needed for a rotation. Diagnosis: `journalctl -u
 edge-mqtt-cred`, and `mosquitto_sub -t '$SYS/broker/connection/edge-1/state'`
 (retained `1` = connected).
 

ansible/files/discover_shelly.py

@@ -1,67 +0,0 @@
-#!/usr/bin/env python3
-"""
-Discover Shelly devices on the network via HTTP API
-Returns JSON array of discovered devices
-"""
-
-import sys
-import json
-import ipaddress
-import concurrent.futures
-import urllib.request
-import urllib.error
-
-def check_shelly(ip):
-    """Check if IP is a Shelly device and return info"""
-    try:
-        url = f"http://{ip}/shelly"
-        req = urllib.request.Request(url, headers={'User-Agent': 'Ansible-Shelly-Discovery'})
-        with urllib.request.urlopen(req, timeout=2) as response:
-            data = json.loads(response.read().decode())
-            # Gen1 devices don't have 'gen' field, default to 1
-            gen = data.get('gen', 1)
-            if gen is None:
-                gen = 1
-            return {
-                'ip': str(ip),
-                'type': data.get('type', 'unknown'),
-                'mac': data.get('mac', ''),
-                'gen': gen,
-                'name': data.get('name', data.get('id', str(ip))),
-                'fw_id': data.get('fw_id', data.get('fw', 'unknown'))
-            }
-    except (urllib.error.URLError, urllib.error.HTTPError, OSError, json.JSONDecodeError):
-        return None
-    except Exception:
-        return None
-
-def main():
-    if len(sys.argv) < 2:
-        print("Usage: discover_shelly.py <network1> [network2] ...")
-        print("Example: discover_shelly.py 10.2.30.0/24 10.2.20.0/24")
-        sys.exit(1)
-
-    networks = sys.argv[1:]
-    devices = []
-
-    # Collect all IPs to scan
-    all_ips = []
-    for network in networks:
-        try:
-            all_ips.extend(ipaddress.IPv4Network(network).hosts())
-        except ValueError as e:
-            print(f"Invalid network: {network} - {e}", file=sys.stderr)
-            continue
-
-    # Scan in parallel
-    with concurrent.futures.ThreadPoolExecutor(max_workers=100) as executor:
-        results = executor.map(check_shelly, all_ips)
-        for result in results:
-            if result:
-                devices.append(result)
-
-    # Output JSON
-    print(json.dumps(devices, indent=2))
-
-if __name__ == "__main__":
-    main()

ansible/inventory/group_vars/all/vars.yml

@@ -5,27 +5,10 @@ pve_token_id: "ansible"
 ansible_user: "ladmin"
 ansible_python_interpreter: /usr/bin/python3
 
-# SSH Public Keys for Cloud-Init
-# ansible-runner@ci-new removed (issue #184): dead key, no such host exists.
-common_ssh_public_keys: |
-  ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIPzFNBP3bq2m/6JqDqod9w+FP/uxXxHMolqhq3Ojflr1 krenner@fortress
-  ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICyNnX1I4W9jyDvCJ1DJauHSmbo1ZXSyBxVhSAwMWgen woodpecker-ci@homelab
-
-# Network-of-origin restriction for the woodpecker-ci@homelab CI key
-# (issue #184). Consumed by plays/configure-ssh-keys.yml as the authorized_key
-# `from=` option so the CI key only authenticates from within the cluster's
-# pod network — NOT from any host-pinned IP.
-#
-# The in-cluster Woodpecker step pods SSH to fleet hosts using their POD IP as
-# source, not a node IP: Cilium runs `ipv4-native-routing-cidr=10.0.0.0/8` +
-# `ipv6-native-routing-cidr=fd00::/8` with masquerade enabled, so pod egress to
-# any 10.x / fd.. LAN destination is NOT SNAT'd, and each node's PodCIDR is
-# advertised to the UDM over BGP (kubernetes/infrastructure/post-crds/
-# cilium-bgp.yaml) so return traffic L3-routes back to the pod. Hosts therefore
-# see the real pod source IP.
-#
-# The cluster pod subnets (kubernetes/talos/patches/cluster.yaml podSubnets)
-# are the stable boundary — they survive node DHCP-lease churn and pod
-# rescheduling across k8s-1/2/3, unlike pinning any node's current IP.
-# v6 is included because some SSH targets (edge IoT hosts) are IPv6-only.
-ci_ssh_from_cidrs: '10.244.0.0/16,fd10:244::/48'
+# The only plain key the admin logins accept on [ssh_keys_managed] hosts
+# (ssh-ca role, tasks/authorized_keys.yml). People log in with OpenBao SSH CA
+# certificates; this one is for when that path is unavailable.
+#   breakglass-neo: PIV key (slot 9a, PIN) on the offline YubiKey NEO.
+#     ssh -I /usr/lib/opensc-pkcs11.so root@<host>
+ssh_admin_authorized_keys:
+  - key: "ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBKvSl9LUP8u3S2Sq5YTWpW0Jxbue8cJhD7/LMFQbEsa3xo145HVR7pBzRxW71MUy+jgrgmpSlDhIb606Hswhvoo= breakglass-neo-6532348"

ansible/inventory/group_vars/claude_workstation/vault.yml

@@ -1,16 +0,0 @@
-$ANSIBLE_VAULT;1.1;AES256
-35646538363164363061366433343963623166336630376233333033646637336266343337343230
-3233356135323762636439336466663430366238363338650a633762623366643137303333383634
-62623739363132303335636261626263333332623066303161633466306431623930666166323833
-6439663964353338350a656435626664646666363831363164393335386666356637613037323838
-63653461656366613331353064656161346263356131346437666632386166623037373363333534
-37323435623366643534633333303534313434613135653237303966656162633266623433363934
-36343133393834393765353338383764303664363431653865633764306138376366623832346262
-36303766623331666632613639366139333661636665363631326565653938343637323861653064
-37393465383263376337376639613162306563653365623036376662303030613264653534353332
-66363030356363373439306164386561363734353631363738656236633164633062613437663366
-62386430396262366336316166353366383233316333333234666538643962336361363630363762
-31653963303032373531386566336632336130383034343430303964396538663237346434613737
-39643765623766373639306132316635376434643232336163303066393736313130323065666232
-39393038616162666666383837326137376233613437636361636238663566336365653863643933
-353338646134383038323134323034653564

ansible/inventory/group_vars/edge_host/vars.yml

@@ -50,3 +50,11 @@ edge_mqtt_host: 127.0.0.1
 edge_mqtt_port: 1883
 edge_open3e_mqtt_user: open3e
 edge_open3e_mqtt_topic: open3e
+
+# Units claude-bot may restart (ssh-ca role); the containers go through docker.
+ssh_ca_claude_sudo_units:
+  - mosquitto
+  - edge-mqtt-cred
+  - edge-alloy
+  - keepalived
+  - chronyd

ansible/inventory/group_vars/netbird_proxy/vars.yml

@@ -0,0 +1,9 @@
+---
+# The host NetBird client (wt0) must not take over DNS: resolv.conf is pinned to
+# the systemd-resolved stub by the netbird-proxy role.
+netbird_disable_dns: true
+
+ssh_ca_claude_sudo_units:
+  - netbird
+  - netbird-proxy-flood-watchdog
+  - crowdsec-firewall-bouncer

ansible/inventory/host_vars/netbird.renner.uno.yml

@@ -2,3 +2,6 @@
 # NetBird server - VPS not managed by Proxmox
 # Enable Docker monitoring (cAdvisor) for container metrics
 docker_monitoring_enabled: true
+
+ssh_ca_claude_sudo_units:
+  - netbird

ansible/inventory/pve_hosts.yml

@@ -13,11 +13,11 @@
 # Their hosts no longer resolve, except the three that resolve to Talos nodes.
 
 [netbird_server]
-netbird.renner.uno ansible_user=root
+netbird.renner.uno ansible_host=netbird.nb.renner.uno ansible_user=root
 
 [netbird_proxy]
-proxy-1.renner.uno ansible_user=root
-proxy-2.renner.uno ansible_user=root
+proxy-1.renner.uno ansible_host=proxy-1.nb.renner.uno ansible_user=root
+proxy-2.renner.uno ansible_host=proxy-2.nb.renner.uno ansible_user=root
 
 # Every bare-metal edge thin client. Gets the host-generic roles only:
 # flash-wear handling, the log shipper, the MQTT bridge, the VLAN
@@ -62,10 +62,28 @@ heating_can
 [ntp_cluster:children]
 edge_host
 
-# Off-site Debian VM (Synology VMM on nas-2, 10.3.40.0/24) running Claude Code.
-# Reached over the site-to-site tunnel at its current DHCP lease. Switch
-# ansible_host to the stable Netbird mesh IP once the host is enrolled — the
-# obg.renner.uno FQDN is split-horizon and resolves to the public proxy from
-# 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
+edge-1.iot.renner.uno
+
+# Hosts whose admin logins accept only ssh_admin_authorized_keys (break-glass);
+# everything else needs a CA certificate. Members must be in [ssh_ca].
+# Added one host at a time after the [ssh_ca] report was reviewed.
+[ssh_keys_managed]
+proxy-1.renner.uno
+proxy-2.renner.uno
+netbird.renner.uno
+edge-1.iot.renner.uno
+
+# Internet hosts whose sshd listens on the NetBird interface only
+# (plays/configure-ssh-mesh-only.yml). Members need the host NetBird client.
+# Added one host at a time after the previous one was verified.
+[ssh_mesh_only]
+proxy-1.renner.uno
+proxy-2.renner.uno
+netbird.renner.uno

ansible/plays/close-connections.yml

@@ -0,0 +1,11 @@
+---
+# Last play of every playbook that is run directly (site.yml and the one-off
+# actions). SSH connections stay open for 30 minutes (ansible.cfg) so a run
+# costs one YubiKey PIN per host; closing them at the end leaves nothing that
+# another process of the same user could reuse.
+- name: Close the SSH connections
+  hosts: all
+  gather_facts: false
+  tasks:
+    - name: Close the connection
+      ansible.builtin.meta: reset_connection

ansible/plays/common.yml

@@ -13,4 +13,5 @@
 
   roles:
     - common
-    - qemu-guest-agent
+    - role: qemu-guest-agent
+      when: ansible_facts['virtualization_role'] == 'guest'

ansible/plays/configure-shelly-ntp.yml

@@ -1,125 +0,0 @@
----
-# Configure NTP server on all Shelly devices
-# Discovers Shelly devices via network scan and configures them to use local NTP server
-#
-# Usage:
-#   ansible-playbook plays/configure-shelly-ntp.yml
-#   ansible-playbook plays/configure-shelly-ntp.yml -e "shelly_ntp_server=10.2.40.4"
-#   ansible-playbook plays/configure-shelly-ntp.yml -e "shelly_networks=10.2.30.0/24,10.2.20.0/24"
-
-- name: Configure Shelly NTP Settings
-  hosts: localhost
-  connection: local
-  gather_facts: no
-
-  vars:
-    shelly_ntp_server: "ntp.renner.uno"
-    shelly_networks: "10.2.30.0/24 10.2.20.0/24"
-    shelly_timeout: 5
-
-  tasks:
-    - name: Discover Shelly devices on network
-      script: "{{ playbook_dir }}/../files/discover_shelly.py {{ shelly_networks }}"
-      args:
-        executable: python3
-      register: discovered_devices
-      changed_when: false
-
-    - name: Parse discovered devices
-      set_fact:
-        shelly_devices: "{{ discovered_devices.stdout | from_json }}"
-
-    - name: Display discovered Shelly devices
-      debug:
-        msg: "Found {{ shelly_devices | length }} Shelly devices"
-
-    - name: Show device list
-      debug:
-        msg: "{{ item.name }} ({{ item.type }}) - {{ item.ip }} - Gen{{ item.gen }}"
-      loop: "{{ shelly_devices }}"
-      when: shelly_devices | length > 0
-
-    - name: Configure NTP on Gen1 devices
-      uri:
-        url: "http://{{ item.ip }}/settings?sntp_server={{ shelly_ntp_server }}"
-        method: GET
-        timeout: "{{ shelly_timeout }}"
-        return_content: yes
-      loop: "{{ shelly_devices | selectattr('gen', 'equalto', 1) | list }}"
-      register: gen1_results
-      ignore_errors: yes
-      when: shelly_devices | length > 0
-
-    - name: Configure NTP on Gen2+ devices
-      uri:
-        url: "http://{{ item.ip }}/rpc/Sys.SetConfig"
-        method: POST
-        body_format: json
-        body:
-          config:
-            sntp:
-              server: "{{ shelly_ntp_server }}"
-        timeout: "{{ shelly_timeout }}"
-        return_content: yes
-      loop: "{{ shelly_devices | selectattr('gen', 'greaterthan', 1) | list }}"
-      register: gen2_results
-      ignore_errors: yes
-      when: shelly_devices | length > 0
-
-    - name: Verify Gen1 NTP configuration
-      uri:
-        url: "http://{{ item.ip }}/settings"
-        method: GET
-        timeout: "{{ shelly_timeout }}"
-        return_content: yes
-      loop: "{{ shelly_devices | selectattr('gen', 'equalto', 1) | list }}"
-      register: gen1_verify
-      ignore_errors: yes
-      when: shelly_devices | length > 0
-
-    - name: Verify Gen2+ NTP configuration
-      uri:
-        url: "http://{{ item.ip }}/rpc/Sys.GetConfig"
-        method: GET
-        timeout: "{{ shelly_timeout }}"
-        return_content: yes
-      loop: "{{ shelly_devices | selectattr('gen', 'greaterthan', 1) | list }}"
-      register: gen2_verify
-      ignore_errors: yes
-      when: shelly_devices | length > 0
-
-    - name: Summary - Gen1 devices configured
-      debug:
-        msg: "{{ item.item.name }} ({{ item.item.ip }}): NTP={{ item.json.sntp.server | default('unknown') }}"
-      loop: "{{ gen1_verify.results | default([]) }}"
-      when:
-        - gen1_verify is defined
-        - gen1_verify.results is defined
-        - item.json is defined
-        - item.json.sntp is defined
-      loop_control:
-        label: "{{ item.item.name | default(item.item.ip) }}"
-
-    - name: Summary - Gen2+ devices configured
-      debug:
-        msg: "{{ item.item.name }} ({{ item.item.ip }}): NTP={{ item.json.sntp.server | default('unknown') }}"
-      loop: "{{ gen2_verify.results | default([]) }}"
-      when:
-        - gen2_verify is defined
-        - gen2_verify.results is defined
-        - item.json is defined
-        - item.json.sntp is defined
-      loop_control:
-        label: "{{ item.item.name | default(item.item.ip) }}"
-
-    - name: Final summary
-      debug:
-        msg: |
-          ==========================================
-          Shelly NTP Configuration Complete
-          ==========================================
-          Total devices found: {{ shelly_devices | length }}
-          Gen1 devices: {{ shelly_devices | selectattr('gen', 'equalto', 1) | list | length }}
-          Gen2+ devices: {{ shelly_devices | selectattr('gen', 'greaterthan', 1) | list | length }}
-          NTP Server: {{ shelly_ntp_server }}
-          ==========================================

ansible/plays/configure-ssh-ca.yml

@@ -0,0 +1,23 @@
+---
+# 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. The role reports the admin logins' authorized_keys; on
+# [ssh_keys_managed] they are then reduced to ssh_admin_authorized_keys.
+#
+# serial: 1 so a host whose sshd rejects the change stops the run before the
+# next host is touched. One play, so each host needs one login (one YubiKey
+# PIN from a workstation).
+- name: Configure the SSH user CA
+  hosts: ssh_ca
+  become: true
+  gather_facts: true
+  serial: 1
+  roles:
+    - ssh-ca
+  tasks:
+    - name: Reduce authorized_keys to the break-glass key
+      ansible.builtin.include_role:
+        name: ssh-ca
+        tasks_from: authorized_keys
+      when: inventory_hostname in groups['ssh_keys_managed']

ansible/plays/configure-ssh-keys.yml

@@ -1,48 +0,0 @@
----
-- name: Deploy authorized SSH keys to all hosts
-  hosts: all:!localhost
-  become: true
-  gather_facts: false
-  # Authorized keys deployed to root and ladmin on every managed host.
-  #
-  # - krenner@fortress (human): unrestricted.
-  # - woodpecker-ci@homelab (CI): restricted with from= to the cluster's pod
-  #   network (ci_ssh_from_cidrs in group_vars/all/vars.yml). The in-cluster
-  #   Woodpecker step pods SSH to fleet hosts presenting their POD IP as source
-  #   (Cilium native-routing-cidr covers the LAN, so no SNAT; PodCIDRs are
-  #   BGP-advertised). This is a network-of-origin restriction, NOT host-pinned,
-  #   so it survives node DHCP churn and pod rescheduling. See vars.yml for the
-  #   full derivation.
-  # - ansible-runner@ci-new: removed — dead key, no such host exists.
-  vars:
-    authorized_keys:
-      - key: "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIPzFNBP3bq2m/6JqDqod9w+FP/uxXxHMolqhq3Ojflr1 krenner@fortress"
-      - key: "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICyNnX1I4W9jyDvCJ1DJauHSmbo1ZXSyBxVhSAwMWgen woodpecker-ci@homelab"
-        options: 'from="{{ ci_ssh_from_cidrs }}"'
-  tasks:
-    - name: Check SSH connectivity
-      ansible.builtin.wait_for_connection:
-        timeout: 5
-      ignore_errors: true
-      register: ssh_check
-
-    - name: Skip unreachable hosts
-      ansible.builtin.meta: end_host
-      when: ssh_check is failed
-
-    - name: Deploy authorized keys to root
-      ansible.builtin.authorized_key:
-        user: root
-        key: "{{ item.key }}"
-        key_options: "{{ item.options | default(omit) }}"
-        state: present
-      loop: "{{ authorized_keys }}"
-
-    - name: Deploy authorized keys to ladmin
-      ansible.builtin.authorized_key:
-        user: ladmin
-        key: "{{ item.key }}"
-        key_options: "{{ item.options | default(omit) }}"
-        state: present
-      loop: "{{ authorized_keys }}"
-      ignore_errors: true

ansible/plays/configure-ssh-mesh-only.yml

@@ -0,0 +1,15 @@
+---
+# sshd on the hosts in [ssh_mesh_only] accepts connections only on the NetBird
+# interface; nothing listens on their public addresses. Run from a workstation
+# in the mesh. A switchover reverts by itself unless the play logs in again
+# through the new listener.
+#
+# serial: 1 so a host that does not come back stops the run before the next
+# host is touched.
+- name: Restrict sshd to the mesh interface
+  hosts: ssh_mesh_only
+  become: true
+  gather_facts: true
+  serial: 1
+  roles:
+    - ssh-mesh-only

ansible/plays/configure-vm-time-sync.yml

@@ -29,6 +29,7 @@
     - name: Check if systemd-timesyncd is installed
       command: systemctl list-unit-files systemd-timesyncd.service
       register: timesyncd_installed
+      check_mode: false
       failed_when: false
       changed_when: false
 
@@ -56,6 +57,7 @@
     - name: Verify time sync status
       command: timedatectl show --property=NTPSynchronized
       register: timesync_status
+      check_mode: false
       changed_when: false
       failed_when: false
 

ansible/plays/edge-mqtt-bridge.yml

@@ -1,33 +0,0 @@
----
-# Local MQTT bridge and its credential receiver only (REN-1307). Run by
-# .woodpecker/deploy-edge-mqtt-bridge.yml on merge, so a change to this role
-# reaches edge-1 without a play run by hand. The full base play
-# (install-edge-host.yml) carries the same role.
-- name: Converge the edge MQTT bridge
-  hosts: edge_host
-  become: true
-
-  # The SML power-meter reader (sml2mqtt) is retired for good: owner decision
-  # 2026-09-19, grid data comes from the E380 on the CAN bus. Its role and
-  # play are gone; this removes the leftover compose project from edge-1 on
-  # the next pipeline run. Idempotent: a no-op once the directory is gone.
-  pre_tasks:
-    - name: Check for the retired sml2mqtt compose project
-      ansible.builtin.stat:
-        path: /opt/edge-host/sml2mqtt/docker-compose.yml
-      register: edge_sml2mqtt_compose
-
-    - name: Stop the retired sml2mqtt container
-      ansible.builtin.command:
-        cmd: docker compose down --remove-orphans
-        chdir: /opt/edge-host/sml2mqtt
-      when: edge_sml2mqtt_compose.stat.exists
-      changed_when: true
-
-    - name: Remove the retired sml2mqtt directory
-      ansible.builtin.file:
-        path: /opt/edge-host/sml2mqtt
-        state: absent
-
-  roles:
-    - mqtt-bridge

ansible/plays/install-claude-workstation.yml

@@ -1,20 +0,0 @@
----
-# Off-site Debian VM running Claude Code — reattachable interactive sessions
-# plus an unattended notes-distill timer. Host creation (Synology VMM), the
-# Netbird dashboard route and secret material are manual prerequisites; see
-# roles/claude-workstation/README.md and docs/claude-workstation.md.
-#
-# CI reaches this off-site host over the site-to-site tunnel (home -> off-site
-# works), same as it reaches every other inventory host.
-
-- name: Deploy the Claude Code workstation
-  hosts: claude_workstation
-  become: true
-  # qemu-guest-agent is applied
-  # to every inventory host by the umbrella plays/common.yml, same as for the
-  # netbird-proxy host — run that against this host too (see RUNBOOK Step 5).
-  roles:
-    - common
-    - role: netbird-client       # mesh enrolment (needs netbird_setup_key in vault)
-      when: netbird_setup_key is defined
-    - claude-workstation

ansible/plays/install-netbird-client.yml

@@ -6,26 +6,25 @@
 #   - host_vars/<hostname>/vars.yml - per-host key (overrides group)
 #   - group_vars/all/vault.yml - encrypted keys
 #
-# Usage:
-#   ansible-playbook -i inventory/ plays/setup-netbird-client.yml
-#
-# Limit to specific hosts:
-#   ansible-playbook -i inventory/ plays/setup-netbird-client.yml --limit caddy_servers
+# Applied by site.yml.
 
