fix(monitoring): one value per stat panel

The OSD panel carried two queries, so it rendered two numbers side by side. Both read the same figure in the normal case, which looks like a duplicate and carries no information — a status box has one job, which is to be one colour. It now shows OSDs down alone. An OSD that is up but out was the second number; that is a state rather than a fault, Ceph already raises a health warning for it, and it does not belong in a red-or-green box. Refs #549
2026-08-27 14:34:44 +02:00
294 changed files with 8896 additions and 13876 deletions
@@ -32,17 +32,17 @@
 #              mechanism as update-audit.yml):
 #                woodpecker repo cron add --repo k.renner/homelab \
 #                  --name alert-monitor --branch master --schedule '*/15 * * * *'
-#   - deploy : woodpecker-cli pipeline deploy k.renner/homelab <n> alert-monitor
-#              where <n> is an existing pipeline to promote.
+#   - manual : woodpecker pipeline create --branch master \
+#                --var PIPELINE=alert-monitor k.renner/homelab
 when:
  - event: cron
    cron: alert-monitor
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "alert-monitor"'
+  - event: manual
+    evaluate: 'PIPELINE == "alert-monitor"'

 steps:
  - name: fetch-alerts
-    image: gitea.renner.uno/gitea_admin/ci-k8s:2026-09-08
+    image: gitea.renner.uno/gitea_admin/ci-k8s:2026-08-10
    environment:
      SOPS_AGE_KEY:
        from_secret: sops_age_key
@@ -101,7 +101,7 @@ steps:
        bash scripts/ci/make-diag-kubeconfig.sh

  - name: alert-triage-agent
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.280
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.247
    environment:
      CLAUDE_CODE_OAUTH_TOKEN:
        from_secret: claude_code_oauth_token
@@ -19,21 +19,20 @@
 # the admin account could (#330).
 #
 # The token is still OWNED by gitea_admin, because Gitea scopes packages to
-# a user or org namespace and most of these images live under `gitea_admin/*`.
-# The rebuild-critical ones additionally publish to `konairius/` — an org
-# created for the ghcr mirror path, with gitea_admin as a member so this same
-# token can push there. The full gitea_admin/* -> org migration is a
-# 38-reference change tracked separately in #330 rather than bundled here.
-# Note this pipeline runs no LLM agent, so the exfil path that motivated the
-# other cutovers does not apply to it.
+# a user or org namespace and these images live under `gitea_admin/*` — a
+# different account cannot publish there. Moving them to a dedicated org is
+# the remaining cleanup; it is a 38-reference migration across pipelines and
+# Flux-deployed CronJobs, so it is tracked separately in #330 rather than
+# bundled here. Note this pipeline runs no LLM agent, so the exfil path that
+# motivated the other cutovers does not apply to it.
 when:
  - event: push
    path:
      - "ci/images/**"
      - "secret-rotator/**"
      - ".woodpecker/build-ci-images.yml"
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "build-ci-images"'
+  - event: manual
+    evaluate: 'PIPELINE == "build-ci-images"'

 steps:
  - name: build-ansible
@@ -45,7 +44,7 @@ steps:
    # secret-rotator commit needlessly rebuilt all four ~1.3G ci-* images and
    # orphaned ~5G of registry layers per run — a main driver of #336.
    when:
-      - event: deployment
+      - event: manual
      - event: push
        path: ["ci/images/ansible/**", ".woodpecker/build-ci-images.yml"]
    environment:
@@ -69,7 +68,7 @@ steps:
    directory: ci/images/k8s
    depends_on: []
    when:
-      - event: deployment
+      - event: manual
      - event: push
        path: ["ci/images/k8s/**", ".woodpecker/build-ci-images.yml"]
    environment:
@@ -88,36 +87,12 @@ steps:
          --destination gitea.renner.uno/gitea_admin/ci-k8s:$TAG \
          --destination gitea.renner.uno/gitea_admin/ci-k8s:latest

-  - name: build-vmtest
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.18-debug
-    directory: ci/images/vmtest
-    depends_on: []
-    when:
-      - event: deployment
-      - event: push
-        path: ["ci/images/vmtest/**", ".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
-      - TAG=$(date +%Y-%m-%d)
-      - |
-        /kaniko/executor \
-          --context . \
-          --dockerfile Containerfile \
-          --destination gitea.renner.uno/gitea_admin/ci-vmtest:$TAG \
-          --destination gitea.renner.uno/gitea_admin/ci-vmtest:latest
-
  - name: build-tofu
    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.18-debug
    directory: ci/images/tofu
    depends_on: []
    when:
-      - event: deployment
+      - event: manual
      - event: push
        path: ["ci/images/tofu/**", ".woodpecker/build-ci-images.yml"]
    environment:
@@ -148,7 +123,7 @@ steps:
    directory: secret-rotator
    depends_on: []
    when:
-      - event: deployment
+      - event: manual
      - event: push
        path: ["secret-rotator/**", ".woodpecker/build-ci-images.yml"]
    environment:
@@ -172,154 +147,87 @@ steps:
  # not for who uses it — its first consumer is the zigbee2mqtt seed-data init
  # container, but nothing about it is zigbee-specific. Exists so tools come from
  # the image rather than an `apk add` on every container start.
-  #
-  # Published THREE times, and the third one is not a typo. Its consumers — the
-  # zigbee2mqtt seed-data init container and the trmnl renderer — start while
-  # the cluster is still being rebuilt, and at that moment gitea.renner.uno does
-  # not exist, because Gitea runs inside the cluster being built. A cold-rebuild
-  # rehearsal caught both in ImagePullBackOff.
-  #
-  # So there is a copy on ghcr.io. But the manifests must NOT point at it:
-  # normal operation pulls from the local registry, and an external reference
-  # would make every steady-state pull leave the network. The recovery source
-  # and the everyday source are different things, exactly as they are for Flux's
-  # git source.
-  #
-  # Talos resolves that with machine.registries.mirrors, which takes an ordered
-  # endpoint list — gitea first, ghcr second (bootstrap.sh). Containerd keeps
-  # the repository path when it falls through, so the two registries have to
-  # agree on it: `gitea_admin/alpine-jq` cannot be served by ghcr, where the
-  # namespace is fixed to the account name. Hence the second Gitea destination
-  # under konairius/, which the manifests reference and which matches the ghcr
-  # path exactly.
-  #
-  # The gitea_admin/ copy stays until nothing references it any more.
  - name: build-alpine-jq
    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.18-debug
    directory: ci/images/alpine-jq
    depends_on: []
    when:
-      - event: deployment
+      - event: manual
      - event: push
        path: ["ci/images/alpine-jq/**", ".woodpecker/build-ci-images.yml"]
    environment:
      GITEA_USER: gitea_admin
      GITEA_TOKEN:
        from_secret: ci_images_token
-      GHCR_USER: konairius
-      GHCR_TOKEN:
-        from_secret: ghcr_mirror_token
    commands:
      - mkdir -p /kaniko/.docker
      - AUTH=$(printf '%s:%s' "$GITEA_USER" "$GITEA_TOKEN" | base64 | tr -d '\n')
-      - GH_AUTH=$(printf '%s:%s' "$GHCR_USER" "$GHCR_TOKEN" | base64 | tr -d '\n')
-      - printf '{"auths":{"gitea.renner.uno":{"auth":"%s"},"ghcr.io":{"auth":"%s"}}}' "$AUTH" "$GH_AUTH" > /kaniko/.docker/config.json
+      - printf '{"auths":{"gitea.renner.uno":{"auth":"%s"}}}' "$AUTH" > /kaniko/.docker/config.json
      - TAG=$(date +%Y-%m-%d)
      - |
        /kaniko/executor \
          --context . \
          --dockerfile Containerfile \
          --destination gitea.renner.uno/gitea_admin/alpine-jq:$TAG \
-          --destination gitea.renner.uno/gitea_admin/alpine-jq:latest \
-          --destination gitea.renner.uno/konairius/alpine-jq:$TAG \
-          --destination gitea.renner.uno/konairius/alpine-jq:latest \
-          --destination ghcr.io/konairius/alpine-jq:$TAG \
-          --destination ghcr.io/konairius/alpine-jq:latest
+          --destination gitea.renner.uno/gitea_admin/alpine-jq:latest

  # Runtime image, not CI tooling: upstream containernetworking/plugins binaries
  # baked in, consumed by the multus cni-plugins-installer DaemonSet. Replaces a
  # node-side fetch from GitHub that had NO checksum verification and sat on the
  # critical path of every node rebuild. The download now happens here, once,
  # where the sha256 is checked — see the Containerfile for the full rationale.
-  #
-  # This one ALSO publishes to ghcr.io. A cold-rebuild rehearsal proved why: the
-  # DaemonSet could not pull from gitea.renner.uno, because Gitea runs inside the
-  # very cluster being rebuilt. Without the plugins there is no macvlan, so
-  # Multus cannot attach ceph-san, so Rook's network canary never starts, so the
-  # CephCluster sits at "Configuring Ceph Mons" — and OpenBao waits forever for a
-  # PVC that will never bind. Moving the download here fixed the integrity gap
-  # but quietly swapped github.com on the critical path for something strictly
-  # worse: a registry that by definition does not exist during a recovery. The
-  # GHCR copy is public, so a bare node can pull it with no credential and no
-  # Gitea.
-  #
-  # The test that proved this also proved the rule is not specific to this
-  # image. alpine-jq and alpine-openssl mirror for the same reason — see the
-  # note on build-alpine-jq. Anything an app needs while the cluster is still
-  # being built cannot live only in that cluster's own registry.
  - name: build-cni-plugins
    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.18-debug
    directory: ci/images/cni-plugins
    depends_on: []
    when:
-      - event: deployment
+      - event: manual
      - event: push
        path: ["ci/images/cni-plugins/**", ".woodpecker/build-ci-images.yml"]
    environment:
      GITEA_USER: gitea_admin
      GITEA_TOKEN:
        from_secret: ci_images_token
-      GHCR_USER: konairius
-      GHCR_TOKEN:
-        from_secret: ghcr_mirror_token
    commands:
      - mkdir -p /kaniko/.docker
      - AUTH=$(printf '%s:%s' "$GITEA_USER" "$GITEA_TOKEN" | base64 | tr -d '\n')
-      - GH_AUTH=$(printf '%s:%s' "$GHCR_USER" "$GHCR_TOKEN" | base64 | tr -d '\n')
-      - printf '{"auths":{"gitea.renner.uno":{"auth":"%s"},"ghcr.io":{"auth":"%s"}}}' "$AUTH" "$GH_AUTH" > /kaniko/.docker/config.json
+      - printf '{"auths":{"gitea.renner.uno":{"auth":"%s"}}}' "$AUTH" > /kaniko/.docker/config.json
      - TAG=$(date +%Y-%m-%d)
      - |
        /kaniko/executor \
          --context . \
          --dockerfile Containerfile \
          --destination gitea.renner.uno/gitea_admin/cni-plugins:$TAG \
-          --destination gitea.renner.uno/gitea_admin/cni-plugins:latest \
-          --destination gitea.renner.uno/konairius/cni-plugins:$TAG \
-          --destination gitea.renner.uno/konairius/cni-plugins:latest \
-          --destination ghcr.io/konairius/cni-plugins:$TAG \
-          --destination ghcr.io/konairius/cni-plugins:latest
+          --destination gitea.renner.uno/gitea_admin/cni-plugins:latest

  # Runtime image, not CI tooling: alpine + the openssl CLI, for shell scripts
  # needing s_client/x509. Named for what it is; first consumer is the paperless
  # fetch-bridge-cert init container. Replaces an `apk add openssl` that ran on
  # every paperless pod start. The openssl CLI is genuinely absent from the alpine
  # base, so this one needs an image rather than a busybox substitute.
-  #
-  # Mirrored to ghcr.io for the reason given on build-alpine-jq: it is an init
-  # container, so paperless does not start without it, and during a rebuild
-  # gitea.renner.uno is not there to serve it. A cold-rebuild rehearsal left
-  # paperless in Init:ErrImagePull on exactly this image.
  - name: build-alpine-openssl
    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.18-debug
    directory: ci/images/alpine-openssl
    depends_on: []
    when:
-      - event: deployment
+      - event: manual
      - event: push
        path: ["ci/images/alpine-openssl/**", ".woodpecker/build-ci-images.yml"]
    environment:
      GITEA_USER: gitea_admin
      GITEA_TOKEN:
        from_secret: ci_images_token
-      GHCR_USER: konairius
-      GHCR_TOKEN:
-        from_secret: ghcr_mirror_token
    commands:
      - mkdir -p /kaniko/.docker
      - AUTH=$(printf '%s:%s' "$GITEA_USER" "$GITEA_TOKEN" | base64 | tr -d '\n')
-      - GH_AUTH=$(printf '%s:%s' "$GHCR_USER" "$GHCR_TOKEN" | base64 | tr -d '\n')
-      - printf '{"auths":{"gitea.renner.uno":{"auth":"%s"},"ghcr.io":{"auth":"%s"}}}' "$AUTH" "$GH_AUTH" > /kaniko/.docker/config.json
+      - printf '{"auths":{"gitea.renner.uno":{"auth":"%s"}}}' "$AUTH" > /kaniko/.docker/config.json
      - TAG=$(date +%Y-%m-%d)
      - |
        /kaniko/executor \
          --context . \
          --dockerfile Containerfile \
          --destination gitea.renner.uno/gitea_admin/alpine-openssl:$TAG \
-          --destination gitea.renner.uno/gitea_admin/alpine-openssl:latest \
-          --destination gitea.renner.uno/konairius/alpine-openssl:$TAG \
-          --destination gitea.renner.uno/konairius/alpine-openssl:latest \
-          --destination ghcr.io/konairius/alpine-openssl:$TAG \
-          --destination ghcr.io/konairius/alpine-openssl:latest
+          --destination gitea.renner.uno/gitea_admin/alpine-openssl:latest

  # Heating CAN readers: open3e (Vitocal/VX3) + E3onCAN (E380 meter), one image
  # run as two services on edge-1. Replaces pip-into-venv on the host, where an
@@ -331,7 +239,7 @@ steps:
    directory: ci/images/heating-can
    depends_on: []
    when:
-      - event: deployment
+      - event: manual
      - event: push
        path: ["ci/images/heating-can/**", ".woodpecker/build-ci-images.yml"]
    environment:
@@ -349,87 +257,3 @@ steps:
          --dockerfile Containerfile \
          --destination gitea.renner.uno/gitea_admin/heating-can:$TAG \
          --destination gitea.renner.uno/gitea_admin/heating-can:latest
-
-  # netbird-service-sync: the controller that reconciles NetBird reverse-proxy
-  # services (public Ingress hosts -> TLS passthrough -> Traefik ClusterIP).
-  # Runtime artifact like heating-can; same registry so the audit tracks it.
-  - name: build-netbird-service-sync
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.18-debug
-    directory: ci/images/netbird-service-sync
-    depends_on: []
-    when:
-      - event: deployment
-      - event: push
-        path: ["ci/images/netbird-service-sync/**", ".woodpecker/build-ci-images.yml"]
-    environment:
-      GITEA_USER: gitea_admin
-      GITEA_TOKEN:
-        from_secret: ci_images_token
-    commands:
-      - mkdir -p /kaniko/.docker
-      - AUTH=$(printf '%s:%s' "$GITEA_USER" "$GITEA_TOKEN" | base64 | tr -d '\n')
-      - printf '{"auths":{"gitea.renner.uno":{"auth":"%s"}}}' "$AUTH" > /kaniko/.docker/config.json
-      - TAG=$(date +%Y-%m-%d)
-      - |
-        /kaniko/executor \
-          --context . \
-          --dockerfile Containerfile \
-          --destination gitea.renner.uno/gitea_admin/netbird-service-sync:$TAG \
-          --destination gitea.renner.uno/gitea_admin/netbird-service-sync:latest
-
-  # wiki-index: embedding index over the Notes repo's wiki/, fed from Gitea and
-  # queried by ~/Notes/bin/wiki_rank.py. Runtime artifact like netbird-service-sync.
-  - name: build-wiki-index
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.18-debug
-    directory: ci/images/wiki-index
-    depends_on: []
-    when:
-      - event: deployment
-      - event: push
-        path: ["ci/images/wiki-index/**", ".woodpecker/build-ci-images.yml"]
-    environment:
-      GITEA_USER: gitea_admin
-      GITEA_TOKEN:
-        from_secret: ci_images_token
-    commands:
-      - mkdir -p /kaniko/.docker
-      - AUTH=$(printf '%s:%s' "$GITEA_USER" "$GITEA_TOKEN" | base64 | tr -d '\n')
-      - printf '{"auths":{"gitea.renner.uno":{"auth":"%s"}}}' "$AUTH" > /kaniko/.docker/config.json
-      - TAG=$(date +%Y-%m-%d)
-      # Also a per-commit tag: several builds a day (branch pushes and the
-      # merge) all rewrite the dated tag, and the deployment pin raced them
-      # on 2026-09-20. The commit tag is immutable and needs no digest lookup.
-      - SHORT=$(printf '%s' "$CI_COMMIT_SHA" | cut -c1-8)
-      - |
-        /kaniko/executor \
-          --context . \
-          --dockerfile Containerfile \
-          --destination gitea.renner.uno/gitea_admin/wiki-index:$TAG \
-          --destination gitea.renner.uno/gitea_admin/wiki-index:$TAG-$SHORT \
-          --destination gitea.renner.uno/gitea_admin/wiki-index:latest
-
-  # bird: BGP daemon for the pod-network mesh over pod0 (#576). Runtime
-  # artifact like heating-can; same registry so the audit tracks it.
-  - name: build-bird
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.18-debug
-    directory: ci/images/bird
-    depends_on: []
-    when:
-      - event: deployment
-      - event: push
-        path: ["ci/images/bird/**", ".woodpecker/build-ci-images.yml"]
-    environment:
-      GITEA_USER: gitea_admin
-      GITEA_TOKEN:
-        from_secret: ci_images_token
-    commands:
-      - mkdir -p /kaniko/.docker
-      - AUTH=$(printf '%s:%s' "$GITEA_USER" "$GITEA_TOKEN" | base64 | tr -d '\n')
-      - printf '{"auths":{"gitea.renner.uno":{"auth":"%s"}}}' "$AUTH" > /kaniko/.docker/config.json
-      - TAG=$(date +%Y-%m-%d)
-      - |
-        /kaniko/executor \
-          --context . \
-          --dockerfile Containerfile \
-          --destination gitea.renner.uno/gitea_admin/bird:$TAG \
-          --destination gitea.renner.uno/gitea_admin/bird:latest
@@ -14,8 +14,8 @@
 #                 and  ci-claude:latest.  The Containerfile makes this layer
 #                 byte-reproducible, so rebuilding an unchanged version dedups
 #                 in the registry instead of orphaning a fresh ~260 MB copy.
-#   3. bump-pr  — (only when any pin is off the latest version) rewrite every
-#                 consumer pin to  ci-claude:<version>  and open a PR. A human
+#   3. bump-pr  — (only when the version actually changed) rewrite the 5
+#                 consumer pins to  ci-claude:<version>  and open a PR. A human
 #                 reviews and merges it; nothing auto-merges.
 #
 # TAG SCHEME — deliberately version tags (ci-claude:<claude-version>), NOT the dated
@@ -54,8 +54,8 @@
 #
 # Triggering:
 #   - cron   : the cron NAMED exactly "ci-claude-refresh" (see above).
-#   - deploy : woodpecker-cli pipeline deploy k.renner/homelab <n> ci-claude-refresh
-#              where <n> is an existing pipeline to promote.
+#   - manual : woodpecker pipeline create --branch master \
+#                --var PIPELINE=ci-claude-refresh k.renner/homelab
 #   - push   : a change to the Containerfile (or this file) ON master forces a
 #              rebuild of the current latest version so Containerfile fixes ship
 #              promptly. Restricted to master ON PURPOSE — a feature branch must
@@ -65,8 +65,8 @@
 when:
  - event: cron
    cron: ci-claude-refresh
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "ci-claude-refresh"'
+  - event: manual
+    evaluate: 'PIPELINE == "ci-claude-refresh"'
  - event: push
    branch: master
    path:
@@ -107,22 +107,31 @@ steps:
          [0-9]*.[0-9]*.[0-9]*) : ;;
          *) echo "npm returned an implausible version '$$NEW' — aborting."; exit 1 ;;
        esac
-        # Distinct tags the consumers currently reference. Divergent pins are
-        # normal (a pipeline bumped on its own); the bump rewrites all of them.
-        CUR=$$(grep -hoE 'ci-claude:[0-9][0-9A-Za-z._-]*' $$CONSUMERS | sed 's/^ci-claude://' | sort -u | tr '\n' ' ' | sed 's/ $$//')
-        [ -n "$$CUR" ] || { echo "No ci-claude pin found in the consumers — aborting."; exit 1; }
-        echo "latest=$$NEW  current=[$$CUR]  event=$$CI_PIPELINE_EVENT"
+        # The tag every consumer currently references. They are kept identical,
+        # so this must resolve to EXACTLY ONE non-empty tag; anything else
+        # (no match, or a partial/disagreeing set) aborts rather than risk a
+        # corrupting sed later. Counting with `grep -c .` (non-empty lines)
+        # instead of `wc -l` is deliberate: an empty result yields 0 here but
+        # 1 under wc -l, which would slip past the guard.
+        CUR=$$(grep -hoE 'ci-claude:[0-9A-Za-z._-]+' $$CONSUMERS | sed 's/^ci-claude://' | sort -u)
+        NTAGS=$$(printf '%s' "$$CUR" | grep -c . || true)
+        if [ -z "$$CUR" ] || [ "$$NTAGS" -ne 1 ]; then
+          echo "Expected exactly one ci-claude tag across the consumers, got [$$CUR]."
+          echo "Refusing to guess — fix the pins by hand."; exit 1
+        fi
+        echo "latest=$$NEW  current=$$CUR  event=$$CI_PIPELINE_EVENT"
        printf '%s' "$$NEW" > "$$CI_WORKSPACE/.ci-refresh/version"
        printf '%s' "$$CUR" > "$$CI_WORKSPACE/.ci-refresh/current"
-        # Build when any pin is off latest, or on a push (Containerfile edit must
-        # ship even if the version is unchanged). Bump when any pin is off latest.
+        # Build when the version changed, or on a push (Containerfile edit must
+        # ship even if the version is unchanged). Bump the pins only when the
+        # version the consumers reference is not the latest.
        if [ "$$CUR" != "$$NEW" ] || [ "$$CI_PIPELINE_EVENT" = "push" ]; then
          touch "$$CI_WORKSPACE/.ci-refresh/do-build"; echo "will build $$NEW"
        else
          echo "already on $$NEW — nothing to build"
        fi
        if [ "$$CUR" != "$$NEW" ]; then
-          touch "$$CI_WORKSPACE/.ci-refresh/do-bump"; echo "will open bump PR [$$CUR] -> $$NEW"
+          touch "$$CI_WORKSPACE/.ci-refresh/do-bump"; echo "will open bump PR $$CUR -> $$NEW"
        else
          echo "consumers already pin $$NEW — no PR"
        fi
@@ -166,9 +175,6 @@ steps:
      - |
        [ -f "$$CI_WORKSPACE/.ci-refresh/do-bump" ] || { echo "no version change — no PR"; exit 0; }
        set -eu
-        # Secret values can carry a trailing newline; it breaks the push URL and the auth header.
-        PUSH_TOKEN=$$(printf '%s' "$$PUSH_TOKEN" | tr -d '\r\n')
-        [ -n "$$PUSH_TOKEN" ] || { echo "PUSH_TOKEN is empty — aborting"; exit 1; }
        NEW=$$(cat "$$CI_WORKSPACE/.ci-refresh/version")
        CUR=$$(cat "$$CI_WORKSPACE/.ci-refresh/current")
        # Both were validated non-empty by the decide step; re-assert before a
@@ -184,11 +190,9 @@ steps:
        # is not a maintained list.
        CONSUMERS=$$(grep -rlE 'ci-claude:[0-9]' .woodpecker)
        [ -n "$$CONSUMERS" ] || { echo "No ci-claude consumers found — refusing to continue."; exit 1; }
-        # NEW goes into a sed replacement: allow only a plain x.y.z version.
-        printf '%s' "$$NEW" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+$$' || { echo "refusing non-x.y.z version '$$NEW'"; exit 1; }
-        # Every version-pinned tag becomes NEW, whatever it was; consumers only.
+        # Exact-string swap of the current tag for the new one, consumers only.
        for f in $$CONSUMERS; do
-          sed -i "s#ci-claude:[0-9][0-9A-Za-z._-]*#ci-claude:$$NEW#g" "$$f"
+          sed -i "s#ci-claude:$$CUR#ci-claude:$$NEW#g" "$$f"
        done
        # Author is claude-bot (the PAT's account); the commit subject makes
        # the automated-bump nature clear.
@@ -60,7 +60,7 @@ steps:
  # run that never touched them. Tracked in #461.
  - name: kustomize-build
    depends_on: [] # see note above `steps:`
-    image: gitea.renner.uno/gitea_admin/ci-k8s:2026-09-08
+    image: gitea.renner.uno/gitea_admin/ci-k8s:2026-08-10
    commands:
      - |
        set -eu
@@ -158,7 +158,7 @@ steps:
  # whenever it trails the deployed server. If you bump the server, bump here.
  - name: woodpecker-lint
    depends_on: [] # see note above `steps:`
-    image: woodpeckerci/woodpecker-cli:v3.18.0-alpine
+    image: woodpeckerci/woodpecker-cli:v3.17.0-alpine
    commands:
      - |
        set -eu
@@ -246,7 +246,7 @@ steps:
  # this step fails permanently on its own documentation.
  - name: no-digest-pins
    depends_on: [] # see note above `steps:`
-    image: gitea.renner.uno/gitea_admin/ci-k8s:2026-09-08
+    image: gitea.renner.uno/gitea_admin/ci-k8s:2026-08-10
    commands:
      - |
        set -eu
@@ -17,6 +17,6 @@ when:

 steps:
  - name: model-selection-tests
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.280
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.247
    commands:
      - sh scripts/ci/test-model-selection.sh
@@ -6,8 +6,8 @@ when:
      - "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"'
+  - event: manual
+    evaluate: 'PIPELINE == "deploy-claude-workstation"'

 timeout: 30

@@ -8,8 +8,8 @@ when:
    path:
      - "opentofu/**"
      - ".woodpecker/deploy-infrastructure.yml"
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "deploy-infrastructure"'
+  - event: manual
+    evaluate: 'PIPELINE == "deploy-infrastructure"'

 steps:
  - name: validate-secrets
@@ -84,7 +84,7 @@ steps:
    image: gitea.renner.uno/gitea_admin/ci-tofu:2026-04-29
    directory: opentofu
    when:
-      - event: deployment
+      - event: manual
        evaluate: 'TOFU_APPLY == "true"'
    environment:
      TF_IN_AUTOMATION: "true"
@@ -7,8 +7,8 @@ when:
      - "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"'
+  - event: manual
+    evaluate: 'PIPELINE == "deploy-netbird-client"'

 timeout: 30

@@ -7,24 +7,10 @@ when:
      # 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"'
+  - event: manual
+    evaluate: 'PIPELINE == "deploy-netbird-proxy"'

 timeout: 30

@@ -9,8 +9,8 @@ when:
      - "ansible/roles/netbird-proxy-watchdog/**"
      - "ansible/plays/install-netbird-server.yml"
      - ".woodpecker/deploy-netbird-server.yml"
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "deploy-netbird-server"'
+  - event: manual
+    evaluate: 'PIPELINE == "deploy-netbird-server"'

 timeout: 30

@@ -1,10 +1,10 @@
 when:
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "e2e-test"'
+  - event: manual
+    evaluate: 'PIPELINE == "e2e-test"'

 steps:
  - name: e2e
-    image: gitea.renner.uno/gitea_admin/ci-k8s:2026-09-08
+    image: gitea.renner.uno/gitea_admin/ci-k8s:2026-08-10
    environment:
      SOPS_AGE_KEY:
        from_secret: sops_age_key
@@ -7,8 +7,7 @@
 #                was harmless at daily/weekly cadence — but alert-monitor.yml
 #                fires every 15 minutes, so piggybacking must be opt-in now.
 #                A new cron that SHOULD also run e2e gets its name added here.
-#   - deploy   : `woodpecker-cli pipeline deploy k.renner/homelab <n> e2e`, where
-#                <n> is an existing pipeline to promote.
+#   - manual   : `woodpecker pipeline create --branch master --var PIPELINE=e2e k.renner/homelab`

 when:
  - event: cron
@@ -17,8 +16,8 @@ when:
    cron: update-audit
  - event: cron
    cron: weekly-update
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "e2e"'
+  - event: manual
+    evaluate: 'PIPELINE == "e2e"'

 steps:
  - name: model-selection-tests
@@ -26,12 +25,12 @@ 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:2.1.280
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.247
    commands:
      - sh scripts/ci/test-model-selection.sh

  - name: e2e-test
-    image: gitea.renner.uno/gitea_admin/ci-k8s:2026-09-08
+    image: gitea.renner.uno/gitea_admin/ci-k8s:2026-08-10
    environment:
      SOPS_AGE_KEY:
        from_secret: sops_age_key
@@ -0,0 +1,27 @@
+when:
+  - event: manual
+    evaluate: 'PIPELINE == "install-garage-synology"'
+
+steps:
+  - name: run-playbook
+    image: gitea.renner.uno/gitea_admin/ci-ansible:2026-04-29
+    environment:
+      ANSIBLE_FORCE_COLOR: "true"
+      ANSIBLE_HOST_KEY_CHECKING: "false"
+      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-garage-synology.yml -v
@@ -34,13 +34,13 @@
 #   - cron   : a cron NAMED exactly "issue-fix":
 #                woodpecker repo cron add --repo k.renner/homelab \
 #                  --name issue-fix --branch master --schedule '41 * * * *'
-#   - deploy : woodpecker-cli pipeline deploy k.renner/homelab <n> issue-fix
-#              where <n> is an existing pipeline to promote.
+#   - manual : woodpecker pipeline create --branch master \
+#                --var PIPELINE=issue-fix k.renner/homelab
 when:
  - event: cron
    cron: issue-fix
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "issue-fix"'
+  - event: manual
+    evaluate: 'PIPELINE == "issue-fix"'

 steps:
  - name: fetch-diag
@@ -49,7 +49,7 @@ steps:
    # (the issue-pick logic needs jq, which only the ci-claude image has);
    # minting a 1h read-only token per run is cheap. Degrades to
    # snapshot-only if the ci-diagnostics ServiceAccount isn't reconciled.
-    image: gitea.renner.uno/gitea_admin/ci-k8s:2026-09-08
+    image: gitea.renner.uno/gitea_admin/ci-k8s:2026-08-10
    environment:
      SOPS_AGE_KEY:
        from_secret: sops_age_key
@@ -62,7 +62,7 @@ steps:
      - bash scripts/ci/make-diag-kubeconfig.sh

  - name: issue-fix-agent
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.280
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.247
    environment:
      CLAUDE_CODE_OAUTH_TOKEN:
        from_secret: claude_code_oauth_token
@@ -53,9 +53,9 @@
 #
 # Triggering: pull_request only — automatic on PR open + push-to-open-PR. To
 # re-review a PR, push a commit (the new head sha clears the dedup marker below
-# and earns a fresh review). There is deliberately no on-demand trigger for a
-# specific PR: Woodpecker exposes injected variables to YAML substitution and
-# `when` filters, NOT to a step's shell environment, so a PR=<n> re-review would
+# and earns a fresh review). There is deliberately no manual PIPELINE trigger:
+# Woodpecker exposes a --var only to YAML variable substitution and `when`
+# filters, NOT to a step's shell environment, so a --var PR=<n> re-review would
 # silently no-op (the step would find no PR number and exit green).
 # (Note: keep literal dollar-brace out of THIS file entirely, even in comments —
 # Woodpecker runs its variable substitution over the whole YAML text, comments
@@ -65,7 +65,7 @@ when:

 steps:
  - name: pr-review-agent
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.280
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.247
    environment:
      CLAUDE_CODE_OAUTH_TOKEN:
        from_secret: claude_code_oauth_token
@@ -1,20 +1,8 @@
-# Trivy scan of the IaC tree and every image referenced from ansible/, with an
-# agent pass that opens a PR for CRITICAL/HIGH findings.
-#
-# Triggers:
-#   - cron       : the named `daily-security-scan` cron, matched by NAME.
-#                  Crons cannot carry variables — `woodpecker-cli repo cron add`
-#                  has no --var — so a variable gate can never match a cron.
-#   - deployment : woodpecker-cli pipeline deploy k.renner/homelab <n> security-scan
-#                  The target rides in pipeline metadata as
-#                  CI_PIPELINE_DEPLOY_TARGET, which the workflow-root filter
-#                  does see, unlike manual-run variables on Woodpecker 3.18
-#                  (#582).
 when:
  - event: cron
-    cron: daily-security-scan
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "security-scan"'
+    evaluate: 'PIPELINE == "security-scan"'
+  - event: manual
+    evaluate: 'PIPELINE == "security-scan"'

 steps:
  - name: iac-scan
@@ -40,28 +28,12 @@ steps:
        cat /tmp/images.txt
        echo "---"
        i=0
-        failed=0
-        failed_names=""
        while IFS= read -r img; do
          i=$$((i+1))
          out="trivy-image-$$i.json"
          echo "=== [$$i] $$img -> $$out ==="
-          # Keep going on a bad image so one unpullable reference cannot cost
-          # the scan of every image after it, but record that it happened.
-          if ! trivy image --skip-db-update --scanners vuln --timeout 15m --severity CRITICAL,HIGH --ignore-unfixed --format json -o "$$out" "$$img"; then
-            failed=$$((failed+1))
-            failed_names="$$failed_names $$img"
-          fi
+          trivy image --skip-db-update --scanners vuln --timeout 15m --severity CRITICAL,HIGH --ignore-unfixed --format json -o "$$out" "$$img" || true
        done < /tmp/images.txt
-        echo "--- scanned $$((i - failed)) of $$i images ---"
-        if [ "$$failed" -gt 0 ]; then
-          echo "NOT SCANNED:$$failed_names"
-          exit 1
-        fi
-    # Non-zero above turns this step red without failing the workflow, so the
-    # fix agent still runs on what was scanned. Coverage is reported, not
-    # enforced: an incomplete scan is visible in the step status instead of
-    # being indistinguishable from a clean one.
    failure: ignore

  - name: security-fix-agent
@@ -70,7 +42,7 @@ steps:
    # this step is skipped — otherwise we'd fork-bomb PRs.
    when:
      - branch: master
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.280
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.247
    environment:
      CLAUDE_CODE_OAUTH_TOKEN:
        from_secret: claude_code_oauth_token
@@ -10,14 +10,14 @@
 # report; the pipeline posts it to a single persistent Gitea issue.
 #
 # Triggering:
-#   - cron   : a cron NAMED exactly "update-audit". Crons carry no variables —
-#              `repo cron add` takes name, branch, schedule and enabled — so the
-#              name filter is the only thing that can select a workflow for a
-#              scheduled run:
+#   - cron   : a cron NAMED exactly "update-audit". Unlike the other pipelines
+#              here (which gate on an injected `PIPELINE` var set at cron-create
+#              time in the UI), this uses Woodpecker's documented `cron:` name
+#              filter so the schedule can be created entirely from the CLI:
 #                woodpecker repo cron add --repo k.renner/homelab \
 #                  --name update-audit --branch master --schedule '@weekly'
-#   - deploy : woodpecker-cli pipeline deploy k.renner/homelab <n> update-audit
-#              where <n> is an existing pipeline to promote.
+#   - manual : woodpecker pipeline create --branch master \
+#                --var PIPELINE=update-audit k.renner/homelab
 #
 # NOTE: e2e.yml runs on an explicit list of cron names that includes this one,
 # so a weekly e2e run piggybacks on the audit (it was a bare `event: cron`
@@ -25,12 +25,12 @@
 when:
  - event: cron
    cron: update-audit
-  - event: deployment
-    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "update-audit"'
+  - event: manual
+    evaluate: 'PIPELINE == "update-audit"'

 steps:
  - name: update-audit-agent
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.280
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.247
    environment:
      CLAUDE_CODE_OAUTH_TOKEN:
        from_secret: claude_code_oauth_token
@@ -1,119 +0,0 @@
-# Nightly wiki maintenance for the Notes vault (k.renner/notes), replacing the
-# workstation's wiki-maintenance.timer: distill the raw/ backlog into wiki/
-# (a `claude` run of the wiki-distill agent), then audit wiki/ with the vault's
-# own script (structural checks, no model). The pipeline commits and pushes as
-# Claude Bot; the push webhook then refreshes the wiki-index service.
-#
-# The agent and its retrieval scripts address the vault as ~/Notes, so the
-# distill step links $HOME/Notes to the checkout instead of rewriting them.
-when:
-  - event: cron
-    cron: wiki-maintenance
-  # Hand-started runs: `woodpecker pipeline create k.renner/homelab --branch master`.
-  # The typesafe_api_key secret is scoped to cron and manual, not deployment.
-  - event: manual
-
-steps:
-  - name: checkout-notes
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.280
-    pull: true
-    environment:
-      WIKI_BOT_TOKEN:
-        from_secret: wiki_bot_token
-    commands:
-      - |
-        set -eu
-        # Token only on the wire, never in .git/config. Secrets set from files carry
-        # a trailing newline (run 10220: "could not read Username"); strip CR/LF.
-        TOKEN=$$(printf '%s' "$$WIKI_BOT_TOKEN" | tr -d '\r\n')
-        git -c http.extraheader="AUTHORIZATION: token $$TOKEN" \
-          clone --depth 50 --branch main https://gitea.renner.uno/k.renner/notes.git notes
-        echo "raw backlog: $$(ls notes/raw/*.md | grep -v _index.md | wc -l) file(s)"
-
-  - name: distill
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.280
-    pull: true
-    environment:
-      CLAUDE_CODE_OAUTH_TOKEN:
-        from_secret: claude_code_oauth_token
-      TYPESAFE_API_KEY:
-        from_secret: typesafe_api_key
-      WIKI_INDEX_BASIC_AUTH:
-        from_secret: wiki_index_basic_auth
-    commands:
-      - |
-        set -eu
-        ln -sfn "$$PWD/notes" "$$HOME/Notes"
-        mkdir -p "$$HOME/.config/wiki-index"
-        printf '%s' "$$WIKI_INDEX_BASIC_AUTH" | tr -d '\r\n' > "$$HOME/.config/wiki-index/basic-auth"
-        chmod 600 "$$HOME/.config/wiki-index/basic-auth"
-        "$$HOME/Notes/bin/wiki_rank.py" --probe-index
-      - |
-        set -eu
-        MODEL=$$(sh scripts/ci/pick-model.sh "distill raw source notes into atomic wiki notes: read sources, check the wiki for existing coverage, write or merge notes; careful writing, moderate reasoning")
-        if [ -n "$$MODEL" ]; then echo "distill: selected model $$MODEL"; else echo "distill: using the CLI default model"; fi
-        cd notes
-        cat ../ci/agents/wiki-maintenance/distill.md | claude $${MODEL:+--model $$MODEL} \
-          --agent wiki-distill \
-          --permission-mode acceptEdits \
-          --allowedTools "Read,Edit,Write,Glob,Grep,Bash(/root/Notes/bin/wiki_rank.py:*),Bash(/root/Notes/bin/wiki_ask.py:*),Bash(mv /root/Notes/raw/:*),Bash(mkdir -p /root/Notes/:*)" \
-          --settings ../ci/agents/wiki-maintenance/settings.json \
-          -p
-
-  - name: audit
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.280
-    pull: true
-    commands:
-      # Findings are report lines in output/, not a pipeline failure.
-      - python3 -B notes/bin/wiki_audit.py --vault "$$PWD/notes"
-
-  - name: push-notes
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.280
-    pull: true
-    environment:
-      WIKI_BOT_TOKEN:
-        from_secret: wiki_bot_token
-    commands:
-      - |
-        set -eu
-        cd notes
-        git config user.email "claude-bot@renner.uno"
-        git config user.name "Claude Bot"
-        # Only the vault content is committed; anything an agent leaves elsewhere
-        # in the checkout (run 10362: scratch scripts in the root) stays behind.
-        if [ -z "$$(git status --porcelain -- wiki raw output)" ]; then
-          echo "wiki-maintenance: no changes"
-          exit 0
-        fi
-        # The workstation pushes main on its own (notes-push.path), so main moves
-        # while the agents run (run 10241: non-fast-forward). The run's work goes
-        # to a branch and a PR that this step merges through Gitea; a conflict
-        # leaves the PR open for a human and fails the run.
-        BRANCH="wiki-maintenance/$$(date -u +%F)-$$CI_PIPELINE_NUMBER"
-        git checkout -q -b "$$BRANCH"
-        git add -A -- wiki raw output
-        git commit -q -m "wiki maintenance $$(date -u +%F): distill + audit (CI run $$CI_PIPELINE_NUMBER)"
-        TOKEN=$$(printf '%s' "$$WIKI_BOT_TOKEN" | tr -d '\r\n')
-        git -c http.extraheader="AUTHORIZATION: token $$TOKEN" push origin "HEAD:$$BRANCH"
-        API="https://gitea.renner.uno/api/v1/repos/k.renner/notes"
-        jq -n --arg title "wiki maintenance $$(date -u +%F) (CI run $$CI_PIPELINE_NUMBER)" \
-              --arg body "Nightly distill + audit. Merged by the pipeline; open only if the merge failed." \
-              --arg head "$$BRANCH" '{title: $$title, body: $$body, head: $$head, base: "main"}' > /tmp/pr.json
-        code=$$(curl -s -o /tmp/pr-resp.json -w '%{http_code}' -X POST \
-          -H "Authorization: token $$TOKEN" -H "Content-Type: application/json" --data @/tmp/pr.json "$$API/pulls")
-        echo "POST pull -> HTTP $$code"
-        [ "$$code" -ge 200 ] && [ "$$code" -lt 300 ] || { cat /tmp/pr-resp.json; exit 1; }
-        NUM=$$(jq -r '.number' /tmp/pr-resp.json)
-        # Merge without delete_branch_after_merge: run 10254 got HTTP 500 from that
-        # call although the merge itself had landed. Verify the PR state instead of
-        # trusting the status code, then drop the branch as a separate, best-effort step.
-        code=$$(curl -s -o /tmp/merge-resp.json -w '%{http_code}' -X POST \
-          -H "Authorization: token $$TOKEN" -H "Content-Type: application/json" \
-          --data '{"Do":"merge"}' "$$API/pulls/$$NUM/merge")
-        echo "POST merge #$$NUM -> HTTP $$code"
-        MERGED=$$(curl -s -H "Authorization: token $$TOKEN" "$$API/pulls/$$NUM" | jq -r '.merged')
-        echo "PR #$$NUM merged: $$MERGED"
-        [ "$$MERGED" = "true" ] || { cat /tmp/merge-resp.json; echo "PR #$$NUM left open"; exit 1; }
-        code=$$(curl -s -o /tmp/del-resp.json -w '%{http_code}' -X DELETE -H "Authorization: token $$TOKEN" \
-          "$$API/branches/$$(printf '%s' "$$BRANCH" | sed 's|/|%2F|g')")
-        echo "DELETE branch $$BRANCH -> HTTP $$code (best effort)"
@@ -1,23 +0,0 @@
---
-# Bouncer key for crowdsec-edge-bouncer, scoped to the proxy hosts.
-#
-# A single encrypted VALUE rather than a whole-file vault like its siblings in
-# group_vars/all and group_vars/edge_host. Deliberate: adding this variable to
-# an existing whole-file vault means decrypting that file first, which exposes
-# every other secret in it for the sake of appending one line. encrypt_string
-# keeps the blast radius at this one value.
-#
-# Same value as OpenBao homelab/infrastructure/crowdsec-edge-bouncer-key, which
-# the crowdsec-edge-bouncer-key ExternalSecret feeds to BOUNCER_KEY_edge on the
-# LAPI. Both sides must move together — and unlike crowdsec-bouncer-key, this
-# one is NOT in the quarterly rotator, because nothing on these hosts re-reads
-# OpenBao on a schedule. Rotating it means updating OpenBao and re-running
-# plays/install-netbird-proxy.yml.
-vault_crowdsec_edge_bouncer_key: !vault |
-          $ANSIBLE_VAULT;1.1;AES256
-          32653764333536316163303838333839616562663862666637626165303837633866643033393239
-          3363376538656236643161386432326437633232643564630a633635306365323537346139626364
-          36613033343938363366306239363638383466396337623333623136313234656366333366623433
-          6437656632373364340a346566343866366433306533353431383064356362346536383136323663
-          39333864643534326433653233303137373162663066633132623931316135323733333863306330
-          6366623463666435636362376238313639666263323163303733
@@ -0,0 +1,37 @@
+---
+# PBS Client configuration for nas-1
+pbs_backup_paths:
+  - /volume1/Documents
+  - /volume1/homes
+  - /volume1/Homeassistant Backup
+  - /volume1/Games
+  - /volume1/Media
+  - /volume1/Music
+  - /volume1/video
+  - /volume2/Backup
+  - /volume1/Movies
+
+  # Add more paths as needed:
+  # - /volume1/photos
+  # - /volume1/music
+
+# PBS Server connection
+pbs_server_host: "pbs2.renner.uno"
+pbs_server_port: 8007
+pbs_datastore: "pool"
+pbs_backup_id: "nas-1"
+
+# PBS Authentication - credentials in vault.yml
+pbs_username: "root@pam!nas-1"
+
+# Garage S3 (K8s backup target)
+garage_image: "dxflrs/garage:v2.3.0"
+garage_zone: "dsm"
+garage_capacity: "2T"
+
+# SSH connection - use password auth (key not supported by DSM)
+ansible_ssh_pass: "{{ nas_ssh_password }}"
+ansible_become_pass: "{{ nas_ssh_password }}"
+
+# Python 3.9+ from Synology package
+ansible_python_interpreter: /usr/local/bin/python3.9
@@ -0,0 +1,27 @@
+$ANSIBLE_VAULT;1.1;AES256
+34663462636437633437613863366266306334666635643839313737343739643864613136613938
+3138393966306561656366396465383539303137333036300a376237376636356230343834386362
+36636535396330333732383233323263613132333166343739396137636538653435336662353138
+6565643866623235610a316266383933303830323936303735623338623165386339383733373435
+62366461363833616438373237383132366438326364363462333265366533323861376630643365
+39343036343838333639363432643738666630363063323636646661313539643465366532363438
+33303837623234613434633563666562346536346435353461373536323737376233386163326537
+61383963343737656438356136613537623538333163343466343739346135333439616432663763
+36663962633037376561326434303035333938646436663832303432346365353439666435613337
+34363636326530333233313231343566306432376532396666643761633136316333376337666135
+65363338623035663438323338663863366362653131336434323865326530326534623631336263
+36633063383031386161363131333636393364623436613331353733313235383062656131313164
+63393665633361313961363637663237616364643236383835393736643937393564656238376362
+31393465383361326264376133393233616264663636383337363962356532613438663637616536
+33653137656335323763313461323633616635346232303062323062333766383931313965346361
+66656461313239633366636463633465636463663937393932636337643861383937663662306466
+32353166643832303234643264633062616330393963333034623432613730366339306637613239
+34626161663666316339323762373639353335653663353635366664643063393432623039306237
+38363161343930363763393364663364353735343236313665313461626165636135303839363164
+37336638396564326166376233353730346563656266323535666265323062646232323938353732
+32636235333839623166633761376334316434613235333730353439343262393537363461333238
+32653435623362666662336532643832356163326332636436346132643237643030343761663332
+36663530356539303636663438646430363335353135323932613863666264363533326137353164
+31663032346236616263343637396439663334396166656364623637666535386530383535663435
+66303037303265616634373763616437333835333136336563323339666563663931396133633131
+3963653266633535303630653335666166313336653831623362
@@ -8,8 +8,6 @@
 #   pve_cluster (jupiter/neptune/saturn)  run Talos on bare metal; no SSH at all
 #   authentik_db / authentik_app          authentik runs in-cluster (CNPG)
 #   grafana                               runs in-cluster
-#   synology_nas (nas-1)                  powered off; Garage and the PBS client
-#                                         it hosted are gone with it
 # Their hosts no longer resolve, except the three that resolve to Talos nodes.

 [netbird_server]
@@ -19,6 +17,10 @@ netbird.renner.uno ansible_user=root
 proxy-1.renner.uno ansible_user=root
 proxy-2.renner.uno ansible_user=root