 - name: Install NetBird client on hosts with setup key defined
   hosts: all
   become: true
-  gather_facts: true
+  # One host at a time: from a workstation every new SSH session asks for the
+  # YubiKey PIN and a touch, and parallel hosts would prompt at once.
+  serial: 1
+  # Facts only after the skip: gathering them first opens an SSH session (a
+  # YubiKey touch from a workstation) to every host, including skipped ones.
+  gather_facts: false
 
   pre_tasks:
-    - name: Check if netbird_setup_key is defined
-      ansible.builtin.debug:
-        msg: "NetBird setup key is defined for {{ inventory_hostname }}"
-      when: netbird_setup_key is defined
-
     - name: Skip hosts without netbird_setup_key
       ansible.builtin.meta: end_host
       when: netbird_setup_key is not defined
 
+    - name: Gather facts
+      ansible.builtin.setup:
+
   roles:
     - netbird-client

ansible/plays/install-netbird-proxy.yml

@@ -1,6 +1,6 @@
 ---
 # Deploy the NetBird reverse-proxy HA cluster members (the public edge).
-# Usage: ansible-playbook -i inventory/ plays/install-netbird-proxy.yml
+# Applied by site.yml.
 #
 # Prerequisites:
 # - Proxy VPS provisioned (proxy-1 is Arch Linux), root SSH reachable, and

ansible/plays/install-netbird-server.yml

@@ -1,6 +1,6 @@
 ---
 # Deploy NetBird Server to VPS
-# Usage: ansible-playbook -i inventory/ plays/install-netbird-server.yml
+# Applied by site.yml.
 #
 # Prerequisites:
 # - VPS provisioned with Ubuntu 22.04/24.04

ansible/plays/install-node-exporter.yml

@@ -1,22 +0,0 @@
----
-# Install Node Exporter on all managed hosts
-# Usage: ansible-playbook -i inventory/ plays/install-node-exporter.yml
-
-- name: Install Node Exporter
-  hosts: all
-  become: yes
-  gather_facts: yes
-
-  roles:
-    - node-exporter
-
-  post_tasks:
-    - name: Verify node-exporter is running
-      uri:
-        url: "http://127.0.0.1:9100/metrics"
-        status_code: 200
-      register: exporter_health
-      retries: 3
-      delay: 5
-      until: exporter_health.status == 200
-      ignore_errors: yes

ansible/plays/install-ntp-ha.yml

@@ -102,32 +102,45 @@
       ansible.builtin.pause:
         seconds: 5
 
-    - name: Verify chrony is serving NTP
-      ansible.builtin.shell: chronyc clients | head -10
-      register: chrony_clients
+    - name: Verify chronyd answers
+      ansible.builtin.command:
+        argv:
+          - chronyc
+          - -n
+          - tracking
+      check_mode: false
       changed_when: false
 
-    - name: Check NTP port is listening
-      ansible.builtin.shell: ss -lun | grep ':123 '
+    - name: Verify chronyd listens on udp/123
+      ansible.builtin.command:
+        argv:
+          - ss
+          - -Hlunp
+          - sport = :123
       register: ntp_port
-      failed_when: false
+      check_mode: false
       changed_when: false
-
-    - name: Display NTP port status
-      ansible.builtin.debug:
-        msg: "NTP port 123: {{ 'LISTENING' if ntp_port.rc == 0 else 'NOT LISTENING' }}"
+      failed_when: "'chronyd' not in ntp_port.stdout"
 
     - name: Check if this server has the VIP
-      ansible.builtin.shell: ip addr show | grep {{ ntp_vip }}
+      ansible.builtin.command:
+        argv:
+          - ip
+          - -4
+          - addr
+          - show
+          - to
+          - "{{ ntp_vip }}"
       register: vip_check
-      failed_when: false
+      check_mode: false
+      failed_when: vip_check.rc != 0
       changed_when: false
       when: ntp_keepalived_enabled | default(false)
 
     - name: Display VIP status
       ansible.builtin.debug:
         msg: >
-          {% if vip_check.rc == 0 %}
+          {% if vip_check.stdout | default('') | length > 0 %}
           This server ({{ inventory_hostname }}) is MASTER and holds the VIP {{ ntp_vip }}
           {% else %}
           This server ({{ inventory_hostname }}) is BACKUP
@@ -159,7 +172,8 @@
           - to
           - "{{ ntp_vip6 }}"
       register: vip6_check
-      failed_when: false
+      check_mode: false
+      failed_when: vip6_check.rc != 0
       changed_when: false
       when: ntp_keepalived_enabled | default(false)
 
@@ -184,18 +198,28 @@
           (keepalived not enabled on this host).
       when: not (ntp_keepalived_enabled | default(false))
 
-    - name: Test NTP via VIP (only on master)
-      ansible.builtin.shell: |
-        chronyc -h {{ ntp_vip }} tracking 2>&1 || echo "Cannot connect to VIP (may need to wait for failover)"
+    # chronyc talks to the command port, which is loopback-only; this is a real
+    # NTP query. Directives on the command line mean no config file and no
+    # pidfile, and -Q opens no server or command port, so it runs alongside
+    # the live daemon.
+    - name: Query NTP through the VIP (only on master)
+      ansible.builtin.command:
+        argv:
+          - chronyd
+          - -Q
+          - -t
+          - "10"
+          - "server {{ ntp_vip }} iburst maxsamples 1"
       register: ntp_vip_test
+      check_mode: false
       when:
         - ntp_keepalived_enabled | default(false)
-        - vip_check.rc == 0
+        - vip_check.stdout | default('') | length > 0
       changed_when: false
 
     - name: Display VIP NTP test result
       ansible.builtin.debug:
-        msg: "{{ ntp_vip_test.stdout_lines | default(['Not master, skipping VIP test']) }}"
+        msg: "{{ ntp_vip_test.stderr_lines + ntp_vip_test.stdout_lines }}"
       when:
         - ntp_keepalived_enabled | default(false)
-        - vip_check.rc == 0
+        - vip_check.stdout | default('') | length > 0

ansible/plays/install-uptime-kuma.yml

@@ -1,13 +1,14 @@
 ---
 # Deploy Uptime Kuma to the NetBird VPS
-# Usage: ansible-playbook -i inventory/ plays/install-uptime-kuma.yml
+# Applied by site.yml.
 #
 # Prerequisites:
 # - netbird-server play applied (docker, Traefik on netbird_netbird)
 # - OpenBao homelab/infrastructure/uptime-kuma with keys username, password
 # - OpenBao homelab/infrastructure/uptime-kuma/smtp with keys server, port, username, token
 # - homelab/infrastructure/uptime-kuma-metrics (key api_key) is written by the role
-# - VAULT_TOKEN in the environment (policy: uptime-kuma-vps)
+# - an OpenBao token with policy uptime-kuma-vps: `bao login -method=oidc`
+#   (role owner) or VAULT_TOKEN
 # - DNS for kuma.renner.uno pointing at the VPS
 
 - name: Deploy Uptime Kuma

ansible/plays/rotate-netbird-secrets.yml

@@ -248,3 +248,6 @@
           - "Commit inventory/group_vars/all/netbird-rotatable.yml — it is encrypted."
           - "NOT rotated: datastore_key (needs dump/restore), auth_client_secret (Authentik side)."
           - "OpenBao is unaffected by design — its NetBird credentials are separate ones."
+
+- name: Close the SSH connections
+  ansible.builtin.import_playbook: close-connections.yml

ansible/plays/update-dist-upgrade.yml

@@ -43,7 +43,6 @@
             - ubuntu_upgrade.rc != 0 
             - "'No new release found' not in ubuntu_upgrade.stdout"
             - "'No new release found' not in ubuntu_upgrade.stderr"
-          ignore_errors: true
 
         - name: Display Upgrade Result
           ansible.builtin.debug:
@@ -111,3 +110,6 @@
       when: 
         - (ansible_distribution == 'Ubuntu' and reboot_required.stat.exists) or
           (ansible_distribution == 'Debian')
+
+- name: Close the SSH connections
+  ansible.builtin.import_playbook: close-connections.yml

ansible/plays/update-os.yml

@@ -0,0 +1,33 @@
+---
+# Package upgrade + reboot for netbird_proxy, edge_host and netbird_server,
+# one host at a time.
+# Usage (from ansible/): ansible-playbook plays/update-os.yml
+#
+# Plays run in order; a failed host stops the whole run (max_fail_percentage: 0).
+
+- name: Update NetBird proxies
+  hosts: netbird_proxy
+  serial: 1
+  max_fail_percentage: 0
+  become: true
+  roles:
+    - os-update
+
+- name: Update edge hosts
+  hosts: edge_host
+  serial: 1
+  max_fail_percentage: 0
+  become: true
+  roles:
+    - os-update
+
+- name: Update NetBird server
+  hosts: netbird_server
+  serial: 1
+  max_fail_percentage: 0
+  become: true
+  roles:
+    - os-update
+
+- name: Close the SSH connections
+  ansible.builtin.import_playbook: close-connections.yml

ansible/roles/chrony-exporter/tasks/main.yml

@@ -18,6 +18,7 @@
 - name: Get installed version
   command: "{{ chrony_exporter_binary }} --version"
   register: installed_version
+  check_mode: false
   when: chrony_exporter_installed.stat.exists
   changed_when: false
   failed_when: false

ansible/roles/claude-workstation/README.md

@@ -1,57 +0,0 @@
-# claude-workstation
-
-An always-on, **off-site** headless Claude Code host (Debian 12 VM under Synology
-VMM on nas-2). It runs (a) reattachable interactive `tmux` sessions and (b) an
-unattended notes-distill timer. It deliberately holds the **least** privilege
-that still does the job.
-
-## What lives here vs. what's manual
-
-This role configures everything **inside** the VM. Three things are **manual**
-(no IaC path) and precede/accompany it — see [`RUNBOOK.md`](RUNBOOK.md) for the
-full step-by-step:
-
-1. **VM creation** in Synology VMM (`ladmin` has no sudo; the DSM API is
-   root-only), with a cloud-init drive that installs the CI SSH key.
-2. **Netbird dashboard route** advertising the k8s API to the mesh, and the
-   **site-to-site return route** on the off-site gateway (backup path).
-3. **Secret material**: `claude setup-token` (subscription OAuth), the claude-bot
-   creds, and the read-only SA kubeconfig — encrypted into the group vault.
-
-## Credential isolation
-
-Two Unix users with separate credential stores so an unattended job cannot read
-the interactive session's secrets:
-
-| User | Holds | Runs |
-|------|-------|------|
-| `claude` | OAuth token, claude-bot creds, **read-only** SA kubeconfig | interactive tmux |
-| `claude-job` | its **own** OAuth token, claude-bot creds (no kubeconfig) | notes-distill timer |
-
-**No talosconfig, no SOPS age key** ever land here (Fable review #1). The
-kubeconfig is a read-only `view` ServiceAccount (`kubernetes/apps/claude-workstation/`).
-
-## Egress lockdown (staged)
-
-`claude_ws_egress_enforce` ships **`false`** so a fresh host is never bricked.
-The deny-default nftables ruleset, the DNS-resolver, and its refresh timer are
-installed regardless. Flip to `true` (in host/group vars) only after confirming
-`claude_ws_egress_allow_fqdns` / `claude_ws_egress_allow_cidrs*` cover real
-traffic — watch the `claude-egress-dropped` counter first.
-
-## Vault keys (encrypt into `inventory/group_vars/claude_workstation/vault.yml`)
-
-```
-netbird_setup_key                  # from the Netbird dashboard
-claude_ws_oauth_token_interactive  # `claude setup-token` (interactive user)
-claude_ws_oauth_token_job          # `claude setup-token` (job user, separate)
-claude_ws_gitea_token              # claude-bot PAT
-claude_ws_gitea_git_credentials    # https://claude-bot:<pat>@gitea.renner.uno
-claude_ws_kubeconfig               # read-only SA kubeconfig (literal YAML)
-```
-
-## Kill switch
-
-Everything unattended hangs off systemd timers; `systemctl disable --now
-claude-notes-distill.timer` (and the egress refresh) stops it. Every credential
-is independently revocable (SA token, claude-bot PAT, OAuth token, Netbird peer).

ansible/roles/claude-workstation/RUNBOOK.md

@@ -1,222 +0,0 @@
-# Runbook — off-site Claude Code workstation (nas-2)
-
-Operator guide for the manual steps around the `claude-workstation` role. The
-role automates everything **inside** the VM; this covers what it can't:
-VM creation, networking, secret material, egress cutover, rotation and DR.
-
-## Architecture (scope)
-
-An always-on **Debian 13 VM under Synology VMM on the off-site nas-2**
-(DS1522+, 10.3.40.0/24, reached over the site-to-site VPN, ~55 ms). It runs:
-
-- **Reattachable interactive sessions** (`tmux` over SSH as user `claude`).
-- **Unattended notes-distill timer** (as user `claude-job`).
-- **A thin is-home-up signal** (the existing external Gatus on the Netbird VPS
-  already covers this — don't duplicate it).
-
-**Out of scope (runs in-cluster instead):** scheduled repo-automation and
-cluster-reports go in as Woodpecker cron / CronJobs with an in-cluster
-ServiceAccount — *not* on this VM, so the VM holds no cluster-write creds.
-
-Credentials on the VM are minimal: a **read-only** `view` SA kubeconfig,
-claude-bot (non-admin) gitea creds, and a Claude subscription OAuth token.
-**No talosconfig, no SOPS age key.**
-
----
-
-## Step 1 — Create + install the VM (Synology VMM)
-
-`ladmin` has no sudo and the DSM API is root-only, so VMM is driven through the
-DSM **web UI**. Two hard facts dictate the method (all confirmed 2026-07-16, as
-built): **VMM has no cloud-init**, and its ISO-install wizard only creates blank
-disks. So the OS is installed from a **remastered Debian netinst ISO that
-auto-boots a preseed** — no console interaction, no boot-menu race.
-
-VMM gotchas that shape this (see the wiki build-record):
-- VMM refuses to change/unmount a VM's ISO while it is **running** ("Failed to
-  replace ISO files"). Do all ISO/boot-device edits with the VM **off**.
-- A **guest reboot does not re-read** VMM's boot-device/ISO config — only a full
-  VMM power-cycle applies it. So an auto-booting install ISO **loops** (reboot →
-  CD → reinstall, wiping the disk). Break it by preseeding the installer to
-  **power off** at the end: `d-i debian-installer/exit/poweroff boolean true`.
-- Attach the NIC to the **untagged `Default VM Network`** — the VLAN-40
-  `40_Server` network is isolated (no DHCP, no network). The LAN has DHCP.
-
-Procedure (build the ISO on a host with `xorriso`):
-1. Download the current Debian **netinst** (`.../debian-cd/current/amd64/iso-cd/`).
-2. Remaster it — add `/preseed.cfg` and replace `/isolinux/isolinux.cfg` with a
-   minimal one (`default preseed`, `timeout 1`, one label:
-   `kernel /install.amd/vmlinuz` /
-   `append auto=true priority=critical preseed/file=/cdrom/preseed.cfg vga=788 initrd=/install.amd/initrd.gz --- quiet`):
-   `xorriso -indev in.iso -outdev out.iso -boot_image any replay -map preseed.cfg /preseed.cfg -map isolinux.cfg /isolinux/isolinux.cfg`.
-   The preseed uses **DHCP** (`netcfg/dhcp_timeout 120` — the virtual-switch port
-   is slow to link), disk **`/dev/sda`** (VirtIO SCSI), **no user** + a locked
-   random root hash (key-only via `PermitRootLogin prohibit-password`), packages
-   `openssh-server sudo qemu-guest-agent python3`, and a `late_command` that
-   injects the SSH keys (`krenner@fortress`, `woodpecker-ci@homelab`, your
-   workstation key) into `/root/.ssh/authorized_keys`, plus the `poweroff` line.
-3. Upload to nas-2 via `ssh 'cat > /volume1/Install/<iso>' < <iso>` — **scp /
-   sftp / rsync are blocked on DSM**. Then VMM → Image → Add → From Synology NAS
-   → import (VMM **copies** it; re-import if you change the source file).
-4. Create VM: 2 vCPU, 4 GB, 50 GB on `/volume1`, **Default VM Network**, Legacy
-   BIOS, **Autostart: Yes**; attach the ISO, **Boot from DVD/CD-ROM**, power on.
-5. It installs unattended and **powers off**. Then (VM off) set **ISO =
-   Unmounted**, **Boot from = Virtual Disk**, power on → boots the installed
-   Debian. `qemu-guest-agent` reports the DHCP lease in VMM's IP column.
-6. **Pin a DSM update window** (Control Panel → Update & Restore) so an
-   auto-reboot doesn't kill tmux/jobs.
-
-> As built 2026-07-16: Debian 13 (trixie), got DHCP `10.3.40.78`, all three keys
-> injected, packages present. Freeing RAM required powering off the pre-existing
-> `pbs1` PBS VM (kept its 3.4 TB backup disk).
-
-> **At-rest encryption (Fable #6).** Off-site physical custody is weaker than
-> home. For true at-rest protection of the VM's secrets *with* unattended
-> autostart, use **network-bound decryption** (clevis + a Tang server at home):
-> a stolen disk off-site can't unlock because it can't reach Tang. Full-disk
-> LUKS with a manual passphrase would break autostart. Until Tang is stood up,
-> secrets rely on 0600 perms + VM access control — documented gap, not a fix.
-
----
-
-## Step 2 — Networking (two paths)
-
-**Netbird mesh (done via CI):** mint a setup key in the dashboard
-(`https://netbird.renner.uno`), vault it as `netbird_setup_key` under
-`group_vars/claude_workstation/`, and run `.woodpecker/deploy-netbird-client.yml`
-(`install-netbird-client.yml --limit claude_workstation`). As built 2026-07-16
-the VM enrolled as `claude-ws-190-112.nb.renner.uno` / `100.96.190.112` (+ IPv6).
-
-> **Mesh reachability caveat.** The mesh IP (`100.96.x`) is only reachable from
-> **other Netbird peers**. The home workstation and the Woodpecker CI agent are
-> **not** peers — they reach the VM only via the site-to-site tunnel at its DHCP
-> lease. So a *stable* mesh-based `ansible_host` needs CI (or a home host) on the
-> mesh first, or a Netbird routing peer bridging tunnel↔mesh. Until then the
-> inventory targets the tunnel DHCP IP.
-
-> **DNS trap.** `claude-ws.obg.renner.uno` resolves to the VM's lease **only at
-> the off-site DNS** (`@10.3.40.1`). The home resolver catch-alls `*.renner.uno`
-> to the public proxy (`162.55.50.97`, the Netbird VPS) — so from home the FQDN
-> lands on `root@netbird`, **not** the VM. Never use it as `ansible_host`.
-
-**Optional — mesh route to the k8s API (redundant read path):** to reach the API
-over the mesh too, add a Netbird dashboard **network route** advertising the
-apiserver's ClusterIP to the `netbird-ingress` peer group, and add an egress
-rule to the `netbird-ingress-egress` CiliumNetworkPolicy
-(`kubernetes/infrastructure/network-policies/ingress-isolation.yaml`) permitting
-`app: netbird-ingress` pods to reach `kube-apiserver:443`. Deferred from this PR
-because it edits a security-critical CNP that can't be validated offline — do it
-as a follow-up when you want the redundant API path.
-
----
-
-## Step 3 — Read-only SA kubeconfig
-
-After the `kubernetes/apps/claude-workstation/` PR merges and Flux reconciles:
-
-```sh
-NS=apps
-TOKEN=$(kubectl -n $NS get secret claude-workstation-token -o jsonpath='{.data.token}' | base64 -d)
-kubectl -n $NS get secret claude-workstation-token -o jsonpath='{.data.ca\.crt}' | base64 -d > /tmp/ca.crt
-# server = the cluster's stable API endpoint (kubernetes/talos/patches/cluster.yaml).
-# Use the name, not an address: it is what the API server certificate carries as a
-# SAN, so an IP here fails TLS verification even when it is reachable. It must
-# resolve from the workstation over the site-to-site route.
-kubectl config set-cluster homelab --server=https://k8s.renner.uno:6443 \
-  --certificate-authority=/tmp/ca.crt --embed-certs=true --kubeconfig=/tmp/claude-ws.kubeconfig
-kubectl config set-credentials claude-workstation --token="$TOKEN" --kubeconfig=/tmp/claude-ws.kubeconfig
-kubectl config set-context homelab --cluster=homelab --user=claude-workstation --kubeconfig=/tmp/claude-ws.kubeconfig
-kubectl config use-context homelab --kubeconfig=/tmp/claude-ws.kubeconfig
-# verify read-only:
-KUBECONFIG=/tmp/claude-ws.kubeconfig kubectl get nodes        # works
-KUBECONFIG=/tmp/claude-ws.kubeconfig kubectl get secrets -A   # Forbidden (view excludes secrets)
-```
-
-The resulting file becomes the `claude_ws_kubeconfig` vault value.
-
----
-
-## Step 4 — Secret material → vault
-
-```sh
-# Two independent OAuth tokens so job jobs can't impersonate the interactive user:
-claude setup-token   # -> claude_ws_oauth_token_interactive
-claude setup-token   # -> claude_ws_oauth_token_job  (run again / separate session)
-```
-
-Encrypt into `ansible/inventory/group_vars/claude_workstation/vault.yml`
-(ansible-vault; same VAULT_PASS the CI uses):
-
-```yaml
-netbird_setup_key: "..."
-claude_ws_oauth_token_interactive: "..."
-claude_ws_oauth_token_job: "..."
-claude_ws_gitea_token: "..."                # claude-bot PAT
-claude_ws_gitea_git_credentials: "https://claude-bot:<PAT>@gitea.renner.uno"
-claude_ws_kubeconfig: |
-  apiVersion: v1
-  ...                                        # the file from Step 3
-```
-
-> **Never run `claude` with `--bare`** here or on the VM — bare mode silently
-> ignores `CLAUDE_CODE_OAUTH_TOKEN` and the jobs will fail auth.
-
----
-
-## Step 5 — Deploy
-
-Merge the PR, then trigger the pipeline (Woodpecker → Run → `PIPELINE ==
-"deploy-claude-workstation"`), or push a change under the role's paths. CI SSHes
-to `10.3.40.60` over the tunnel and applies `common`, `netbird-client`, and this
-role. Also run the umbrella `plays/common.yml` against the new host once, so it
-picks up `qemu-guest-agent` like every other inventory host.
-
----
-
-## Step 6 — Egress cutover (staged)
-
-The nftables allowlist ships **disabled**. To enforce:
-
-1. Leave it off for a few days; watch what the box actually talks to.
-2. Confirm `claude_ws_egress_allow_fqdns` + `claude_ws_egress_allow_cidrs*`
-   (home Prometheus/Loki/API) cover it.
-3. Set `claude_ws_egress_enforce: true` in host/group vars, redeploy.
-4. Watch the `claude-egress-dropped` nft counter (`nft list ruleset`) and Loki
-   for anything legitimate being dropped; widen the allowlist as needed.
-
----
-
-## Step 7 — Notes (Syncthing pairing)
-
-The role installs Syncthing for `claude-job` and starts
-`syncthing@claude-job`. Pair it once (manual): from the VM's GUI (SSH tunnel to
-`127.0.0.1:8384`) add your existing vault's device ID and accept the shared
-`Notes` folder pointed at `{{ claude_ws_notes_dir }}`. The distill timer runs
-daily at 04:30 and only ever **creates** new atomic notes.
-
----
-
-## Rotation
-
-- **OAuth token** (expires/can be revoked): re-run `claude setup-token` on your
-  laptop, update the two vault keys, redeploy. Headless auth failures surface in
-  Loki (the wrapper logs `result=failure`) — don't let them go quiet.
-- **claude-bot PAT**: rotate in Gitea, update `claude_ws_gitea_*`, redeploy.
-- **SA token**: `kubectl -n apps delete secret claude-workstation-token` (Flux
-  recreates it), re-assemble the kubeconfig (Step 3), update vault, redeploy.
-
-## Kill switch
-
-```sh
-systemctl disable --now claude-notes-distill.timer claude-egress-refresh.timer
-```
-
-Every credential is independently revocable: delete the SA, revoke the PAT,
-revoke the OAuth token, or remove the Netbird peer — no shared blast radius.
-
-## Disaster recovery (cattle, not pet)
-
-The VM holds no unique state — the only real state is the Notes replica, which
-re-syncs from Syncthing. To rebuild: redo **Step 1** (VM + cloud-init), then
-**Step 5** (pipeline). No VMM snapshots needed (they'd bloat the 86%-full
-`/volume1`).

ansible/roles/claude-workstation/defaults/main.yml

@@ -1,68 +0,0 @@
----
-# claude-workstation role defaults
-#
-# An always-on headless host that runs Claude Code for (a) reattachable
-# interactive sessions and (b) unattended notes/wiki timers. It deliberately
-# holds the LEAST privilege that still lets it do its job: a read-only k8s
-# ServiceAccount kubeconfig, claude-bot (non-admin) gitea creds, and a Claude
-# subscription OAuth token — NO talosconfig and NO SOPS age key. See README.
-
-# --- Users -----------------------------------------------------------------
-# Two Unix users with separate credential stores so an unattended (timer) job
-# cannot read the interactive session's OAuth token / kube / gitea creds.
-claude_ws_interactive_user: claude          # human tmux sessions
-claude_ws_job_user: claude-job              # unattended systemd-timer jobs
-
-claude_ws_base_dir: /opt/claude-workstation
-
-# --- Toolchain -------------------------------------------------------------
-claude_ws_node_major: 22                     # matches the ci-claude image
-claude_ws_claude_code_pkg: "@anthropic-ai/claude-code"
-claude_ws_base_packages:
-  - git
-  - tmux
-  - jq
-  - curl
-  - ca-certificates
-  - ripgrep
-  - unzip
-  - nftables
-  - python3
-  - python3-venv
-
-# --- Egress allowlist ------------------------------------------------------
-# Deny-default OUTPUT is the target end-state, but it can brick a fresh host if
-# an allowed destination is missed, so it ships DISABLED and is tightened after
-# observing real egress (staged rollout). Flip claude_ws_egress_enforce to true
-# once the allowlist below is confirmed complete. See templates/nftables.conf.j2.
-claude_ws_egress_enforce: false
-# Static destinations the host must always reach. CDN-backed hosts (Anthropic,
-# npm, apt) are matched by name at apply time via the fqdn set; home services
-# are matched by IP. Tune in host_vars.
-claude_ws_egress_allow_fqdns:
-  - api.anthropic.com
-  - statsig.anthropic.com
-  - gitea.renner.uno
-  - fsn1.your-objectstorage.com          # Hetzner Object Storage (SOPS bundle)
-  - deb.debian.org
-  - security.debian.org
-  - deb.nodesource.com
-  - pkgs.netbird.io
-  - registry.npmjs.org
-claude_ws_egress_allow_cidrs: []          # home Prometheus/Loki/API (v4), per-host
-claude_ws_egress_allow_cidrs6: []         # same (v6) — IPv6-first, prefer these
-
-# --- Notes / wiki pipeline -------------------------------------------------
-# The Obsidian vault syncs onto this host via Syncthing (matches the user's
-# existing multi-device setup). Unattended pipeline jobs must CREATE new atomic
-# files rather than rewrite existing ones, to keep Syncthing conflicts rare.
-claude_ws_notes_enabled: true
-claude_ws_notes_dir: "/home/{{ claude_ws_job_user }}/Notes"
-claude_ws_syncthing_gui_bind: "127.0.0.1:8384"
-
-# --- Secrets (populated from the ansible-vault'd group_vars — see README) ---
-# claude_ws_oauth_token_interactive : CLAUDE_CODE_OAUTH_TOKEN for the human user
-# claude_ws_oauth_token_job         : CLAUDE_CODE_OAUTH_TOKEN for timer jobs
-# claude_ws_gitea_token             : claude-bot PAT
-# claude_ws_gitea_git_credentials   : https://claude-bot:<pat>@gitea.renner.uno line
-# claude_ws_kubeconfig              : read-only SA kubeconfig (base64 or literal)

ansible/roles/claude-workstation/files/claude-notes-distill-prompt.md

@@ -1,22 +0,0 @@
-You are running unattended as a scheduled job on the claude-workstation host.
-Your job is a conservative distillation pass over the Obsidian wiki vault.
-
-Scope and rules (follow exactly — you have only Read, Write, Glob, Grep):
-
-1. Look at `~/Notes/raw/` (ignore `~/Notes/raw/_processed/` and `~/Notes/_archive/`
-   entirely) for source material.
-2. For each raw source, check whether `~/Notes/wiki/` already contains a note
-   grounded in it (Grep the wiki for the source filename / its `sources:` slug).
-   If a note already exists, SKIP that source — do not rewrite or duplicate it.
-3. For raw sources with NO corresponding wiki note yet, create new atomic
-   concept notes in `~/Notes/wiki/`: one concept per file, self-contained,
-   tagged, cross-linked with `[[wikilinks]]`, every claim grounded in a
-   `sources:` entry. Never invent facts not present in the source.
-4. CREATE new files only. Never rewrite, move, delete, or truncate an existing
-   file in `~/Notes/` — appending a missing cross-link to a note you created
-   THIS run is fine; touching pre-existing notes is not.
-5. If there is nothing new to distill, do nothing and stop. Do not manufacture
-   work.
-
-Preserve disagreement: if sources conflict, surface the conflict in the note
-rather than silently picking a winner. Keep each note short and single-purpose.

ansible/roles/claude-workstation/files/tmux.conf

@@ -1,8 +0,0 @@
-# claude-workstation shared tmux config — reattachable long-running sessions.
-set -g history-limit 100000
-set -g mouse on
-set -g base-index 1
-setw -g pane-base-index 1
-set -g status-right "#H  %Y-%m-%d %H:%M"
-# Keep sessions alive across client disconnects (the whole point of this host).
-set -g destroy-unattached off

ansible/roles/claude-workstation/handlers/main.yml

@@ -1,10 +0,0 @@
----
-- name: Reload systemd
-  ansible.builtin.systemd:
-    daemon_reload: true
-
-- name: Reload nftables
-  ansible.builtin.systemd:
-    name: nftables.service
-    state: reloaded
-  when: claude_ws_egress_enforce | bool

ansible/roles/claude-workstation/tasks/firewall.yml

@@ -1,42 +0,0 @@
----
-# Deny-default egress allowlist. Ships DISABLED (claude_ws_egress_enforce:
-# false) so a fresh host is never bricked by a missed destination; the ruleset,
-# the FQDN-resolver, and its refresh timer are installed regardless, and the
-# operator flips the toggle to true once egress is confirmed complete against
-# real traffic (staged rollout). CDN-backed hosts are matched via nft named
-# sets that the refresh unit repopulates from DNS; static home services are
-# matched by claude_ws_egress_allow_cidrs.
-
-- name: Deploy the egress-refresh resolver
-  ansible.builtin.template:
-    src: claude-egress-refresh.sh.j2
-    dest: "{{ claude_ws_base_dir }}/claude-egress-refresh.sh"
-    mode: "0755"
-
-- name: Deploy the egress-refresh service + timer
-  ansible.builtin.template:
-    src: "{{ item }}.j2"
-    dest: "/etc/systemd/system/{{ item }}"
-    mode: "0644"
-  loop:
-    - claude-egress-refresh.service
-    - claude-egress-refresh.timer
-  notify: Reload systemd
-
-- name: Deploy the nftables ruleset
-  ansible.builtin.template:
-    src: nftables.conf.j2
-    dest: /etc/nftables.conf
-    mode: "0644"
-    validate: "nft -c -f %s"
-  notify: Reload nftables
-
-- name: Enforce or relax egress lockdown
-  ansible.builtin.systemd:
-    name: "{{ item }}"
-    enabled: "{{ claude_ws_egress_enforce | bool }}"
-    state: "{{ 'started' if (claude_ws_egress_enforce | bool) else 'stopped' }}"
-    daemon_reload: true
-  loop:
-    - nftables.service
-    - claude-egress-refresh.timer

ansible/roles/claude-workstation/tasks/main.yml

@@ -1,183 +0,0 @@
----
-# claude-workstation: an always-on headless Claude Code host.
-# Debian 12 VM on the off-site nas-2 (Synology VMM). See README for the manual
-# bootstrap (VM creation, Netbird route, secret material) that precedes this.
-#
-# common.yml already applies `common` and `qemu-guest-agent`
-# to every inventory host, so this role owns only the
-# Claude-specific surface: toolchain, the two credential-isolated users, the
-# read-only creds, notes sync, the unattended timers, and egress lockdown.
-
-- name: Assert we are on Debian (role is apt-only)
-  ansible.builtin.assert:
-    that:
-      - ansible_facts['os_family'] == 'Debian'
-    fail_msg: "claude-workstation targets Debian; got {{ ansible_facts['os_family'] }}."
-
-# --- Base packages ---------------------------------------------------------
-- name: Install base packages
-  ansible.builtin.apt:
-    name: "{{ claude_ws_base_packages }}"
-    state: present
-    update_cache: true
-
-# --- Node.js 22 + Claude Code (matches the ci-claude image toolchain) -------
-- name: Add NodeSource signing key
-  ansible.builtin.get_url:
-    url: https://deb.nodesource.com/gpgkey/nodesource-repo.gpg.key
-    dest: /usr/share/keyrings/nodesource.gpg
-    mode: "0644"
-    force: false
-
-- name: Add NodeSource apt repository
-  ansible.builtin.apt_repository:
-    repo: "deb [signed-by=/usr/share/keyrings/nodesource.gpg] https://deb.nodesource.com/node_{{ claude_ws_node_major }}.x nodistro main"
-    state: present
-    filename: nodesource
-
-- name: Install Node.js
-  ansible.builtin.apt:
-    name: nodejs
-    state: present
-    update_cache: true
-
-# NodeSource installs Node under /usr, so global npm modules land in
-# /usr/lib/node_modules and `claude` is on PATH for every user/timer. `creates`
-# keeps it idempotent (re-run `npm install -g` manually to bump the version).
-- name: Install Claude Code globally
-  ansible.builtin.command:
-    cmd: "npm install -g {{ claude_ws_claude_code_pkg }}"
-    creates: /usr/lib/node_modules/@anthropic-ai/claude-code
-
-# --- Credential-isolated users --------------------------------------------
-- name: Create Claude users
-  ansible.builtin.user:
-    name: "{{ item }}"
-    shell: /bin/bash
-    create_home: true
-  loop:
-    - "{{ claude_ws_interactive_user }}"
-    - "{{ claude_ws_job_user }}"
-
-- name: Create the role base directory (scripts, prompts)
-  ansible.builtin.file:
-    path: "{{ claude_ws_base_dir }}"
-    state: directory
-    mode: "0755"
-
-# Let the interactive user's tmux server survive SSH logout / reboot.
-- name: Enable lingering for the interactive user
-  ansible.builtin.command: "loginctl enable-linger {{ claude_ws_interactive_user }}"
-  args:
-    creates: "/var/lib/systemd/linger/{{ claude_ws_interactive_user }}"
-
-- name: Deploy shared tmux config
-  ansible.builtin.copy:
-    src: tmux.conf
-    dest: "/home/{{ item }}/.tmux.conf"
-    owner: "{{ item }}"
-    group: "{{ item }}"
-    mode: "0644"
-  loop:
-    - "{{ claude_ws_interactive_user }}"
-    - "{{ claude_ws_job_user }}"
-
-# --- Secrets: each user gets only what its role needs ----------------------
-# The interactive user gets gitea + OAuth + read-only kubeconfig. The job user
-# gets its OWN OAuth token + gitea (to open PRs) but NO kubeconfig.
-- name: Create ~/.config/claude-bot for the interactive user
-  ansible.builtin.file:
-    path: "/home/{{ item }}/.config/claude-bot"
-    state: directory
-    owner: "{{ item }}"
-    group: "{{ item }}"
-    mode: "0700"
-  loop:
-    - "{{ claude_ws_interactive_user }}"
-    - "{{ claude_ws_job_user }}"
-
-- name: Deploy claude-bot gitea token
-  ansible.builtin.copy:
-    content: "{{ claude_ws_gitea_token }}\n"
-    dest: "/home/{{ item }}/.config/claude-bot/gitea-token"
-    owner: "{{ item }}"
-    group: "{{ item }}"
-    mode: "0600"
-  loop:
-    - "{{ claude_ws_interactive_user }}"
-    - "{{ claude_ws_job_user }}"
-  no_log: true
-
-- name: Deploy claude-bot git-credentials
-  ansible.builtin.copy:
-    content: "{{ claude_ws_gitea_git_credentials }}\n"
-    dest: "/home/{{ item }}/.config/claude-bot/git-credentials"
-    owner: "{{ item }}"
-    group: "{{ item }}"
-    mode: "0600"
-  loop:
-    - "{{ claude_ws_interactive_user }}"
-    - "{{ claude_ws_job_user }}"
-  no_log: true
-
-# CLAUDE_CODE_OAUTH_TOKEN is delivered as an EnvironmentFile so both interactive
-# shells and timer units can source it without it landing in shell history.
-# NEVER run claude with --bare here: bare mode silently ignores this token.
-- name: Deploy per-user Claude OAuth environment file
-  ansible.builtin.copy:
-    content: "CLAUDE_CODE_OAUTH_TOKEN={{ item.token }}\n"
-    dest: "/home/{{ item.user }}/.config/claude-code.env"
-    owner: "{{ item.user }}"
-    group: "{{ item.user }}"
-    mode: "0600"
-  loop:
-    - { user: "{{ claude_ws_interactive_user }}", token: "{{ claude_ws_oauth_token_interactive }}" }
-    - { user: "{{ claude_ws_job_user }}", token: "{{ claude_ws_oauth_token_job }}" }
-  loop_control:
-    label: "{{ item.user }}"
-  no_log: true
-
-- name: Create ~/.kube for the interactive user
-  ansible.builtin.file:
-    path: "/home/{{ claude_ws_interactive_user }}/.kube"
-    state: directory
-    owner: "{{ claude_ws_interactive_user }}"
-    group: "{{ claude_ws_interactive_user }}"
-    mode: "0700"
-
-- name: Deploy read-only SA kubeconfig (interactive user only)
-  ansible.builtin.copy:
-    content: "{{ claude_ws_kubeconfig }}"
-    dest: "/home/{{ claude_ws_interactive_user }}/.kube/config"
-    owner: "{{ claude_ws_interactive_user }}"
-    group: "{{ claude_ws_interactive_user }}"
-    mode: "0600"
-  no_log: true
-
-# This VM's only git identity IS claude-bot (unlike the shared human
-# workstation, where a global credential.helper is forbidden), so a per-user
-# ~/.gitconfig pointing at each user's own claude-bot store is appropriate.
-- name: Configure git identity + credential store for the Claude users
-  ansible.builtin.copy:
-    dest: "/home/{{ item }}/.gitconfig"
-    owner: "{{ item }}"
-    group: "{{ item }}"
-    mode: "0644"
-    content: |
-      [user]
-      	name = Claude Bot
-      	email = claude-bot@renner.uno
-      [credential]
-      	helper = store --file=/home/{{ item }}/.config/claude-bot/git-credentials
-  loop:
-    - "{{ claude_ws_interactive_user }}"
-    - "{{ claude_ws_job_user }}"
-
-# --- Notes / wiki pipeline (Syncthing + timers) ----------------------------
-- name: Notes pipeline
-  ansible.builtin.include_tasks: notes.yml
-  when: claude_ws_notes_enabled | bool
-
-# --- Egress lockdown -------------------------------------------------------
-- name: Egress firewall
-  ansible.builtin.include_tasks: firewall.yml