+
+[synology_nas]
+nas-1.renner.uno ansible_user=ladmin ansible_python_interpreter=/usr/bin/python3
+
 # Every bare-metal edge thin client. Gets the host-generic roles only:
 # flash-wear handling, the log shipper, the MQTT bridge, the VLAN
 # sub-interface. Nothing here assumes any peripheral is attached.
@@ -0,0 +1,313 @@
+---
+# Synology-specific playbook using raw module (Python 3.8 workaround)
+# Deploys Garage (https://garagehq.deuxfleurs.fr) as a single-node S3 target
+# for K8s backups (Velero + CNPG Barman Cloud Plugin).
+#
+# Required secrets in host_vars/nas-1.renner.uno/vault.yml:
+#   garage_rpc_secret:     "<openssl rand -hex 32>"
+#   garage_admin_token:    "<openssl rand -base64 32>"
+#   garage_metrics_token:  "<openssl rand -base64 32>"
+#
+# Post-install bootstrap (run once, record the returned secret keys):
+#   docker exec garaged /garage status
+#   docker exec garaged /garage bucket create k8s-velero
+#   docker exec garaged /garage bucket create k8s-cnpg
+#   docker exec garaged /garage bucket create k8s-secrets
+#   docker exec garaged /garage bucket create k8s-migration
+#   docker exec garaged /garage key create velero-key
+#   docker exec garaged /garage key create cnpg-key
+#   docker exec garaged /garage key create secrets-key
+#   docker exec garaged /garage key create migration-key
+#   docker exec garaged /garage bucket allow --read --write --owner k8s-velero    --key velero-key
+#   docker exec garaged /garage bucket allow --read --write --owner k8s-cnpg      --key cnpg-key
+#   docker exec garaged /garage bucket allow --read --write --owner k8s-secrets   --key secrets-key
+#   docker exec garaged /garage bucket allow --read --write --owner k8s-migration --key migration-key
+- name: Install Garage S3 on Synology NAS
+  hosts: synology_nas
+  gather_facts: false
+
+  vars:
+    garage_data_dir: "/volume1/docker/garage"
+
+  tasks:
+    - name: Create Garage directory tree
+      ansible.builtin.raw: |
+        mkdir -p {{ garage_data_dir }}/config \
+                 {{ garage_data_dir }}/meta \
+                 {{ garage_data_dir }}/data
+      changed_when: true
+
+    # Secret writes use the same compare-then-write pattern as garage.toml so
+    # rotation is idempotent AND a real change can drive force-recreate below.
+    # Garage reads these files once at startup; without container restart, a
+    # rotated token leaves the running process holding the previous value.
+    - name: Write rpc_secret
+      ansible.builtin.raw: |
+        cat > {{ garage_data_dir }}/config/rpc_secret.new << 'SECRET_EOF'
+        {{ garage_rpc_secret }}
+        SECRET_EOF
+        chmod 600 {{ garage_data_dir }}/config/rpc_secret.new
+        if [ ! -f {{ garage_data_dir }}/config/rpc_secret ] \
+        || ! cmp -s {{ garage_data_dir }}/config/rpc_secret.new {{ garage_data_dir }}/config/rpc_secret; then
+          mv {{ garage_data_dir }}/config/rpc_secret.new {{ garage_data_dir }}/config/rpc_secret
+          echo RPC_SECRET_CHANGED
+        else
+          rm {{ garage_data_dir }}/config/rpc_secret.new
+        fi
+      register: rpc_secret_write
+      changed_when: "'RPC_SECRET_CHANGED' in rpc_secret_write.stdout"
+      no_log: true
+
+    - name: Write admin_token
+      ansible.builtin.raw: |
+        cat > {{ garage_data_dir }}/config/admin_token.new << 'SECRET_EOF'
+        {{ garage_admin_token }}
+        SECRET_EOF
+        chmod 600 {{ garage_data_dir }}/config/admin_token.new
+        if [ ! -f {{ garage_data_dir }}/config/admin_token ] \
+        || ! cmp -s {{ garage_data_dir }}/config/admin_token.new {{ garage_data_dir }}/config/admin_token; then
+          mv {{ garage_data_dir }}/config/admin_token.new {{ garage_data_dir }}/config/admin_token
+          echo ADMIN_TOKEN_CHANGED
+        else
+          rm {{ garage_data_dir }}/config/admin_token.new
+        fi
+      register: admin_token_write
+      changed_when: "'ADMIN_TOKEN_CHANGED' in admin_token_write.stdout"
+      no_log: true
+
+    - name: Write metrics_token
+      ansible.builtin.raw: |
+        cat > {{ garage_data_dir }}/config/metrics_token.new << 'SECRET_EOF'
+        {{ garage_metrics_token }}
+        SECRET_EOF
+        chmod 600 {{ garage_data_dir }}/config/metrics_token.new
+        if [ ! -f {{ garage_data_dir }}/config/metrics_token ] \
+        || ! cmp -s {{ garage_data_dir }}/config/metrics_token.new {{ garage_data_dir }}/config/metrics_token; then
+          mv {{ garage_data_dir }}/config/metrics_token.new {{ garage_data_dir }}/config/metrics_token
+          echo METRICS_TOKEN_CHANGED
+        else
+          rm {{ garage_data_dir }}/config/metrics_token.new
+        fi
+      register: metrics_token_write
+      changed_when: "'METRICS_TOKEN_CHANGED' in metrics_token_write.stdout"
+      no_log: true
+
+    - name: Write garage.toml
+      ansible.builtin.raw: |
+        cat > {{ garage_data_dir }}/config/garage.toml.new << 'TOML_EOF'
+        metadata_dir = "/var/lib/garage/meta"
+        data_dir     = "/var/lib/garage/data"
+
+        # SQLite chosen over LMDB: single-node deployment has no peers to
+        # rebuild metadata from on unclean-shutdown corruption. SQLite is
+        # slower but portable and has no LMDB corruption window.
+        db_engine = "sqlite"
+
+        # 6-hour auto-snapshot of the metadata DB as a backstop against
+        # corruption; last two snapshots retained.
+        metadata_auto_snapshot_interval = "6h"
+
+        # Single-zone, single-node: only coherent replication factor.
+        replication_factor = 1
+
+        rpc_bind_addr    = "[::]:3901"
+        rpc_secret_file  = "/etc/garage/rpc_secret"
+
+        compression_level = 2
+
+        # 64 MB blocks (default 1 MB; previously 20 MB). On the 5 × 7 TB
+        # Btrfs RAID 5 volume the per-block fixed cost (SQLite lookup,
+        # dir traversal, hash verify, zstd decompress, nginx buffering)
+        # is the dominant overhead per object; larger blocks amortize
+        # it. block_size is a maximum, so 16 MiB CNPG WAL segments
+        # still upload as one block each. Only applies to NEW uploads;
+        # existing objects keep their original chunking until re-uploaded.
+        block_size = "64M"
+
+        [s3_api]
+        api_bind_addr = "[::]:3900"
+        s3_region     = "garage"
+        root_domain   = ".s3.{{ inventory_hostname }}"
+
+        [s3_web]
+        bind_addr   = "[::]:3902"
+        root_domain = ".web.{{ inventory_hostname }}"
+
+        [admin]
+        api_bind_addr      = "[::]:3903"
+        admin_token_file   = "/etc/garage/admin_token"
+        metrics_token_file = "/etc/garage/metrics_token"
+        TOML_EOF
+        if [ ! -f {{ garage_data_dir }}/config/garage.toml ] \
+        || ! cmp -s {{ garage_data_dir }}/config/garage.toml.new {{ garage_data_dir }}/config/garage.toml; then
+          mv {{ garage_data_dir }}/config/garage.toml.new {{ garage_data_dir }}/config/garage.toml
+          echo GARAGE_TOML_CHANGED
+        else
+          rm {{ garage_data_dir }}/config/garage.toml.new
+        fi
+      register: garage_toml_write
+      changed_when: "'GARAGE_TOML_CHANGED' in garage_toml_write.stdout"
+
+    - name: Write docker-compose.yml
+      ansible.builtin.raw: |
+        cat > {{ garage_data_dir }}/docker-compose.yml << 'COMPOSE_EOF'
+        services:
+          garage:
+            image: {{ garage_image }}
+            container_name: garaged
+            restart: unless-stopped
+            # HTTP services (3900/3902/3903) bind to loopback; DSM
+            # reverse proxy fronts and TLS-terminates them. RPC 3901
+            # is exposed directly — the Noise handshake is raw TCP,
+            # so DSM RP cannot front it. rpc_secret gates auth.
+            ports:
+              - "3901:3901"
+              - "127.0.0.1:3900:3900"
+              - "127.0.0.1:3902:3902"
+              - "127.0.0.1:3903:3903"
+            volumes:
+              - {{ garage_data_dir }}/config/garage.toml:/etc/garage.toml:ro
+              - {{ garage_data_dir }}/config/rpc_secret:/etc/garage/rpc_secret:ro
+              - {{ garage_data_dir }}/config/admin_token:/etc/garage/admin_token:ro
+              - {{ garage_data_dir }}/config/metrics_token:/etc/garage/metrics_token:ro
+              - {{ garage_data_dir }}/meta:/var/lib/garage/meta
+              - {{ garage_data_dir }}/data:/var/lib/garage/data
+        COMPOSE_EOF
+      changed_when: true
+
+    - name: Pull image and start Garage container
+      ansible.builtin.shell: |
+        export PATH=$PATH:/usr/local/bin
+        cd {{ garage_data_dir }} && docker compose pull && docker compose up -d
+      become: true
+      changed_when: true
+
+    # Garage does not reload config on SIGHUP and compose does not notice
+    # when a bind-mounted host file changes. Force-recreate the container
+    # when garage.toml OR any of the three secret files changed so the new
+    # config / rotated tokens are picked up.
+    - name: Force-recreate garaged when garage.toml or secrets changed
+      ansible.builtin.shell: |
+        export PATH=$PATH:/usr/local/bin
+        cd {{ garage_data_dir }} && docker compose up -d --force-recreate garage
+      become: true
+      when: garage_toml_write.changed
+            or rpc_secret_write.changed
+            or admin_token_write.changed
+            or metrics_token_write.changed
+      changed_when: true
+
+    - name: Wait for Garage to accept CLI calls
+      ansible.builtin.shell: |
+        export PATH=$PATH:/usr/local/bin
+        for i in $(seq 1 30); do
+          if docker exec garaged /garage status >/dev/null 2>&1; then
+            exit 0
+          fi
+          sleep 2
+        done
+        exit 1
+      become: true
+      changed_when: false
+
+    - name: Check whether cluster layout is already applied
+      ansible.builtin.shell: |
+        export PATH=$PATH:/usr/local/bin
+        docker exec garaged /garage status
+      become: true
+      register: garage_status
+      changed_when: false
+
+    - name: Apply single-node layout (idempotent — only on first run)
+      when: "'NO ROLE ASSIGNED' in garage_status.stdout"
+      ansible.builtin.shell: |
+        export PATH=$PATH:/usr/local/bin
+        NODE_ID=$(docker exec garaged /garage node id | head -n 1 | cut -d@ -f1)
+        docker exec garaged /garage layout assign "$NODE_ID" \
+          -z {{ garage_zone }} \
+          -c {{ garage_capacity }} \
+          -t {{ inventory_hostname_short }}
+        docker exec garaged /garage layout apply --version 1
+      become: true
+      changed_when: true
+
+    - name: Report Garage status
+      ansible.builtin.shell: |
+        export PATH=$PATH:/usr/local/bin
+        docker exec garaged /garage status
+      become: true
+      register: garage_status_final
+      changed_when: false
+
+    - name: Show Garage status
+      ansible.builtin.debug:
+        var: garage_status_final.stdout_lines
+
+    # Bootstrap buckets + keys. Idempotent: bucket_info / key_info return
+    # non-zero when missing, so we only create on first run. Access-key
+    # secrets are captured at create time and persisted to chmod-600 files
+    # under {{ garage_data_dir }}/config/keys/<key>.creds on nas-1. These
+    # files are the only post-install record of the secrets — Garage does
+    # not expose them again.
+    - name: Bootstrap Garage buckets, keys, and grants
+      ansible.builtin.shell: |
+        set -e
+        export PATH=$PATH:/usr/local/bin
+        KEYS_DIR={{ garage_data_dir }}/config/keys
+        mkdir -p "$KEYS_DIR"
+        chmod 700 "$KEYS_DIR"
+
+        bootstrap_pair() {
+          local BUCKET="$1"
+          local KEY="$2"
+          local CREDS_FILE="$KEYS_DIR/$KEY.creds"
+
+          if ! docker exec garaged /garage bucket info "$BUCKET" >/dev/null 2>&1; then
+            docker exec garaged /garage bucket create "$BUCKET"
+          fi
+
+          if ! docker exec garaged /garage key info "$KEY" >/dev/null 2>&1; then
+            CREATE_OUT=$(docker exec garaged /garage key create "$KEY")
+            KEY_ID=$(echo "$CREATE_OUT"   | awk '/^Key ID:/     {print $3}')
+            SECRET=$(echo "$CREATE_OUT"   | awk '/^Secret key:/ {print $3}')
+            umask 177
+            printf 'KEY_ID=%s\nSECRET_KEY=%s\n' "$KEY_ID" "$SECRET" > "$CREDS_FILE"
+          fi
+
+          docker exec garaged /garage bucket allow \
+            --read --write --owner \
+            "$BUCKET" --key "$KEY"
+        }
+
+        bootstrap_pair k8s-velero    velero-key
+        bootstrap_pair k8s-cnpg      cnpg-key
+        bootstrap_pair k8s-secrets   secrets-key
+        bootstrap_pair k8s-migration migration-key
+        bootstrap_pair tfstate       tfstate-key
+      become: true
+      changed_when: true
+      no_log: true
+
+    - name: Report bucket + key state (no secrets)
+      ansible.builtin.shell: |
+        export PATH=$PATH:/usr/local/bin
+        docker exec garaged /garage bucket list
+        echo "---"
+        docker exec garaged /garage key list
+        echo "---"
+        ls -l {{ garage_data_dir }}/config/keys/ 2>&1
+      become: true
+      register: garage_bootstrap_state
+      changed_when: false
+
+    - name: Show bucket + key state
+      ansible.builtin.debug:
+        var: garage_bootstrap_state.stdout_lines
+
+    - name: Post-install note
+      ansible.builtin.debug:
+        msg:
+          - "Buckets: k8s-velero, k8s-cnpg, k8s-secrets, k8s-migration, tfstate"
+          - "Keys:    velero-key, cnpg-key, secrets-key, migration-key, tfstate-key"
+          - "Secrets are written to {{ garage_data_dir }}/config/keys/<key>.creds on nas-1 (chmod 600, root-owned)."
+          - "SSH to nas-1 and `sudo cat` the file to retrieve KEY_ID + SECRET_KEY for Velero / CNPG / migration / tfstate config."
@@ -26,7 +26,3 @@
    - docker-install
    - netbird-proxy
    - netbird-proxy-watchdog
-    # Enforces the cluster's CrowdSec decisions here, where public traffic
-    # enters. Deployed in dry-run: it logs what it would block and creates no
-    # nftables rules until crowdsec_bouncer_mode is flipped per host.
-    - crowdsec-edge-bouncer
@@ -0,0 +1,104 @@
+---
+# Synology-specific playbook using raw module (Python 3.8 workaround)
+- name: Install PBS Client on Synology NAS
+  hosts: synology_nas
+  gather_facts: false
+
+  vars:
+    pbs_client_data_dir: "/volume1/docker/pbs-client"
+
+  tasks:
+    - name: Create PBS client directory
+      ansible.builtin.raw: |
+        mkdir -p {{ pbs_client_data_dir }}/state
+      changed_when: true
+
+    - name: Create docker-compose.yml
+      ansible.builtin.raw: |
+        cat > {{ pbs_client_data_dir }}/docker-compose.yml << 'COMPOSE_EOF'
+        services:
+          pbs-client:
+            image: proxmox/proxmox-backup-client:latest
+            container_name: pbs-client
+            restart: unless-stopped
+            hostname: {{ pbs_backup_id }}
+            env_file:
+              - .env
+            volumes:
+              - {{ pbs_client_data_dir }}/state:/root/.proxmox-backup
+        {% for path in pbs_backup_paths %}
+              - "{{ path }}:{{ path }}:ro"
+        {% endfor %}
+            mem_limit: 2g
+            command: ["sleep", "infinity"]
+        COMPOSE_EOF
+      changed_when: true
+
+    - name: Create .env file
+      ansible.builtin.raw: |
+        cat > {{ pbs_client_data_dir }}/.env << 'ENV_EOF'
+        PBS_REPOSITORY={{ pbs_username }}@{{ pbs_server_host }}:{{ pbs_server_port }}:{{ pbs_datastore }}
+        PBS_PASSWORD={{ pbs_password }}
+        ENV_EOF
+        chmod 600 {{ pbs_client_data_dir }}/.env
+      changed_when: true
+
+    - name: Create backup script
+      ansible.builtin.raw: |
+        cat > {{ pbs_client_data_dir }}/backup.sh << 'SCRIPT_EOF'
+        #!/bin/bash
+        set -e
+        source {{ pbs_client_data_dir }}/.env
+
+        BACKUP_SOURCES=""
+        {% for path in pbs_backup_paths %}
+        BACKUP_SOURCES="$BACKUP_SOURCES {{ path | basename }}.pxar:{{ path }}"
+        {% endfor %}
+
+        echo "[$(date '+%Y-%m-%d %H:%M:%S')] Starting backup for {{ pbs_backup_id }}"
+        docker exec pbs-client proxmox-backup-client backup \
+            $BACKUP_SOURCES \
+            --backup-id {{ pbs_backup_id }} \
+            --repository "${PBS_REPOSITORY}"
+
+        echo "[$(date '+%Y-%m-%d %H:%M:%S')] Backup completed, pruning..."
+        docker exec pbs-client proxmox-backup-client prune \
+            --repository "${PBS_REPOSITORY}" \
+            --backup-id {{ pbs_backup_id }} \
+            --keep-last {{ pbs_keep_last | default(3) }} \
+            --keep-daily {{ pbs_keep_daily | default(7) }} \
+            --keep-weekly {{ pbs_keep_weekly | default(4) }} \
+            --keep-monthly {{ pbs_keep_monthly | default(6) }}
+
+        echo "[$(date '+%Y-%m-%d %H:%M:%S')] Done"
+        SCRIPT_EOF
+        chmod 755 {{ pbs_client_data_dir }}/backup.sh
+      changed_when: true
+
+    - name: Start PBS client container
+      ansible.builtin.shell: |
+        export PATH=$PATH:/usr/local/bin
+        cd {{ pbs_client_data_dir }} && docker compose pull && docker compose up -d
+      become: true
+      changed_when: true
+
+    - name: Setup cron job for daily backup at 2 AM (root crontab)
+      ansible.builtin.shell: |
+        # Remove existing entry if present
+        crontab -l 2>/dev/null | grep -v "pbs-client/backup.sh" | crontab - 2>/dev/null || true
+        # Add new entry
+        (crontab -l 2>/dev/null; echo "0 2 * * * {{ pbs_client_data_dir }}/backup.sh >> /var/log/pbs-backup.log 2>&1") | crontab -
+      become: true
+      changed_when: true
+
+    - name: Verify container is running
+      ansible.builtin.shell: |
+        export PATH=$PATH:/usr/local/bin
+        docker ps --filter name=pbs-client --format "{{ '{{' }}.Status{{ '}}' }}"
+      become: true
+      register: container_status
+      changed_when: false
+
+    - name: Show container status
+      ansible.builtin.debug:
+        msg: "PBS client container status: {{ container_status.stdout }}"
@@ -0,0 +1,11 @@
+---
+- name: Install PBS Client on Synology NAS
+  hosts: synology_nas
+  become: true
+  # Variables are set in:
+  # - Role defaults: ansible/roles/pbs-client/defaults/main.yml
+  # - Host overrides: ansible/inventory/host_vars/<hostname>/vars.yml
+  # - Secrets: ansible/inventory/host_vars/<hostname>/vault.yml
+
+  roles:
+    - pbs-client
@@ -1,56 +0,0 @@
---
-# CrowdSec firewall bouncer on the NetBird proxy hosts.
-#
-# 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
-# cluster.
-#
-# Detection stays in the cluster. The reverse-proxy produces no parseable
-# access log and there is no CrowdSec collection for it, while Traefik has a
-# working one — and every scenario in use needs HTTP detail (paths, status
-# codes, user agents) that does not exist at this layer.
-
-# Pinned. A release tarball URL is immutable, and this checksum is of the
-# amd64 asset for exactly this tag.
-crowdsec_bouncer_version: v0.0.36
-crowdsec_bouncer_sha256: f86e4b72693549d99f40a9402abefb894108f047a3fbe6e72fada25ee17ce88b
-
-# The LAPI over the public path these hosts already serve, see
-# kubernetes/infrastructure/crowdsec/lapi-ingress.yaml. The proxies cannot
-# reach it over the mesh: the reverse-proxy container runs non-root, so its
-# embedded NetBird client terminates the tunnel in userspace and the tunnel
-# belongs to that process rather than to the host netns.
-#
-# No ca_cert_path: Traefik serves a Let's Encrypt certificate for this name,
-# and the bouncer adds ca_cert_path to the system pool rather than replacing
-# it — the system pool already trusts LE.
-crowdsec_bouncer_api_url: https://crowdsec.renner.uno/
-crowdsec_bouncer_api_key: "{{ vault_crowdsec_edge_bouncer_key }}"
-
-# Enforcing. The bouncer creates two nftables tables (ip crowdsec, ip6
-# crowdsec6) holding the decisions it pulled, touches no existing chain and
-# sets no chain policy — SSH and :443 stay open unless the source is banned.
-#
-# `dry-run` is the other value: it pulls and logs what it would block without
-# creating a single rule. That is what a new host should be given before it
-# enforces, and what an existing one can be dropped back to, per host through
-# inventory/host_vars, without disarming the rest.
-#
-# Worth knowing before arming anything new: the first bouncer on a path
-# enforces the whole CAPI set at once — around 15k addresses today — so the
-# false-positive window belongs before the switch, not after it. And because
-# this chain sits on the INPUT hook while these hosts run no other firewall,
-# there is no conntrack rule accepting established flows ahead of it: a banned
-# address is dropped even when it is answering our own outbound connection.
-# That is why capi_whitelists.yaml carries the proxies and netbird.renner.uno.
-crowdsec_bouncer_mode: nftables
-
-crowdsec_bouncer_update_frequency: 10s
-crowdsec_bouncer_log_level: info
-
-# Bound to loopback deliberately. These hosts are public and have no metrics
-# collection path at all today — opening :60601 to the internet to gain a
-# scrape target is the wrong trade. Revisit when host metrics exist.
-crowdsec_bouncer_metrics_listen: 127.0.0.1
-crowdsec_bouncer_metrics_port: 60601
@@ -1,10 +0,0 @@
---
-# A restart drops both nftables tables and rebuilds them from the next
-# successful LAPI pull, so there is a short window with no blocklist. That is
-# the documented behaviour of a clean shutdown, not a defect — and it is why
-# retry_initial_connect matters.
- name: Restart crowdsec firewall bouncer
-  ansible.builtin.systemd:
-    name: crowdsec-firewall-bouncer.service
-    state: restarted
-    daemon_reload: true
@@ -1,111 +0,0 @@
---
-# See defaults/main.yml for why this exists and why it starts inert.
-#
-# The static release tarball, not a distribution package: the AUR package
-# `crowdsec-firewall-bouncer-nftables` depends on `crowdsec` and would pull the
-# whole Security Engine onto hosts that only need the bouncer, the group is
-# mixed (proxy-1 Arch, VPS-1 Debian), and the AUR would be a new pattern this
-# repo does not otherwise have. The tarball is the same artefact the AUR
-# package downloads.
-
- name: Ensure nftables is present (the enforcing backend)
-  ansible.builtin.package:
-    name: nftables
-    state: present
-
- name: Ensure the bouncer config directory exists
-  ansible.builtin.file:
-    path: /etc/crowdsec/bouncers
-    state: directory
-    mode: "0755"
-
-# Fetched on the CONTROLLER and pushed, not pulled by the host.
-#
-# proxy-1 is IPv6-only, and neither github.com nor objects.githubusercontent.com
-# publishes an AAAA record — a get_url on the host fails with "Network is
-# unreachable" and no amount of retrying fixes it. Mirroring into
-# gitea.renner.uno is no help either: its public records are the internal LB
-# VIP (10.2.99.86 / fd99::86), so it is unreachable from outside the LAN. And
-# 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.
- name: Fetch the pinned bouncer release on the controller
-  ansible.builtin.get_url:
-    url: >-
-      https://github.com/crowdsecurity/cs-firewall-bouncer/releases/download/{{
-      crowdsec_bouncer_version }}/crowdsec-firewall-bouncer-linux-amd64.tgz
-    dest: /tmp/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}.tgz
-    checksum: sha256:{{ crowdsec_bouncer_sha256 }}
-    mode: "0644"
-  delegate_to: localhost
-  become: false
-  run_once: true
-
-# Only the download had to move to the controller — the extraction stays on
-# the host. The ci-ansible image ships a tar that ansible rejects ("detected as
-# tar type None. GNU tar required"), while both host distributions have GNU
-# tar. Shipping the archive rather than the unpacked binary also keeps the
-# artefact that the checksum was verified against intact all the way to the
-# host.
- name: Copy the bouncer archive to the host
-  ansible.builtin.copy:
-    src: /tmp/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}.tgz
-    dest: /opt/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}.tgz
-    mode: "0644"
-
-# Only the binary. The tarball also carries install.sh / upgrade.sh /
-# uninstall.sh, which manage systemd and config themselves — that is this
-# role's job, and letting them run would leave two owners for the same files.
- name: Unpack the bouncer binary
-  ansible.builtin.unarchive:
-    src: /opt/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}.tgz
-    dest: /opt
-    remote_src: true
-    include:
-      - crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}/crowdsec-firewall-bouncer
-    creates: /opt/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}/crowdsec-firewall-bouncer
-
- name: Install the bouncer binary
-  ansible.builtin.copy:
-    src: /opt/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}/crowdsec-firewall-bouncer
-    dest: /usr/local/bin/crowdsec-firewall-bouncer
-    remote_src: true
-    mode: "0755"
-  notify: Restart crowdsec firewall bouncer
-
-# 0600: this file carries the LAPI key.
- name: Deploy the bouncer configuration
-  ansible.builtin.template:
-    src: crowdsec-firewall-bouncer.yaml.j2
-    dest: /etc/crowdsec/bouncers/crowdsec-firewall-bouncer.yaml
-    mode: "0600"
-  notify: Restart crowdsec firewall bouncer
-
- name: Deploy the bouncer systemd unit
-  ansible.builtin.template:
-    src: crowdsec-firewall-bouncer.service.j2
-    dest: /etc/systemd/system/crowdsec-firewall-bouncer.service
-    mode: "0644"
-  notify: Restart crowdsec firewall bouncer
-
- name: Enable and start the bouncer
-  ansible.builtin.systemd:
-    name: crowdsec-firewall-bouncer.service
-    enabled: true
-    state: started
-    daemon_reload: true
-
- name: Report how to read it
-  ansible.builtin.debug:
-    msg: |
-      crowdsec-firewall-bouncer deployed in mode "{{ crowdsec_bouncer_mode }}".
-
-      What it would block:  journalctl -u crowdsec-firewall-bouncer -f
-      What it does block:   nft list table ip crowdsec ; nft list table ip6 crowdsec6
-      Metrics:              curl -s {{ crowdsec_bouncer_metrics_listen }}:{{ crowdsec_bouncer_metrics_port }}/metrics
-
-      Rollback: systemctl stop crowdsec-firewall-bouncer. A clean stop deletes
-      both nftables tables by itself. Only after a kill -9 do they need
-      removing by hand: nft delete table ip crowdsec ; nft delete table ip6 crowdsec6
@@ -1,24 +0,0 @@
-# Managed by Ansible (crowdsec-edge-bouncer role) — do not edit.
-#
-# Upstream's shipped unit orders itself After=crowdsec.service. There is no
-# local Security Engine on these hosts — the LAPI is in the cluster — so that
-# dependency is dropped; nss-lookup instead, because api_url is a public name
-# that has to resolve before the first connect.
-[Unit]
-Description=CrowdSec firewall bouncer (edge enforcement for the NetBird proxy)
-After=network-online.target nss-lookup.target
-Wants=network-online.target
-
-[Service]
-Type=notify
-# -t validates the config and exits non-zero on a bad one, so a broken config
-# fails the start instead of taking the running rules down with it.
-ExecStartPre=/usr/local/bin/crowdsec-firewall-bouncer -c /etc/crowdsec/bouncers/crowdsec-firewall-bouncer.yaml -t
-ExecStart=/usr/local/bin/crowdsec-firewall-bouncer -c /etc/crowdsec/bouncers/crowdsec-firewall-bouncer.yaml
-Restart=always
-RestartSec=10
-LimitNOFILE=65536
-KillMode=mixed
-
-[Install]
-WantedBy=multi-user.target
@@ -1,55 +0,0 @@
-# Managed by Ansible (crowdsec-edge-bouncer role) — do not edit.
-mode: {{ crowdsec_bouncer_mode }}
-update_frequency: {{ crowdsec_bouncer_update_frequency }}
-
-# stdout, so journald owns the log and there is no second rotation policy to
-# keep in sync. The shipped example writes to /var/log; that only matters for
-# hosts without journald.
-log_mode: stdout
-log_level: {{ crowdsec_bouncer_log_level }}
-
-api_url: {{ crowdsec_bouncer_api_url }}
-api_key: {{ crowdsec_bouncer_api_key }}
-
-# Without this the process EXITS when the LAPI is unreachable at startup —
-# there is no retry on the first connect. And because a clean shutdown deletes
-# the nftables tables, the systemd restart loop would leave the host with no
-# blocklist at all until the first successful connect. Present in the code,
-# absent from the shipped example config.
-retry_initial_connect: true
-
-disable_ipv4: false
-disable_ipv6: false
-deny_action: DROP
-
-supported_decisions_types:
-  - ban
-
-# Separate tables per family; the bouncer never touches an existing table or
-# chain, and never sets a chain policy. Priority -10 puts it ahead of anything
-# at the default filter priority.
-nftables:
-  ipv4:
-    enabled: true
-    set-only: false
-    table: crowdsec
-    chain: crowdsec-chain
-    priority: -10
-  ipv6:
-    enabled: true
-    set-only: false
-    table: crowdsec6
-    chain: crowdsec6-chain
-    priority: -10
-
-# input is the traffic this exists for: the reverse-proxy is host-networked and
-# owns :443, so its packets traverse INPUT. forward covers the bridge-networked
-# http-redirect sidecar, whose packets never do.
-nftables_hooks:
-  - input
-  - forward
-
-prometheus:
-  enabled: true
-  listen_addr: {{ crowdsec_bouncer_metrics_listen }}
-  listen_port: {{ crowdsec_bouncer_metrics_port }}
@@ -26,16 +26,8 @@ edge_open3e_poll_seconds: 30
 # entries when added), so the multi-frame read is cheap at a 30 s poll.
 # Records faults/info events only (NormalOperation, LagDeviceDtcReported,
 # LegionellaProtectionTemperatureReached) — NOT setpoint or program changes.
-# onebase.*: the 29 paired ZigBee slots on the One Base gateway (ECU 0x6c3) --
-# 8 radiator valves, 9 climate sensors, 9 underfloor actuators, 3 floor
-# thermostats. Per-device room temperature, active setpoint, humidity, valve
-# opening/demand, battery and RSSI; the local replacement for the ViCare cloud
-# room sensors. Needs the onebase overlay (files/open3e-onebase.py) -- the stock
-# codec declares 57 bytes and a paired slot answers with 68.
-# Only CurrentValues are polled. The room and device registries (1884.., 2084..)
-# are static configuration and are read on demand, not every 30 s.
 edge_open3e_datapoints: >-
-  vitocal.259,vitocal.260,vitocal.268,vitocal.269,vitocal.271,vitocal.274,vitocal.286,vitocal.288,vitocal.318,vitocal.321,vitocal.324,vitocal.335,vitocal.336,vitocal.396,vitocal.402,vitocal.403,vitocal.476,vitocal.477,vitocal.543,vitocal.548,vitocal.565,vitocal.1007,vitocal.1043,vitocal.1190,vitocal.1211,vitocal.1391,vitocal.1416,vitocal.1417,vitocal.2320,vitocal.2346,vitocal.2350,vitocal.2351,vitocal.2352,vitocal.2369,vitocal.2370,vitocal.2486,vitocal.2487,vitocal.2488,vitocal.2543,vitocal.2560,vitocal.2622,vitocal.2624,vitocal.2625,vitocal.2735,vitocal.3016,vx3.266,vx3.378,vx3.379,vx3.380,vx3.535,vx3.1603,vx3.1664,vx3.1690,vx3.1801,vx3.1802,vx3.1810,vx3.1828,vx3.1830,vx3.1577,vx3.1578,vx3.1579,vx3.1580,vx3.1581,vx3.1582,vx3.1834,vx3.1836,vx3.2214,vx3.2240,vx3.3085,vx3.3086,vx3.3087,vx3.3088,vx3.3089,vx3.3090,vcmu.320,vcmu.322,vcmu.325,vcmu.355,vcmu.389,vcmu.391,vcmu.1772,vcmu.1773,vcmu.1775,vcmu.1776,vcmu.2256,vcmu.2259,vcmu.2333,vcmu.2334,vcmu.2569,vcmu.2571,vitocal.2791,onebase.2086,onebase.2089,onebase.2092,onebase.2095,onebase.2098,onebase.2101,onebase.2104,onebase.2107,onebase.2110,onebase.2113,onebase.2116,onebase.2119,onebase.2122,onebase.2125,onebase.2128,onebase.2131,onebase.2134,onebase.2137,onebase.2140,onebase.2143,onebase.2262,onebase.2265,onebase.2268,onebase.2271,onebase.2274,onebase.2277,onebase.2280,onebase.2283,onebase.2286
+  vitocal.259,vitocal.260,vitocal.268,vitocal.269,vitocal.271,vitocal.274,vitocal.286,vitocal.288,vitocal.318,vitocal.321,vitocal.324,vitocal.335,vitocal.336,vitocal.396,vitocal.402,vitocal.403,vitocal.476,vitocal.477,vitocal.543,vitocal.548,vitocal.565,vitocal.1007,vitocal.1043,vitocal.1190,vitocal.1211,vitocal.1391,vitocal.1416,vitocal.1417,vitocal.2320,vitocal.2346,vitocal.2350,vitocal.2351,vitocal.2352,vitocal.2369,vitocal.2370,vitocal.2486,vitocal.2487,vitocal.2488,vitocal.2543,vitocal.2560,vitocal.2622,vitocal.2624,vitocal.2625,vitocal.2735,vitocal.3016,vx3.266,vx3.378,vx3.379,vx3.380,vx3.535,vx3.1603,vx3.1664,vx3.1690,vx3.1801,vx3.1802,vx3.1810,vx3.1828,vx3.1830,vx3.1577,vx3.1578,vx3.1579,vx3.1580,vx3.1581,vx3.1582,vx3.1834,vx3.1836,vx3.2214,vx3.2240,vx3.3085,vx3.3086,vx3.3087,vx3.3088,vx3.3089,vx3.3090,vcmu.320,vcmu.322,vcmu.325,vcmu.355,vcmu.389,vcmu.391,vcmu.1772,vcmu.1773,vcmu.1775,vcmu.1776,vcmu.2256,vcmu.2259,vcmu.2333,vcmu.2334,vcmu.2569,vcmu.2571,vitocal.2791
 # ECU addresses; -dev selects codec set, tx selects the UDS address.
 # vcmu (refrigerant-circuit controller) has no dedicated codec set —
 # omitting dpList makes open3e fall back to the generic datapoint list,
@@ -46,9 +38,6 @@ edge_open3e_devices:
  # files/open3e-vx3plus.py) — die Stock-vx3-Liste filtert sie sonst weg.
  vx3: { tx: "0x6a1", dpList: "/config/vx3plus.py" }
  vcmu: { tx: "0x68c" }
-  # One Base ZigBee gateway. Overlay re-declares the paired ZigBee slots at
-  # their real 68-byte length (see files/open3e-onebase.py).
-  onebase: { tx: "0x6c3", dpList: "/config/onebase.py" }