ansible/roles/claude-workstation/tasks/notes.yml

@@ -1,48 +0,0 @@
----
-# Notes/wiki pipeline: the Obsidian vault syncs onto this host via Syncthing
-# (matching the user's existing multi-device setup), and a hardened, bounded
-# systemd timer runs an unattended `claude -p` distill pass over it as the
-# credential-isolated job user. Device pairing is a one-time manual step (see
-# README) — this only installs Syncthing and the timer.
-
-- name: Install Syncthing
-  ansible.builtin.apt:
-    name: syncthing
-    state: present
-    update_cache: true
-
-- name: Enable Syncthing for the job user
-  ansible.builtin.systemd:
-    name: "syncthing@{{ claude_ws_job_user }}.service"
-    enabled: true
-    state: started
-    daemon_reload: true
-
-- name: Deploy the notes-distill prompt
-  ansible.builtin.copy:
-    src: claude-notes-distill-prompt.md
-    dest: "{{ claude_ws_base_dir }}/claude-notes-distill-prompt.md"
-    mode: "0644"
-
-- name: Deploy the notes-distill wrapper
-  ansible.builtin.template:
-    src: claude-notes-distill.sh.j2
-    dest: "{{ claude_ws_base_dir }}/claude-notes-distill.sh"
-    mode: "0755"
-
-- name: Deploy the notes-distill service + timer
-  ansible.builtin.template:
-    src: "{{ item }}.j2"
-    dest: "/etc/systemd/system/{{ item }}"
-    mode: "0644"
-  loop:
-    - claude-notes-distill.service
-    - claude-notes-distill.timer
-  notify: Reload systemd
-
-- name: Enable the notes-distill timer
-  ansible.builtin.systemd:
-    name: claude-notes-distill.timer
-    enabled: true
-    state: started
-    daemon_reload: true

ansible/roles/claude-workstation/templates/claude-egress-refresh.service.j2

@@ -1,10 +0,0 @@
-[Unit]
-# {{ ansible_managed }}
-Description=Refresh claude-workstation egress allowlist from DNS
-After=nftables.service network-online.target
-Wants=network-online.target
-Requires=nftables.service
-
-[Service]
-Type=oneshot
-ExecStart={{ claude_ws_base_dir }}/claude-egress-refresh.sh

ansible/roles/claude-workstation/templates/claude-egress-refresh.sh.j2

@@ -1,27 +0,0 @@
-#!/usr/bin/env bash
-# {{ ansible_managed }}
-# Resolve the egress FQDN allowlist to current IPs and load them into the
-# nftables @allow4/@allow6 sets. CDN IPs rotate, so this runs on a timer.
-# No-op unless the claude_egress table is loaded (i.e. enforcement is on).
-set -euo pipefail
-
-TABLE="inet claude_egress"
-FQDNS=(
-{% for fqdn in claude_ws_egress_allow_fqdns %}
-    "{{ fqdn }}"
-{% endfor %}
-)
-
-nft list table $TABLE >/dev/null 2>&1 || { echo "claude_egress table not loaded; enforcement off"; exit 0; }
-
-v4=(); v6=()
-for host in "${FQDNS[@]}"; do
-    while read -r ip; do [ -n "$ip" ] && v4+=("$ip"); done < <(getent ahostsv4 "$host" | awk '{print $1}' | sort -u)
-    while read -r ip; do [ -n "$ip" ] && v6+=("$ip"); done < <(getent ahostsv6 "$host" | awk '{print $1}' | sort -u)
-done
-
-nft flush set $TABLE allow4
-nft flush set $TABLE allow6
-[ ${#v4[@]} -gt 0 ] && nft add element $TABLE allow4 "{ $(IFS=,; echo "${v4[*]}") }"
-[ ${#v6[@]} -gt 0 ] && nft add element $TABLE allow6 "{ $(IFS=,; echo "${v6[*]}") }"
-echo "claude-egress-refresh: ${#v4[@]} v4 + ${#v6[@]} v6 addresses loaded"

ansible/roles/claude-workstation/templates/claude-egress-refresh.timer.j2

@@ -1,10 +0,0 @@
-[Unit]
-# {{ ansible_managed }}
-Description=Periodically refresh the claude-workstation egress allowlist
-
-[Timer]
-OnBootSec=30s
-OnUnitActiveSec=15min
-
-[Install]
-WantedBy=timers.target

ansible/roles/claude-workstation/templates/claude-notes-distill.service.j2

@@ -1,32 +0,0 @@
-[Unit]
-# {{ ansible_managed }}
-Description=Claude Code unattended notes-distill pass
-After=network-online.target syncthing@{{ claude_ws_job_user }}.service
-Wants=network-online.target
-
-[Service]
-Type=oneshot
-User={{ claude_ws_job_user }}
-Group={{ claude_ws_job_user }}
-EnvironmentFile=/home/{{ claude_ws_job_user }}/.config/claude-code.env
-ExecStart={{ claude_ws_base_dir }}/claude-notes-distill.sh
-# Hard wall-clock kill — the runaway/kill switch for this unattended agent.
-TimeoutStartSec=1800
-
-# --- Hardening: an unattended LLM job on internet-influenced input ----------
-NoNewPrivileges=true
-PrivateTmp=true
-ProtectSystem=strict
-ReadWritePaths=/home/{{ claude_ws_job_user }}
-# Credential isolation: cannot read the interactive session's tokens/kubeconfig.
-InaccessiblePaths=/home/{{ claude_ws_interactive_user }}
-ProtectKernelTunables=true
-ProtectKernelModules=true
-ProtectControlGroups=true
-RestrictSUIDSGID=true
-RestrictNamespaces=true
-LockPersonality=true
-MemoryDenyWriteExecute=false
-
-[Install]
-WantedBy=multi-user.target

ansible/roles/claude-workstation/templates/claude-notes-distill.sh.j2

@@ -1,32 +0,0 @@
-#!/usr/bin/env bash
-# {{ ansible_managed }}
-# Unattended notes-distill pass. Prompt via stdin (never shell-substituted),
-# tool-allowlisted, no --bare (bare silently drops CLAUDE_CODE_OAUTH_TOKEN).
-# Bounded by the unit's TimeoutStartSec, not a CLI flag (--max-turns is absent
-# in the installed Claude Code). Emits a terminal state line to the journal on
-# EVERY outcome so a Loki alert can catch silent failures (dead-man switch).
-set -euo pipefail
-
-export HOME="/home/{{ claude_ws_job_user }}"
-NOTES="{{ claude_ws_notes_dir }}"
-PROMPT="{{ claude_ws_base_dir }}/claude-notes-distill-prompt.md"
-
-log() { logger -t claude-notes-distill -- "$*"; echo "claude-notes-distill: $*"; }
-
-if [ ! -d "$NOTES/raw" ]; then
-  log "result=skipped reason=no-vault path=$NOTES"
-  exit 0
-fi
-
-log "result=start"
-if claude -p \
-     --add-dir "$NOTES" \
-     --allowedTools "Read,Write,Glob,Grep" \
-     --model sonnet \
-     < "$PROMPT"; then
-  log "result=success"
-else
-  rc=$?
-  log "result=failure rc=$rc"
-  exit "$rc"
-fi

ansible/roles/claude-workstation/templates/claude-notes-distill.timer.j2

@@ -1,11 +0,0 @@
-[Unit]
-# {{ ansible_managed }}
-Description=Run the Claude Code notes-distill pass daily
-
-[Timer]
-OnCalendar=*-*-* 04:30:00
-Persistent=true
-RandomizedDelaySec=900
-
-[Install]
-WantedBy=timers.target

ansible/roles/claude-workstation/templates/nftables.conf.j2

@@ -1,55 +0,0 @@
-#!/usr/sbin/nft -f
-# {{ ansible_managed }}
-# Deny-default egress for the claude-workstation. CDN-backed destinations are
-# matched via the @allow4/@allow6 named sets, repopulated from DNS by
-# claude-egress-refresh. Static home services are matched by the @static* sets.
-# Only loaded when claude_ws_egress_enforce is true.
-flush ruleset
-
-table inet claude_egress {
-    set allow4 { type ipv4_addr; flags interval; }
-    set allow6 { type ipv6_addr; flags interval; }
-
-    set static4 {
-        type ipv4_addr
-        flags interval
-{% if (claude_ws_egress_allow_cidrs | default([])) | length > 0 %}
-        elements = { {{ claude_ws_egress_allow_cidrs | join(', ') }} }
-{% endif %}
-    }
-    set static6 {
-        type ipv6_addr
-        flags interval
-{% if (claude_ws_egress_allow_cidrs6 | default([])) | length > 0 %}
-        elements = { {{ claude_ws_egress_allow_cidrs6 | join(', ') }} }
-{% endif %}
-    }
-
-    chain output {
-        type filter hook output priority 0; policy drop;
-
-        oif "lo" accept
-        ct state established,related accept
-
-        # DNS — required to resolve the allowlist itself.
-        udp dport 53 accept
-        tcp dport 53 accept
-
-        # Diagnostics + DHCP lease renewal on the bridged interface.
-        ip protocol icmp accept
-        ip6 nexthdr icmpv6 accept
-        udp dport { 67, 68 } accept
-
-        # NetBird / WireGuard control + data plane (initial handshakes).
-        udp dport { 3478, 51820 } accept
-
-        # Allowed destinations.
-        ip  daddr @allow4  accept
-        ip6 daddr @allow6  accept
-        ip  daddr @static4 accept
-        ip6 daddr @static6 accept
-
-        # Everything else is dropped and counted for inspection.
-        counter comment "claude-egress-dropped"
-    }
-}

ansible/roles/common/tasks/main.yml

@@ -51,10 +51,8 @@
 # -------------------------------------------------------
 # 4. SSH Configuration
 # -------------------------------------------------------
-# Authorized keys (human + woodpecker-ci, the latter from=-restricted) are
-# managed by the dedicated ansible/plays/configure-ssh-keys.yml play. The old
-# "Add Ansible Runner SSH Key" task deployed ansible-runner@ci-new, a dead key
-# for a host that no longer exists — removed (issue #184).
+# SSH access (CA trust, admin authorized_keys) is managed by the ssh-ca role
+# via plays/configure-ssh-ca.yml.
 
 # -------------------------------------------------------
 # 5. Disable NTP on VMs/LXC (use host time)

ansible/roles/crowdsec-edge-bouncer/defaults/main.yml

@@ -3,7 +3,7 @@
 #
 # Enforces the decisions the in-cluster CrowdSec already detects, at the point
 # where public traffic actually enters: these hosts terminate TLS for every
-# *.renner.uno name. A drop here never reaches the mesh, the relay or the
+# public renner.uno name. A drop here never reaches the mesh, the relay or the
 # cluster.
 #
 # Detection stays in the cluster. The reverse-proxy produces no parseable

ansible/roles/crowdsec-edge-bouncer/tasks/main.yml

@@ -29,9 +29,11 @@
 # upstream ships no container image for this bouncer, which is expected —
 # it manipulates host netfilter.
 #
-# The CI runner has v4, so it does the fetching. The checksum is verified
-# there, before anything is copied to a host.
+# The controller has v4, so it does the fetching. The checksum is verified
+# there, before anything is copied to a host. Also in check mode: the fetch
+# only writes on the controller, and the copy below needs the file.
 - name: Fetch the pinned bouncer release on the controller
+  check_mode: false
   ansible.builtin.get_url:
     url: >-
       https://github.com/crowdsecurity/cs-firewall-bouncer/releases/download/{{

ansible/roles/heating-can/tasks/main.yml

@@ -87,6 +87,7 @@
   ansible.builtin.command:
     argv: [pgrep, -af, "edge-host/(open3e|e3oncan)"]
   register: heating_can_survivors
+  check_mode: false
   changed_when: false
   failed_when: false
 

ansible/roles/keepalived-ntp/tasks/main.yml

@@ -65,6 +65,7 @@
       - /etc/network/interfaces
       - /etc/network/interfaces.d/
   register: keepalived_ntp_static6_ifupdown
+  check_mode: false
   changed_when: false
   failed_when: false
   when:
@@ -123,6 +124,7 @@
       - "{{ keepalived_ntp_vip6.split('/')[0] }}\\b"
       - /etc/systemd/network/
   register: keepalived_ntp_static6_networkd
+  check_mode: false
   changed_when: false
   failed_when: false
   when:
@@ -140,9 +142,8 @@
       Handing the address to keepalived while networkd also assigns it means
       it would NOT be withdrawn when check_ntp fails -- the host would keep
       serving time on an address VRRP believes it has released.
-      Re-apply the edge-vlan role first, whose template no longer carries the
-      [Address] block:
-      ansible-playbook -i inventory/pve_hosts.yml plays/install-edge-host.yml
+      Re-apply the edge-vlan role first (site.yml runs it before this play),
+      whose template no longer carries the [Address] block.
     success_msg: >-
       No static networkd assignment of {{ keepalived_ntp_vip6 }}; safe for
       keepalived to own it.

ansible/roles/netbird-client/defaults/main.yml

@@ -6,3 +6,13 @@ netbird_management_url: "https://netbird.renner.uno"
 
 # Setup key - should be defined in group_vars or host_vars
 # netbird_setup_key: ""
+
+# Release installed on hosts without a NetBird package repository (Arch).
+# Debian/Ubuntu follow the apt repository instead.
+netbird_client_version: "0.75.0"
+netbird_release_url: "https://github.com/netbirdio/netbird/releases/download/v{{ netbird_client_version }}"
+# On the controller; the archive is copied from there to the hosts.
+netbird_download_dir: "{{ lookup('ansible.builtin.env', 'HOME') }}/.cache/ansible/netbird"
+
+# Leave the host's DNS configuration alone (hosts with a pinned resolv.conf).
+netbird_disable_dns: false

ansible/roles/netbird-client/tasks/main.yml

@@ -2,47 +2,79 @@
 # NetBird Client Installation Role
 # Installs and configures NetBird client on hosts with netbird_setup_key defined
 
-- name: Install required packages
-  ansible.builtin.apt:
-    name:
-      - curl
-      - ca-certificates
-      - gnupg
-    state: present
-    update_cache: true
+- name: Install NetBird from the NetBird apt repository
+  when: ansible_facts['os_family'] == 'Debian'
+  block:
+    - name: Install required packages
+      ansible.builtin.apt:
+        name:
+          - curl
+          - ca-certificates
+          - gnupg
+        state: present
+        update_cache: true
 
-- name: Add NetBird repository key
-  ansible.builtin.shell:
-    cmd: |
-      curl -sSL https://pkgs.netbird.io/debian/public.key | gpg --dearmor -o /usr/share/keyrings/netbird-archive-keyring.gpg
-    creates: /usr/share/keyrings/netbird-archive-keyring.gpg
+    - name: Add NetBird repository key
+      ansible.builtin.shell:
+        cmd: |
+          curl -sSL https://pkgs.netbird.io/debian/public.key | gpg --dearmor -o /usr/share/keyrings/netbird-archive-keyring.gpg
+        creates: /usr/share/keyrings/netbird-archive-keyring.gpg
 
-- name: Add NetBird repository
-  ansible.builtin.apt_repository:
-    repo: "deb [signed-by=/usr/share/keyrings/netbird-archive-keyring.gpg] https://pkgs.netbird.io/debian stable main"
-    state: present
-    filename: netbird
+    - name: Add NetBird repository
+      ansible.builtin.apt_repository:
+        repo: "deb [signed-by=/usr/share/keyrings/netbird-archive-keyring.gpg] https://pkgs.netbird.io/debian stable main"
+        state: present
+        filename: netbird
 
-- name: Install NetBird client
-  ansible.builtin.apt:
-    name: netbird
-    state: present
-    update_cache: true
+    - name: Install NetBird client
+      ansible.builtin.apt:
+        name: netbird
+        state: present
+        update_cache: true
 
-- name: Check if NetBird is already connected
-  ansible.builtin.command: netbird status
-  register: netbird_status
-  changed_when: false
-  failed_when: false
+# Arch has no netbird package in its repositories; the release binary is
+# verified against the release's checksums file. It is downloaded on the
+# controller and copied over: github.com has no IPv6 address, and proxy-1 is
+# IPv6-only. The controller steps also run in check mode: they only write on
+# the controller, and the install step needs the archive.
+- name: Install NetBird from the release tarball
+  when: ansible_facts['os_family'] == 'Archlinux'
+  block:
+    - name: Create the controller download directory
+      ansible.builtin.file:
+        path: "{{ netbird_download_dir }}"
+        state: directory
+        mode: "0755"
+      delegate_to: localhost
+      become: false
+      run_once: true
+      check_mode: false
 
-- name: Connect NetBird to management server
-  ansible.builtin.command: >
-    netbird up
-    --management-url {{ netbird_management_url }}
-    --setup-key {{ netbird_setup_key }}
-  when: "'Connected' not in netbird_status.stdout"
-  register: netbird_connect
-  changed_when: netbird_connect.rc == 0
+    - name: Download the NetBird release on the controller
+      check_mode: false
+      ansible.builtin.get_url:
+        url: "{{ netbird_release_url }}/netbird_{{ netbird_client_version }}_linux_amd64.tar.gz"
+        dest: "{{ netbird_download_dir }}/netbird_{{ netbird_client_version }}_linux_amd64.tar.gz"
+        checksum: "sha256:{{ netbird_release_url }}/netbird_{{ netbird_client_version }}_checksums.txt"
+        mode: "0644"
+      delegate_to: localhost
+      become: false
+      run_once: true
+
+    - name: Install the NetBird binary
+      ansible.builtin.unarchive:
+        src: "{{ netbird_download_dir }}/netbird_{{ netbird_client_version }}_linux_amd64.tar.gz"
+        dest: /usr/local/bin
+        include:
+          - netbird
+        owner: root
+        group: root
+        mode: "0755"
+
+    - name: Install the NetBird service
+      ansible.builtin.command: netbird service install
+      args:
+        creates: /etc/systemd/system/netbird.service
 