 edge_e3oncan_gap_seconds: 10
 edge_e3oncan_mqtt_format: "{device}_{didNumber:04d}_{didName}"
@@ -1,54 +0,0 @@
-# Managed by ansible (roles/heating-can). Datapoint overlay for the One Base
-# ZigBee gateway on ECU 0x6c3 (BACKENDGATEWAY).
-#
-# Upstream declares ZigBee<N>DeviceCurrentValues as 57 bytes. A PAIRED device
-# slot on this gateway answers with 68: the 57 known bytes plus the parent
-# device serial and three trailing bytes. udsoncan reads only the declared
-# length and then treats the next two bytes -- the first half of that serial --
-# as a foreign data identifier, so every paired slot fails to decode with
-# "Server returned values for data identifier 0x.... that was not requested".
-# The bogus identifier differs per device because the serial does.
-#
-# This overlay re-declares the 29 paired slots at 68 bytes, reusing upstream's
-# sub-type list so the per-device-type O3ESwitch (climate sensor / TRV / floor
-# thermostat / actuator, incl. DeviceTemperatureSetpoint) is inherited rather
-# than copied.
-#
-# EMPTY slots answer with 57 and decode against the stock codec, so they are
-# left alone and are not polled. A slot that is later unpaired therefore starts
-# reporting a decode error on its topic instead of a value.
-#
-# Verified on ECU 0x6c3, 2026-09-17: 29 paired slots, all 68 bytes.
-from open3e.Open3Ecodecs import O3EComplexType, RawCodec
-from open3e.Open3Edatapoints import dataIdentifiers as _master
-
-# ZigBee<N>DeviceCurrentValues of the paired slots: devices 1-20 run 2086..2143
-# in steps of 3, devices 21-29 continue at 2262..2286.
-_PAIRED_CURRENT_VALUES = [2086 + 3 * n for n in range(20)] + [
-    2262 + 3 * n for n in range(9)
-]
-
-
-def _with_parent_serial(did):
-    stock = _master["dids"][did]
-    return O3EComplexType(
-        68,
-        stock.id,
-        list(stock.subTypes)
-        + [
-            RawCodec(8, "ParentDeviceSerialnumber"),
-            RawCodec(2, "Unknown_65_66"),
-            RawCodec(1, "Unknown_67"),
-        ],
-        desc=stock.desc,
-        info=stock.info,
-        acc=stock.acc,
-    )
-
-
-dataIdentifiers = {
-    "dids": {
-        **_master["dids"],
-        **{did: _with_parent_serial(did) for did in _PAIRED_CURRENT_VALUES},
-    }
-}
@@ -129,13 +129,6 @@
    mode: "0644"
  notify: Restart heating-can

- name: Deploy open3e One Base datapoint overlay (68-byte ZigBee slots)
-  ansible.builtin.copy:
-    src: open3e-onebase.py
-    dest: "{{ heating_can_base_dir }}/onebase.py"
-    mode: "0644"
-  notify: Restart heating-can
-
 # --- Compose project ---------------------------------------------------------
 - name: Deploy the broker credential env file
  ansible.builtin.template:
@@ -17,7 +17,6 @@ services:
    volumes:
      - ./devices.json:/config/devices.json:ro
      - ./vx3plus.py:/config/vx3plus.py:ro
-      - ./onebase.py:/config/onebase.py:ro
    env_file:
      # Broker credential, 0600 -- see heating-can.env.j2.
      - heating-can.env
@@ -32,13 +32,8 @@ netbird_watchdog_fail_threshold: 3

 # Minimum seconds between watchdog-issued restarts, so a genuinely broken
 # backend can't put the proxy into a restart loop. Shared by both the URL-probe
-# watchdog and the flood watchdog below. One minute: the route-manager wedge
-# recurs on every routing-peer loss, and rolling node reboots lose one peer
-# every few minutes; a suppressed restart there leaves the wedge standing
-# until the URL probe's three rounds fire (3.5 min of 000 on every domain,
-# measured 2026-09-07). A minute still caps a loop at one restart per
-# probe interval.
-netbird_watchdog_cooldown_seconds: 60
+# watchdog and the flood watchdog below.
+netbird_watchdog_cooldown_seconds: 600

 # Log fingerprint of the reverse-proxy route-manager wedge, matched as a plain
 # substring in the proxy's docker logs by the flood watchdog. On this build the
@@ -0,0 +1,18 @@
+#!/bin/sh
+# Forced-command target for the netbird-backup SSH key (see the
+# "Authorize the cluster backup key" task): takes a CONSISTENT snapshot
+# of the management SQLite store via the online-backup API (safe against
+# a live writer, unlike copying store.db) and streams a gzipped tar to
+# stdout. The key's authorized_keys entry is restricted to exactly this
+# script — the in-cluster puller cannot run anything else.
+#
+# Deliberately store.db ONLY: /opt/netbird/config is fully regenerable
+# from the netbird-server role's templates + vault, and including it
+# would put the plaintext TURN secret (turnserver.conf) into every
+# nightly tarball. Restore = re-run the role (rebuilds config), then
+# untar this dump into /opt/netbird/management/.
+set -eu
+tmp=$(mktemp -d)
+trap 'rm -rf "$tmp"' EXIT
+sqlite3 /opt/netbird/management/store.db ".backup '$tmp/store.db'"
+tar -C "$tmp" -czf - store.db
@@ -77,22 +77,29 @@
  register: docker_compose_result
  changed_when: "'Started' in docker_compose_result.stdout or 'Creating' in docker_compose_result.stdout"

-# 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.
- name: Remove the backup dump script
-  ansible.builtin.file:
-    path: /usr/local/bin/netbird-backup-dump
-    state: absent
+# Off-VPS backup of the management store (SPOF assessment 2026-07-25:
+# this SQLite DB — peers, setup keys, groups, routes — had zero backup
+# coverage; losing the VPS meant re-enrolling the entire mesh). The VPS
+# cannot reach any PBS (both PBS names resolve to the public proxy,
+# ports closed), so the CLUSTER pulls: a CronJob
+# (kubernetes/infrastructure/netbird-backup) ssh's in with a dedicated
+# key that is locked to the dump script below, and lands the tarball on
+# a Ceph PVC that Velero ships offsite. The dump is store.db ONLY —
+# /opt/netbird/config is regenerable from this role's templates + vault
+# and would otherwise leak the TURN secret into every tarball. Restore:
+# re-run this role (rebuilds config), then untar the dump into
+# /opt/netbird/management/.
+- name: Install the backup dump script
+  ansible.builtin.copy:
+    src: netbird-backup-dump
+    dest: /usr/local/bin/netbird-backup-dump
+    mode: "0755"

- name: Revoke the cluster backup key
+- name: Authorize the cluster backup key (forced command, no shell)
  ansible.posix.authorized_key:
    user: root
    key: "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFeW/L9bHMTSa5/Qb0ClppCf4Z0hL39JwzI6tBmKd2FG netbird-backup@homelab-cluster"
-    state: absent
+    key_options: 'restrict,command="/usr/local/bin/netbird-backup-dump"'

 - name: Wait for management container to be ready
  ansible.builtin.pause:
@@ -0,0 +1,32 @@
+---
+# PBS Client configuration
+pbs_client_version: "latest"
+pbs_client_data_dir: "/opt/pbs-client"
+
+# PBS Server connection (override in host_vars)
+pbs_server_host: "pbs.obg.renner.uno"
+pbs_server_port: 8007
+pbs_datastore: "backups"
+
+# Authentication (override in vault!)
+pbs_username: "backup@pbs"
+pbs_password: ""
+# pbs_fingerprint: ""  # Optional - omit for Let's Encrypt certs
+
+# Backup configuration
+pbs_backup_id: "nas-1"
+pbs_backup_paths:
+  - /volume1/docker
+  - /volume1/homes
+
+# Schedule (cron format)
+pbs_backup_schedule: "0 2 * * *"  # 2 AM daily
+
+# Retention policy (prune settings)
+pbs_keep_last: 3
+pbs_keep_daily: 7
+pbs_keep_weekly: 4
+pbs_keep_monthly: 6
+
+# Container resource limits
+pbs_memory_limit: "2g"
@@ -0,0 +1,6 @@
+---
+- name: Restart PBS client
+  community.docker.docker_compose_v2:
+    project_src: "{{ pbs_client_data_dir }}"
+    state: restarted
+    docker_cli: "{{ docker_cli | default('/usr/local/bin/docker') }}"
@@ -0,0 +1,23 @@
+---
+- name: Create PBS client directories
+  ansible.builtin.file:
+    path: "{{ item }}"
+    state: directory
+    mode: '0755'
+  loop:
+    - "{{ pbs_client_data_dir }}"
+    - "{{ pbs_client_data_dir }}/state"
+
+- name: Copy PBS client docker-compose file
+  ansible.builtin.template:
+    src: docker-compose.yml.j2
+    dest: "{{ pbs_client_data_dir }}/docker-compose.yml"
+    mode: '0644'
+  notify: Restart PBS client
+
+- name: Start PBS client via Docker Compose
+  community.docker.docker_compose_v2:
+    project_src: "{{ pbs_client_data_dir }}"
+    state: present
+    pull: always
+    docker_cli: "{{ docker_cli | default('/usr/local/bin/docker') }}"
@@ -0,0 +1,6 @@
+# PBS Client Environment Configuration
+PBS_REPOSITORY={{ pbs_username }}@{{ pbs_server_host }}:{{ pbs_server_port }}:{{ pbs_datastore }}
+PBS_PASSWORD={{ pbs_password }}
+{% if pbs_fingerprint | default('') != '' %}
+PBS_FINGERPRINT={{ pbs_fingerprint }}
+{% endif %}
@@ -0,0 +1,36 @@
+#!/bin/bash
+# PBS Backup Script for {{ pbs_backup_id }}
+# Managed by Ansible - do not edit manually
+
+set -e
+
+# Load environment
+source {{ pbs_client_data_dir }}/.env
+
+# Build backup command with all paths
+BACKUP_SOURCES=""
+{% for path in pbs_backup_paths %}
+BACKUP_SOURCES="$BACKUP_SOURCES {{ path | basename }}.pxar:{{ path }}"
+{% endfor %}
+
+echo "[$(date '+%Y-%m-%d %H:%M:%S')] Starting backup for {{ pbs_backup_id }}"
+
+# Run backup via Docker
+docker exec pbs-client proxmox-backup-client backup \
+    $BACKUP_SOURCES \
+    --backup-id {{ pbs_backup_id }} \
+    --repository "${PBS_REPOSITORY}"
+
+echo "[$(date '+%Y-%m-%d %H:%M:%S')] Backup completed"
+
+# Prune old backups
+echo "[$(date '+%Y-%m-%d %H:%M:%S')] Pruning old backups"
+docker exec pbs-client proxmox-backup-client prune \
+    --repository "${PBS_REPOSITORY}" \
+    --backup-id {{ pbs_backup_id }} \
+    --keep-last {{ pbs_keep_last }} \
+    --keep-daily {{ pbs_keep_daily }} \
+    --keep-weekly {{ pbs_keep_weekly }} \
+    --keep-monthly {{ pbs_keep_monthly }}
+
+echo "[$(date '+%Y-%m-%d %H:%M:%S')] Prune completed"
@@ -0,0 +1,30 @@
+services:
+  pbs-client:
+    image: aterfax/pbs-client:{{ pbs_client_version }}
+    container_name: pbs-client
+    restart: unless-stopped
+    hostname: {{ pbs_backup_id }}
+    environment:
+      - PBS_ENDPOINT={{ pbs_server_host }}:{{ pbs_server_port }}
+      - PBS_DATASTORE={{ pbs_datastore }}
+      - PBS_API_KEY_NAME={{ pbs_username }}
+      - PBS_API_KEY_SECRET={{ pbs_password }}
+      - PBS_PASSWORD={{ pbs_password }}
+      - PBS_ENCRYPTION_PASSWORD={{ pbs_encryption_password | default(pbs_password) }}
+      - PBS_REPOSITORY={{ pbs_username }}@{{ pbs_server_host }}:{{ pbs_server_port }}:{{ pbs_datastore }}
+      - PBS_BACKUP_ID={{ pbs_backup_id }}
+      - CRON_SCHEDULE={{ pbs_backup_schedule }}
+      - PBS_BACKUP_CMD_APPEND_EXTRA_OPTS=--crypt-mode=none
+      - PRUNE_KEEP_LAST={{ pbs_keep_last | default(3) }}
+      - PRUNE_KEEP_DAILY={{ pbs_keep_daily | default(7) }}
+      - PRUNE_KEEP_WEEKLY={{ pbs_keep_weekly | default(4) }}
+      - PRUNE_KEEP_MONTHLY={{ pbs_keep_monthly | default(6) }}
+      - CRON_BACKUP_ONLY=1
+    volumes:
+      - {{ pbs_client_data_dir }}/state:/root/.config/proxmox-backup
+{% for path in pbs_backup_paths %}
+      - "{{ path }}:/backups/{{ path | basename | replace(' ', '_') }}:ro"
+{% endfor %}
+    tmpfs:
+      - /tmp
+    mem_limit: {{ pbs_memory_limit }}
@@ -1,7 +0,0 @@
-You are running as the scheduled wiki-maintenance job in CI. The Notes vault is checked out at ~/Notes (the repository k.renner/notes). Do exactly this, nothing else:
-
-Glob ~/Notes/raw/*.md (top level only, never ~/Notes/raw/_processed/). Distill every file you find into ~/Notes/wiki/ following your process, including the ranker check for every concept. Move each fully processed source to ~/Notes/raw/_processed/. If raw/ has no top-level files besides _index.md, say so and stop.
-
-Do not commit or push; the pipeline does that after you finish. Do not touch anything outside ~/Notes/wiki/ and ~/Notes/raw/.
-
-End with one line per file: which wiki notes it produced or merged into, or "nothing distillable".
@@ -1,37 +0,0 @@
-{
-  "//": "Permission scope for the wiki-maintenance agent (wiki-distill) in CI.",
-  "//2": "The step's environment holds a Gitea push token, a TypeSafe key and the wiki-index",
-  "//3": "client credential, so the Read tool is kept away from /proc (env dumps), /root outside",
-  "//4": "the vault symlink target, /etc and the checkout's .git/. The vault itself is the work.",
-  "//5": "Mirrors ci/agents/issue-fix/settings.json; absolute globs because the vault is reached",
-  "//6": "through the ~/Notes symlink the pipeline creates.",
-  "permissions": {
-    "allow": [
-      "Read(//root/Notes/**)",
-      "Edit(//root/Notes/wiki/**)",
-      "Edit(//root/Notes/output/**)",
-      "Edit(//root/Notes/raw/**)",
-      "Bash(/root/Notes/bin/wiki_rank.py:*)",
-      "Bash(/root/Notes/bin/wiki_ask.py:*)",
-      "Bash(mv /root/Notes/raw/:*)",
-      "Bash(mkdir -p /root/Notes/:*)",
-      "Bash(ls:*)",
-      "Bash(date:*)",
-      "Bash(wc:*)",
-      "Bash(head:*)",
-      "Bash(tail:*)"
-    ],
-    "deny": [
-      "Read(//proc/**)",
-      "Read(//etc/**)",
-      "Read(//root/.config/**)",
-      "Read(//root/Notes/.git/**)",
-      "Read(//root/Notes/_archive/**)",
-      "Edit(//root/Notes/_archive/**)",
-      "Bash(rm:*)",
-      "Bash(git:*)",
-      "Bash(curl:*)",
-      "Bash(wget:*)"
-    ]
-  }
-}
@@ -1,22 +0,0 @@
-FROM alpine:3.22@sha256:14358309a308569c32bdc37e2e0e9694be33a9d99e68afb0f5ff33cc1f695dce
-
-# bird: BGP daemon for the pod-network mesh over pod0. Distro package, no build
-# step — the image is the binary plus its runtime.
-#
-# 3.22 rather than the 3.21 the other images here pin: bird2 first appears in
-# 3.22/community.
-#
-# Config is read from /etc/bird/bird.conf, not the package default
-# /etc/bird.conf, so the mount cannot shadow what the package ships.
-#
-# kubectl renders the init container's per-node config: go-template-file for
-# the templating, a field selector for excluding the node itself, in-cluster
-# config for the auth. From the distro, so there is no version literal to drift
-# and no download to trust. It is only ever used to read core/v1 Nodes.
-RUN apk add --no-cache bird2 kubectl
-
-# Fails the build rather than the first pod if a binary or its path is wrong.
-RUN /usr/sbin/bird --version \
- && kubectl version --client > /dev/null
-
-ENTRYPOINT ["/usr/sbin/bird", "-f", "-c", "/etc/bird/bird.conf"]
@@ -13,9 +13,7 @@ RUN apk add --no-cache \
      git \
      jq \
      openssh-client \
-      openssl \
-      python3 \
-      py3-yaml
+      openssl

 # Install Claude Code, then make the resulting layer byte-stable so that a
 # rebuild of the SAME version DEDUPS in the Gitea registry instead of orphaning
@@ -1,9 +1,9 @@
 FROM alpine:3.21@sha256:48b0309ca019d89d40f670aa1bc06e426dc0931948452e8491e3d65087abc07d

-ARG TALOS_VERSION=v1.13.9
+ARG TALOS_VERSION=v1.12.6
 ARG VELERO_VERSION=v1.16.0
-ARG KUBECTL_VERSION=v1.36.3
-ARG FLUX_VERSION=2.9.5
+ARG KUBECTL_VERSION=v1.36.2
+ARG FLUX_VERSION=2.9.2

 RUN apk add --no-cache \
      aws-cli \
@@ -18,7 +18,7 @@ RUN apk add --no-cache \

 RUN curl -sfL -o /usr/local/bin/talosctl \
      "https://github.com/siderolabs/talos/releases/download/${TALOS_VERSION}/talosctl-linux-amd64" \
- && echo "7e1d4b7d5846964bdcf63a794e3c8161bb6ef2983d5ace58ea5322f3bf32a27e  /usr/local/bin/talosctl" | sha256sum -c - \
+ && echo "4c41a3b10b075292e64b182283d558e9d8e935f43239de1ed4e4b14359593efb  /usr/local/bin/talosctl" | sha256sum -c - \
 && chmod +x /usr/local/bin/talosctl

 RUN curl -sfL -o /usr/local/bin/kubectl \
@@ -31,7 +31,7 @@ RUN curl -sfL -o /usr/local/bin/kubectl \

 RUN curl -sfL -o /tmp/flux.tar.gz \
      "https://github.com/fluxcd/flux2/releases/download/v${FLUX_VERSION}/flux_${FLUX_VERSION}_linux_amd64.tar.gz" \
- && echo "b853df82adfd7736f580692f9f734473d571606307139f8fd20c2a80dd1ff473  /tmp/flux.tar.gz" | sha256sum -c - \
+ && echo "4092b367fd060097976fb7261601f79420ecf7266328417dfd8dfee27de0e6a3  /tmp/flux.tar.gz" | sha256sum -c - \
 && tar -xzf /tmp/flux.tar.gz -C /usr/local/bin flux \
 && chmod +x /usr/local/bin/flux \
 && rm -f /tmp/flux.tar.gz
@@ -1,12 +0,0 @@
-# netbird-service-sync: reconciles NetBird reverse-proxy services (public
-# domains -> TLS passthrough -> Traefik ClusterIP) from Ingresses carrying the
-# public label. Standard library only, so the image is the interpreter plus one
-# file; runs unprivileged as its own user.
-FROM python:3.13-slim
-
-RUN useradd --system --no-create-home --shell /usr/sbin/nologin controller
-COPY controller.py /opt/controller.py
-
-ENV PYTHONUNBUFFERED=1
-USER controller
-ENTRYPOINT ["python3", "/opt/controller.py"]
@@ -1,275 +0,0 @@
-#!/usr/bin/env python3
-"""netbird-service-sync: reconcile NetBird reverse-proxy services from Ingresses.
-
-Source of truth: every Ingress carrying the public label (dns.renner.uno/public).
-For each host on such an Ingress the NetBird management gets one reverse-proxy
-service in TLS-passthrough mode on :443, targeting Traefik's ClusterIP through a
-subnet resource that covers the cluster's service CIDR. SNI and Host reach
-Traefik untouched, the proxy terminates nothing, and no domain resource is
-involved -- the routing peers stay ordinary IP routers. The target sends a
-PROXY protocol v2 header so Traefik (and CrowdSec behind its access log) sees
-the WAN client address instead of the routing peer's pod IP.
-
-Ownership is derived from NetBird itself, not from local state: a service is
-managed iff its mode is "tls" and its target is this controller's subnet
-resource. Services that do not match (the hand-made HTTP/domain ones) are never
-touched; a desired host held by such a service is reported and skipped until
-that service is removed by hand.
-
-Credentials: the NetBird PAT is read from OpenBao on every pass through the
-Kubernetes auth role, exactly like the setup-key rotator; it never lands in a
-Kubernetes Secret or in a log line.
-"""
-
-import json
-import logging
-import os
-import sys
-import time
-import urllib.error
-import urllib.parse
-import urllib.request
-
-LOG = logging.getLogger("netbird-service-sync")
-
-NB = os.environ.get("NB_MANAGEMENT_URL", "https://netbird.renner.uno").rstrip("/")
-BAO_ADDR = os.environ.get("BAO_ADDR", "http://openbao.openbao.svc.cluster.local:8200").rstrip("/")
-BAO_ROLE = os.environ.get("BAO_ROLE", "netbird-service-sync")
-BAO_PAT_PATH = os.environ.get("BAO_PAT_PATH", "homelab/data/infrastructure/secret-rotators-bootstrap/netbird")
-BAO_PAT_KEY = os.environ.get("BAO_PAT_KEY", "pat")
-SERVICE_CIDR = os.environ.get("SERVICE_CIDR", "10.96.0.0/12")
-NETWORK_NAME = os.environ.get("NETWORK_NAME", "k8s public ingress")
-ROUTER_GROUP = os.environ.get("ROUTER_GROUP_NAME", "k8s-ingress-router")
-SOURCE_GROUP = os.environ.get("SOURCE_GROUP_NAME", "All")
-TRAEFIK_NS, TRAEFIK_SVC = os.environ.get("TRAEFIK_SERVICE", "ingress/traefik").split("/", 1)
-PUBLIC_LABEL = os.environ.get("PUBLIC_LABEL", "dns.renner.uno/public")
-LISTEN_PORT = int(os.environ.get("LISTEN_PORT", "443"))
-INTERVAL = int(os.environ.get("INTERVAL_SECONDS", "60"))
-HTTP_TIMEOUT = 20
-
-K8S_API = "https://kubernetes.default.svc"
-K8S_TOKEN_FILE = "/var/run/secrets/kubernetes.io/serviceaccount/token"
-K8S_CA_FILE = "/var/run/secrets/kubernetes.io/serviceaccount/ca.crt"
-
-
-class ApiError(Exception):
-    pass
-
-
-def http(method, url, body=None, headers=None, cafile=None):
-    data = None if body is None else json.dumps(body).encode()
-    req = urllib.request.Request(url, data=data, method=method)
-    req.add_header("Accept", "application/json")
-    if data is not None:
-        req.add_header("Content-Type", "application/json")
-    for k, v in (headers or {}).items():
-        req.add_header(k, v)
-    ctx = None
-    if cafile:
-        import ssl
-        ctx = ssl.create_default_context(cafile=cafile)
-    try:
-        with urllib.request.urlopen(req, timeout=HTTP_TIMEOUT, context=ctx) as resp:
-            raw = resp.read()
-            return json.loads(raw) if raw else None
-    except urllib.error.HTTPError as e:
-        detail = e.read().decode(errors="replace")[:300]
-        raise ApiError(f"{method} {url} -> {e.code}: {detail}") from None
-
-
-# --- Kubernetes -------------------------------------------------------------
-
-def k8s(path):
-    with open(K8S_TOKEN_FILE) as f:
-        token = f.read().strip()
-    return http("GET", K8S_API + path, headers={"Authorization": f"Bearer {token}"}, cafile=K8S_CA_FILE)
-
-
-def desired_hosts():
-    sel = urllib.parse.quote(f"{PUBLIC_LABEL}=true")
-    ingresses = k8s(f"/apis/networking.k8s.io/v1/ingresses?labelSelector={sel}")
-    hosts = {}
-    for ing in ingresses.get("items", []):
-        ref = f'{ing["metadata"]["namespace"]}/{ing["metadata"]["name"]}'
-        for rule in ing.get("spec", {}).get("rules", []):
-            host = rule.get("host")
-            if not host or host.startswith("*"):
-                continue
-            hosts.setdefault(host, ref)
-    return hosts
-
-
-def traefik_cluster_ip():
-    svc = k8s(f"/api/v1/namespaces/{TRAEFIK_NS}/services/{TRAEFIK_SVC}")
-    for ip in svc["spec"].get("clusterIPs", []):
-        if ":" not in ip:
-            return ip
-    raise ApiError(f"{TRAEFIK_NS}/{TRAEFIK_SVC} has no IPv4 ClusterIP")
-
-
-# --- OpenBao ----------------------------------------------------------------
-
-def netbird_pat():
-    with open(K8S_TOKEN_FILE) as f:
-        jwt = f.read().strip()
-    login = http("POST", f"{BAO_ADDR}/v1/auth/kubernetes/login", {"role": BAO_ROLE, "jwt": jwt})
-    bao_token = login["auth"]["client_token"]
-    kv = http("GET", f"{BAO_ADDR}/v1/{BAO_PAT_PATH}", headers={"X-Vault-Token": bao_token})
-    pat = kv["data"]["data"].get(BAO_PAT_KEY)
-    if not pat:
-        raise ApiError(f"OpenBao {BAO_PAT_PATH} has no key {BAO_PAT_KEY}")
-    return pat
-
-
-# --- NetBird management -----------------------------------------------------
-
-class NetBird:
-    def __init__(self, pat):
-        self.h = {"Authorization": f"Token {pat}"}
-
-    def get(self, path):
-        return http("GET", f"{NB}/api/{path}", headers=self.h)
-
-    def list(self, path):
-        # An empty collection comes back as an empty body / null, not [].
-        return self.get(path) or []
-
-    def post(self, path, body):
-        return http("POST", f"{NB}/api/{path}", body, headers=self.h)
-
-    def put(self, path, body):
-        return http("PUT", f"{NB}/api/{path}", body, headers=self.h)
-
-    def delete(self, path):
-        return http("DELETE", f"{NB}/api/{path}", headers=self.h)
-
-
-def group_id(nb, name):
-    for g in nb.list("groups"):
-        if g["name"] == name:
-            return g["id"]
-    raise ApiError(f"NetBird group {name!r} not found")
-
-
-def ensure_network(nb):
-    for n in nb.list("networks"):
-        if n["name"] == NETWORK_NAME:
-            return n["id"]
-    n = nb.post("networks", {"name": NETWORK_NAME,
-                             "description": "managed by netbird-service-sync; public ingress via TLS passthrough"})
-    LOG.info("created network %s (%s)", NETWORK_NAME, n["id"])
-    return n["id"]
-
-
-def ensure_resource(nb, net):
-    for r in nb.list(f"networks/{net}/resources"):
-        if r.get("address") == SERVICE_CIDR:
-            return r["id"]
-    r = nb.post(f"networks/{net}/resources", {"name": "cluster service CIDR", "address": SERVICE_CIDR,
-                                              "description": "managed by netbird-service-sync",
-                                              "enabled": True, "groups": []})
-    LOG.info("created subnet resource %s (%s)", SERVICE_CIDR, r["id"])
-    return r["id"]
-
-
-def ensure_router(nb, net, router_group):
-    for r in nb.list(f"networks/{net}/routers"):
-        if router_group in (r.get("peer_groups") or []):
-            return r["id"]
-    r = nb.post(f"networks/{net}/routers", {"peer_groups": [router_group], "metric": 9999,
-                                            "masquerade": True, "enabled": True})
-    LOG.info("created router on group %s (%s)", ROUTER_GROUP, r["id"])
-    return r["id"]
-
-
-def ensure_policy(nb, resource, source_group):
-    name = f"{NETWORK_NAME} access"
-    for p in nb.list("policies"):
-        if p["name"] == name:
-            return p["id"]
-    p = nb.post("policies", {"name": name, "enabled": True, "rules": [{
-        "name": name, "enabled": True, "action": "accept", "protocol": "tcp",
-        "ports": [str(LISTEN_PORT)], "bidirectional": False, "sources": [source_group],
-        "destinationResource": {"id": resource, "type": "subnet"}}]})
-    LOG.info("created policy %s (%s)", name, p["id"])
-    return p["id"]
-
-
-def service_body(host, resource, target_ip):
-    # proxy_protocol: PROXY v2 header carries the WAN client address to
-    # Traefik (proxyProtocol.trustedIPs on websecure); TCP/TLS modes only.
-    return {"name": host, "domain": host, "mode": "tls", "listen_port": LISTEN_PORT, "enabled": True,
-            "targets": [{"target_type": "subnet", "target_id": resource, "protocol": "tcp",
-                         "host": target_ip, "port": 443, "enabled": True,
-                         "options": {"proxy_protocol": True}}]}
-
-
-def is_managed(svc, resource):
-    return svc.get("mode") == "tls" and any(t.get("target_id") == resource for t in svc.get("targets") or [])
-
-
-def target_matches(svc, target_ip):
-    if svc.get("listen_port") != LISTEN_PORT or not svc.get("enabled"):
-        return False
-    ts = svc.get("targets") or []
-    return len(ts) == 1 and ts[0].get("host") == target_ip and ts[0].get("port") == 443 \
-        and ts[0].get("protocol") == "tcp" and ts[0].get("enabled") \
-        and (ts[0].get("options") or {}).get("proxy_protocol") is True
-
-
-def reconcile():
-    hosts = desired_hosts()
-    target_ip = traefik_cluster_ip()
-    nb = NetBird(netbird_pat())
-
-    router_group = group_id(nb, ROUTER_GROUP)
-    source_group = group_id(nb, SOURCE_GROUP)
-    net = ensure_network(nb)
-    resource = ensure_resource(nb, net)
-    ensure_router(nb, net, router_group)
-    ensure_policy(nb, resource, source_group)
-
-    by_domain = {s["domain"]: s for s in nb.list("reverse-proxies/services")}
-    created = updated = deleted = held = 0
-
-    for host, ref in sorted(hosts.items()):
-        svc = by_domain.get(host)
-        if svc is None:
-            nb.post("reverse-proxies/services", service_body(host, resource, target_ip))
-            LOG.info("created %s (from %s) -> %s:443", host, ref, target_ip)
-            created += 1
-        elif not is_managed(svc, resource):
-            LOG.warning("%s is held by unmanaged service %s (mode %s); remove it to migrate",
-                        host, svc["id"], svc.get("mode"))
-            held += 1
-        elif not target_matches(svc, target_ip):
-            nb.put(f"reverse-proxies/services/{svc['id']}", service_body(host, resource, target_ip))
-            LOG.info("updated %s -> %s:443", host, target_ip)
-            updated += 1
-
-    for domain, svc in by_domain.items():
-        if is_managed(svc, resource) and domain not in hosts:
-            nb.delete(f"reverse-proxies/services/{svc['id']}")
-            LOG.info("deleted %s (no public Ingress carries it any more)", domain)
-            deleted += 1
-
-    LOG.info("reconciled: %d hosts desired, %d created, %d updated, %d deleted, %d held by unmanaged services",
-             len(hosts), created, updated, deleted, held)
-
-
-def main():
-    logging.basicConfig(level=os.environ.get("LOG_LEVEL", "INFO"), stream=sys.stdout,
-                        format="%(asctime)s %(levelname)s %(message)s")
-    if os.environ.get("ONCE") == "1":
-        reconcile()
-        return
-    while True:
-        try:
-            reconcile()
-        except Exception as e:  # keep running; the next pass retries
-            LOG.error("reconcile failed: %s", e)
-        time.sleep(INTERVAL)
-
-
-if __name__ == "__main__":
-    main()
@@ -1,84 +0,0 @@
-FROM alpine:3.21@sha256:48b0309ca019d89d40f670aa1bc06e426dc0931948452e8491e3d65087abc07d
-
-# Everything `bootstrap.sh vmtest` needs, so the rebuild test can run as a Job in
-# the cluster instead of on a workstation. The workstation has 31G and the test
-# wants ~14.5G for four VMs — a single run left under 1G headroom, and two
-# overlapping runs OOM-killed the session. The nodes have ~94G with 70G free.
-#
-# Separate from ci-k8s rather than built on it: that image pins talosctl v1.12.6,
-# and this test creates a cluster at the version talos/patches/cluster.yaml
-# installs. A talosctl older than the Talos it provisions is exactly the kind of
-# skew the test exists to catch, so it must not be baked in here.
-#
-# KEEP TALOS_VERSION IN STEP with the installer image tag in
-# kubernetes/talos/patches/cluster.yaml. The phase reads the version from that
-# file at run time and passes it to the provisioner; this pin only decides which
-# client talks to it.
-ARG TALOS_VERSION=v1.13.9
-ARG KUBECTL_VERSION=v1.36.2
-ARG FLUX_VERSION=2.9.2
-ARG KOPIA_VERSION=0.23.1
-
-# qemu-system-x86_64 and qemu-img are the provisioner's actual backend, and ovmf
-# supplies the UEFI firmware those VMs boot from — without it the provisioner
-# stops with "the required flash image was not found in any of the expected
-# paths", having already downloaded the ISO and generated the PKI. Note the
-# firmware comes from ovmf specifically: qemu-system-x86_64 ships an edk2 CODE
-# image but no VARS, which is the half the provisioner needs.
-#
-# iptables is shelled out to by the CNI plugins that build the VM network; the
-# provisioner fails with "error accessing iptables" without it. The rest is
-# what the phase shells out to: helm for the Cilium install, yq to read the
-# HelmRelease and the installer image, jq for OpenBao's seal status.
-#
-# Versions come from the digest-pinned base rather than being pinned one by one,
-# the same way ci-ansible does it.
-RUN apk add --no-cache \
-      bash \
-      ca-certificates \
-      curl \
-      git \
-      helm \
-      iptables \
-      jq \
-      openssl \
-      ovmf \
-      qemu-img \
-      qemu-system-x86_64 \
-      yq
-
-RUN curl -sfL -o /usr/local/bin/talosctl \
-      "https://github.com/siderolabs/talos/releases/download/${TALOS_VERSION}/talosctl-linux-amd64" \
- && echo "7e1d4b7d5846964bdcf63a794e3c8161bb6ef2983d5ace58ea5322f3bf32a27e  /usr/local/bin/talosctl" | sha256sum -c - \
- && chmod +x /usr/local/bin/talosctl
-
-RUN curl -sfL -o /usr/local/bin/kubectl \
-      "https://dl.k8s.io/release/${KUBECTL_VERSION}/bin/linux/amd64/kubectl" \
- && curl -sfL -o /tmp/kubectl.sha256 \
-      "https://dl.k8s.io/release/${KUBECTL_VERSION}/bin/linux/amd64/kubectl.sha256" \
- && echo "$(cat /tmp/kubectl.sha256)  /usr/local/bin/kubectl" | sha256sum -c - \
- && rm -f /tmp/kubectl.sha256 \
- && chmod +x /usr/local/bin/kubectl
-
-RUN curl -sfL -o /tmp/flux.tar.gz \
-      "https://github.com/fluxcd/flux2/releases/download/v${FLUX_VERSION}/flux_${FLUX_VERSION}_linux_amd64.tar.gz" \
- && echo "4092b367fd060097976fb7261601f79420ecf7266328417dfd8dfee27de0e6a3  /tmp/flux.tar.gz" | sha256sum -c - \
- && tar -xzf /tmp/flux.tar.gz -C /usr/local/bin flux \
- && chmod +x /usr/local/bin/flux \
- && rm -f /tmp/flux.tar.gz
-
-# kopia reads the Velero backup repository directly, which is what the OpenBao
-# restore does when there is no Velero yet to do it: the credentials Velero
-# needs live in OpenBao, so OpenBao cannot be restored by Velero. Its absence
-# was found by a rebuild rehearsal reaching the restore for the first time and
-# stopping at "kopia not found".
-#
-# Same checksum-verified download as the tools above; the tarball unpacks into
-# a versioned directory, so the binary is pulled out by name.
-RUN curl -sfL -o /tmp/kopia.tar.gz \
-      "https://github.com/kopia/kopia/releases/download/v${KOPIA_VERSION}/kopia-${KOPIA_VERSION}-linux-x64.tar.gz" \
- && echo "416d0f84a3dbb321a8b2d8f0997b1a0a6e915babe79ee76fa6e4d2bd1e1c5178  /tmp/kopia.tar.gz" | sha256sum -c - \
- && tar -xzf /tmp/kopia.tar.gz -C /tmp \
- && mv "/tmp/kopia-${KOPIA_VERSION}-linux-x64/kopia" /usr/local/bin/kopia \
- && chmod +x /usr/local/bin/kopia \
- && rm -rf /tmp/kopia.tar.gz "/tmp/kopia-${KOPIA_VERSION}-linux-x64"
@@ -1,10 +0,0 @@
-# wiki-index: embedding index over the Notes repo's wiki/, fed from Gitea,
-# queried by ~/Notes/bin/wiki_rank.py. Standard library only; runs unprivileged.
-FROM python:3.13-slim
-
-RUN useradd --system --no-create-home --shell /usr/sbin/nologin wikiindex
-COPY wiki_index.py /opt/wiki_index.py
-
-ENV PYTHONUNBUFFERED=1
-USER wikiindex
-ENTRYPOINT ["python3", "/opt/wiki_index.py"]
@@ -1,178 +0,0 @@
-#!/usr/bin/env python3
-"""Unit tests for wiki_index. Run: python3 -m unittest test_wiki_index"""
-
-import hashlib
-import hmac
-import json
-import tempfile
-import unittest
-from pathlib import Path
-
-import wiki_index as wi
-
-NOTE = """---
-title: 'UDM intercepts DNS'
-type: wiki
-tags: [dns, unifi]
-aliases: [udm dns interception, dig 1.1.1.1 wrong]
---
-
-# UDM intercepts DNS
-
-The UDM answers every UDP/53 query itself.
-
-## Details
-
-More.
-"""
-
-
-class ParseTests(unittest.TestCase):
-    def test_note_text(self):
-        title, text = wi.note_text("udm-dns", NOTE)
-        self.assertEqual(title, "UDM intercepts DNS")
-        self.assertIn("udm dns UDM intercepts DNS udm dns interception", text)
-        self.assertIn("dns unifi", text)
-        self.assertTrue(text.endswith("The UDM answers every UDP/53 query itself."))
-        self.assertLessEqual(len(text), wi.EMBED_CHARS)
-
-    def test_credentials_are_stripped(self):
-        original = wi.http
-        wi.http = lambda method, url, body=None, headers=None, timeout=60.0: (
-            {"auth": {"client_token": "t"}} if url.endswith("/login")
-            else {"data": {"data": {"gitea_token": "abc\n", "webhook_secret": " s3cret\n"}}})
-        original_sa = wi.SA_TOKEN
-        try:
-            with tempfile.TemporaryDirectory() as d:
-                wi.SA_TOKEN = Path(d) / "token"
-                wi.SA_TOKEN.write_text("jwt\n")
-                self.assertEqual(wi.Credentials().fetch(), {"gitea_token": "abc", "webhook_secret": "s3cret"})
-        finally:
-            wi.http, wi.SA_TOKEN = original, original_sa
-
-    def test_tree_paging_stops_on_short_last_page(self):
-        # Gitea: truncated=true on every page including the last, "tree": null past it.
-        pages = {
-            1: {"tree": [{"path": f"wiki/n{i}.md", "type": "blob", "sha": f"s{i}"} for i in range(1000)], "truncated": True, "total_count": 1192},
-            2: {"tree": [{"path": f"wiki/n{i}.md", "type": "blob", "sha": f"s{i}"} for i in range(1000, 1192)] + [{"path": "raw/x.md", "type": "blob", "sha": "r"}, {"path": "wiki/sub/y.md", "type": "blob", "sha": "y"}], "truncated": True, "total_count": 1192},
-            3: {"tree": None, "truncated": False, "total_count": 1192},
-        }
-        calls = []
-        original = wi.http
-
-        def fake_http(method, url, body=None, headers=None, timeout=60.0):
-            page = int(url.rsplit("page=", 1)[1])
-            calls.append(page)
-            return pages[page]
-
-        wi.http = fake_http
-        try:
-            tree = wi.Gitea("t").tree("abc")
-        finally:
-            wi.http = original
-        self.assertEqual(calls, [1, 2])
-        self.assertEqual(len(tree), 1192)
-        self.assertNotIn("raw/x.md", tree)
-        self.assertNotIn("wiki/sub/y.md", tree)
-        self.assertEqual(tree["wiki/n1191.md"], "s1191")
-
-    def test_signature(self):
-        body = b'{"ref":"refs/heads/master"}'
-        sig = hmac.new(b"s3cret", body, hashlib.sha256).hexdigest()
-        self.assertTrue(wi.verify_signature("s3cret", body, sig))
-        self.assertFalse(wi.verify_signature("other", body, sig))
-        self.assertFalse(wi.verify_signature("s3cret", body, ""))
-
-
-class FakeGitea:
-    def __init__(self, head, tree, files):
-        self._head, self._tree, self.files = head, tree, files
-        self.raw_calls = []
-
-    def head(self):
-        return self._head
-
-    def tree(self, commit):
-        return self._tree
-
-    def raw(self, path, ref):
-        self.raw_calls.append(path)
-        return self.files[path]
-
-
-class IndexTests(unittest.TestCase):
-    def setUp(self):
-        self.tmp = tempfile.TemporaryDirectory()
-        self.path = Path(self.tmp.name) / "index.json"
-        self.original_embed = wi.embed
-        self.embed_calls = []
-
-        def fake_embed(texts, batch=2):
-            self.embed_calls.append(list(texts))
-            return [wi.unit([1.0, float(len(t) % 7)]) for t in texts]
-
-        wi.embed = fake_embed
-
-    def tearDown(self):
-        wi.embed = self.original_embed
-        self.tmp.cleanup()
-
-    def test_sync_is_incremental_and_persists(self):
-        files = {"wiki/udm-dns.md": NOTE, "wiki/ceph.md": "---\ntitle: Ceph\n---\n# Ceph\n\nOSD.\n", "wiki/_index.md": "---\ntitle: Wiki\n---\n"}
-        tree = {"wiki/udm-dns.md": "aaa", "wiki/ceph.md": "bbb", "wiki/_index.md": "ccc"}
-        g = FakeGitea("c1", tree, files)
-        idx = wi.Index(self.path)
-        s = idx.sync(g)
-        self.assertEqual((s["changed"], s["removed"], s["notes"]), (2, 0, 2))
-        self.assertEqual(set(idx.notes), {"udm-dns", "ceph"})
-        self.assertEqual(idx.notes["udm-dns"]["title"], "UDM intercepts DNS")
-        self.assertTrue(self.path.exists())
-
-        # head unchanged: nothing fetched
-        s = idx.sync(g)
-        self.assertEqual(s.get("skipped"), "head unchanged")
-        self.assertEqual(len(g.raw_calls), 2)
-
-        # one note changed, one removed, new head
-        g2 = FakeGitea("c2", {"wiki/udm-dns.md": "aaa2"}, {"wiki/udm-dns.md": NOTE.replace("itself", "itself!")})
-        s = idx.sync(g2)
-        self.assertEqual((s["changed"], s["removed"], s["notes"]), (1, 1, 1))
-        self.assertEqual(g2.raw_calls, ["wiki/udm-dns.md"])
-
-        # restart loads the persisted index
-        idx2 = wi.Index(self.path)
-        self.assertEqual(idx2.commit, "c2")
-        self.assertEqual(set(idx2.notes), {"udm-dns"})
-
-    def test_rank_orders_by_cosine(self):
-        idx = wi.Index(self.path)
-        idx.notes = {"a": {"sha": "1", "title": "A", "vector": wi.unit([1.0, 0.0])},
-                     "b": {"sha": "2", "title": "B", "vector": wi.unit([0.0, 1.0])}}
-        wi.embed = lambda texts, batch=2: [wi.unit([0.2, 1.0])]
-        rows = idx.rank("q", k=5)
-        self.assertEqual([r["slug"] for r in rows], ["b", "a"])
-        self.assertGreater(rows[0]["score"], rows[1]["score"])
-
-    def test_status_reports_age_and_errors(self):
-        idx = wi.Index(self.path)
-        self.assertFalse(idx.status()["ready"])
-        g = FakeGitea("c1", {"wiki/a.md": "x"}, {"wiki/a.md": "---\ntitle: A\n---\n# A\n\nt\n"})
-        idx.sync(g)
-        st = idx.status()
-        self.assertTrue(st["ready"])
-        self.assertEqual(st["notes"], 1)
-        self.assertEqual(st["commit"], "c1")
-
-        class Broken(FakeGitea):
-            def head(self):
-                raise wi.ApiError("gitea down")
-
-        with self.assertRaises(wi.ApiError):
-            idx.sync(Broken("c1", {}, {}))
-        self.assertIn("gitea down", idx.status()["last_error"])
-        self.assertEqual(idx.status()["notes"], 1)  # last good index kept
-        self.assertTrue(idx.status()["ready"])  # and still served
-
-
-if __name__ == "__main__":
-    unittest.main()
@@ -1,408 +0,0 @@
-#!/usr/bin/env python3
-"""wiki-index: embedding index over the Notes repo's wiki/, fed from Gitea.
-
-Source of truth is the notes repository on Gitea. The index holds, per wiki
-note, the git blob sha, title and a bge-m3 vector of slug/title/aliases/tags/
-first paragraph. A sync fetches the repo tree, embeds every note whose blob sha
-changed (via wiki-embed, in-cluster) and drops notes that left the tree; it
-runs at start, on every push webhook from Gitea, and every RESYNC_SECONDS.
-
-HTTP:
-  POST /rank     {"query": str, "k": int}   -> {"rows": [{"slug","title","score"}], "index": {...}}
-  GET  /health   -> 200 always (liveness) with {"ready", "notes", "commit", "synced_at", "age_s", "syncing", "last_error"}
-  GET  /ready    -> 200 when an index exists, else 503 (readiness)
-  POST /webhook  Gitea push event, HMAC-SHA256 in X-Gitea-Signature -> {"queued": true}
-
-Credentials (Gitea token, webhook secret) are read from OpenBao through the
-Kubernetes auth role on every use; they never land in a Secret or a log line.
-Standard library only.
-"""
-
-from __future__ import annotations
-
-import hashlib
-import hmac
-import json
-import logging
-import os
-import re
-import sys
-import threading
-import time
-import urllib.error
-import urllib.parse
-import urllib.request
-from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
-from pathlib import Path
-
-LOG = logging.getLogger("wiki-index")
-
-GITEA_URL = os.environ.get("GITEA_URL", "https://gitea.renner.uno").rstrip("/")
-NOTES_REPO = os.environ.get("NOTES_REPO", "k.renner/notes")
-NOTES_BRANCH = os.environ.get("NOTES_BRANCH", "master")
-WIKI_DIR = os.environ.get("WIKI_DIR", "wiki").strip("/")
-EMBED_URL = os.environ.get("EMBED_URL", "http://wiki-embed.ai.svc.cluster.local:8080").rstrip("/")
-EMBED_MODEL = os.environ.get("EMBED_MODEL", "bge-m3")
-EMBED_CHARS = int(os.environ.get("EMBED_CHARS", "1500"))
-INDEX_PATH = Path(os.environ.get("INDEX_PATH", "/data/index.json"))
-RESYNC_SECONDS = int(os.environ.get("RESYNC_SECONDS", "1800"))
-LISTEN_PORT = int(os.environ.get("LISTEN_PORT", "8080"))
-BAO_ADDR = os.environ.get("BAO_ADDR", "http://openbao.openbao.svc.cluster.local:8200").rstrip("/")
-BAO_ROLE = os.environ.get("BAO_ROLE", "wiki-index")
-BAO_SECRET_PATH = os.environ.get("BAO_SECRET_PATH", "homelab/data/apps/ai/wiki-index")
-SA_TOKEN = Path(os.environ.get("SA_TOKEN", "/var/run/secrets/kubernetes.io/serviceaccount/token"))
-
-
-class ApiError(Exception):
-    pass
-
-
-# ---------------------------------------------------------------- http helpers
-
-
-def http(method: str, url: str, body=None, headers=None, timeout: float = 60.0):
-    data = None
-    hdrs = dict(headers or {})
-    if body is not None:
-        data = json.dumps(body).encode("utf-8")
-        hdrs.setdefault("Content-Type", "application/json")
-    req = urllib.request.Request(url, data=data, method=method, headers=hdrs)
-    try:
-        with urllib.request.urlopen(req, timeout=timeout) as resp:
-            raw = resp.read()
-            ctype = resp.headers.get("Content-Type", "")
-    except urllib.error.HTTPError as e:
-        raise ApiError(f"{method} {url}: HTTP {e.code}: {e.read().decode('utf-8', 'replace')[:300]}") from e
-    except urllib.error.URLError as e:
-        raise ApiError(f"{method} {url}: {e.reason}") from e
-    if "json" in ctype:
-        return json.loads(raw.decode("utf-8"))
-    return raw
-
-
-# ---------------------------------------------------------------- credentials
-
-
-class Credentials:
-    """Gitea token and webhook secret from OpenBao, fetched per use."""
-
-    def __init__(self, static: dict | None = None):
-        self.static = static  # tests / local runs
-
-    def fetch(self) -> dict:
-        if self.static is not None:
-            return self.static
-        jwt = SA_TOKEN.read_text(encoding="utf-8").strip()
-        login = http("POST", f"{BAO_ADDR}/v1/auth/kubernetes/login", {"role": BAO_ROLE, "jwt": jwt})
-        token = login["auth"]["client_token"]
-        kv = http("GET", f"{BAO_ADDR}/v1/{BAO_SECRET_PATH}", headers={"X-Vault-Token": token})
-        data = {k: str(v).strip() for k, v in kv["data"]["data"].items()}  # `bao kv put key=@file` keeps the file's newline
-        for key in ("gitea_token", "webhook_secret"):
-            if not data.get(key):
-                raise ApiError(f"OpenBao {BAO_SECRET_PATH} has no key {key}")
-        return data
-
-
-# ---------------------------------------------------------------- gitea
-
-
-class Gitea:
-    def __init__(self, token: str, base: str = GITEA_URL, repo: str = NOTES_REPO, branch: str = NOTES_BRANCH):
-        self.base, self.repo, self.branch = base, repo, branch
-        self.headers = {"Authorization": f"token {token}"}
-
-    def api(self, path: str, **params):
-        q = ("?" + urllib.parse.urlencode(params)) if params else ""
-        return http("GET", f"{self.base}/api/v1/repos/{self.repo}{path}{q}", headers=self.headers)
-
-    def head(self) -> str:
-        return self.api(f"/branches/{urllib.parse.quote(self.branch, safe='')}")["commit"]["id"]
-
-    def tree(self, commit: str) -> dict[str, str]:
-        """path -> blob sha for every wiki note at that commit."""
-        out: dict[str, str] = {}
-        page, per_page, seen = 1, 1000, 0
-        while True:
-            t = self.api(f"/git/trees/{commit}", recursive="true", per_page=per_page, page=page)
-            entries = t.get("tree") or []  # Gitea answers "tree": null past the last page
-            for e in entries:
-                p = e.get("path", "")
-                if e.get("type") == "blob" and p.startswith(WIKI_DIR + "/") and p.endswith(".md") and "/" not in p[len(WIKI_DIR) + 1:]:
-                    out[p] = e["sha"]
-            seen += len(entries)
-            total = int(t.get("total_count") or 0)
-            if not entries or len(entries) < per_page or (total and seen >= total):
-                break
-            page += 1
-            if page > 50:
-                raise ApiError("tree paging runaway")
-        return out
-
-    def raw(self, path: str, ref: str) -> str:
-        data = http("GET", f"{self.base}/api/v1/repos/{self.repo}/raw/{urllib.parse.quote(path)}?ref={urllib.parse.quote(ref, safe='')}",
-                    headers=self.headers)
-        return data.decode("utf-8") if isinstance(data, bytes) else json.dumps(data)
-
-
-# ---------------------------------------------------------------- notes
-
-
-def parse_frontmatter(text: str) -> tuple[dict, str]:
-    m = re.match(r"^---[ \t]*\n(.*?)\n---[ \t]*(?:\n|$)", text, re.DOTALL)
-    if not m:
-        return {}, text
-    fm: dict = {}
-    for line in m.group(1).splitlines():
-        mm = re.match(r"^([A-Za-z_][\w-]*):\s*(.*)$", line)
-        if mm:
-            fm[mm.group(1)] = mm.group(2).strip()
-    return fm, text[m.end():]
-
-
-def as_list(value: str) -> list[str]:
-    s = (value or "").strip()
-    if s.startswith("[") and s.endswith("]"):
-        s = s[1:-1]
-    return [p.strip().strip("'\"") for p in s.split(",") if p.strip()]
-
-
-def first_paragraph(body: str) -> str:
-    para: list[str] = []
-    seen_h1 = False
-    for line in body.splitlines():
-        if line.startswith("# "):
-            seen_h1 = True
-            continue
-        if not seen_h1:
-            continue
-        if line.strip() == "" or line.startswith("#"):
-            if para:
-                break
-            continue
-        para.append(line.strip())
-    return " ".join(para)
-
-
-def note_text(slug: str, text: str) -> tuple[str, str]:
-    """(title, embedding text) for one note file."""
-    fm, body = parse_frontmatter(text)
-    title = (fm.get("title") or slug).strip().strip("'\"")
-    parts = [slug.replace("-", " "), title, " ".join(as_list(fm.get("aliases", ""))),
-             " ".join(as_list(fm.get("tags", ""))), first_paragraph(body)]
-    return title, " ".join(parts)[:EMBED_CHARS]
-
-
-# ---------------------------------------------------------------- embeddings
-
-
-def embed(texts: list[str], batch: int = 2) -> list[list[float]]:
-    out: list[list[float]] = []
-    for i in range(0, len(texts), batch):
-        resp = http("POST", f"{EMBED_URL}/v1/embeddings", {"model": EMBED_MODEL, "input": texts[i:i + batch]}, timeout=120)
-        rows = sorted(resp["data"], key=lambda d: d["index"])
-        out.extend(unit(d["embedding"]) for d in rows)
-    return out
-
-
-def unit(v: list[float]) -> list[float]:
-    n = sum(x * x for x in v) ** 0.5 or 1.0
-    return [round(x / n, 5) for x in v]
-
-
-# ---------------------------------------------------------------- index
-
-
-class Index:
-    def __init__(self, path: Path):
-        self.path = path