 - name: Enable NetBird service
   ansible.builtin.service:
@@ -50,9 +82,29 @@
     state: started
     enabled: true
 
+- name: Check if NetBird is already connected
+  ansible.builtin.command: netbird status
+  register: netbird_status
+  check_mode: false
+  changed_when: false
+  failed_when: false
+
+# "Disconnected" contains "Connected", so match the management line.
+- name: Connect NetBird to management server
+  ansible.builtin.command: >
+    netbird up
+    --management-url {{ netbird_management_url }}
+    --setup-key {{ netbird_setup_key }}
+    {{ '--disable-dns' if netbird_disable_dns else '' }}
+  when: "'Management: Connected' not in netbird_status.stdout"
+  register: netbird_connect
+  changed_when: netbird_connect.rc == 0
+  no_log: true
+
 - name: Get NetBird status
   ansible.builtin.command: netbird status
   register: netbird_final_status
+  check_mode: false
   changed_when: false
 
 - name: Display NetBird status

ansible/roles/netbird-server/tasks/main.yml

@@ -136,27 +136,41 @@
     - /opt/netbird/proxy
     - /opt/netbird/proxy-state
 
-# The management store has no cluster-side backup. Pulling one put a root
-# key on this host that the cluster held, and this server's own state is
-# its own business to protect rather than the cluster's. Dropping the two
-# tasks that placed them would only stop ansible managing the key and the
-# script — the pair below revokes them instead, and can go once the role
-# has run against every host that ever carried them.
+# The management store has no cluster-side backup; the cluster's backup
+# key is gone with the managed authorized_keys (ssh-ca role).
 - name: Remove the backup dump script
   ansible.builtin.file:
     path: /usr/local/bin/netbird-backup-dump
     state: absent
 
-- name: Revoke the cluster backup key
-  ansible.posix.authorized_key:
-    user: root
-    key: "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFeW/L9bHMTSa5/Qb0ClppCf4Z0hL39JwzI6tBmKd2FG netbird-backup@homelab-cluster"
-    state: absent
-
 - name: Wait for management container to be ready
   ansible.builtin.pause:
     seconds: 10
 
+# The host's mesh client must not manage DNS: containers here resolve through
+# the host stub, and the renner.uno nameserver group is unreachable from it.
+- name: Check for the host NetBird client
+  ansible.builtin.stat:
+    path: /usr/bin/netbird
+  register: _netbird_client
+
+- name: Read the host NetBird client config
+  ansible.builtin.command: netbird debug config
+  register: _netbird_client_config
+  check_mode: false
+  changed_when: false
+  when: _netbird_client.stat.exists
+
+# disable-dns is only applied on a fresh `up`, not to a connected client.
+- name: Reconnect the host NetBird client with DNS management disabled
+  ansible.builtin.shell: |
+    set -eu
+    netbird down
+    netbird up --disable-dns
+  when:
+    - _netbird_client.stat.exists
+    - not (_netbird_client_config.stdout | from_json).disableDns
+
 - name: Display deployment status
   ansible.builtin.debug:
     msg: |

ansible/roles/netbird-server/templates/docker-compose.yml.j2

@@ -61,6 +61,10 @@ services:
       - AUTH_AUDIENCE={{ netbird_auth_audience }}
       - AUTH_CLIENT_ID={{ netbird_auth_client_id }}
       - AUTH_AUTHORITY={{ netbird_auth_issuer }}
+      # The CSP allows AUTH_AUTHORITY only as a path (/application/o/netbird/);
+      # Authentik's token/userinfo endpoints sit outside it, so the browser
+      # would block the code exchange and every token refresh.
+      - NETBIRD_CSP={{ netbird_auth_issuer | urlsplit('scheme') }}://{{ netbird_auth_issuer | urlsplit('netloc') }}
       - USE_AUTH0=false
       - AUTH_SUPPORTED_SCOPES=openid profile email
       - NETBIRD_TOKEN_SOURCE=idToken

ansible/roles/node-exporter/defaults/main.yml

@@ -1,20 +0,0 @@
----
-# Node Exporter defaults
-
-node_exporter_version: "1.8.2"
-node_exporter_port: 9100
-node_exporter_user: node-exporter
-node_exporter_group: node-exporter
-
-# Installation paths
-node_exporter_install_dir: /opt/node-exporter
-node_exporter_binary: "{{ node_exporter_install_dir }}/node_exporter"
-
-# Collectors to enable (defaults are usually sufficient)
-node_exporter_enabled_collectors:
-  - systemd
-  - processes
-  - timex
-
-# Collectors to disable
-node_exporter_disabled_collectors: []

ansible/roles/node-exporter/files/chrony-metrics.sh

@@ -1,62 +0,0 @@
-#!/bin/bash
-# Generate Prometheus metrics from chronyc tracking output
-# Runs as a cron job and outputs to textfile collector directory
-
-OUTPUT_FILE="${1:-/var/lib/node-exporter/chrony.prom}"
-
-# Get chrony tracking info
-tracking=$(chronyc tracking 2>/dev/null)
-
-if [ -z "$tracking" ]; then
-    echo "chrony_up 0" > "$OUTPUT_FILE.tmp"
-    mv "$OUTPUT_FILE.tmp" "$OUTPUT_FILE"
-    exit 0
-fi
-
-# Parse values
-stratum=$(echo "$tracking" | grep "^Stratum" | awk '{print $3}')
-system_time=$(echo "$tracking" | grep "^System time" | awk '{print $4}')
-root_delay=$(echo "$tracking" | grep "^Root delay" | awk '{print $4}')
-root_dispersion=$(echo "$tracking" | grep "^Root dispersion" | awk '{print $4}')
-last_offset=$(echo "$tracking" | grep "^Last offset" | awk '{print $4}')
-rms_offset=$(echo "$tracking" | grep "^RMS offset" | awk '{print $4}')
-frequency=$(echo "$tracking" | grep "^Frequency" | awk '{print $3}')
-ref_id=$(echo "$tracking" | grep "^Reference ID" | awk '{print $4}' | tr -d '()')
-
-# Handle negative offsets (remove leading + or keep -)
-system_time=$(echo "$system_time" | sed 's/^+//')
-last_offset=$(echo "$last_offset" | sed 's/^+//')
-rms_offset=$(echo "$rms_offset" | sed 's/^+//')
-
-# Output Prometheus metrics
-cat > "$OUTPUT_FILE.tmp" << EOF
-# HELP chrony_stratum Current stratum of the NTP server
-# TYPE chrony_stratum gauge
-chrony_stratum ${stratum:-0}
-# HELP chrony_system_time_offset_seconds System time offset from NTP time
-# TYPE chrony_system_time_offset_seconds gauge
-chrony_system_time_offset_seconds ${system_time:-0}
-# HELP chrony_root_delay_seconds Total round-trip delay to the primary reference clock
-# TYPE chrony_root_delay_seconds gauge
-chrony_root_delay_seconds ${root_delay:-0}
-# HELP chrony_root_dispersion_seconds Total dispersion to the primary reference clock
-# TYPE chrony_root_dispersion_seconds gauge
-chrony_root_dispersion_seconds ${root_dispersion:-0}
-# HELP chrony_last_offset_seconds Estimated offset of the last update
-# TYPE chrony_last_offset_seconds gauge
-chrony_last_offset_seconds ${last_offset:-0}
-# HELP chrony_rms_offset_seconds RMS offset
-# TYPE chrony_rms_offset_seconds gauge
-chrony_rms_offset_seconds ${rms_offset:-0}
-# HELP chrony_frequency_ppm Frequency offset in parts per million
-# TYPE chrony_frequency_ppm gauge
-chrony_frequency_ppm ${frequency:-0}
-# HELP chrony_up Whether chrony is running and synchronized
-# TYPE chrony_up gauge
-chrony_up 1
-# HELP chrony_reference_info Reference clock information
-# TYPE chrony_reference_info gauge
-chrony_reference_info{reference="${ref_id:-unknown}"} 1
-EOF
-
-mv "$OUTPUT_FILE.tmp" "$OUTPUT_FILE"

ansible/roles/node-exporter/handlers/main.yml

@@ -1,9 +0,0 @@
----
-- name: Reload systemd
-  systemd:
-    daemon_reload: yes
-
-- name: Restart node-exporter
-  systemd:
-    name: node-exporter
-    state: restarted

ansible/roles/node-exporter/tasks/main.yml

@@ -1,88 +0,0 @@
----
-# Install and configure Node Exporter
-
-- name: Create node-exporter system group
-  group:
-    name: "{{ node_exporter_group }}"
-    system: yes
-    state: present
-
-- name: Create node-exporter system user
-  user:
-    name: "{{ node_exporter_user }}"
-    group: "{{ node_exporter_group }}"
-    system: yes
-    shell: /usr/sbin/nologin
-    home: "{{ node_exporter_install_dir }}"
-    createhome: no
-
-- name: Create installation directory
-  file:
-    path: "{{ node_exporter_install_dir }}"
-    state: directory
-    owner: "{{ node_exporter_user }}"
-    group: "{{ node_exporter_group }}"
-    mode: '0755'
-
-- name: Check if node_exporter is already installed
-  stat:
-    path: "{{ node_exporter_binary }}"
-  register: node_exporter_installed
-
-- name: Get installed version
-  command: "{{ node_exporter_binary }} --version"
-  register: installed_version
-  when: node_exporter_installed.stat.exists
-  changed_when: false
-  failed_when: false
-
-- name: Download node_exporter
-  get_url:
-    url: "https://github.com/prometheus/node_exporter/releases/download/v{{ node_exporter_version }}/node_exporter-{{ node_exporter_version }}.linux-amd64.tar.gz"
-    dest: /tmp/node_exporter.tar.gz
-    mode: '0644'
-  when: not node_exporter_installed.stat.exists or (installed_version.stdout is defined and node_exporter_version not in installed_version.stdout)
-
-- name: Extract node_exporter
-  unarchive:
-    src: /tmp/node_exporter.tar.gz
-    dest: /tmp
-    remote_src: yes
-  when: not node_exporter_installed.stat.exists or (installed_version.stdout is defined and node_exporter_version not in installed_version.stdout)
-
-- name: Install node_exporter binary
-  copy:
-    src: "/tmp/node_exporter-{{ node_exporter_version }}.linux-amd64/node_exporter"
-    dest: "{{ node_exporter_binary }}"
-    owner: "{{ node_exporter_user }}"
-    group: "{{ node_exporter_group }}"
-    mode: '0755'
-    remote_src: yes
-  when: not node_exporter_installed.stat.exists or (installed_version.stdout is defined and node_exporter_version not in installed_version.stdout)
-  notify: Restart node-exporter
-
-- name: Create systemd service
-  template:
-    src: node_exporter.service.j2
-    dest: /etc/systemd/system/node-exporter.service
-    owner: root
-    group: root
-    mode: '0644'
-  notify:
-    - Reload systemd
-    - Restart node-exporter
-
-- name: Enable and start node-exporter service
-  systemd:
-    name: node-exporter
-    enabled: yes
-    state: started
-    daemon_reload: yes
-
-- name: Clean up downloaded files
-  file:
-    path: "{{ item }}"
-    state: absent
-  loop:
-    - /tmp/node_exporter.tar.gz
-    - "/tmp/node_exporter-{{ node_exporter_version }}.linux-amd64"

ansible/roles/node-exporter/templates/node_exporter.service.j2

@@ -1,38 +0,0 @@
-[Unit]
-Description=Prometheus Node Exporter
-Documentation=https://github.com/prometheus/node_exporter
-After=network-online.target
-Wants=network-online.target
-
-[Service]
-Type=simple
-User={{ node_exporter_user }}
-Group={{ node_exporter_group }}
-ExecStart={{ node_exporter_binary }} \
-  --web.listen-address=:{{ node_exporter_port }} \
-{% for collector in node_exporter_enabled_collectors %}
-  --collector.{{ collector }} \
-{% endfor %}
-{% for collector in node_exporter_disabled_collectors %}
-  --no-collector.{{ collector }} \
-{% endfor %}
-{% if node_exporter_textfile_dir is defined %}
-  --collector.textfile \
-  --collector.textfile.directory={{ node_exporter_textfile_dir }} \
-{% endif %}
-  --collector.filesystem.mount-points-exclude='^/(sys|proc|dev|host|etc)($$|/)'
-Restart=on-failure
-RestartSec=10s
-
-# Security hardening
-NoNewPrivileges=yes
-ProtectSystem=strict
-ProtectHome=yes
-PrivateTmp=yes
-ReadOnlyPaths=/
-{% if node_exporter_textfile_dir is defined %}
-ReadWritePaths={{ node_exporter_textfile_dir }}
-{% endif %}
-
-[Install]
-WantedBy=multi-user.target

ansible/roles/os-update/tasks/main.yml

@@ -0,0 +1,142 @@
+---
+- name: Fail on unsupported distribution
+  ansible.builtin.fail:
+    msg: >-
+      os-update supports Debian and Archlinux only;
+      this host reports os_family={{ ansible_facts['os_family'] }}
+  when: ansible_facts['os_family'] not in ['Debian', 'Archlinux']
+
+# --- Baseline: what is healthy before the upgrade must be healthy after ---
+- name: Record failed units before upgrade
+  ansible.builtin.command: systemctl list-units --state=failed --plain --no-legend --no-pager
+  register: os_update_failed_before
+  changed_when: false
+  check_mode: false
+
+- name: Check for docker
+  ansible.builtin.stat:
+    path: /usr/bin/docker
+  register: os_update_docker
+
+- name: Record running containers before upgrade
+  ansible.builtin.command: docker ps --format "{{ '{{' }}.Names{{ '}}' }}"
+  register: os_update_containers_before
+  changed_when: false
+  check_mode: false
+  when: os_update_docker.stat.exists
+
+- name: Assert at least 1 GiB free on /
+  ansible.builtin.assert:
+    that: >-
+      (ansible_facts['mounts'] | selectattr('mount', 'equalto', '/') | first)['size_available']
+      >= 1073741824
+    fail_msg: "Less than 1 GiB free on / -- free space before upgrading"
+
+# --- Arch Linux ---
+- name: Upgrade keyring first (Arch)
+  community.general.pacman:
+    name: archlinux-keyring
+    state: latest
+    update_cache: true
+  when: ansible_facts['os_family'] == 'Archlinux'
+
+- name: Upgrade all packages (Arch)
+  community.general.pacman:
+    upgrade: true
+  register: os_update_pacman
+  when: ansible_facts['os_family'] == 'Archlinux'
+
+# --- Debian/Ubuntu ---
+- name: Upgrade all packages (Debian)
+  ansible.builtin.apt:
+    update_cache: true
+    upgrade: full
+    autoremove: true
+  environment:
+    DEBIAN_FRONTEND: noninteractive
+  when: ansible_facts['os_family'] == 'Debian'
+
+- name: Check reboot-required flag (Debian)
+  ansible.builtin.stat:
+    path: /var/run/reboot-required
+  register: os_update_reboot_flag
+  when: ansible_facts['os_family'] == 'Debian'
+
+# --- Reboot ---
+- name: Read running kernel before reboot (Arch)
+  ansible.builtin.command: uname -r
+  register: os_update_kernel_before
+  changed_when: false
+  check_mode: false
+  when: ansible_facts['os_family'] == 'Archlinux'
+
+# Missing modules dir: a newer kernel is installed but not booted, including
+# from an earlier interrupted run where pacman now reports no change.
+- name: Check running kernel is still installed (Arch)
+  ansible.builtin.stat:
+    path: "/usr/lib/modules/{{ os_update_kernel_before.stdout }}/vmlinuz"
+  register: os_update_kernel_present
+  when: ansible_facts['os_family'] == 'Archlinux'
+
+- name: Reboot
+  ansible.builtin.reboot:
+    msg: "Rebooting after package upgrade"
+    reboot_timeout: 900
+    post_reboot_delay: 30
+  when: >-
+    (ansible_facts['os_family'] == 'Archlinux' and
+      (os_update_pacman is changed or not os_update_kernel_present.stat.exists)) or
+    (ansible_facts['os_family'] == 'Debian' and os_update_reboot_flag.stat.exists)
+
+# --- Verify ---
+- name: Read running kernel
+  ansible.builtin.command: uname -r
+  register: os_update_kernel
+  changed_when: false
+  check_mode: false
+
+# Arch keeps only the installed kernel's modules; the directory existing means
+# the host booted the kernel pacman installed.
+- name: Assert running kernel is the installed one (Arch)
+  ansible.builtin.stat:
+    path: "/usr/lib/modules/{{ os_update_kernel.stdout }}/vmlinuz"
+  register: os_update_kernel_installed
+  failed_when: not os_update_kernel_installed.stat.exists
+  when: ansible_facts['os_family'] == 'Archlinux'
+
+- name: Assert no reboot pending (Debian)
+  ansible.builtin.stat:
+    path: /var/run/reboot-required
+  register: os_update_reboot_flag_after
+  failed_when: os_update_reboot_flag_after.stat.exists
+  when: ansible_facts['os_family'] == 'Debian'
+
+- name: Wait for previously running containers
+  ansible.builtin.command: docker ps --format "{{ '{{' }}.Names{{ '}}' }}"
+  register: os_update_containers_after
+  changed_when: false
+  check_mode: false
+  until: >-
+    os_update_containers_before.stdout_lines
+    | difference(os_update_containers_after.stdout_lines)
+    | length == 0
+  retries: 20
+  delay: 15
+  when: os_update_docker.stat.exists
+
+- name: Wait for no new failed units
+  ansible.builtin.command: systemctl list-units --state=failed --plain --no-legend --no-pager
+  register: os_update_failed_after
+  changed_when: false
+  check_mode: false
+  until: >-
+    os_update_failed_after.stdout_lines
+    | map('split') | map('first')
+    | difference(os_update_failed_before.stdout_lines | map('split') | map('first'))
+    | length == 0
+  retries: 10
+  delay: 15
+
+- name: Report kernel
+  ansible.builtin.debug:
+    msg: "{{ inventory_hostname }} runs {{ os_update_kernel.stdout }}"

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

@@ -0,0 +1,18 @@
+---
+# SSH user CA (OpenBao ssh-client-signer). Hosts trust certificates signed by
+# it; the public key is fetched from OpenBao on the controller at run time.
+ssh_ca_public_key_url: "https://openbao.renner.uno/v1/ssh-client-signer/public_key"
+
+# Owner certificates (role owner) carry this principal. It is accepted for
+# whichever admin login the distro has; users that do not exist are skipped.
+ssh_ca_owner_principal: k.renner
+ssh_ca_owner_users:
+  - root
+  - ladmin
+
+# Claude's own account. Certificates (role claude, 1h) carry the principal.
+ssh_ca_claude_user: claude-bot
+ssh_ca_claude_principal: claude-bot
+
+# Units claude-bot may restart/reload via sudo on this host, e.g. [netbird].
+ssh_ca_claude_sudo_units: []

ansible/roles/ssh-ca/files/revoked_keys

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

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

@@ -0,0 +1,23 @@
+---
+# Replaces the admin logins' authorized_keys with ssh_admin_authorized_keys
+# (break-glass + CI). Everything else logs in with a CA certificate.
+- name: Look up the admin logins
+  ansible.builtin.getent:
+    database: passwd
+    key: "{{ item }}"
+    fail_key: false
+  loop: "{{ ssh_ca_owner_users }}"
+  register: ssh_ca_admin_lookup
+
+- name: Set the admin logins' authorized_keys to the managed list
+  ansible.posix.authorized_key:
+    user: "{{ item.item }}"
+    key: |
+      {% for k in ssh_admin_authorized_keys %}
+      {{ (k.options ~ ' ') if (k.options | default('')) else '' }}{{ k.key }}
+      {% endfor %}
+    exclusive: true
+  loop: "{{ ssh_ca_admin_lookup.results }}"
+  loop_control:
+    label: "{{ item.item }}"
+  when: (item.ansible_facts.getent_passwd | default({})).get(item.item) is not none

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

@@ -0,0 +1,167 @@
+---
+- 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
+  check_mode: false
+
+- 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"
+
+# systemd-journal: read every journal without sudo (see sudoers-claude.j2).
+- name: Create the Claude account
+  ansible.builtin.user:
+    name: "{{ ssh_ca_claude_user }}"
+    shell: /bin/bash
+    create_home: true
+    password: "!"
+    groups: systemd-journal
+    append: true
+
+- 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. Not in check mode: sshd -T
+# reads the files on disk, which check mode has not written.
+- name: Check sshd uses the CA, principals and revocation list
+  when: not ansible_check_mode
+  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"
+      - "'passwordauthentication no' in ssh_ca_effective_lines"
+      - "'kbdinteractiveauthentication no' 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,
+# where sshd.service is an alias that resolves to it. sshd -T only parses the
+# files, so the running daemon is reloaded on every run; a reload keeps open
+# sessions. None runs when sshd is socket activated and stopped, or per
+# connection (ssh-mesh-only role); the next start reads the config.
+# systemctl directly: service_facts took 3-12 s per host.
+- name: Find the running sshd unit
+  ansible.builtin.command: systemctl list-units --state=running --plain --no-legend --type=service sshd.service ssh.service
+  changed_when: false
+  register: ssh_ca_sshd_running
+  check_mode: false
+
+- name: Reload the running sshd unit
+  vars:
+    ssh_ca_sshd_units: "{{ ssh_ca_sshd_running.stdout_lines | map('split') | map('first') | unique | list }}"
+  block:
+    - name: Check at most one sshd unit is running
+      ansible.builtin.assert:
+        that:
+          - ssh_ca_sshd_units | length <= 1
+        fail_msg: "Expected at most 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
+      when: ssh_ca_sshd_units | length == 1
+
+- name: Report the admin logins' authorized keys
+  ansible.builtin.include_tasks: report.yml

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

@@ -0,0 +1,27 @@
+---
+# Read-only: what the admin logins accept besides certificates. Hosts in
+# [ssh_keys_managed] have this reduced to ssh_admin_authorized_keys.
+- name: Find the admin logins' authorized_keys
+  ansible.builtin.stat:
+    path: "{{ item.ansible_facts.getent_passwd[item.item][4] }}/.ssh/authorized_keys"
+  loop: "{{ ssh_ca_owner_lookup.results }}"
+  loop_control:
+    label: "{{ item.item }}"
+  when: (item.ansible_facts.getent_passwd | default({})).get(item.item) is not none
+  register: ssh_ca_keyfiles
+
+- name: Fingerprint the admin logins' authorized keys
+  ansible.builtin.command: ssh-keygen -lf {{ item.stat.path }}
+  loop: "{{ ssh_ca_keyfiles.results | selectattr('stat', 'defined') | selectattr('stat.exists') | list }}"
+  loop_control:
+    label: "{{ item.stat.path }}"
+  changed_when: false
+  register: ssh_ca_fingerprints
+  check_mode: false
+
+- name: Report the admin logins' authorized keys
+  ansible.builtin.debug:
+    msg: "{{ item.item.stat.path }}: {{ item.stdout_lines }}"
+  loop: "{{ ssh_ca_fingerprints.results }}"
+  loop_control:
+    label: "{{ item.item.stat.path }}"

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

@@ -0,0 +1,6 @@
+# {{ ansible_managed }}
+TrustedUserCAKeys /etc/ssh/trusted_user_ca_keys
+AuthorizedPrincipalsFile /etc/ssh/auth_principals/%u
+RevokedKeys /etc/ssh/revoked_keys
+PasswordAuthentication no
+KbdInteractiveAuthentication no

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

@@ -0,0 +1,12 @@
+# {{ ansible_managed }}
+# Logs and unit status come from the systemd-journal group, not sudo:
+# journalctl as root would also allow --vacuum-*/--rotate.
+# Commands are listed for both the Arch and the Debian/Ubuntu path.
+# nft only with fixed arguments: it joins argv into one command line, so a
+# wildcard would admit "; flush ruleset". No docker start: -a/-i attach to a
+# container's stdin; docker restart also starts stopped containers.
+{{ ssh_ca_claude_user }} ALL=(root) NOPASSWD:NOEXEC: /usr/bin/ss -tulpn, /usr/sbin/sshd -T, /usr/bin/nft list ruleset, /usr/sbin/nft list ruleset, /usr/bin/netbird status, /usr/bin/netbird status *, /usr/local/bin/netbird status, /usr/local/bin/netbird status *
+{{ ssh_ca_claude_user }} ALL=(root) NOPASSWD:NOEXEC: /usr/bin/docker ps, /usr/bin/docker ps *, /usr/bin/docker logs *, /usr/bin/docker stats --no-stream, /usr/bin/docker restart *
+{% 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 %}

ansible/roles/ssh-mesh-only/defaults/main.yml

@@ -0,0 +1,9 @@
+---
+# The only interface sshd accepts connections on.
+ssh_mesh_interface: wt0
+
+# Minutes until a switchover reverts to the distro listener, unless a new
+# login through the mesh-only listener confirms it first.
+ssh_mesh_revert_minutes: 5
+
+ssh_mesh_udev_rule: /etc/udev/rules.d/90-ssh-mesh-only.rules

ansible/roles/ssh-mesh-only/tasks/main.yml

@@ -0,0 +1,114 @@
+---
+- name: Load the distro's sshd unit names
+  ansible.builtin.include_vars: "{{ ansible_facts['os_family'] }}.yml"
+
+- name: Look for the mesh interface
+  ansible.builtin.stat:
+    path: "/sys/class/net/{{ ssh_mesh_interface }}"
+  register: ssh_mesh_iface
+
+- name: Check the mesh interface exists
+  ansible.builtin.assert:
+    that:
+      - ssh_mesh_iface.stat.exists
+    fail_msg: "No {{ ssh_mesh_interface }}: sshd would be unreachable. Install the NetBird client first."
+
+- name: Create the socket unit directory
+  ansible.builtin.file:
+    path: "{{ ssh_mesh_socket_file | dirname }}"
+    state: directory
+    owner: root
+    group: root
+    mode: "0755"
+
+- name: Install the mesh-only socket
+  ansible.builtin.template:
+    src: "{{ ssh_mesh_socket_template }}"
+    dest: "{{ ssh_mesh_socket_file }}"
+    owner: root
+    group: root
+    mode: "0644"
+
+- name: Bind the sshd service to the socket
+  when: ssh_mesh_service_dropin | length > 0
+  block:
+    - name: Create the service drop-in directory
+      ansible.builtin.file:
+        path: "{{ ssh_mesh_service_dropin | dirname }}"
+        state: directory
+        owner: root
+        group: root
+        mode: "0755"
+
+    - name: Install the service drop-in
+      ansible.builtin.template:
+        src: ssh.service-dropin.conf.j2
+        dest: "{{ ssh_mesh_service_dropin }}"
+        owner: root
+        group: root
+        mode: "0644"
+
+- name: Install the udev rule that starts the socket with the interface
+  ansible.builtin.template:
+    src: udev.rules.j2
+    dest: "{{ ssh_mesh_udev_rule }}"
+    owner: root
+    group: root
+    mode: "0644"
+  register: ssh_mesh_udev
+
+- name: Reload the udev rules
+  ansible.builtin.command: udevadm control --reload
+  when: ssh_mesh_udev is changed
+  changed_when: true
+
+- name: Install the switch and revert scripts
+  ansible.builtin.template:
+    src: "{{ item }}.j2"
+    dest: "/usr/local/sbin/{{ item }}"
+    owner: root
+    group: root
+    mode: "0755"
+  loop:
+    - ssh-mesh-switch
+    - ssh-mesh-revert
+
+- name: Reload systemd units
+  ansible.builtin.systemd:
+    daemon_reload: true
+
+- name: Read the sshd listeners
+  ansible.builtin.command: ss -Htln 'sport = :22'
+  changed_when: false
+  register: ssh_mesh_listeners
+  check_mode: false
+
+# Each run that finds a listener outside the interface switches over. An
+# include, because meta reset_connection ignores when: and a reconnect costs a
+# YubiKey PIN from a workstation.
+- name: Switch sshd to the mesh-only socket
+  ansible.builtin.include_tasks: switch.yml
+  when: >-
+    ssh_mesh_listeners.stdout_lines | length == 0 or
+    ssh_mesh_listeners.stdout_lines | reject('search', '%' ~ ssh_mesh_interface ~ ':22\s') | list | length > 0
+
+- name: Check sshd listens on the mesh interface only
+  ansible.builtin.assert:
+    that:
+      - ssh_mesh_listeners.stdout_lines | length > 0
+      - ssh_mesh_listeners.stdout_lines | reject('search', '%' ~ ssh_mesh_interface ~ ':22\s') | list | length == 0
+    fail_msg: "Listeners outside {{ ssh_mesh_interface }}: {{ ssh_mesh_listeners.stdout_lines }}"
+
+- name: Cancel the revert timer
+  ansible.builtin.command: systemctl stop ssh-mesh-revert.timer
+  changed_when: false
+  failed_when: false
+
+- name: Check the public name refuses SSH
+  ansible.builtin.wait_for:
+    host: "{{ inventory_hostname }}"
+    port: 22
+    state: stopped
+    timeout: 15
+  delegate_to: localhost
+  become: false

ansible/roles/ssh-mesh-only/tasks/switch.yml

@@ -0,0 +1,27 @@
+---
+# The revert timer runs in its own unit, so a switch that locks the play out is
+# undone after ssh_mesh_revert_minutes. main.yml cancels it after checking the
+# listeners read through the new one.
+- name: Clear a revert timer left by an earlier run
+  ansible.builtin.command: systemctl stop ssh-mesh-revert.timer ssh-mesh-revert.service
+  changed_when: false
+  failed_when: false
+
+- name: Arm the revert timer
+  ansible.builtin.command: >-
+    systemd-run --unit=ssh-mesh-revert --collect
+    --on-active={{ ssh_mesh_revert_minutes }}min
+    /usr/local/sbin/ssh-mesh-revert
+  changed_when: true
+
+- name: Switch the listener
+  ansible.builtin.command: systemd-run --unit=ssh-mesh-switch --collect --wait /usr/local/sbin/ssh-mesh-switch
+  changed_when: true
+
+- name: Reconnect through the new listener
+  ansible.builtin.meta: reset_connection
+
+- name: Read the sshd listeners after reconnecting
+  ansible.builtin.command: ss -Htln 'sport = :22'
+  changed_when: false
+  register: ssh_mesh_listeners

ansible/roles/ssh-mesh-only/templates/ssh-mesh-revert.j2

@@ -0,0 +1,9 @@
+#!/bin/sh
+# {{ ansible_managed }}
+# Restores the distro listener on all addresses. Armed as a timer by every
+# switchover; the play cancels it after a login through the new listener.
+systemctl stop {{ ssh_mesh_service }} {{ ssh_mesh_socket }}
+rm -f {{ ssh_mesh_udev_rule }} {{ ssh_mesh_socket_file }}{{ (' ' ~ ssh_mesh_service_dropin) if ssh_mesh_service_dropin else '' }}
+udevadm control --reload
+systemctl daemon-reload
+systemctl enable --now {{ ssh_mesh_distro_listener }}

ansible/roles/ssh-mesh-only/templates/ssh-mesh-switch.j2

@@ -0,0 +1,11 @@
+#!/bin/sh
+# {{ ansible_managed }}
+# Replaces the distro listener with the {{ ssh_mesh_interface }}-only socket.
+# Open sessions survive: they run in logind scopes and the sshd units use
+# KillMode=process. Any failure restores the distro listener at once.
+set -eu
+trap '/usr/local/sbin/ssh-mesh-revert' EXIT
+systemctl disable {{ ssh_mesh_disable_units }}
+systemctl stop {{ ssh_mesh_service }} {{ ssh_mesh_socket }}
+systemctl start {{ ssh_mesh_socket }}
+trap - EXIT

ansible/roles/ssh-mesh-only/templates/ssh.service-dropin.conf.j2

@@ -0,0 +1,7 @@
+# {{ ansible_managed }}
+# sshd holds the socket's listener; it stops with the socket, so it never keeps
+# a listener on a removed {{ ssh_mesh_interface }}. Replaces the Requires= that
+# enabling {{ ssh_mesh_socket }} would add.
+[Unit]
+BindsTo={{ ssh_mesh_socket }}
+After={{ ssh_mesh_socket }}

ansible/roles/ssh-mesh-only/templates/ssh.socket-addresses.conf.j2

@@ -0,0 +1,8 @@
+# {{ ansible_managed }}
+# Listen on {{ ssh_mesh_interface }} only. The unit is disabled; the udev rule
+# starts it whenever {{ ssh_mesh_interface }} appears.
+[Socket]
+ListenStream=
+ListenStream=22
+BindToDevice={{ ssh_mesh_interface }}
+BindIPv6Only=both

ansible/roles/ssh-mesh-only/templates/sshd.socket.j2

@@ -0,0 +1,12 @@
+# {{ ansible_managed }}
+# Started by the udev rule whenever {{ ssh_mesh_interface }} appears; BindToDevice
+# stops it when the interface goes away. No [Install]: waiting for the device
+# from sockets.target would hold up boot until NetBird is up.
+[Unit]
+Description=OpenSSH on {{ ssh_mesh_interface }} only
+
+[Socket]
+ListenStream=22
+BindToDevice={{ ssh_mesh_interface }}
+BindIPv6Only=both
+Accept=yes

ansible/roles/ssh-mesh-only/templates/udev.rules.j2

@@ -0,0 +1,3 @@
+# {{ ansible_managed }}
+# NetBird deletes and recreates {{ ssh_mesh_interface }} on every engine restart.
+SUBSYSTEM=="net", KERNEL=="{{ ssh_mesh_interface }}", ENV{SYSTEMD_WANTS}+="{{ ssh_mesh_socket }}"

ansible/roles/ssh-mesh-only/vars/Archlinux.yml

@@ -0,0 +1,10 @@
+---
+# No packaged socket; sshd.socket (Accept=yes) pairs with the packaged
+# per-connection sshd@.service, since sshd -D cannot take a listening fd.
+ssh_mesh_socket: sshd.socket
+ssh_mesh_service: sshd.service
+ssh_mesh_distro_listener: sshd.service
+ssh_mesh_disable_units: sshd.service
+ssh_mesh_socket_file: /etc/systemd/system/sshd.socket
+ssh_mesh_socket_template: sshd.socket.j2
+ssh_mesh_service_dropin: ""

ansible/roles/ssh-mesh-only/vars/Debian.yml

@@ -0,0 +1,10 @@
+---
+# Ubuntu's ssh.socket (Accept=no) hands its listener to ssh.service. The
+# drop-in is named like sshd-socket-generator's output so it masks it.
+ssh_mesh_socket: ssh.socket
+ssh_mesh_service: ssh.service
+ssh_mesh_distro_listener: ssh.socket
+ssh_mesh_disable_units: ssh.service ssh.socket
+ssh_mesh_socket_file: /etc/systemd/system/ssh.socket.d/addresses.conf
+ssh_mesh_socket_template: ssh.socket-addresses.conf.j2
+ssh_mesh_service_dropin: /etc/systemd/system/ssh.service.d/ssh-mesh-only.conf

ansible/roles/uptime-kuma/defaults/main.yml

@@ -14,3 +14,8 @@ uptime_kuma_openbao_mount: homelab
 uptime_kuma_openbao_path: infrastructure/uptime-kuma
 uptime_kuma_openbao_smtp_path: infrastructure/uptime-kuma/smtp
 uptime_kuma_openbao_metrics_path: infrastructure/uptime-kuma-metrics
+# Token with policy uptime-kuma-vps, looked up like the bao CLI does:
+# VAULT_TOKEN, else the token helper file written by `bao login -method=oidc`.
+uptime_kuma_openbao_token: >-
+  {{ lookup('ansible.builtin.env', 'VAULT_TOKEN')
+     or (lookup('ansible.builtin.file', '~/.vault-token', errors='ignore') | default('', true)) }}

ansible/roles/uptime-kuma/tasks/main.yml

@@ -2,43 +2,58 @@
 # Admin bootstrap runs with the Traefik route disabled so /setup is never
 # reachable from outside; the route is enabled once the admin exists.
 