-        self.lock = threading.Lock()
-        self.notes: dict[str, dict] = {}  # slug -> {sha, title, vector}
-        self.commit = ""
-        self.synced_at = 0.0
-        self.syncing = False
-        self.last_error = ""
-        if path.exists():
-            try:
-                d = json.loads(path.read_text(encoding="utf-8"))
-                self.notes, self.commit, self.synced_at = d.get("notes", {}), d.get("commit", ""), d.get("synced_at", 0.0)
-                LOG.info("loaded index: %d notes at %s", len(self.notes), self.commit[:8])
-            except (OSError, ValueError) as e:
-                LOG.warning("index unreadable (%s); starting empty", e)
-
-    def save(self) -> None:
-        self.path.parent.mkdir(parents=True, exist_ok=True)
-        tmp = self.path.with_suffix(".tmp")
-        tmp.write_text(json.dumps({"notes": self.notes, "commit": self.commit, "synced_at": self.synced_at}), encoding="utf-8")
-        tmp.replace(self.path)
-
-    def sync(self, gitea: Gitea) -> dict:
-        """Bring the index to the branch head; returns a summary."""
-        with self.lock:
-            self.syncing = True
-        try:
-            head = gitea.head()
-            if head == self.commit and self.notes:
-                summary = {"commit": head, "changed": 0, "removed": 0, "notes": len(self.notes), "skipped": "head unchanged"}
-                self.synced_at = time.time()
-                self.save()
-                return summary
-            tree = gitea.tree(head)
-            slugs = {p[len(WIKI_DIR) + 1:-3]: (p, sha) for p, sha in tree.items() if not p.endswith("/_index.md")}
-            todo = [s for s, (p, sha) in slugs.items() if self.notes.get(s, {}).get("sha") != sha]
-            removed = [s for s in list(self.notes) if s not in slugs]
-            LOG.info("sync %s: %d notes, %d to embed, %d removed", head[:8], len(slugs), len(todo), len(removed))
-            fresh: dict[str, dict] = {}
-            for i in range(0, len(todo), 20):
-                chunk = todo[i:i + 20]
-                texts, titles = [], {}
-                for s in chunk:
-                    title, text = note_text(s, gitea.raw(slugs[s][0], head))
-                    titles[s] = title
-                    texts.append(text)
-                for s, vec in zip(chunk, embed(texts)):
-                    fresh[s] = {"sha": slugs[s][1], "title": titles[s], "vector": vec}
-            with self.lock:
-                for s in removed:
-                    self.notes.pop(s, None)
-                self.notes.update(fresh)
-                self.commit = head
-                self.synced_at = time.time()
-                self.last_error = ""
-                self.save()
-            return {"commit": head, "changed": len(todo), "removed": len(removed), "notes": len(self.notes)}
-        except Exception as e:
-            with self.lock:
-                self.last_error = str(e)[:300]
-            raise
-        finally:
-            with self.lock:
-                self.syncing = False
-
-    def rank(self, query: str, k: int = 60) -> list[dict]:
-        q = embed([query])[0]
-        with self.lock:
-            rows = [(s, n["title"], sum(a * b for a, b in zip(q, n["vector"]))) for s, n in self.notes.items()]
-        rows.sort(key=lambda r: -r[2])
-        return [{"slug": s, "title": t, "score": round(sc, 4)} for s, t, sc in rows[:k]]
-
-    def status(self) -> dict:
-        """`ready` = an index exists and can answer /rank; a failed sync keeps the last good index."""
-        with self.lock:
-            return {"ready": bool(self.notes), "notes": len(self.notes), "commit": self.commit,
-                    "synced_at": self.synced_at, "age_s": round(time.time() - self.synced_at) if self.synced_at else None,
-                    "syncing": self.syncing, "last_error": self.last_error or None}
-
-
-# ---------------------------------------------------------------- syncer
-
-
-class Syncer(threading.Thread):
-    """One worker: syncs on demand (webhook) and every RESYNC_SECONDS."""
-
-    def __init__(self, index: Index, creds: Credentials, interval: int):
-        super().__init__(daemon=True, name="syncer")
-        self.index, self.creds, self.interval = index, creds, interval
-        self.wake = threading.Event()
-
-    def trigger(self) -> None:
-        self.wake.set()
-
-    RETRY_SECONDS = 60
-
-    def run(self) -> None:
-        while True:
-            try:
-                data = self.creds.fetch()
-                summary = self.index.sync(Gitea(data["gitea_token"]))
-                LOG.info("sync done: %s", summary)
-                wait = self.interval
-            except Exception as e:  # keep serving the last good index; retry soon, not next interval
-                LOG.error("sync failed: %s", e)
-                wait = self.RETRY_SECONDS
-            self.wake.wait(wait)
-            self.wake.clear()
-
-
-def verify_signature(secret: str, body: bytes, signature: str) -> bool:
-    digest = hmac.new(secret.encode("utf-8"), body, hashlib.sha256).hexdigest()
-    return hmac.compare_digest(digest, (signature or "").strip())
-
-
-# ---------------------------------------------------------------- server
-
-
-def make_handler(index: Index, syncer: Syncer, creds: Credentials):
-    class Handler(BaseHTTPRequestHandler):
-        def log_message(self, fmt, *args):
-            LOG.info("%s %s", self.address_string(), fmt % args)
-
-        def send_json(self, code: int, obj) -> None:
-            data = json.dumps(obj).encode("utf-8")
-            self.send_response(code)
-            self.send_header("Content-Type", "application/json")
-            self.send_header("Content-Length", str(len(data)))
-            self.end_headers()
-            self.wfile.write(data)
-
-        def body(self) -> bytes:
-            n = int(self.headers.get("Content-Length") or 0)
-            return self.rfile.read(n) if n else b""
-
-        def do_GET(self):
-            if self.path == "/health":  # liveness: the process serves
-                return self.send_json(200, index.status())
-            if self.path == "/ready":  # readiness: an index exists
-                st = index.status()
-                return self.send_json(200 if st["ready"] else 503, st)
-            self.send_json(404, {"error": "not found"})
-
-        def do_POST(self):
-            if self.path == "/rank":
-                try:
-                    req = json.loads(self.body() or b"{}")
-                    query = str(req.get("query", "")).strip()
-                    k = max(1, min(int(req.get("k", 60)), 500))
-                    if not query:
-                        return self.send_json(400, {"error": "query required"})
-                    rows = index.rank(query, k)
-                    return self.send_json(200, {"rows": rows, "index": index.status()})
-                except ApiError as e:
-                    return self.send_json(502, {"error": str(e)})
-                except (ValueError, TypeError) as e:
-                    return self.send_json(400, {"error": str(e)})
-            if self.path == "/webhook":
-                raw = self.body()
-                try:
-                    secret = creds.fetch()["webhook_secret"]
-                except ApiError as e:
-                    return self.send_json(503, {"error": str(e)})
-                if not verify_signature(secret, raw, self.headers.get("X-Gitea-Signature", "")):
-                    return self.send_json(403, {"error": "bad signature"})
-                try:
-                    event = json.loads(raw or b"{}")
-                except ValueError:
-                    return self.send_json(400, {"error": "bad json"})
-                ref = event.get("ref", "")
-                if ref and ref != f"refs/heads/{NOTES_BRANCH}":
-                    return self.send_json(200, {"queued": False, "ref": ref})
-                syncer.trigger()
-                return self.send_json(200, {"queued": True})
-            self.send_json(404, {"error": "not found"})
-
-    return Handler
-
-
-def main() -> int:
-    logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s", stream=sys.stdout)
-    index = Index(INDEX_PATH)
-    creds = Credentials()
-    syncer = Syncer(index, creds, RESYNC_SECONDS)
-    syncer.start()
-    server = ThreadingHTTPServer(("", LISTEN_PORT), make_handler(index, syncer, creds))
-    LOG.info("listening on :%d, repo %s@%s, embed %s", LISTEN_PORT, NOTES_REPO, NOTES_BRANCH, EMBED_URL)
-    server.serve_forever()
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())
@@ -50,18 +50,15 @@ pass insert homelab/openbao/root-token
 kubectl -n openbao exec -it openbao-0 -- bao operator unseal   # paste key
 ```

-**Unseal is automatic since 2026-09-08** (static seal, PR #825, issue #805):
-the seal key lives in the `openbao-seal-key` Secret (created by `bootstrap.sh`
-from `pass show homelab/openbao/seal-key`) and every restarted replica unseals
-itself. The shamir key above became the **recovery key** in the migration; it
-is kept in `pass` under its old name, `homelab/openbao/unseal-key`. The server
-runs three raft peers (see `infrastructure/openbao/helmrelease.yaml`); a sealed
-one is neither a voter nor a standby, so a replica that stays sealed after a
-restart — wrong or missing seal-key Secret — costs redundancy, two cost
-quorum. The trade-off taken with the static seal: the key that unlocks the
-store sits in the same etcd as the Secrets ESO already syncs there in
-plaintext. Symptom of sealed: ESO stores go NotReady, synced Secrets keep
-their last value (they are real k8s Secrets — pods keep running).
+**Manual unseal is required after every pod restart** (node drain, upgrade,
+crash), **per replica** — the server runs three raft peers (see
+`infrastructure/openbao/helmrelease.yaml`), and a sealed one is neither a
+voter nor a standby, so it stays out of the cluster until unsealed:
+`kubectl -n openbao exec -it openbao-<N> -- bao operator unseal`, same key for
+all three. Three peers mean one sealed replica is survivable; two are not.
+Accepted for now; auto-unseal needs a second trust root (transit/KMS) and is
+explicitly out of scope. Symptom of sealed: ESO stores go NotReady, synced
+Secrets keep their last value (they are real k8s Secrets — pods keep running).

 ## Phase 2 — configure + ClusterSecretStore (follow-up PR)

@@ -237,19 +234,16 @@ one full reconcile + one OpenBao pod restart/unseal cycle:
 - **Backups:** ✅ nightly raft-snapshot CronJob (03:00, keeps 7 on a
  dedicated PVC; see infrastructure/openbao/snapshot-cronjob.yaml) + velero
  `openbao-daily` Schedule (06:15) ships that PVC offsite, 30 d retention.
-  A raft snapshot restore needs the matching seal key — which lives in
+  A raft snapshot restore needs the matching unseal key — which lives in
  `pass`, outside the cluster (GPG key backed up externally 2026-07-14).
  A failed snapshot Job is the sealed-after-restart alarm. Still owed:
  one tested restore before phase 4.
- **Cluster rebuild order:** seal-key Secret from `pass` → Flux brings up
-  openbao (empty) → init → restore raft snapshot → replicas unseal themselves
-  → ClusterSecretStore Ready → ESO materializes Secrets → apps start
-  (`bootstrap.sh flux` does all of it; RUNBOOK-cold-rebuild.md Step 4 by
-  hand). Until then, secret-consuming apps simply stay Pending on missing
-  Secrets — same as any missing dependency.
- **Break-glass:** `pass` holds seal key, recovery key + root token (GPG,
-  offline-capable). With those, everything is recoverable from a raft
-  snapshot alone.
+- **Cluster rebuild order:** Flux brings up openbao (sealed, empty) → restore
+  raft snapshot → unseal (key from `pass`) → ClusterSecretStore Ready → ESO
+  materializes Secrets → apps start. Until unseal, secret-consuming apps
+  simply stay Pending on missing Secrets — same as any missing dependency.
+- **Break-glass:** `pass` holds unseal key + root token (GPG, offline-capable).
+  With those two, everything is recoverable from a raft snapshot alone.
 - **Ansible Vault password:** `ansible/vault-password.sh` reads
  `ANSIBLE_VAULT_PASSWORD` from the environment with no offline backup as of
  2026-07-14. It gates decryption of several Ansible-Vault files (PBS
@@ -1,99 +0,0 @@
-# Traffic classes on the k8s nodes
-
-Issue #576. Five classes, each on its own VLAN.
-
-## Where each class runs
-
-| class | link | mechanism |
-|---|---|---|
-| Ceph replication | `ceph-san`, VLAN 49 | the whole link is handed to the OSD pod (Multus `host-device`) |
-| pod↔pod | `pod0`, VLAN 48 | pod-sourced traffic is routed from table 47; bird puts the peers' pod CIDRs there via `pod0` |
-| world↔pod | `ingress0`, VLAN 47 | BGP session sourced there (next hop of every LoadBalancer VIP); pod egress takes table 47's default |
-| node↔node | `node0`, VLAN 46 | the node InternalIP and etcd live there; so do apiserver↔kubelet, cilium-health and host→remote-pod traffic |
-| world↔node | `mgmt0`, VLAN 40 | API VIP for kubectl, talosctl from outside, node egress (DNS, NTP, image pulls) |
-
-Hard constraint, set by the owner: inter-node and pod traffic never traverses
-the UDM. Everything but world↔node stays on the 10G switch. VLAN 46 and 48 are
-statically addressed, without a gateway; VLAN 46 is isolated in UniFi.
-
-## Pod traffic: one table
-
-Two rules, one per family, send every packet with a pod source to table 47
-(`talos/patches/site-homelab.yaml`, priorities 1000/1001, below main). The
-table decides by longest prefix; no rule carves out exceptions.
-
-bird (`kubernetes/infrastructure/bird/`) owns table 47 and fills it with:
-
- the node's attached networks — `mgmt0`, `ingress0`, `pod0`, `node0` —
-  taken from the interfaces;
- the peers' pod CIDRs, learned over an iBGP mesh on `pod0`, next hop the
-  peer's `pod0` address;
- the node's own pod CIDR via `cilium_host`, originated rather than read back
-  from the kernel (reading it back made BIRD depend on the shape of Cilium's
-  route, and KRT rejects the IPv4 one);
- the egress default via the UDM on `ingress0`, from the node annotations
-  `net.renner.uno/egress-gw-v4/v6`.
-
-`node0` has to be in the table: a pod reaching a node address — the
-`kubernetes` ClusterIP, which socket LB rewrites to the apiserver's advertise
-address, or a hostNetwork pod — would otherwise take the default to the UDM.
-
-The routing decision runs before Cilium's masquerade hook, so the rule sees the
-pod address and the masquerade then rewrites it to the egress link's.
-
-Node-originated traffic does not match the rules and uses main, where Cilium
-routes each peer's pod CIDR via the peer's InternalIP — on `node0`.
-
-No address is written into this repo twice. Each node publishes its `pod0`
-addresses as `nodeAnnotations` beside the `VLANConfig` that assigns them; the
-pod CIDRs come from the Node objects. bird's init container renders both from
-the API and ends with `bird -p`, so BIRD's own parser gates startup.
-
-## Node↔node
-
-`kubelet.nodeIP.validSubnets` and `cluster.etcd.advertisedSubnets` point at
-VLAN 46. Talos picks one InternalIP per family, IPv4 first — the service CIDR
-is IPv4, and the apiserver's advertise address must match it.
-
-The API VIP stays on `mgmt0` for kubectl. No in-cluster client uses it:
-kubelet, scheduler, controller-manager and Cilium go through KubePrism
-(`localhost:7445`), which balances over every address of every control-plane
-member; pods use the ClusterIP.
-
-Talos never updates an existing etcd member's peer URLs
-(siderolabs/talos#12720). Changing `advertisedSubnets` means, per member:
-stage the config, `talosctl etcd forfeit-leadership`, `talosctl etcd leave`,
-reboot. `leave` removes only `/var/lib/etcd`; the node rejoins as a learner
-and is promoted. EPHEMERAL does not need a wipe.
-
-## Moving node IPs: the mixed state
-
-While some nodes have their InternalIP on the new network and some on the old,
-host→remote-pod traffic leaves with a node address that is not an InternalIP:
-the kernel picks the source from the route to the peer's InternalIP. Cilium
-classifies that as `world`, and every ingress policy that admits only
-`host`/`remote-node` (rook-ceph, monitoring, …) drops it. Kernel Ceph clients
-lose the OSDs on the other side; RBD mounts hang.
-
-Bridge it for the duration with a temporary `CiliumClusterwideNetworkPolicy`
-admitting the node subnets of both networks, both families, with
-`enableDefaultDeny: false` so it restricts nothing else, and delete it once
-every node has moved. Keep all OSD nodes schedulable while one is drained:
-draining two takes Ceph below its data availability.
-
-## Failure behaviour
-
-If bird stops, table 47 empties, the rules find nothing and fall through to
-main: pod traffic returns to the node networks, unseparated rather than
-misrouted. The same holds during a cold rebuild until Gitea serves bird's
-image. The default route lives in table 47, not in the Talos config, so a
-default cannot outlive the specific routes and send pod traffic to the UDM.
-
-## Sources
-
-Cilium v1.20 `pkg/datapath/linux/node.go`; BIRD 2.17 user manual (kernel
-protocol, `strict bind`, `direct`); Talos v1.13 `RoutingRuleConfig`,
-`machine.nodeAnnotations`, configuration patching (lists are appended,
-`$patch: delete`), etcd `LeaveCluster`; KubePrism docs;
-siderolabs/talos#12720. PRs #831, #833, #835, #836, #837, #842, #852, #854,
-#855, #857, #858, #918, #919, #922; closed unmerged: #830, #838, #839.
@@ -1,111 +0,0 @@
-# Cilium: one owner
-
-## The rule
-
-Cilium is owned by **Flux**, through `infrastructure/cilium/helmrelease.yaml`.
-Talos provides the conditions for a CNI and nothing else. Never both.
-
-Talos-only would also be a valid answer — it is the simpler one, and it keeps a
-cold rebuild self-forming. It is rejected here only because it costs Flux's
-reconciliation, image automation and value ergonomics for the one component
-most likely to need a careful, reviewed change.
-
-## Where we are
-
-Both own it, which is the state this document exists to end.
-
- 22 Cilium objects are listed in the `talos-bootstrap-manifests-inventory`
-  ConfigMap: both DaemonSets, the operator Deployment, both ConfigMaps, the
-  ServiceAccounts, the ClusterRoles/Bindings and the `cilium-secrets`
-  namespace. That is the whole installation, not a fragment.
- The same objects carry `meta.helm.sh/release-name: cilium`.
- `cilium-config` has three field managers: `helm-controller`, `talos` and
-  `kubectl-patch`.
-
-The consequences are not theoretical. The seed sat at Cilium 1.19.2 for twelve
-days while the chart was on 1.20.1, and `upgrade-k8s --dry-run` shows that a
-Kubernetes upgrade in that state downgrades the CNI and switches off socket
-load balancing. Separately, `enable-bgp-control-plane` and the two
-native-routing CIDRs exist in no file at all — applied by hand, so a cold
-rebuild would have come up with BGP off while the peering CRDs in git made it
-look configured.
-
-Nothing fails when these drift. That is the whole problem.
-
-## Target state
-
-**Talos** keeps exactly this, in `talos/patches/cluster.yaml`, and gains nothing
-else:
-
-```yaml
-cluster:
-  network:
-    cni:
-      name: none
-  proxy:
-    disabled: true
-```
-
-No `inlineManifests` entry for cilium. `talos/patches/cilium-cni.yaml` is
-deleted.
-
-**Flux** owns everything else. `helmrelease.yaml` is the single source for
-every Cilium setting, including the three that were hand-patched.
-
-**A cold rebuild** installs Cilium once, by hand, between `talosctl bootstrap`
-and the Flux phase, from the same HelmRelease values. This is the cost of the
-decision and it is deliberate: the cluster no longer forms itself from the
-machine config alone. Given `bootstrap.sh talos` is already dead and Step 2 of
-RUNBOOK-cold-rebuild.md is already a manual procedure, the marginal cost is one
-documented command.
-
-## Transition
-
-The order matters, because Talos prunes what its inventory used to list and no
-longer does — removing the manifest naively deletes the CNI.
-
-1. **Track the untracked settings first.** `bgpControlPlane.enabled`,
-   `ipv4NativeRoutingCIDR`, `ipv6NativeRoutingCIDR` into the HelmRelease. Note
-   this is not a pure change of ownership: enabling bgpControlPlane through the
-   chart also emits five companion keys the hand-patch never set, so Cilium has
-   been running on its own defaults for router-id allocation. Verify the BGP
-   sessions after Flux applies it.
-
-2. **Remove cilium from `cluster.inlineManifests`.** This has no immediate
-   effect. Evidence: Talos was upgraded to 1.13.9 four days ago and Cilium
-   stayed at 1.20.1 — an OS upgrade does not reconcile bootstrap manifests.
-   Only `upgrade-k8s` does.
-
-3. **Prove the prune before running it.** `upgrade-k8s --dry-run
-   --manifests-no-prune` and confirm the 22 objects are not listed for
-   deletion. `NoPrune` is honoured by the dry run as well as the apply
-   (`pkg/cluster/kubernetes/talos_managed.go`), so this is a real test and not
-   a reading of the flag description.
-
-4. **Run `upgrade-k8s --manifests-no-prune`.** The inventory is rewritten
-   without Cilium and the objects survive. Helm is then sole owner. This is the
-   same run that takes Kubernetes 1.35.2 → 1.36.3.
-
-5. **Verify** the inventory lists no Cilium, the agents did not restart, and
-   the BGP sessions are still established.
-
-6. **Delete `talos/patches/cilium-cni.yaml`** and add the install step to
-   RUNBOOK-cold-rebuild.md.
-
-## Not part of this, and not a defect either
-
-The cluster runs `routingMode: tunnel` (the chart default, set nowhere) while
-also advertising pod CIDRs over BGP. That is not one layer too many — the two
-carry different directions:
-
- **VXLAN** carries pod-to-pod between nodes, directly, node to node.
- **BGP** gives the UDM routes into the pod CIDRs so traffic from the LAN can
-  reach pods. That path goes through the router by definition.
-
-Dropping the encapsulation in favour of native routing would not simplify
-anything; it would push inter-node pod traffic onto the underlay path and
-through the UDM, replacing a direct node-to-node hop with a router hop.
-
-`routingMode` being unset is still worth knowing — the current behaviour is a
-default nobody chose rather than a decision anyone recorded — but the default
-is the right one here, and this document is not the place to revisit it.
@@ -0,0 +1,194 @@
+# Proposal — separate the four traffic classes onto their own VLANs
+
+Status: draft. The question this started with is **answered** — from the Cilium
+source and flag reference, not from a test — and the answer changes the shape
+of the proposal rather than confirming it.
+
+Supersedes the framing in issue #576, which described this as "give node
+management its own NIC, and Ceph public its own VLAN". That was two of four
+classes and one of them turned out already solved.
+
+## The four classes
+
+| class | what it is | where it goes today |
+|---|---|---|
+| **Ceph replication** | OSD-to-OSD heartbeat, replication, recovery | VLAN 49, its own X710 port — **separated** |
+| **cluster-internal** | pod-to-pod east-west, including Ceph client I/O | pod network, VXLAN over `mgmt0` |
+| **cluster-external** | ingress to LoadBalancer VIPs, egress to LAN and internet | `mgmt0` |
+| **management** | Talos API, etcd, kube-apiserver, kubelet | `mgmt0` |
+
+Three of four share one interface. That is not a design decision — until the
+bare-metal conversion there was one NIC to work with.
+
+Ceph client I/O living on the pod network is correct rather than a leftover:
+that traffic *is* cluster-internal. Ceph is done.
+
+## Principle
+
+**Each class gets its own VLAN. Which physical interface a VLAN lands on is a
+separate, changeable decision.**
+
+Defining classes by VLAN means the separation survives recabling, port failures
+and capacity changes, and it does not require one port per class. Defining them
+by interface would freeze a capacity decision into the architecture.
+
+## The finding that shapes everything else
+
+The original open question was whether `nodePort.directRoutingDevice` moves the
+next-hop of Cilium's direct routes, or only selects an interface. It is
+answerable from the source, and the answer is: **only the interface.**
+
+`installDirectRoute` takes the next-hop as a parameter:
+
+```go
+func installDirectRoute(log *slog.Logger, prefix netip.Prefix, nodeIP net.IP,
+    skipUnreachable bool) (routeSpec *netlink.Route, err error)
+```
+
+and `nodeUpdate` supplies it as `newNode.GetNodeIP(false)`. `GetNodeIP` returns,
+in priority order, `NodeInternalIP` → `NodeExternalIP` → anything else. The
+same `newIP4` is what tunnel mode uses as the VXLAN endpoint.
+
+`NodeInternalIP` comes from the Kubernetes Node object. `--ipv4-node` looks like
+an override but is not one: `initFromConfig()` calls `SetNodeInternalIP` and
+`initFromK8s()` runs **after** it and overwrites the value. In a Kubernetes
+cluster there is no path by which Cilium's node IP differs from the kubelet's
+`InternalIP`.
+
+`--direct-routing-device` is documented as "Device name used to connect nodes in
+direct routing mode" — a device, not an address.
+
+**So cluster-internal traffic is welded to the node IP, and the node IP is the
+kubelet InternalIP.** Two consequences:
+
+- The class cannot be moved off whatever VLAN the node IP lives on.
+- **Routing mode is irrelevant to this problem.** Tunnel mode sources the VXLAN
+  from the node IP; native mode uses it as the direct-route next-hop. Native
+  routing buys nothing here, so the disruptive, non-rolling step this proposal
+  previously contained is simply gone.
+
+## Consequence: draw the line the other way
+
+If cluster-internal cannot leave the node IP, then separation has to come from
+moving *management services* off it — and each one has to be checked
+individually, because they do not share a mechanism.
+
+| management service | can it leave the node IP? | lever |
+|---|---|---|
+| etcd | **yes** | `cluster.etcd.advertisedSubnets` (+ `listenSubnets`, which defaults to it) |
+| kube-apiserver endpoint | **yes** | already a VIP — `Layer2VIPConfig` with a `link:` field |
+| Talos API | **n/a** | `apid` answers on every node address (measured); a client and firewall choice, not a bind setting |
+| kubelet | **no** | it *is* the node IP, by definition |
+
+So four VLANs are reachable, but the boundary does not fall where the class
+names suggest: **kubelet stays with cluster-internal.** That is the honest
+result, and it is worth stating plainly rather than filing kubelet under
+management and hoping.
+
+The remaining classes keep the levers established earlier:
+
+- **cluster-external ingress** — `CiliumBGPNodeConfigOverride.spec.bgpInstances[].peers[].localAddress`.
+  For eBGP the session source is the next-hop, so pinning the session pins
+  where return traffic arrives. The session to the UDM has been running for
+  months.
+- **cluster-external egress** — eBPF masquerading follows the output device, so
+  this is a default-route decision plus `enable-masquerade-to-route-source`
+  (today `false`).
+- **Ceph replication** — Multus macvlan on VLAN 49, done.
+
+## The general escape hatch
+
+Ceph is separated because its OSDs got a second interface and stopped using the
+pod network for replication. That is the *only* mechanism that fully detaches a
+workload from the node IP, and it generalises: anything that must not ride the
+node IP gets its own `NetworkAttachmentDefinition`.
+
+It is also expensive per workload — an attachment, an IPAM pool, a pod spec
+change. Worth it for Ceph replication. Not worth it for east-west traffic in
+general.
+
+## Recommended mapping
+
+Two ways to arrange this, and they differ only in which VLAN gets relabelled:
+
+**A — move the node IP to a new cluster VLAN.** VLAN 40 keeps etcd, the API VIP
+and Talos API. Cleanest match to the class names, but it changes every node's
+identity, which is the one address the whole cluster is administered through.
+
+**B (recommended) — leave the node IP on VLAN 40 and move management off it.**
+VLAN 40 becomes the cluster VLAN; a new VLAN carries etcd and the API VIP.
+Identical end state, and no node ever changes its InternalIP.
+
+Under B:
+
+| VLAN | carries |
+|---|---|
+| 49 | Ceph replication |
+| 40 (relabelled *cluster*) | pod east-west, kubelet |
+| new *management* | etcd, kube-apiserver VIP, Talos API by convention |
+| new *external* | LoadBalancer ingress, egress default route |
+
+The property the user asked for — management carries only management traffic —
+holds under B. The label moves; the property is what matters.
+
+## Migration shape
+
+Every step is rolling and reversible. The routing-mode change is gone.
+
+1. **New VLANs** on the switch, trunked to the X710. Nothing uses them.
+2. **Addresses** on the new VLANs via Talos, one node at a time, `--mode=try`.
+   Still unused; this only proves the L2 works.
+3. **etcd** to the management VLAN via `advertisedSubnets`. One node at a time,
+   waiting for a healthy quorum between each.
+4. **API VIP** to the management VLAN via `Layer2VIPConfig.link`. DNS for
+   `k8s.renner.uno` follows.
+5. **cluster-external**: BGP `localAddress`, default route, masquerade flag.
+   Reversible by reverting the override; failure is visible immediately in
+   `cilium-dbg shell -- bgp/peers`.
+6. Verify VLAN 40 by what is *absent* from it, not by what still works.
+
+Step 3 is the one that deserves care — etcd is the only step where a mistake
+costs quorum rather than connectivity.
+
+## What this does not buy
+
+Management currently shares a 10 Gb link and is not contended. Nothing observed
+today is slow because of this. The case for the split is that traffic classes
+with different failure modes and security postures should not be
+indistinguishable — not that something is broken.
+
+## Sources and measurements
+
+Source, Cilium v1.20.1 (the running version):
+
+- `pkg/datapath/linux/node.go` — `installDirectRoute(…, nodeIP net.IP, …)`,
+  fed from `newIP4 = newNode.GetNodeIP(false)`; `createDirectRouteSpec` rejects
+  a next-hop that is not directly reachable.
+- `pkg/node/types/node.go` — `GetNodeIP` prefers `NodeInternalIP`.
+- `pkg/node/sync/local_node_sync.go` — `initFromConfig()` applies
+  `--ipv4-node`, `initFromK8s()` runs afterwards and overwrites it from the
+  Kubernetes Node.
+- `cilium-agent` flag reference — `--direct-routing-device`: "Device name used
+  to connect nodes in direct routing mode".
+
+Talos:
+
+- Multihoming guide — `cluster.etcd.advertisedSubnets`; `listenSubnets`
+  defaults to it. kube-apiserver and Talos API listen addresses are not
+  covered there.
+- `kubernetes/talos/patches/k8s-{1,2,3}.yaml` — `Layer2VIPConfig` for
+  `10.2.40.60` with `link: mgmt0`.
+
+Measured on the cluster:
+
+- `apid` answered on a node address that is not the InternalIP, so the Talos
+  API is not bound to one address.
+- k8s-1 currently holds one routable v4 address plus the VIP on `mgmt0`; its
+  InternalIP had changed since the last session, which is why nothing here
+  names an address as fixed.
+- Cilium runs `routing-mode: tunnel` with `enable-masquerade-to-route-source`
+  unset and no direct-routing device configured.
+
+Not verified: whether the kube-apiserver's `--advertise-address` follows the
+node IP independently of the VIP. It does not affect the recommendation, since
+clients reach the API through the VIP either way.
@@ -2,12 +2,7 @@

 Converts one MS-01 from "Proxmox host running a Talos VM" to "Talos on bare
 metal", and swaps its Ceph OSD onto a Samsung PM983 at the same time. Written
-after doing jupiter on 2026-08-25.
-
-All three nodes are now on bare metal — `talosctl get systeminformation`
-reports Minisforum MS-01 hardware with distinct chassis serials for k8s-1,
-k8s-2 and k8s-3, with no hypervisor in between. Kept as the procedure for a
-rebuild, not as outstanding work.
+after doing jupiter on 2026-08-25; saturn and neptune remain.

 Everything here that reads like an over-specific warning is something that
 actually happened. The conversion itself is straightforward — the failures were
@@ -203,7 +198,8 @@ talosctl gen secrets --from-controlplane-config cp.yaml -o secrets.yaml
 talosctl gen config homelab https://k8s.renner.uno:6443 \
  --with-secrets secrets.yaml --output-types controlplane \
  --config-patch @talos/patches/cluster.yaml \
-  --config-patch @talos/patches/containerd-layer-retention.yaml \
+  --config-patch @<cilium additive half> \
+  --config-patch @talos/patches/registry-mirror.yaml \
  --config-patch @talos/patches/k8s-N.yaml -o install.yaml
 ```