+# OpenBao's KV v2 HTTP API directly, so the controller needs no hvac library.
+# Reads also run in check mode.
+- name: Check for an OpenBao token
+  ansible.builtin.assert:
+    that:
+      - uptime_kuma_openbao_token | length > 0
+    fail_msg: "No OpenBao token: run 'bao login -method=oidc' (policy uptime-kuma-vps) or set VAULT_TOKEN."
+  run_once: true
+
 - name: Read admin credentials from OpenBao
-  community.hashi_vault.vault_kv2_get:
-    url: "{{ uptime_kuma_openbao_url }}"
-    engine_mount_point: "{{ uptime_kuma_openbao_mount }}"
-    path: "{{ uptime_kuma_openbao_path }}"
-    auth_method: token
+  ansible.builtin.uri:
+    url: "{{ uptime_kuma_openbao_url }}/v1/{{ uptime_kuma_openbao_mount }}/data/{{ uptime_kuma_openbao_path }}"
+    headers:
+      X-Vault-Token: "{{ uptime_kuma_openbao_token }}"
   delegate_to: localhost
   become: false
   run_once: true
-  register: _uptime_kuma_secret
+  check_mode: false
+  register: _uptime_kuma_secret_read
   no_log: true
 
 - name: Read SMTP credentials from OpenBao
-  community.hashi_vault.vault_kv2_get:
-    url: "{{ uptime_kuma_openbao_url }}"
-    engine_mount_point: "{{ uptime_kuma_openbao_mount }}"
-    path: "{{ uptime_kuma_openbao_smtp_path }}"
-    auth_method: token
+  ansible.builtin.uri:
+    url: "{{ uptime_kuma_openbao_url }}/v1/{{ uptime_kuma_openbao_mount }}/data/{{ uptime_kuma_openbao_smtp_path }}"
+    headers:
+      X-Vault-Token: "{{ uptime_kuma_openbao_token }}"
   delegate_to: localhost
   become: false
   run_once: true
-  register: _uptime_kuma_smtp
+  check_mode: false
+  register: _uptime_kuma_smtp_read
   no_log: true
 
+# 404 until the role has stored a key for the first time.
 - name: Read metrics API key from OpenBao
-  community.hashi_vault.vault_kv2_get:
-    url: "{{ uptime_kuma_openbao_url }}"
-    engine_mount_point: "{{ uptime_kuma_openbao_mount }}"
-    path: "{{ uptime_kuma_openbao_metrics_path }}"
-    auth_method: token
+  ansible.builtin.uri:
+    url: "{{ uptime_kuma_openbao_url }}/v1/{{ uptime_kuma_openbao_mount }}/data/{{ uptime_kuma_openbao_metrics_path }}"
+    headers:
+      X-Vault-Token: "{{ uptime_kuma_openbao_token }}"
+    status_code: [200, 404]
   delegate_to: localhost
   become: false
   run_once: true
-  register: _uptime_kuma_metrics_secret
-  failed_when:
-    - _uptime_kuma_metrics_secret.failed | default(false)
-    - "'Invalid or missing path' not in (_uptime_kuma_metrics_secret.msg | default(''))"
+  check_mode: false
+  register: _uptime_kuma_metrics_read
+  no_log: true
+
+- name: Extract the OpenBao secrets
+  ansible.builtin.set_fact:
+    _uptime_kuma_secret: "{{ _uptime_kuma_secret_read.json.data.data }}"
+    _uptime_kuma_smtp: "{{ _uptime_kuma_smtp_read.json.data.data }}"
+    _uptime_kuma_metrics_key: "{{ _uptime_kuma_metrics_read.json.data.data.api_key if _uptime_kuma_metrics_read.status == 200 else '' }}"
   no_log: true
 
 - name: Ensure Uptime Kuma directories exist
@@ -102,8 +117,6 @@
     headers:
       Authorization: "Basic {{ (':' ~ _uptime_kuma_metrics_key) | b64encode }}"
     status_code: [200, 401]
-  vars:
-    _uptime_kuma_metrics_key: "{{ (_uptime_kuma_metrics_secret.secret | default({})).api_key | default('') }}"
   when: _uptime_kuma_metrics_key | length > 0
   register: _uptime_kuma_metrics_check
   no_log: true
@@ -148,13 +161,13 @@
   args:
     chdir: "{{ uptime_kuma_dir }}"
   environment:
-    KUMA_SETUP_USERNAME: "{{ _uptime_kuma_secret.secret.username }}"
-    KUMA_SETUP_PASSWORD: "{{ _uptime_kuma_secret.secret.password }}"
+    KUMA_SETUP_USERNAME: "{{ _uptime_kuma_secret.username }}"
+    KUMA_SETUP_PASSWORD: "{{ _uptime_kuma_secret.password }}"
     KUMA_BASE_URL: "{{ uptime_kuma_base_url }}"
-    KUMA_SMTP_HOST: "{{ _uptime_kuma_smtp.secret.server }}"
-    KUMA_SMTP_PORT: "{{ _uptime_kuma_smtp.secret.port }}"
-    KUMA_SMTP_USERNAME: "{{ _uptime_kuma_smtp.secret.username }}"
-    KUMA_SMTP_PASSWORD: "{{ _uptime_kuma_smtp.secret.token }}"
+    KUMA_SMTP_HOST: "{{ _uptime_kuma_smtp.server }}"
+    KUMA_SMTP_PORT: "{{ _uptime_kuma_smtp.port }}"
+    KUMA_SMTP_USERNAME: "{{ _uptime_kuma_smtp.username }}"
+    KUMA_SMTP_PASSWORD: "{{ _uptime_kuma_smtp.token }}"
     KUMA_SMTP_FROM: "{{ uptime_kuma_smtp_from }}"
     KUMA_SMTP_TO: "{{ uptime_kuma_smtp_to }}"
     KUMA_METRICS_ROTATE: "{{ 'false' if (_uptime_kuma_metrics_check.status | default(0)) == 200 else 'true' }}"
@@ -179,13 +192,16 @@
       no_log: true
 
     - name: Write the metrics API key to OpenBao
-      community.hashi_vault.vault_kv2_write:
-        url: "{{ uptime_kuma_openbao_url }}"
-        engine_mount_point: "{{ uptime_kuma_openbao_mount }}"
-        path: "{{ uptime_kuma_openbao_metrics_path }}"
-        auth_method: token
-        data:
-          api_key: "{{ _uptime_kuma_new_metrics_key.content | b64decode }}"
+      ansible.builtin.uri:
+        url: "{{ uptime_kuma_openbao_url }}/v1/{{ uptime_kuma_openbao_mount }}/data/{{ uptime_kuma_openbao_metrics_path }}"
+        method: POST
+        headers:
+          X-Vault-Token: "{{ uptime_kuma_openbao_token }}"
+        body_format: json
+        body:
+          data:
+            api_key: "{{ _uptime_kuma_new_metrics_key.content | b64decode }}"
+        status_code: [200, 204]
       delegate_to: localhost
       become: false
       run_once: true

ansible/site.yml

@@ -0,0 +1,40 @@
+---
+# The whole defined state of every Ansible-managed host, in dependency order.
+# Run from ansible/ on a mesh-connected workstation; the inventory comes from
+# ansible.cfg:
+#
+#   ansible-playbook site.yml
+#
+# One-off actions are not state and stay separate: plays/update-os.yml,
+# plays/update-dist-upgrade.yml, plays/rotate-netbird-secrets.yml.
+
+- name: Base system
+  ansible.builtin.import_playbook: plays/common.yml
+- name: VM time sync
+  ansible.builtin.import_playbook: plays/configure-vm-time-sync.yml
+
+- name: SSH user CA
+  ansible.builtin.import_playbook: plays/configure-ssh-ca.yml
+- name: NetBird host clients
+  ansible.builtin.import_playbook: plays/install-netbird-client.yml
+- name: sshd on the mesh interface only
+  ansible.builtin.import_playbook: plays/configure-ssh-mesh-only.yml
+
+- name: NetBird server
+  ansible.builtin.import_playbook: plays/install-netbird-server.yml
+- name: Uptime Kuma
+  ansible.builtin.import_playbook: plays/install-uptime-kuma.yml
+- name: NetBird proxies
+  ansible.builtin.import_playbook: plays/install-netbird-proxy.yml
+
+- name: Edge host base
+  ansible.builtin.import_playbook: plays/install-edge-host.yml
+- name: Z-Wave gateway
+  ansible.builtin.import_playbook: plays/install-zwave-gateway.yml
+- name: Heating CAN
+  ansible.builtin.import_playbook: plays/install-heating-can.yml
+- name: NTP service
+  ansible.builtin.import_playbook: plays/install-ntp-ha.yml
+
+- name: Close the SSH connections
+  ansible.builtin.import_playbook: plays/close-connections.yml

ci/images/alpine-jq/Containerfile

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

ci/images/alpine-openssl/Containerfile

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

ci/images/ansible/Containerfile

@@ -1,4 +1,4 @@
-FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
+FROM alpine:3.24@sha256:be2656061b536c1883c4034790e21d0a09c5aaaf51968b89368a3c0371ea2c9a
 
 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@sha256:2da676046630d7bf14c6764ae1143dc7fa0377a53f94bf5a642f0b214aca5bce AS test
+FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51 AS test
 WORKDIR /src
 COPY controller.py test_controller.py ./
 RUN python3 -B -m unittest -v
 
-FROM python:3.15-slim@sha256:2da676046630d7bf14c6764ae1143dc7fa0377a53f94bf5a642f0b214aca5bce
+FROM python:3.15-slim@sha256:533b0b2f9b5d46fd097091cf826f27902f1d6c3bca714b6dc74551356aa97a51
 
 RUN useradd --system --no-create-home --shell /usr/sbin/nologin controller
 COPY --from=test /src/controller.py /opt/controller.py

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

@@ -1,34 +1,26 @@
 #!/usr/bin/env python3
-"""authentik-gate-sync: an ingress class that puts an Authentik proxy gate in front of an app.
+"""authentik-gate-sync: the Authentik side of the gate Middleware.
 
-Source of truth: every Ingress with spec.ingressClassName "authentik-gate". Traefik
-ignores that class (its IngressClass names another controller), so a source
-Ingress is never served directly. For each one this controller builds:
+An Ingress is gated when its traefik.ingress.kubernetes.io/router.middlewares
+annotation names the gate Middleware (authentik/gate, a ForwardAuth against the
+embedded outpost in authentik-server; kubernetes/apps/authentik/gate.yaml). The
+gate's configuration lives on that Ingress; for each one this controller builds:
 
-  Authentik   proxy provider + application + outpost (+ group-membership
-              expression policy bound to the application).
-              Authentik's own Kubernetes integration then runs the outpost as
-              ak-outpost-<gate> in the authentik namespace.
-  app ns      ExternalName Service <ingress>-gate -> the outpost Service,
-              Traefik Ingress <ingress>-gate: the source's hosts, paths, TLS,
-              labels and annotations, backend swapped for the gate,
-              CNP <ingress>-gate: the backend pods admit this outpost.
-  authentik   CNP gate-<gate>: the outpost may reach only those backend pods.
+  Authentik   forward_single proxy provider for the Ingress's host +
+              application (+ group-membership expression policy bound to it),
+              the provider attached to the embedded outpost.
+  app ns      CNP <ingress>-gate: the backend pods admit Traefik.
 
-Like any ingress controller it publishes the source's status.loadBalancer: the
-address Traefik reports for the route, or none while the gate has no route.
-
-The source Ingress's backend is the real upstream; it becomes the provider's
-internal host and its host the external host. Annotations (all optional):
+Annotations (all optional):
 
   auth.renner.uno/group               group whose members may pass; none = any user
   auth.renner.uno/login-flow          authentication flow slug; none = the brand's
   auth.renner.uno/authorization-flow  authorization flow slug (default below)
   auth.renner.uno/skip-path           provider skip_path_regex
 
-Fail closed: the Traefik Ingress is applied last and only after the Authentik
-side reconciled, and is removed when that fails (e.g. the named group is gone),
-so there is never a route to an unguarded backend.
+Fail closed: until the provider exists, or after it is removed (e.g. the named
+group is gone), the embedded outpost has no provider for the host and rejects
+the request; Traefik answers 500 when the outpost is unreachable.
 
 Ownership: Kubernetes objects carry app.kubernetes.io/managed-by; Authentik
 applications carry meta_publisher. Anything without the marker is never touched.
@@ -48,10 +40,8 @@ LOG = logging.getLogger("authentik-gate-sync")
 
 AK_URL = os.environ.get("AK_URL", "http://authentik-server.authentik.svc.cluster.local").rstrip("/")
 AK_TOKEN_FILE = os.environ.get("AK_TOKEN_FILE", "/var/run/secrets/authentik-gate-sync/token")
-INGRESS_CLASS = os.environ.get("INGRESS_CLASS", "authentik-gate")
-TARGET_CLASS = os.environ.get("TARGET_INGRESS_CLASS", "traefik")
-OUTPOST_NS = os.environ.get("OUTPOST_NAMESPACE", "authentik")
-SERVICE_CONNECTION = os.environ.get("SERVICE_CONNECTION", "Local Kubernetes Cluster")
+GATE_MIDDLEWARE = os.environ.get("GATE_MIDDLEWARE", "authentik-gate@kubernetescrd")
+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")
@@ -63,14 +53,9 @@ ANN = "auth.renner.uno/"
 MANAGER = "authentik-gate-sync"
 MANAGED_BY = {"app.kubernetes.io/managed-by": MANAGER}
 GATE_LABEL = "auth.renner.uno/gate"
-OUTPOST_PORT = 9000
-
-# Never copied from the source onto the generated Ingress: cert-manager would
-# issue a second Certificate for the same secret, Flux would treat it as its own,
-# and the gate annotations mean nothing to Traefik.
-DROP_LABEL_PREFIXES = ("kustomize.toolkit.fluxcd.io/", "app.kubernetes.io/managed-by")
-DROP_ANNOTATION_PREFIXES = (ANN, "cert-manager.io/", "acme.cert-manager.io/",
-                            "kubectl.kubernetes.io/last-applied-configuration")
+EMBEDDED_OUTPOST = "goauthentik.io/outposts/embedded"
+TRAEFIK = {"k8s:io.kubernetes.pod.namespace": INGRESS_NS, "app.kubernetes.io/name": "traefik"}
+MIDDLEWARES_ANN = "traefik.ingress.kubernetes.io/router.middlewares"
 
 K8S_API = "https://kubernetes.default.svc"
 K8S_TOKEN_FILE = "/var/run/secrets/kubernetes.io/serviceaccount/token"
@@ -114,7 +99,7 @@ def http(method, url, body=None, headers=None, cafile=None, content_type="applic
 
 def gate_name(ing):
     """<ns>-<ingress>, truncated, plus a hash of both: unambiguous (a-b/c vs a/b-c)
-    and short enough for label values and ak-outpost-<name> (63)."""
+    and short enough for label values (63)."""
     ns, name = ing["metadata"]["namespace"], ing["metadata"]["name"]
     digest = hashlib.sha256(f"{ns}/{name}".encode()).hexdigest()[:6]
     return f"{ns}-{name}"[:45].rstrip("-") + "-" + digest
@@ -126,6 +111,24 @@ def group_expression(group):
     return f"return ak_is_group_member(request.user, name={group!r})"
 
 
+def is_gated(ing):
+    chain = ((ing.get("metadata") or {}).get("annotations") or {}).get(MIDDLEWARES_ANN, "")
+    return GATE_MIDDLEWARE in (m.strip() for m in chain.split(","))
+
+
+def shared_hosts(sources):
+    """Hosts named by more than one gated Ingress. The outpost finds the provider
+    by host, so such a host would get one gate for several Ingresses."""
+    seen, shared = set(), set()
+    for ing in sources:
+        for r in ing.get("spec", {}).get("rules") or []:
+            host = r.get("host")
+            if host in seen:
+                shared.add(host)
+            seen.add(host)
+    return shared
+
+
 def gate_spec(ing):
     """Translate a source Ingress into the gate it asks for. Raises GateError."""
     meta = ing["metadata"]
@@ -174,63 +177,15 @@ def gate_labels(gate):
     return {**MANAGED_BY, GATE_LABEL: gate["name"]}
 
 
-def outpost_service(gate):
-    return f"ak-outpost-{gate['name']}"
-
-
-def external_name_service(gate):
-    return {"apiVersion": "v1", "kind": "Service",
-            "metadata": {"name": f"{gate['ingress']}-gate", "namespace": gate["namespace"],
-                         "labels": gate_labels(gate), "ownerReferences": owner_ref(gate)},
-            "spec": {"type": "ExternalName",
-                     "externalName": f"{outpost_service(gate)}.{OUTPOST_NS}.svc.cluster.local",
-                     "ports": [{"name": "http", "port": OUTPOST_PORT, "targetPort": OUTPOST_PORT}]}}
-
-
-def route_ingress(ing, gate):
-    """The Traefik Ingress: the source with its backend swapped for the gate."""
-    meta = ing["metadata"]
-    labels = {k: v for k, v in (meta.get("labels") or {}).items() if not k.startswith(DROP_LABEL_PREFIXES)}
-    annotations = {k: v for k, v in (meta.get("annotations") or {}).items()
-                   if not k.startswith(DROP_ANNOTATION_PREFIXES)}
-    backend = {"service": {"name": f"{gate['ingress']}-gate", "port": {"number": OUTPOST_PORT}}}
-    rules = []
-    for r in ing["spec"]["rules"]:
-        paths = [{"path": p.get("path", "/"), "pathType": p.get("pathType", "Prefix"), "backend": backend}
-                 for p in r["http"]["paths"]]
-        rules.append({"host": r["host"], "http": {"paths": paths}})
-    spec = {"ingressClassName": TARGET_CLASS, "rules": rules}
-    if ing["spec"].get("tls"):
-        spec["tls"] = ing["spec"]["tls"]
-    return {"apiVersion": "networking.k8s.io/v1", "kind": "Ingress",
-            "metadata": {"name": f"{gate['ingress']}-gate", "namespace": gate["namespace"],
-                         "labels": {**labels, **gate_labels(gate)}, "annotations": annotations,
-                         "ownerReferences": owner_ref(gate)},
-            "spec": spec}
-
-
-def outpost_selector(gate):
-    return {"k8s:io.kubernetes.pod.namespace": OUTPOST_NS, "goauthentik.io/outpost-name": gate["name"]}
-
-
 def backend_ingress_cnp(gate, pod_selector, target_port):
     return {"apiVersion": "cilium.io/v2", "kind": "CiliumNetworkPolicy",
             "metadata": {"name": f"{gate['ingress']}-gate", "namespace": gate["namespace"],
                          "labels": gate_labels(gate), "ownerReferences": owner_ref(gate)},
             "spec": {"endpointSelector": {"matchLabels": pod_selector},
-                     "ingress": [{"fromEndpoints": [{"matchLabels": outpost_selector(gate)}],
+                     "ingress": [{"fromEndpoints": [{"matchLabels": TRAEFIK}],
                                   "toPorts": [{"ports": [{"port": str(target_port), "protocol": "TCP"}]}]}]}}
 
 
-def outpost_egress_cnp(gate, pod_selector, target_port):
-    peer = {"k8s:io.kubernetes.pod.namespace": gate["namespace"], **pod_selector}
-    return {"apiVersion": "cilium.io/v2", "kind": "CiliumNetworkPolicy",
-            "metadata": {"name": f"gate-{gate['name']}", "namespace": OUTPOST_NS, "labels": gate_labels(gate)},
-            "spec": {"endpointSelector": {"matchLabels": {"goauthentik.io/outpost-name": gate["name"]}},
-                     "egress": [{"toEndpoints": [{"matchLabels": peer}],
-                                 "toPorts": [{"ports": [{"port": str(target_port), "protocol": "TCP"}]}]}]}}
-
-
 def resolve_backend(gate, service):
     """(service port number, pod selector, target port) for the gate's backend.
     A named targetPort stays a name: Cilium resolves named ports against the
@@ -254,34 +209,20 @@ def resolve_backend(gate, service):
     return sp["port"], selector, target
 
 
-def outpost_config():
-    return {
-        "log_level": "info",
-        "authentik_host": AK_URL,
-        "authentik_host_insecure": False,
-        "authentik_host_browser": AK_BROWSER_URL,
-        "refresh_interval": "minutes=5",
-        "container_image": None,
-        "object_naming_template": "ak-outpost-%(name)s",
-        "kubernetes_namespace": OUTPOST_NS,
-        "kubernetes_replicas": 1,
-        "kubernetes_service_type": "ClusterIP",
-        "kubernetes_disabled_components": ["ingress"],
-        "kubernetes_image_pull_secrets": [],
-        "kubernetes_ingress_annotations": {},
-        "kubernetes_ingress_class_name": None,
-        "kubernetes_ingress_secret_name": "authentik-outpost-tls",
-        "kubernetes_json_patches": None,
-    }
+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, svc_port, flows):
+def provider_body(gate, flows):
     return {
         "name": gate["name"],
-        "mode": "proxy",
+        "mode": "forward_single",
         "external_host": f"{gate['scheme']}://{gate['host']}",
-        "internal_host": f"http://{gate['service']}.{gate['namespace']}.svc.cluster.local:{svc_port}",
-        "internal_host_ssl_validation": False,
+        "internal_host": "",
         "cookie_domain": COOKIE_DOMAIN,
         "access_token_validity": "hours=24",
         "refresh_token_validity": "days=30",
@@ -293,18 +234,6 @@ def provider_body(gate, svc_port, flows):
     }
 
 
-def lb_ingress(obj):
-    return ((obj or {}).get("status") or {}).get("loadBalancer", {}).get("ingress") or []
-
-
-def status_patch(source, addresses):
-    """Merge patch publishing `addresses` as the source Ingress's load-balancer
-    status, as an ingress controller does; None when it already matches."""
-    if lb_ingress(source) == addresses:
-        return None
-    return {"status": {"loadBalancer": {"ingress": addresses or None}}}
-
-
 def drift(current, desired):
     return {k: v for k, v in desired.items() if current.get(k) != v}
 
@@ -342,23 +271,9 @@ class K8s:
             if e.code != 404:
                 raise
 
-    def patch_status(self, ns, name, patch):
-        path = f"/apis/networking.k8s.io/v1/namespaces/{ns}/ingresses/{name}/status"
-        return http("PATCH", K8S_API + path, patch, headers=self._h(), cafile=K8S_CA_FILE,
-                    content_type="application/merge-patch+json")
-
-    def delete_managed(self, obj):
-        try:
-            live = self.get(object_path(obj))
-        except ApiError as e:
-            if e.code == 404:
-                return
-            raise
-        if (live["metadata"].get("labels") or {}).get("app.kubernetes.io/managed-by") == MANAGER:
-            self.delete(obj)
-            LOG.info("deleted %s %s/%s", obj["kind"], obj["metadata"]["namespace"], obj["metadata"]["name"])
-
-
+# Swept by label: any object of these kinds marked as this controller's that no
+# gate wants is deleted. It creates only CNPs; Ingresses and Services carrying
+# the label are routes a gate must not have besides its own Ingress.
 COLLECTIONS = {
     "Ingress": "/apis/networking.k8s.io/v1/namespaces/{ns}/ingresses",
     "Service": "/api/v1/namespaces/{ns}/services",
@@ -425,7 +340,24 @@ def get_application(ak, slug):
     return ak.get(f"core/applications/{slug}/")
 
 
-def ensure_gate(ak, gate, svc_port, flows, connection):
+def embedded_outpost(ak):
+    # Matched again here: a filter the server ignored must not select another outpost.
+    found = [o for o in ak.list("outposts/instances/", managed__iexact=EMBEDDED_OUTPOST)
+             if o.get("managed") == EMBEDDED_OUTPOST]
+    if len(found) != 1:
+        raise ApiError(f"expected one embedded outpost, found {len(found)}")
+    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:
         raise GateError(f"group {gate['group']!r} not found in Authentik")
@@ -434,7 +366,7 @@ def ensure_gate(ak, gate, svc_port, flows, connection):
     if app is not None and app.get("meta_publisher") != MANAGER:
         raise GateError(f"application {name} exists and is not managed by {MANAGER}")
 
-    want = provider_body(gate, svc_port, flows)
+    want = provider_body(gate, flows)
     provider = ak.one("providers/proxy/", name__iexact=name)
     if provider is None:
         provider = ak.req("POST", "providers/proxy/", want)
@@ -461,17 +393,22 @@ def ensure_gate(ak, gate, svc_port, flows, connection):
 
     ensure_access(ak, gate, app["pbm_uuid"])
 
-    want_outpost = {"name": name, "type": "proxy", "service_connection": connection,
-                    "providers": [provider["pk"]], "config": outpost_config()}
-    outpost = ak.one("outposts/instances/", name__iexact=name)
-    if outpost is None:
-        ak.req("POST", "outposts/instances/", want_outpost)
-        LOG.info("%s: created outpost", name)
-    elif set(outpost.get("providers") or []) - {provider["pk"]}:
-        raise GateError(f"outpost {name} serves providers this controller does not own")
-    elif drift(outpost, want_outpost):
-        ak.req("PATCH", f"outposts/instances/{outpost['pk']}/", drift(outpost, want_outpost))
-        LOG.info("%s: updated outpost %s", name, sorted(drift(outpost, want_outpost)))
+    # Re-read per gate: the providers list is replaced whole.
+    embedded = embedded_outpost(ak)
+    if provider["pk"] not in (embedded.get("providers") or []):
+        ak.req("PATCH", f"outposts/instances/{embedded['pk']}/",
+               {"providers": [*(embedded.get("providers") or []), provider["pk"]]})
+        LOG.info("%s: attached provider to the embedded outpost", name)
+    remove_dedicated_outposts(ak, name, provider["pk"])
+
+
+def remove_dedicated_outposts(ak, name, provider):
+    """Outposts named after the gate that serve only its provider: the embedded
+    outpost serves every gate, so Authentik tears these and their pods down."""
+    for o in ak.list("outposts/instances/", name__iexact=name):
+        if o.get("providers") == [provider] and not o.get("managed"):
+            ak.req("DELETE", f"outposts/instances/{o['pk']}/")
+            LOG.info("%s: removed dedicated outpost", name)
 
 
 def ensure_access(ak, gate, target):
@@ -511,15 +448,12 @@ def ensure_access(ak, gate, target):
 
 
 def remove_gate(ak, app):
-    """Delete an owned gate. The outpost serving only its provider goes first
-    (Authentik tears its pods down), then the application (bindings cascade; its
-    provider is PROTECTed while referenced), the provider, the policy. Ownership
-    is found through the application, so until it is gone a failed step is
-    retried on the next pass."""
+    """Delete an owned gate: the application (bindings cascade; its provider is
+    PROTECTed while referenced), then the provider (which leaves the embedded
+    outpost with it), the policy. Ownership is found through the application,
+    so until it is gone a failed step is retried on the next pass."""
     name, provider = app["slug"], app.get("provider")
-    for o in ak.list("outposts/instances/", name__iexact=name):
-        if o.get("providers") == [provider]:
-            ak.req("DELETE", f"outposts/instances/{o['pk']}/")
+    remove_dedicated_outposts(ak, name, provider)
     ak.req("DELETE", f"core/applications/{name}/")
     if provider:
         ak.req("DELETE", f"providers/proxy/{provider}/")
@@ -543,32 +477,15 @@ def owned_applications(ak):
 
 # --- reconcile --------------------------------------------------------------
 
-def publish_status(k8s, source, addresses):
-    """Status is cosmetic for the gate itself: a failure is logged, never fatal."""
-    patch = status_patch(source, addresses)
-    if patch is None:
-        return
-    m = source["metadata"]
-    try:
-        k8s.patch_status(m["namespace"], m["name"], patch)
-        LOG.info("%s/%s: status %s", m["namespace"], m["name"],
-                 [a.get("ip") or a.get("hostname") for a in addresses])
-    except Exception as e:
-        LOG.warning("%s/%s: publishing status: %s", m["namespace"], m["name"], e)
-
-
 def reconcile():
     k8s = K8s()
     with open(AK_TOKEN_FILE) as f:
         ak = Authentik(f.read().strip())
 
-    sources = [i for i in k8s.get("/apis/networking.k8s.io/v1/ingresses").get("items", [])
-               if i.get("spec", {}).get("ingressClassName") == INGRESS_CLASS]
+    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/")}
-    connection = ak.one("outposts/service_connections/kubernetes/", name=SERVICE_CONNECTION)
-    if connection is None:
-        raise ApiError(f"Kubernetes service connection {SERVICE_CONNECTION!r} not found")
-    connection = connection["pk"]
+    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
@@ -578,6 +495,8 @@ def reconcile():
         ref = f'{ing["metadata"]["namespace"]}/{ing["metadata"]["name"]}'
         try:
             gate = gate_spec(ing)
+            if gate["host"] in shared:
+                raise GateError(f"host {gate['host']} is gated by more than one Ingress")
             for slug in filter(None, (gate["authorization_flow"], gate["login_flow"], INVALIDATION_FLOW)):
                 if slug not in flows:
                     raise GateError(f"flow {slug!r} not found in Authentik")
@@ -588,28 +507,18 @@ def reconcile():
                 if e.code == 404:
                     raise GateError(f"backend Service {gate['service']} does not exist") from None
                 raise
-            svc_port, pods, target_port = resolve_backend(gate, service)
+            _, pods, target_port = resolve_backend(gate, service)
             gates.add(gate["name"])
-            ensure_gate(ak, gate, svc_port, flows, connection)
-            objs = [outpost_egress_cnp(gate, pods, target_port), backend_ingress_cnp(gate, pods, target_port),
-                    external_name_service(gate), route_ingress(ing, gate)]  # the route goes last
-            for obj in objs:
-                live = k8s.apply(obj)
-                desired.add((obj["kind"], obj["metadata"]["namespace"], obj["metadata"]["name"]))
-            publish_status(k8s, ing, lb_ingress(live))  # the route's address, from Traefik
+            ensure_gate(ak, gate, flows)
+            cnp = backend_ingress_cnp(gate, pods, target_port)
+            k8s.apply(cnp)
+            desired.add((cnp["kind"], cnp["metadata"]["namespace"], cnp["metadata"]["name"]))
         except GateError as e:
-            # The Ingress cannot be gated as written: its route goes now, the
-            # rest with the sweep below.
+            # The Ingress cannot be gated as written: its provider goes with the
+            # sweep below, after which the outpost rejects the host.
             LOG.error("%s: %s", ref, e)
             failed += 1
             gates.discard(gate_name(ing))
-            route = {"kind": "Ingress", "metadata": {"namespace": ing["metadata"]["namespace"],
-                                                     "name": f'{ing["metadata"]["name"]}-gate'}}
-            try:
-                k8s.delete_managed(route)
-            except Exception as e:  # the sweep retries
-                LOG.error("%s: removing route: %s", ref, e)
-            publish_status(k8s, ing, [])
         except Exception as e:
             # Transient: leave this gate exactly as the last good pass left it.
             LOG.error("%s: %s", ref, e)

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

@@ -11,11 +11,12 @@ LLAMA = {
             "cert-manager.io/cluster-issuer": "letsencrypt-cluster",
             "auth.renner.uno/login-flow": "sso-authentication",
             "auth.renner.uno/skip-path": r"^/(manifest\.webmanifest|sw\.js)$",
-            "traefik.ingress.kubernetes.io/router.middlewares": "ingress-foo@kubernetescrd",
+            "traefik.ingress.kubernetes.io/router.middlewares":
+                "authentik-gate@kubernetescrd, ingress-foo@kubernetescrd",
         },
     },
     "spec": {
-        "ingressClassName": "authentik-gate",
+        "ingressClassName": "traefik",
         "tls": [{"hosts": ["llm.renner.uno"], "secretName": "llama-server-tls"}],
         "rules": [{"host": "llm.renner.uno", "http": {"paths": [
             {"path": "/", "pathType": "Prefix",
@@ -41,7 +42,7 @@ class Names(unittest.TestCase):
 
     def test_bounded(self):
         n = c.gate_name(ing("n" * 63, "i" * 253))
-        self.assertLessEqual(len(c.outpost_service({"name": n})), 63)
+        self.assertLessEqual(len(n), 63)
         self.assertNotIn("--", n)
 
     def test_group_expression_is_a_literal(self):
@@ -90,6 +91,22 @@ class GateSpec(unittest.TestCase):
         with self.assertRaises(c.GateError):
             c.gate_spec(ing)
 
+    def test_shared_hosts(self):
+        other = copy.deepcopy(LLAMA)
+        other["metadata"]["name"] = "llama-admin"
+        self.assertEqual(c.shared_hosts([LLAMA, other]), {"llm.renner.uno"})
+        other["spec"]["rules"][0]["host"] = "admin.renner.uno"
+        self.assertEqual(c.shared_hosts([LLAMA, other]), set())
+
+    def test_gated_by_middleware_reference(self):
+        self.assertTrue(c.is_gated(LLAMA))
+        ing = copy.deepcopy(LLAMA)
+        ing["metadata"]["annotations"]["traefik.ingress.kubernetes.io/router.middlewares"] = \
+            "ingress-foo@kubernetescrd,authentik-gate-other@kubernetescrd"
+        self.assertFalse(c.is_gated(ing))
+        del ing["metadata"]["annotations"]
+        self.assertFalse(c.is_gated(ing))
+
 
 class Backend(unittest.TestCase):
     def test_named_target_port_stays_named(self):
@@ -126,65 +143,34 @@ class Objects(unittest.TestCase):
     def setUp(self):
         self.g = c.gate_spec(LLAMA)
 
-    def test_route_ingress(self):
-        r = c.route_ingress(LLAMA, self.g)
-        self.assertEqual(r["metadata"]["name"], "llama-server-gate")
-        self.assertEqual(r["spec"]["ingressClassName"], "traefik")
-        self.assertEqual(r["spec"]["tls"], LLAMA["spec"]["tls"])
-        backend = r["spec"]["rules"][0]["http"]["paths"][0]["backend"]["service"]
-        self.assertEqual(backend, {"name": "llama-server-gate", "port": {"number": 9000}})
-        labels, ann = r["metadata"]["labels"], r["metadata"]["annotations"]
-        self.assertEqual(labels["dns.renner.uno/public"], "true")
-        self.assertNotIn("kustomize.toolkit.fluxcd.io/name", labels)
-        self.assertEqual(labels["app.kubernetes.io/managed-by"], c.MANAGER)
-        self.assertEqual(ann, {"traefik.ingress.kubernetes.io/router.middlewares": "ingress-foo@kubernetescrd"})
-        self.assertEqual(r["metadata"]["ownerReferences"][0]["uid"], "u-1")
-
-    def test_external_name(self):
-        s = c.external_name_service(self.g)
-        self.assertEqual(s["spec"]["externalName"], f"ak-outpost-{self.g['name']}.authentik.svc.cluster.local")
-
-    def test_cnps(self):
+    def test_backend_admits_traefik_only(self):
         pods = {"app.kubernetes.io/name": "llama-server"}
-        e = c.outpost_egress_cnp(self.g, pods, 8080)
-        self.assertEqual(e["metadata"]["namespace"], "authentik")
-        self.assertEqual(e["spec"]["endpointSelector"]["matchLabels"],
-                         {"goauthentik.io/outpost-name": self.g["name"]})
-        self.assertEqual(e["spec"]["egress"][0]["toEndpoints"][0]["matchLabels"],
-                         {"k8s:io.kubernetes.pod.namespace": "ai", "app.kubernetes.io/name": "llama-server"})
         i = c.backend_ingress_cnp(self.g, pods, 8080)
         self.assertEqual(i["metadata"]["namespace"], "ai")
-        self.assertEqual(i["spec"]["ingress"][0]["fromEndpoints"][0]["matchLabels"],
-                         {"k8s:io.kubernetes.pod.namespace": "authentik",
-                          "goauthentik.io/outpost-name": self.g["name"]})
+        self.assertEqual(i["spec"]["ingress"][0]["fromEndpoints"],
+                         [{"matchLabels": {"k8s:io.kubernetes.pod.namespace": "ingress",
+                                           "app.kubernetes.io/name": "traefik"}}])
         self.assertEqual(i["spec"]["ingress"][0]["toPorts"][0]["ports"][0]["port"], "8080")
 
     def test_provider_body(self):
         flows = {c.DEFAULT_AUTHZ_FLOW: "az", "sso-authentication": "au",
                  c.INVALIDATION_FLOW: "inv"}
-        p = c.provider_body(self.g, 8080, flows)
+        p = c.provider_body(self.g, flows)
+        self.assertEqual(p["mode"], "forward_single")
         self.assertEqual(p["external_host"], "https://llm.renner.uno")
-        self.assertEqual(p["internal_host"], "http://llama-server.ai.svc.cluster.local:8080")
+        self.assertEqual(p["internal_host"], "")
         self.assertEqual((p["authorization_flow"], p["authentication_flow"], p["invalidation_flow"]),
                          ("az", "au", "inv"))
         self.assertEqual(p["skip_path_regex"], r"^/(manifest\.webmanifest|sw\.js)$")
 
-    def test_status_mirrors_route_address(self):
-        addrs = [{"ip": "10.2.99.86"}, {"ip": "fd99::86"}]
-        route = {"status": {"loadBalancer": {"ingress": addrs}}}
-        self.assertEqual(c.status_patch(LLAMA, c.lb_ingress(route)),
-                         {"status": {"loadBalancer": {"ingress": addrs}}})
-        synced = dict(LLAMA, status={"loadBalancer": {"ingress": addrs}})
-        self.assertIsNone(c.status_patch(synced, addrs))
-
-    def test_status_cleared_without_route(self):
-        stale = dict(LLAMA, status={"loadBalancer": {"ingress": [{"ip": "10.2.99.86"}]}})
-        self.assertEqual(c.status_patch(stale, []), {"status": {"loadBalancer": {"ingress": None}}})
-        self.assertIsNone(c.status_patch(LLAMA, []))
-
     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."""
@@ -267,20 +253,69 @@ class Reconcile(unittest.TestCase):
     def setUp(self):
         self.ak = FakeAuthentik()
         self.g = c.gate_spec(LLAMA)
+        self.embedded = self.ak.add("outposts/instances/", {
+            "name": "authentik Embedded Outpost", "managed": c.EMBEDDED_OUTPOST,
+            "providers": [], "config": {"log_level": "info"}})
 
     def gate(self, group=None):
         g = dict(self.g, group=group)
-        c.ensure_gate(self.ak, g, 8080, FLOWS, "conn")
+        c.ensure_gate(self.ak, g, FLOWS)
         return g
 
+    def embedded_providers(self):
+        return self.ak.get(f"outposts/instances/{self.embedded['pk']}/")["providers"]
+
     def test_creates_owned_gate(self):
         self.gate()
         app = self.ak.get(f"core/applications/{self.g['name']}/")
         self.assertEqual(app["meta_publisher"], c.MANAGER)
-        outpost = self.ak.one("outposts/instances/", name__iexact=self.g["name"])
-        self.assertEqual(outpost["providers"], [app["provider"]])
+        self.assertEqual(self.embedded_providers(), [app["provider"]])
+        self.assertEqual(self.ak.list("outposts/instances/", name__iexact=self.g["name"]), [])
         self.assertEqual(self.ak.list("policies/bindings/"), [])
 
+    def test_keeps_other_providers_on_embedded_outpost(self):
+        self.ak.db["outposts/instances/"][self.embedded["pk"]]["providers"] = [999]
+        self.gate()
+        app = self.ak.get(f"core/applications/{self.g['name']}/")
+        self.assertEqual(self.embedded_providers(), [999, app["provider"]])
+
+    def test_removes_dedicated_outpost(self):
+        self.gate()
+        app = self.ak.get(f"core/applications/{self.g['name']}/")
+        self.ak.add("outposts/instances/", {"name": self.g["name"], "providers": [app["provider"]]})
+        shared = self.ak.add("outposts/instances/", {"name": self.g["name"].upper(),
+                                                     "providers": [app["provider"], 999]})
+        self.gate()
+        self.assertEqual([o["pk"] for o in self.ak.list("outposts/instances/", name__iexact=self.g["name"])],
+                         [shared["pk"]])
+
+    def test_embedded_lookup_ignores_unfiltered_results(self):
+        ldap = self.ak.add("outposts/instances/", {"name": "LDAP Outpost", "managed": None, "providers": [7]})
+        unfiltered = self.ak.list
+        self.ak.list = lambda path, **q: unfiltered(path)  # a server that ignores the filter
+        self.assertEqual(c.embedded_outpost(self.ak)["pk"], self.embedded["pk"])
+        del self.ak.db["outposts/instances/"][self.embedded["pk"]]
+        with self.assertRaises(c.ApiError):
+            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",
+                                         "assigned_application_slug": None})
+        self.gate()
+        provider = self.ak.one("providers/proxy/", name__iexact=self.g["name"])
+        self.assertEqual((provider["mode"], provider["internal_host"]), ("forward_single", ""))
+
     def test_second_pass_is_a_noop(self):
         self.gate()
         before = len(self.ak.calls)
@@ -329,15 +364,15 @@ class Reconcile(unittest.TestCase):
         self.assertIsNone(self.ak.one("policies/expression/", name=self.g["name"]))
 
     def test_remove_gate_and_ownership_scan(self):
-        self.ak.add("providers/proxy/", {"name": "foreign", "assigned_application_slug": "foreign"})
-        self.ak.add("core/applications/", {"slug": "foreign", "meta_publisher": "", "provider": 1})
+        foreign = self.ak.add("providers/proxy/", {"name": "foreign", "assigned_application_slug": "foreign"})
+        self.ak.add("core/applications/", {"slug": "foreign", "meta_publisher": "", "provider": foreign["pk"]})
         self.gate()
         owned = list(c.owned_applications(self.ak))
         self.assertEqual([a["slug"] for a in owned], [self.g["name"]])
         c.remove_gate(self.ak, owned[0])
         self.assertIsNone(self.ak.get(f"core/applications/{self.g['name']}/"))
         self.assertEqual([p["name"] for p in self.ak.list("providers/proxy/")], ["foreign"])
-        self.assertEqual(self.ak.list("outposts/instances/"), [])
+        self.assertEqual([o["pk"] for o in self.ak.list("outposts/instances/")], [self.embedded["pk"]])
 
     def test_adopts_provider_orphaned_by_interrupted_teardown(self):
         self.gate()