@@ -212,11 +208,9 @@ Confirm `cluster.id` matches the running cluster before applying.
 Strip the generated `HostnameConfig` document — it collides with
 `machine.network.hostname` from the per-node patch. `bootstrap.sh` does the same.

-There is no CNI patch to pass any more. Talos supplies only `cni: none` and
-`proxy: disabled`; Cilium is installed from its HelmRelease values, which is
-Step 2b of RUNBOOK-cold-rebuild.md. A node converted into an existing cluster
-gets its CNI from the Cilium DaemonSet already running there, so nothing extra
-is needed here.
+`cilium-cni.yaml` cannot be passed whole: its `$patch: delete` document fails
+against a base with no `inlineManifests` (issue #581). Use only the additive
+second document.

 Validate:

@@ -432,8 +426,8 @@ is why it belongs here.
  among its devices but not `ens19`, because `ens19` is deliberately
  address-less. Cilium therefore owns `mgmt0` and sees VLAN 40 frames already
  untagged by the 8021q layer, while VLAN 30 frames only ever meet the filter
-  on the shared parent `uplink`, still tagged. Any future address-less VLAN
-  carrying pod traffic will need the same treatment.
+  on the shared parent `enp2s0f0np0`, still tagged. Any future address-less
+  VLAN carrying pod traffic will need the same treatment.

  The symptom does not look like a VLAN problem. A tc-layer drop reaches an
  AF_PACKET sender as ENOBUFS, so the CNI dhcp plugin reports `no buffer space
@@ -67,12 +67,10 @@ These must exist outside the cluster or the rebuild cannot complete:
      `flux` phase creates the `sops-age` Secret, and any not-yet-migrated sops
      files decrypt with it. (Post-OpenBao-phase-4 this may be retired — see
      `MIGRATION-sops-openbao.md`.)
- [ ] **OpenBao seal key, recovery key + root token** — in the GPG `pass`
-      store (`homelab/openbao/seal-key`, `homelab/openbao/unseal-key` — the
-      former shamir key, now the recovery key — and `homelab/openbao/root-token`),
-      and the GPG private key backed up off-machine. The seal key is the one
-      the snapshots are encrypted under: without it, no OpenBao snapshot can be
-      restored and no secret-consuming app can start.
+- [ ] **OpenBao unseal key + root token** — in the GPG `pass` store
+      (`homelab/openbao/unseal-key`, `homelab/openbao/root-token`), and the GPG
+      private key backed up off-machine. Without the unseal key, no OpenBao
+      snapshot can be restored and no secret-consuming app can start.
 - [ ] **OpenBao raft snapshot** reachable — nightly PVC snapshots
      (`infrastructure/openbao/snapshot-cronjob.yaml`) plus the Velero
      `openbao-daily` offsite copy. In a total-loss rebuild the offsite Velero
@@ -121,11 +119,9 @@ against do not exist, and the node ends up with no address on any interface.
 Beyond that it carries:

 - `siderolabs/intel-ucode` — no hypervisor supplies microcode here
- `siderolabs/i915` — the Alder Lake-P Iris Xe. The Intel GPU device plugin
-  (`infrastructure/intel-gpu-plugin`) turns this into the schedulable resource
-  `gpu.intel.com/i915`, which `apps/llama-server` requests for LLM inference
-  and which any hardware-transcoding workload would use too. Without the
-  extension the plugin finds no `/dev/dri` and advertises nothing
+- `siderolabs/i915` — the Alder Lake-P Iris Xe. Nothing requests `/dev/dri`
+  today; present so wanting hardware transcoding later is a config change
+  rather than another rolling reinstall
 - `siderolabs/thunderbolt` — inert until `machine.kernel.modules` requests
  `thunderbolt`/`thunderbolt_net`, present for the same reason. Note its udev
  rule auto-authorises any Thunderbolt device attached once those modules load
@@ -140,18 +136,11 @@ in `talos/patches/k8s-N.yaml`.

 ## Step 2 — talos: form the cluster + get kubeconfig

-`kubernetes/bootstrap.sh talos` does this, including the CNI install that used
-to be a hand-typed step. It was unusable for months because it passed
-`cilium-cni.yaml` whole and the file's `$patch: delete` document failed against
-a fresh config (#581); that file no longer exists, so the failure is gone with
-it.
-
-Verified as far as it can be without wiping a cluster: `talosctl gen config`
-with exactly the patches the script passes produces a config carrying
-`cni: none` and `proxy: disabled` that passes `talosctl validate --mode metal`.
-The apply-and-bootstrap half has not been exercised since the rewrite. Read the
-manual procedure below before running the script, so you know what it is doing
-and can take over at any step if it stops.
+**Do not use `kubernetes/bootstrap.sh talos`.** That phase cannot generate a
+config: it passes `talos/patches/cilium-cni.yaml` whole, and that file's
+`$patch: delete` document fails against a base with no `inlineManifests`
+(#581). Its other phases — `flux`, `wait-apps` — are still used, in Steps 3, 5
+and 6; only config generation is broken.

 The procedure below is what actually works, and is the same one
 `RUNBOOK-baremetal-conversion.md` uses.
@@ -171,17 +160,17 @@ for N in 1 2 3; do
  talosctl gen config homelab https://k8s.renner.uno:6443 \
    --with-secrets secrets.yaml --output-types controlplane \
    --config-patch @talos/patches/cluster.yaml \
-    --config-patch @talos/patches/containerd-layer-retention.yaml \
+    --config-patch @<cilium additive half> \
+    --config-patch @talos/patches/registry-mirror.yaml \
    --config-patch @talos/patches/k8s-$N.yaml -o install-k8s-$N.yaml
 done
 ```

-There is no CNI patch here any more. Talos supplies `cni: none` and
-`proxy: disabled` from `cluster.yaml` and nothing else; Cilium is installed in
-Step 2b below. See PROPOSAL-cilium-single-owner.md.
-
-One thing the generator gets wrong for this repo, and it bites silently:
+Two things the generator gets wrong for this repo, both of which will bite
+silently:

+- **`cilium-cni.yaml` cannot be passed whole** — extract only its additive
+  second document. See issue #581.
 - **Strip the generated `HostnameConfig`** — it collides with
  `machine.network.hostname` from the per-node patch.

@@ -220,53 +209,8 @@ talosctl -n k8s-1.srv.renner.uno bootstrap
 talosctl -n k8s-1.srv.renner.uno kubeconfig .
 ```

-`scripts/import-cluster-access.sh` is the supported way to get the kubeconfig
-into place afterwards.
-
-The nodes will **not** reach `Ready` here. Talos is configured with `cni: none`,
-so there is no pod network until Step 2b — expect `NotReady` with
-`container runtime network not ready` and carry on.
-
-## Step 2b — cilium: install the CNI
-
-Nothing schedules without it, Flux included, so this comes before Step 3. Talos
-no longer carries a rendered copy of Cilium; `helmrelease.yaml` is the only
-place it is configured, and this installs from those same values so the cluster
-comes up on what git describes rather than on a second, drifting copy. See
-PROPOSAL-cilium-single-owner.md for why it works this way.
-
-`bootstrap.sh talos` already did this. What follows is the same thing by hand,
-for when the script stopped partway or you are not using it.
-
-Every input is read out of `helmrelease.yaml`. Nothing here is a version or a
-URL you have to keep in step with anything — copy the block as it stands:
-
-```sh
-HR=kubernetes/infrastructure/cilium/helmrelease.yaml
-
-helm repo add cilium "$(yq -r 'select(.kind == "HelmRepository") | .spec.url' "$HR")"
-helm repo update cilium
-
-yq 'select(.kind == "HelmRelease") | .spec.values' "$HR" > /tmp/cilium-values.yaml
-
-helm install cilium cilium/cilium \
-  --version "$(yq -r 'select(.kind == "HelmRelease") | .spec.chart.spec.version' "$HR")" \
-  --namespace kube-system \
-  -f /tmp/cilium-values.yaml \
-  --set prometheus.serviceMonitor.enabled=false
-```
-
-`--version` takes the HelmRelease's range verbatim; helm resolves it to the same
-release Flux would pick, so the two cannot diverge. That is the point of writing
-it this way — a pinned version in a runbook is a copy nobody maintains, and the
-next rebuild installs something the HelmRelease will immediately fight.
-
-The one literal is `serviceMonitor`, disabled for this install only: its CRD
-arrives with the monitoring stack much later and the object would fail to apply.
-Flux adds the real one once it owns the release. Nothing else is overridden,
-which is what lets helm-controller adopt this release rather than replace it.
-
-Ends when all three nodes are `Ready`.
+Ends when all three nodes are `Ready`. `scripts/import-cluster-access.sh` is the
+supported way to get the kubeconfig into place afterwards.

 ## Step 3 — flux: bootstrap GitOps **from the GitHub mirror** (break-glass)

@@ -296,65 +240,42 @@ output** — a green step over a still-forming Ceph is a known trap.
 > Steady-state (non-rebuild) bootstrap is just `kubernetes/bootstrap.sh flux`
 > with `GITEA_TOKEN` set; `FLUX_SOURCE` defaults to `gitea`.

-## Step 4 — openbao: restore the snapshot
+## Step 4 — openbao: restore the snapshot + unseal

-`bootstrap.sh flux` does this step itself (`restore_openbao`): it creates the
-`openbao-seal-key` Secret from `pass` before Flux brings OpenBao up, initialises
-the empty server, restores the newest raft snapshot straight out of the Velero
-kopia repository, and waits until every replica has unsealed itself from the
-static seal. What follows is the same procedure by hand, for when the script
-is not an option.
-
-OpenBao unseals itself from the static seal (`openbao-seal-key` Secret, key
-`key`, the 32-byte base64 key from `pass show homelab/openbao/seal-key`). The
-snapshots are encrypted under that key, so it must be the same key the backed
-up cluster used — a different one restores nothing. Until the snapshot is
-restored, the `ClusterSecretStore` stays NotReady, ESO cannot materialize
-Secrets, and every secret-consuming app stays Pending.
+After Step 3, OpenBao comes up **sealed and empty**. Until it is restored and
+unsealed, the `ClusterSecretStore` stays NotReady, ESO cannot materialize
+Secrets, and every secret-consuming app stays Pending. This step is **manual**
+(the unseal key lives in `pass`, off-cluster by design).

 ```sh
-# 1. The seal key, before the pods start (a pod without it never starts).
-kubectl create namespace openbao --dry-run=client -o yaml | kubectl apply -f -
-kubectl -n openbao create secret generic openbao-seal-key \
-  --from-literal=key="$(pass show homelab/openbao/seal-key)"
+# 1. Wait for the OpenBao pods to exist (all three sealed, 0/1 Ready is expected).
+kubectl -n openbao get pods

-# 2. Wait for openbao-0 (uninitialised: 0/1 Ready is expected), then
-#    initialise it. With an auto-seal, init hands out recovery keys and the
-#    server unseals itself. These keys are throwaway: the restore replaces them.
-kubectl -n openbao exec -it openbao-0 -- bao operator init \
-  -recovery-shares=1 -recovery-threshold=1
-
-# 3. Restore the most recent raft snapshot. Source it from the snapshot PVC
+# 2. Restore the most recent raft snapshot. Source it from the snapshot PVC
 #    (infrastructure/openbao/snapshot-cronjob.yaml) or, in a total-loss rebuild,
-#    from the Velero `openbao-daily` offsite copy. Root token from the init
-#    output. No -force: OpenBao checks the snapshot was written under this
-#    server's seal key and refuses otherwise ("different autoseal key") — that
-#    refusal is the signal the Secret is wrong. -force would skip the check and
-#    leave a server that can never unseal.
+#    from the Velero `openbao-daily` offsite copy. Copy it into the pod, then:
 kubectl -n openbao cp <snapshot>.snap openbao-0:/tmp/restore.snap
-kubectl -n openbao exec -it openbao-0 -- \
-  env BAO_TOKEN=<init root token> bao operator raft snapshot restore /tmp/restore.snap
+kubectl -n openbao exec -it openbao-0 -- bao operator raft snapshot restore /tmp/restore.snap

-# 4. The server seals against the snapshot's keyring and unseals itself from
-#    the static seal; openbao-1 and openbao-2 follow (OrderedReady). Nothing
-#    to type. Afterwards the tokens and recovery key from pass apply again.
-kubectl -n openbao get pods -w
+# 3. Unseal with the key from pass (threshold 1) — EVERY replica, same key.
+#    A sealed server is neither a raft voter nor a standby, so unsealing only
+#    openbao-0 leaves the three-peer cluster one node short of quorum.
+kubectl -n openbao exec -it openbao-0 -- bao operator unseal   # paste homelab/openbao/unseal-key
+kubectl -n openbao exec -it openbao-1 -- bao operator unseal   # same key
+kubectl -n openbao exec -it openbao-2 -- bao operator unseal   # same key
 ```

 Verify the store recovers before moving on:

 ```sh
-kubectl -n openbao exec openbao-0 -- bao status   # want: Seal Type static, Sealed false
-kubectl get clustersecretstore openbao            # want: Valid / Ready
-kubectl -n <ns> get externalsecret                # want: SecretSynced
+kubectl get clustersecretstore openbao        # want: Valid / Ready
+kubectl -n <ns> get externalsecret            # want: SecretSynced
 ```

-> A replica that stays **sealed** after a restart could not use the static
-> seal — the Secret is missing or does not match the key the data was
-> written under. Fix the Secret and restart the pod; `bao operator unseal`
-> with the recovery key (`pass show homelab/openbao/unseal-key`) does not
-> unseal an auto-sealed server and is only for recovery-mode operations.
-> Details + rationale: `MIGRATION-sops-openbao.md`.
+> **Manual unseal is required after every OpenBao pod restart**, not just
+> during rebuilds, and for *each* replica that restarts — a rolling node
+> drain seals all three in turn. Details + rationale:
+> `MIGRATION-sops-openbao.md`.

 ## Step 5 — apps: let the rest reconcile

@@ -418,15 +339,14 @@ it: repo → **Settings → Repository → Mirror Settings** in Gitea, or
 - **`bootstrap.sh talos` is dead** — it cannot generate a config (#581), and
  Step 2 no longer uses it. Its `flux` and `wait-apps` phases are still used in
  Steps 3, 5 and 6 and work; do not read this as the whole script being gone.
-  Its `flux` phase carries the OpenBao restore (Step 4); the seal key and the
-  other secrets are read from `pass` or streamed in at run time and never live
-  in CI.
- **OpenBao unseals itself, but only under the seal key the snapshot was
-  written with.** Three raft replicas mean the service survives losing one; a
-  sealed server is neither a voter nor a standby. A pod that stays sealed after
-  a restart has the wrong `openbao-seal-key` Secret — Step 4 covers this; it is
-  repeated here because it is the step most likely to be half-done under
-  pressure.
+  It has also never had an `openbao` phase — Step 4 is manual because the
+  unseal key must not live in CI; see issue #187 on whether to wire a
+  semi-automated OpenBao restore.
+- **OpenBao seals on every restart and each replica must be unsealed
+  individually.** Three raft replicas mean the service survives losing one, but
+  a sealed server is neither a voter nor a standby — unsealing only one leaves
+  the cluster short of quorum. Step 4 covers this; it is repeated here because
+  it is the step most likely to be half-done under pressure.
 - Ceph's cluster network is a Multus attachment on VLAN 49 with whereabouts
  IPAM, not host networking. Nothing in the rebuild needs special handling for
  it — the nodes hold no address on that segment — but a rebuilt cluster will
@@ -21,9 +21,6 @@ metadata:
  namespace: audiobookshelf
  labels:
    app.kubernetes.io/name: audiobookshelf
-  annotations:
-    # envFrom does not restart the pod when the ConfigMap changes; Reloader does.
-    configmap.reloader.stakater.com/reload: audiobookshelf-config
 spec:
  replicas: 1
  strategy:
@@ -70,7 +67,7 @@ spec:
              mountPath: /ca
      containers:
        - name: audiobookshelf
-          image: ghcr.io/advplyr/audiobookshelf:2.36.1 # {"$imagepolicy": "flux-system:audiobookshelf"}
+          image: ghcr.io/advplyr/audiobookshelf:2.36.0 # {"$imagepolicy": "flux-system:audiobookshelf"}
          ports:
            - name: http
              containerPort: 80
@@ -0,0 +1,18 @@
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: barman-cloud-creds
+  namespace: authentik
+  annotations:
+    # Prune-disabled — a standing guard kept from the seed->authentik-KS handoff (barman creds).
+    kustomize.toolkit.fluxcd.io/prune: disabled
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    kind: ClusterSecretStore
+    name: openbao
+  target:
+    name: barman-cloud-creds # keeps the old Secret's name — consumers unchanged
+  dataFrom:
+    - extract:
+        key: seed/authentik/barman-creds
@@ -25,13 +25,20 @@ data:
        attrs:
          local: true

-      # Retired OIDC layer. Access is gated by the paperless-gate
-      # ProxyProvider below, which forwards identity as X-authentik-* headers
-      # consumed via PAPERLESS_ENABLE_HTTP_REMOTE_USER.
+      # Retired OIDC layer. Paperless's URL-level access is gated by the
+      # paperless-gate ProxyProvider (below); user identity is forwarded
+      # from the gate to paperless via the X-authentik-* request headers
+      # and consumed by paperless via PAPERLESS_ENABLE_HTTP_REMOTE_USER
+      # (see kubernetes/apps/paperless/paperless.yaml). One Authentik
+      # Application, one Provider — the dual-OAuth2-flow setup with a
+      # separate paperless OIDC client + django-allauth callback was
+      # structurally fine but added a second consent screen on first
+      # login for no real defense-in-depth gain.
      #
-      # ORDER MATTERS: delete the Application BEFORE the OAuth2Provider.
-      # Application.provider is on_delete=PROTECT, so the provider cannot be
-      # removed while an Application still references it.
+      # Order matters: delete the Application BEFORE the OAuth2Provider
+      # because Application.provider is on_delete=PROTECT, so the
+      # OAuth2Provider can't be removed while the Application still
+      # references it.
      - model: authentik_core.application
        identifiers:
          slug: paperless
@@ -42,15 +49,22 @@ data:
          name: Paperless
        state: absent

-      # Orphan ProxyProvider, unbound — leftover DB state.
+      # Also clean up the very-early orphan `paperless` ProxyProvider
+      # left behind from this session's first attempts. It's not bound
+      # to anything any more, just leftover state in the DB.
      - model: authentik_providers_proxy.proxyprovider
        identifiers:
          name: paperless
        state: absent

-      # Dedicated forward-auth gate for paperless: its own outpost
-      # Deployment + Service, so every request is authenticated before it
-      # reaches paperless.
+      # Dedicated forward-auth gate for paperless. This is a SEPARATE
+      # outpost (its own Deployment + Service `ak-outpost-paperless-
+      # gate`) running in front of paperless so every request is
+      # authenticated and authorized by Authentik before it reaches
+      # paperless's own attack surface. The gate sits on top of, and
+      # separate from, the OIDC OAuth2Provider above (which is what
+      # paperless's django-allauth uses for SSO once a request makes
+      # it through the gate).
      - id: paperless-gate-provider
        model: authentik_providers_proxy.proxyprovider
        identifiers:
@@ -59,13 +73,16 @@ data:
        attrs:
          authorization_flow: !Find [authentik_flows.flow, [slug, default-provider-authorization-implicit-consent]]
          invalidation_flow: !Find [authentik_flows.flow, [slug, default-provider-invalidation-flow]]
-          # Proxy, NOT forward_domain: the outpost terminates the request
-          # itself, so the trust boundary sits here rather than at the ingress
-          # controller, which only routes to the outpost Service and never
-          # reaches paperless directly. The outpost populates
-          # X-Authentik-Username, and the paperless NetworkPolicy admits
-          # traffic only from this outpost — so nothing else in the cluster
-          # can bypass the gate and inject those headers.
+          # Proxy (not forward_domain) so the outpost itself terminates
+          # the request and forwards to paperless — moving the trust
+          # boundary off ingress-nginx and onto paperless-gate. ingress-
+          # nginx now only routes paperless.renner.uno to the outpost
+          # service; it never talks to paperless directly. The outpost
+          # is what populates X-Authentik-Username on the upstream
+          # request, and the NetworkPolicy in the paperless namespace
+          # only allows traffic to paperless from the gate outpost pod
+          # itself, so ingress-nginx (or any other in-cluster workload)
+          # cannot bypass the gate to inject headers.
          mode: proxy
          internal_host: http://paperless.paperless.svc.cluster.local
          internal_host_ssl_validation: false
@@ -74,12 +91,19 @@ data:
          access_token_validity: hours=24
          refresh_token_validity: days=30
          intercept_header_auth: true
-          # The static-asset tree passes anonymously, and must. A
-          # <link rel="manifest"> is fetched with `credentials: 'omit'` per
-          # the W3C spec, so the session cookie is never sent and every page
-          # load turns into a redirect loop through the login origin. Django's
-          # STATIC tree is public by design; MEDIA under /api/documents/*
-          # stays gated.
+          # Pass paperless's entire static-asset tree through anonymously.
+          # Two reasons:
+          # 1. <link rel="manifest"> is fetched with `credentials: 'omit'`
+          #    (W3C spec, no crossorigin attr) so the cookie is never sent
+          #    — every page load and every SPA navigation turned into a
+          #    302 → auth.renner.uno round-trip with an orphan session JWT.
+          #    Same root cause as the retired music-assistant-gate (see
+          #    comment further below); paperless can't retire the gate so
+          #    it carves out the offending paths instead.
+          # 2. Every CSS/JS/icon fetch otherwise validates the cookie at
+          #    the outpost — pure overhead on assets that carry no
+          #    authentication value. Django's STATIC tree is public by
+          #    design; MEDIA (under /api/documents/*) stays gated.
          skip_path_regex: ^/static/.*

      - model: authentik_core.application
@@ -106,14 +130,18 @@ data:
          negate: false
          failure_result: false

-      # Retired: the music-assistant gate. A forward-auth gate cannot work in
-      # front of a PWA — the manifest and service worker are fetched with
-      # `credentials: 'omit'`, and a cached service worker bypasses fresh
-      # navigations, so the session cookie never reaches the installed app.
-      # Do not reintroduce one there; MA delegates auth to Home Assistant.
-      #
-      # ORDER MATTERS: Application before Provider before Outpost, because
-      # Application.provider is on_delete=PROTECT.
+      # Retired: the music-assistant-gate ProxyProvider, Application,
+      # and dedicated Outpost. The gate fundamentally conflicted with
+      # MA's PWA model — Chrome fetches manifest.webmanifest / sw.js /
+      # icons with `credentials: 'omit'` (per W3C spec, no crossorigin
+      # attribute on MA's <link rel="manifest">), and the cached
+      # service worker bypasses fresh navigations on PWA cold-start so
+      # the Authentik cookie never lands in the WebAPK's cookie jar.
+      # MA has its own auth (delegated to Home Assistant); the gate's
+      # marginal value didn't justify the recurring breakage.
+      # Order matters: Application before Provider before Outpost.
+      # Application.provider is on_delete=PROTECT, so the Provider
+      # can't be removed while the Application still references it.
      - model: authentik_core.application
        identifiers:
          slug: music-assistant-gate
@@ -129,13 +157,18 @@ data:
          name: music-assistant-gate
        state: absent

-      # Dedicated outpost, serving the in-cluster auth endpoint only.
-      #
-      # The browser-facing legs of the OAuth flow must happen on
-      # auth.renner.uno, because that is the origin WebAuthn credentials are
-      # bound to. Hence the ProxyProvider is attached to BOTH this outpost and
-      # the embedded one, and authentik_host_browser points at auth.renner.uno
-      # here too — so any redirect this outpost emits names the right host.
+      # Dedicated outpost: its ONLY job is to serve the in-cluster
+      # /outpost.goauthentik.io/auth/nginx endpoint that nginx
+      # auth_request hits for every request to paperless. The
+      # browser-facing legs of the OAuth flow (/start, /callback, the
+      # `/if/...` login UI, /application/o/authorize, /api, etc.) all
+      # need to happen on auth.renner.uno because that's the origin
+      # WebAuthn/FIDO/TOTP credentials are bound to. So we attach the
+      # ProxyProvider to BOTH outposts (see embedded outpost below) and
+      # set authentik_host_browser to auth.renner.uno here too — the
+      # nginx auth_request happens server-to-server, but if the
+      # dedicated outpost ever does emit a redirect URL, it points at
+      # the right host.
      - model: authentik_outposts.outpost
        identifiers:
          name: paperless-gate
@@ -163,7 +196,12 @@ data:
            kubernetes_ingress_secret_name: "authentik-outpost-tls"
            kubernetes_json_patches: null

-      # Leftover Application from an earlier experiment.
+      # Tear down the leftover paperless-proxy Application from an
+      # earlier experiment. The orphan `paperless` ProxyProvider that
+      # used to back paperless.app is left in place — it's PROTECTed
+      # by Application.provider as long as anything references it, and
+      # leftover orphans don't break anything. Delete via the Authentik
+      # UI once everything's confirmed working.
      - model: authentik_policies.policybinding
        identifiers:
          target: !Find [authentik_core.application, [slug, paperless-proxy]]
@@ -179,11 +217,15 @@ data:
      # ------------------------------------------------------------------
      # vscode config-editor gate
      #
-      # code-server runs with --auth=none, as root, mounting the whole HA
-      # /config including plaintext secrets.yaml and .storage. This gate is
-      # the only thing in front of it: the outpost terminates the request and
-      # enforces a passkey step-up, Traefik routes only to the outpost, and
-      # the home-assistant CNP admits :8080 from the gate alone.
+      # code-server (the HA /config editor sidecar) runs with --auth=none,
+      # as root, mounting the whole HA /config incl. plaintext secrets.yaml
+      # and .storage. This gate moves it behind Authentik with a passkey
+      # step-up, mirroring the paperless-gate proxy-outpost pattern above:
+      # the dedicated ak-outpost-vscode-gate terminates the request,
+      # enforces the session, and forwards to the code-server Service.
+      # Traefik only ever routes vscode.home.renner.uno to the outpost; the
+      # home-assistant CNP is tightened so ONLY the gate outpost may reach
+      # :8080 (see home-assistant-ns.yaml + vscode-gate-egress.yaml).
      # ------------------------------------------------------------------
      - id: vscode-config-editors-group
        model: authentik_core.group
@@ -223,14 +265,17 @@ data:
          access_token_validity: hours=24
          refresh_token_validity: days=30
          intercept_header_auth: true
-          # code-server is a service-worker app, so its manifest and SW are
-          # fetched with credentials:'omit' and 302-loop unless carved out.
-          # The editor's actual content rides authenticated websocket/API
-          # paths and stays gated.
-          #
-          # This skip set is version-specific: re-check it after a
-          # code-server bump, because a renamed asset path reintroduces the
-          # loop silently.
+          # code-server is a service-worker app: <link rel="manifest"> and
+          # the service worker are fetched with credentials:'omit', which
+          # turned into a /authorize redirect loop and forced the RETIREMENT
+          # of the music-assistant gate (see comment above). Carve its
+          # static/manifest/SW tree out so those cookieless fetches pass
+          # through instead of 302-looping; the editor's actual content
+          # (the /config tree) is served over authenticated websocket/API
+          # paths, which stay gated.
+          # NOTE: the exact skip set is code-server-version-specific and
+          # MUST be confirmed post-deploy against the real redirect-loop
+          # behaviour (see the PR validation checklist).
          skip_path_regex: ^/(_static/|manifest\.json|.*\.webmanifest|.*serviceWorker\.js).*

      - model: authentik_core.application
@@ -286,11 +331,16 @@ data:
      # ------------------------------------------------------------------
      # shelly-manager gate
      #
-      # shelly-manager has no authentication of its own: anything that reaches
-      # :8080 can rewrite device config, push scripts and read the stored
-      # per-device AdminPassword values. Same shape as the vscode gate — the
-      # outpost is the only control, Traefik routes only to it, and the CNP
-      # admits :8080 from this outpost alone.
+      # shelly-manager has no authentication of its own: anything that can
+      # reach :8080 can rewrite Shelly device config, push scripts, and read
+      # the stored per-device AdminPassword values. Until now the only
+      # control was reachability of shelly-manager.home.renner.uno.
+      #
+      # Same shape as the vscode-gate above: a dedicated outpost terminates
+      # the request, enforces a passkey step-up, and forwards to the
+      # shelly-manager Service. Traefik only ever routes the hostname to the
+      # outpost; the home-assistant CNP allows ONLY this outpost to reach
+      # :8080 (see home-assistant-ns.yaml + shelly-manager-gate-egress.yaml).
      # ------------------------------------------------------------------
      - id: shelly-managers-group
        model: authentik_core.group
@@ -877,105 +927,6 @@ data:
            kubernetes_ingress_secret_name: "authentik-outpost-tls"
            kubernetes_json_patches: null

-      # llama-server WebUI gate
-      #
-      # llama-server has no authentication of its own — it serves its chat UI
-      # and a full OpenAI-compatible API to anyone who can reach the port. That
-      # is why it was LAN-only until now. This gate is what makes a public
-      # hostname defensible: the outpost terminates every request, enforces the
-      # session, and only then forwards to llama-server.
-      #
-      # Same reasoning as vscode-gate, and the same passkey step-up: what sits
-      # behind the gate is entirely unprotected, so the gate is the whole of the
-      # access control rather than a second factor on top of an app login.
-      #
-      # In-cluster consumers (Home Assistant, Paperless, CI) are unaffected:
-      # they address llama-server.ai.svc.cluster.local directly and never pass
-      # through Traefik or this outpost.
-      #
-      # No group and no policy binding: any user who can authenticate gets in,
-      # as with Immich, Audiobookshelf, Home Assistant and Music Assistant. The
-      # gates that pin membership to a named user in git — vscode, esphome,
-      # zigbee2mqtt, shelly-manager, prometheus — are admin interfaces, where
-      # the allowlist is the point. A chat UI is not one of those, and deciding
-      # its membership here would put an access-control choice in a manifest
-      # instead of leaving it where the user directory belongs.
-      # ------------------------------------------------------------------
-      - id: llama-gate-provider
-        model: authentik_providers_proxy.proxyprovider
-        identifiers:
-          name: llama-gate
-        state: present
-        attrs:
-          # Both flows, mirroring the Audiobookshelf provider. Setting only
-          # authorization_flow leaves authentication on Authentik's default
-          # flow, which is what made the first login clumsy — the step-up ran
-          # on top of a password prompt instead of replacing it. With the
-          # passwordless flow named explicitly, signing in is the passkey
-          # itself.
-          #
-          # Referenced by !Find rather than !KeyOf: both flows are defined in
-          # the passkey-stepup document of this ConfigMap, and !KeyOf only
-          # resolves within one document.
-          authentication_flow: !Find [authentik_flows.flow, [slug, passkey-passwordless-authentication]]
-          authorization_flow: !Find [authentik_flows.flow, [slug, passkey-stepup-authorization]]
-          invalidation_flow: !Find [authentik_flows.flow, [slug, default-provider-invalidation-flow]]
-          mode: proxy
-          internal_host: http://llama-server.ai.svc.cluster.local:8080
-          internal_host_ssl_validation: false
-          external_host: https://llm.renner.uno
-          cookie_domain: renner.uno
-          access_token_validity: hours=24
-          refresh_token_validity: days=30
-          intercept_header_auth: true
-          # The WebUI ships `<link rel="manifest">` and registers a service
-          # worker. Per the W3C spec a manifest is fetched with
-          # `credentials: 'omit'`, so it carries no session cookie and the gate
-          # answers it with a 302 to auth.renner.uno — which turns every page
-          # load into a redirect round-trip. This is the failure that forced
-          # paperless-gate's own carve-out and that retired music-assistant-gate
-          # outright. Both paths serve no authenticated content, so letting them
-          # through anonymously costs nothing.
-          skip_path_regex: ^/(manifest\.webmanifest|sw\.js)$
-
-      - model: authentik_core.application
-        identifiers:
-          slug: llama-gate
-        state: present
-        attrs:
-          name: Local LLM (Gate)
-          slug: llama-gate
-          provider: !KeyOf llama-gate-provider
-          meta_launch_url: https://llm.renner.uno
-          meta_description: "Forward-auth gate in front of the local llama-server WebUI"
-
-      - model: authentik_outposts.outpost
-        identifiers:
-          name: llama-gate
-        state: present
-        attrs:
-          type: proxy
-          service_connection: !KeyOf k8s-conn
-          providers:
-            - !KeyOf llama-gate-provider
-          config:
-            log_level: info
-            authentik_host: "http://authentik-server.authentik.svc.cluster.local"
-            authentik_host_insecure: false
-            authentik_host_browser: "https://auth.renner.uno/"
-            refresh_interval: "minutes=5"
-            container_image: null
-            object_naming_template: "ak-outpost-%(name)s"
-            kubernetes_namespace: authentik
-            kubernetes_replicas: 1
-            kubernetes_service_type: ClusterIP
-            kubernetes_disabled_components: ["ingress"]
-            kubernetes_image_pull_secrets: []
-            kubernetes_ingress_annotations: {}
-            kubernetes_ingress_class_name: null
-            kubernetes_ingress_secret_name: "authentik-outpost-tls"
-            kubernetes_json_patches: null
-
      - model: authentik_outposts.outpost
        identifiers:
          name: authentik Embedded Outpost
@@ -120,14 +120,7 @@ spec:
    server:
      resources:
        requests:
-          # 500m, not 200m: the HPA below targets 70% of *this* request, so at
-          # 200m the scale-up threshold sat at 140m — below the pod's own
-          # ordinary peak. Measured over 7d, a warm server pod p99s at ~108m
-          # and peaks at ~190m, and a freshly-started one burns ~300m booting
-          # Django. That made the HPA oscillate 2<->3<->4 all day and pin at
-          # maxReplicas (KubeHpaMaxedOut, issue #761). At 500m the threshold
-          # is 350m/pod, above the boot burst, so only real load scales out.
-          cpu: 500m
+          cpu: 200m
          memory: 1Gi
        limits:
          memory: 2Gi
@@ -161,11 +154,7 @@ spec:
    worker:
      resources:
        requests:
-          # Same reasoning as server above, and the worker is burstier still:
-          # over 7d its per-pod p99 reaches ~336m and peaks hit ~630m while
-          # running blueprint applies and scheduled tasks. 200m understated
-          # that badly enough that routine task batches read as saturation.
-          cpu: 500m
+          cpu: 200m
          memory: 1Gi
        limits:
          memory: 2Gi
@@ -15,4 +15,4 @@ spec:
    name: hetzner-s3-creds # keeps the old Secret's name — consumers unchanged
  dataFrom:
    - extract:
-        key: infrastructure/hetzner-s3
+        key: seed/authentik/hetzner-creds
@@ -15,7 +15,7 @@ resources:
  - alertmanager-gate-egress.yaml
  - prometheus-gate-egress.yaml
  - wordpress-gate-egress.yaml
-  - llama-gate-egress.yaml
+  - outpost-servicemonitors.yaml
  - ldap-outpost-cert.yaml
  - ldap-outpost-lb.yaml
  - ldap-outpost-cnp.yaml
@@ -27,4 +27,5 @@ resources:
  - cluster.yaml
  - objectstore.yaml
  - scheduled-backup.yaml
+  - barman-creds-externalsecret.yaml
  - hetzner-creds-externalsecret.yaml
@@ -40,7 +40,7 @@ metadata:
    # so this Service produces no public record — LDAP stays
    # LAN-internal, which matches the threat model of the cleartext
    # bind on 389.
-    external-dns.kubernetes.io/hostname: ldap.renner.uno
+    external-dns.alpha.kubernetes.io/hostname: ldap.renner.uno
 spec:
  type: LoadBalancer
  externalTrafficPolicy: Local
@@ -1,30 +0,0 @@
---
-# Lets the llama-gate outpost reach llama-server. The cluster baseline CNP
-# (kubernetes/infrastructure/network-policies/authentik-ns.yaml) otherwise stops
-# any authentik-namespace pod from entering the ai namespace.
-#
-# The outpost is the trust boundary: it forwards to llama-server only after
-# validating the Authentik session, and the matching ingress rule in
-# ai-ns.yaml admits nothing else — so nothing in the cluster can route around
-# the gate to reach the unauthenticated API through the public hostname.
-#
-# Scoped to this outpost's pod label rather than the whole namespace, so the
-# other gates cannot reach llama-server either.
-apiVersion: cilium.io/v2
-kind: CiliumNetworkPolicy
-metadata:
-  name: llama-gate-egress
-  namespace: authentik
-spec:
-  endpointSelector:
-    matchLabels:
-      goauthentik.io/outpost-name: llama-gate
-  egress:
-    - toEndpoints:
-        - matchLabels:
-            "k8s:io.kubernetes.pod.namespace": ai
-            app.kubernetes.io/name: llama-server
-      toPorts:
-        - ports:
-            - port: "8080"
-              protocol: TCP
@@ -1,10 +1,50 @@
 ---
-# Only radius needs a hand-written ServiceMonitor. The goauthentik.io operator
-# creates one per outpost and Prometheus discovers those directly, because
-# serviceMonitorSelector here is empty (see monitoring/helmrelease-prometheus.yaml).
-# Standalone copies for ldap and paperless-gate used to live here as well; they
-# duplicated the operator's and were removed.
-#
+# The goauthentik.io operator (inside authentik-worker) auto-creates a
+# ServiceMonitor per outpost, but it does not stamp the
+# `release: kube-prometheus-stack` label that this cluster's Prometheus
+# requires on serviceMonitorSelector. Those operator-owned SMs are
+# silently ignored. Declare standalone SMs here with the correct label
+# so the outposts actually get scraped.
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: authentik-outpost-ldap
+  namespace: authentik
+  labels:
+    release: kube-prometheus-stack
+spec:
+  namespaceSelector:
+    matchNames:
+      - authentik
+  selector:
+    matchLabels:
+      goauthentik.io/outpost-name: ldap-outpost
+      goauthentik.io/outpost-type: ldap
+  endpoints:
+    - port: http-metrics
+      path: /metrics
+      interval: 30s
+---
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: authentik-outpost-paperless-gate
+  namespace: authentik
+  labels:
+    release: kube-prometheus-stack
+spec:
+  namespaceSelector:
+    matchNames:
+      - authentik
+  selector:
+    matchLabels:
+      goauthentik.io/outpost-name: paperless-gate
+      goauthentik.io/outpost-type: proxy
+  endpoints:
+    - port: http-metrics
+      path: /metrics
+      interval: 30s
+---
 # Radius requires extra plumbing. The radius binary listens on :9300 just
 # like ldap/proxy (hardcoded in authentik/lib/default.yml), but authentik's
 # Python operator (`providers/radius/controllers/kubernetes.py`) omits the
@@ -13,11 +53,6 @@
 # it, radius does not. Result: the operator-managed `ak-outpost-local-radius`
 # Service exposes only UDP 1812. Add a sibling Service here that selects the
 # same pod labels and exposes 9300/TCP, then a ServiceMonitor for it.
-#
-# The operator's own `ak-outpost-local-radius` ServiceMonitor cannot cover
-# this: it selects on `app.kubernetes.io/managed-by: goauthentik.io` together
-# with `goauthentik.io/service-type: metrics`, and no Service carries both —
-# the operator's has the first, the one below has the second.
 apiVersion: v1
 kind: Service
 metadata:
@@ -51,8 +86,6 @@ spec:
    matchNames:
      - authentik
  selector:
-    # Pinned to the Service above. Without managed-by this would also match the
-    # operator's Service and scrape the same endpoint twice.
    matchLabels:
      app.kubernetes.io/managed-by: homelab
      goauthentik.io/outpost-name: local-radius
@@ -3,4 +3,3 @@ kind: Kustomization
 resources:
  - externalsecret.yaml
  - helmrelease.yaml
-  - networkpolicy.yaml
@@ -1,22 +0,0 @@
-# The apps namespace is default-deny-ingress, so the ServiceMonitor added in
-# monitoring-rules/external-dns-servicemonitor.yaml scraped into a timeout.
-# The selector matches both releases — the Cloudflare one deployed here and
-# external-dns-unifi from infrastructure/ — since they share the chart's
-# app.kubernetes.io/name and land in the same namespace.
-apiVersion: cilium.io/v2
-kind: CiliumNetworkPolicy
-metadata:
-  name: external-dns-allow-metrics-scrape
-  namespace: apps
-spec:
-  endpointSelector:
-    matchLabels:
-      app.kubernetes.io/name: external-dns
-  ingress:
-    - fromEndpoints:
-        - matchLabels:
-            k8s:io.kubernetes.pod.namespace: monitoring
-      toPorts:
-        - ports:
-            - port: "7979"
-              protocol: TCP
@@ -0,0 +1,31 @@
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: file
+  namespace: apps
+  labels:
+    app.kubernetes.io/name: file
+  annotations:
+    cert-manager.io/cluster-issuer: letsencrypt-cluster
+    # Backend serves HTTPS with a self-signed cert; re-encrypt + skip
+    # verify via the shared insecure-backend ServersTransport (see
+    # apps/insecure-backend-serverstransport.yaml).
+    traefik.ingress.kubernetes.io/service.serversscheme: https
+    traefik.ingress.kubernetes.io/service.serverstransport: insecure-backend@kubernetescrd
+spec:
+  ingressClassName: traefik
+  rules:
+    - host: file.renner.uno
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: file
+                port:
+                  number: 7001
+  tls:
+    - secretName: file-tls
+      hosts:
+        - file.renner.uno
@@ -1,5 +1,5 @@
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:
-  - deployment.yaml
+  - service.yaml
  - ingress.yaml
@@ -0,0 +1,18 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: file
+  namespace: apps
+  labels:
+    app.kubernetes.io/name: file
+spec:
+  # Caddy reverse-proxied https://nas.renner.uno:7001. nas.renner.uno
+  # is a CNAME -> nas-1.renner.uno owned by UniFi DNS, k8s-gateway
+  # forwards srv lookups so this resolves cluster-side.
+  type: ExternalName
+  externalName: nas.renner.uno
+  ports:
+    - name: https
+      port: 7001
+      targetPort: 7001
+      protocol: TCP
@@ -18,18 +18,15 @@ metadata:
 #
 # Opaque-label map (maintainer reference only — NOT served publicly):
 #   services group                   infrastructure group
-#     Web Service 1 = Authentik        Infrastructure 1 = retired (was PBS 2)
+#     Web Service 1 = Authentik        Infrastructure 1 = PBS 2 (pbs2.renner.uno)
 #     Web Service 2 = Gitea            Infrastructure 2 = retired (was Proxmox VE)
 #     Web Service 3 = Immich           Infrastructure 3 = UDM DNS (10.2.40.1)
 #     Web Service 4 = Woodpecker CI    Infrastructure 4 = Mosquitto MQTT broker
 #     Web Service 5 = Grafana
 #     Web Service 6 = Home Assistant
-#     Web Service 7 = retired (was the NAS file UI; never Paperless, which
-#                     this map claimed and which nothing here checks)
+#     Web Service 7 = Paperless
 #     Web Service 8 = Audiobookshelf
 #     Web Service 9 = Music Assistant
-#     Web Service 10 = TRMNL
-#     Web Service 11 = Paperless (gate-level only, see its entry)
 data:
  config.yaml: |
    storage:
@@ -124,10 +121,18 @@ data:
        conditions:
          - "[STATUS] == any(200, 301, 302)"

-      # Removed 2026-08-28: the NAS file UI (file.renner.uno). Its Ingress and
-      # ExternalName Service were deleted in #696 because they pointed at
-      # nas-1, which is powered off; this check outlived them and had been
-      # reporting failure on the public page since.
+      - name: Web Service 7
+        group: services
+        url: https://file.renner.uno
+        interval: 60s
+        ui:
+          hide-hostname: true
+          hide-url: true
+          hide-port: true
+          hide-conditions: true
+          hide-errors: true
+        conditions:
+          - "[STATUS] == any(200, 301, 302)"

      - name: Web Service 8
        group: services
@@ -173,29 +178,6 @@ data:
        conditions:
          - "[STATUS] == any(200, 301, 302)"

-      # Paperless sits entirely behind the Authentik gate — every path,
-      # including /api/, answers 302 to unauthenticated callers, so there is no
-      # endpoint that proves the app rather than the gate. This check is
-      # therefore reachability only: DNS, TLS, Traefik and the outpost. It
-      # stays green if paperless itself is dead behind a live gate.
-      #
-      # Closing that blind spot needs an in-cluster probe of the paperless
-      # ClusterIP, which crosses a namespace boundary and so needs a
-      # CiliumNetworkPolicy first — the monitoring probes get away without one
-      # only because their targets share a namespace with the prober.
-      - name: Web Service 11
-        group: services
-        url: https://paperless.renner.uno
-        interval: 60s
-        ui:
-          hide-hostname: true
-          hide-url: true
-          hide-port: true
-          hide-conditions: true
-          hide-errors: true
-        conditions:
-          - "[STATUS] == any(200, 301, 302)"
-
      # Removed 2026-05-21: Jellyfin (media.renner.uno), Wiki (wiki.renner.uno),
      # InfluxDB (influx.renner.uno) — hostnames NXDOMAIN, no Ingress; services
      # no longer deployed. Re-add when/if they come back.
@@ -209,11 +191,20 @@ data:
      # NoData). Monitor the offsite PBS from the offsite side or via a
      # check that doesn't depend on this cluster's DNS path.

-      # Removed 2026-08-28: PBS 2 (pbs2.renner.uno:8007) — it has no clients
-      # left. Its two were the PVE cluster, retired to bare-metal Talos, and
-      # nas-1, powered off and dropped from the repo. Checking the liveness of
-      # a backup server that nothing backs up to reports on nothing. Re-add
-      # alongside the first host that is declared to back up to it.
+      - name: Infrastructure 1
+        group: infrastructure
+        url: https://pbs2.renner.uno:8007
+        interval: 60s
+        client:
+          insecure-skip-verify: true
+        ui:
+          hide-hostname: true
+          hide-url: true
+          hide-port: true
+          hide-conditions: true
+          hide-errors: true
+        conditions:
+          - "[STATUS] == any(200, 301, 302)"

      - name: Infrastructure 3
        group: infrastructure
@@ -5,12 +5,6 @@ metadata:
  namespace: apps
  labels:
    app: gatus
-  annotations:
-    # Gatus reads its config once at startup and never re-reads the file, so
-    # without this a ConfigMap change reconciles cleanly and then does nothing:
-    # git and the running checks drift apart silently, with no failed resource
-    # to notice. Adding a check would not take effect either.
-    configmap.reloader.stakater.com/reload: gatus-config
 spec:
  replicas: 1
  # RWO PVC (`gatus-data`, ceph-block) — RollingUpdate's default 25% surge
@@ -28,30 +22,9 @@ spec:
      labels:
        app: gatus
    spec:
-      # The upstream image is FROM scratch with no USER, so without this the
-      # pod runs as root and trips PodSecurity restricted on four counts.
-      #
-      # The uid is numeric because a scratch image carries no /etc/passwd for
-      # the kubelet to resolve a name against. fsGroup is what makes the switch
-      # survivable: the only write path is the sqlite store on the RWO volume
-      # (/data/gatus.db, see the storage stanza in the ConfigMap), and fsGroup
-      # both chowns the existing volume and leaves the directory group-writable
-      # so sqlite can create its -wal and -journal siblings next to the db.
-      securityContext:
-        runAsNonRoot: true
-        runAsUser: 65532
-        runAsGroup: 65532
-        fsGroup: 65532
-        seccompProfile:
-          type: RuntimeDefault
      containers:
        - name: gatus
          image: twinproduction/gatus:v5.36.0 # {"$imagepolicy": "flux-system:gatus"}
-          securityContext:
-            allowPrivilegeEscalation: false
-            capabilities:
-              drop:
-                - ALL
          ports:
            - containerPort: 8080
              name: http
@@ -2,7 +2,7 @@ apiVersion: networking.k8s.io/v1
 kind: Ingress
 metadata:
  name: gitea
-  namespace: gitea
+  namespace: apps
  labels:
    app.kubernetes.io/name: gitea
  annotations:
@@ -2,7 +2,7 @@ apiVersion: traefik.io/v1alpha1
 kind: IngressRouteTCP
 metadata:
  name: gitea-ssh
-  namespace: gitea
+  namespace: apps
  labels:
    app.kubernetes.io/name: gitea
 spec:
@@ -1,8 +1,28 @@
-# Prometheus scrape and Traefik are admitted by the namespace baseline in
-# infrastructure/network-policies/gitea-ns.yaml.
-#
+apiVersion: cilium.io/v2
+kind: CiliumNetworkPolicy
+metadata:
+  name: gitea-allow-metrics-scrape
+  namespace: apps
+spec:
+  # Prometheus (monitoring ns) scrapes gitea's /metrics on :3000. The apps
+  # default-deny-ingress only allows same-ns / home-assistant / host, so the
+  # scrape is dropped (context deadline exceeded). This became necessary only
+  # after the LXC->in-cluster cutover — the old static target was external, so
+  # no in-cluster policy applied. Scoped to the gitea pod + :3000.
+  endpointSelector:
+    matchLabels:
+      app.kubernetes.io/name: gitea
+  ingress:
+    - fromEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": monitoring
+      toPorts:
+        - ports:
+            - port: "3000"
+              protocol: TCP
+---
 # Secret rotation: the flux-git rotator (openbao ns) reaches gitea to mint a new
-# flux PAT. It uses the in-cluster Service (gitea.gitea.svc:3000) — the public
+# flux PAT. It uses the in-cluster Service (gitea.apps.svc:3000) — the public
 # gitea.renner.uno name hairpins off the ingress LB from a pod (same failure as
 # pve.renner.uno). Scoped to the gitea pod :3000 and the rotator label; the
 # egress half is rotator-gitea-flux-egress in network-policies/openbao-ns.yaml.
@@ -10,7 +30,7 @@ apiVersion: cilium.io/v2
 kind: CiliumNetworkPolicy
 metadata:
  name: gitea-allow-flux-rotator
-  namespace: gitea
+  namespace: apps
 spec:
  endpointSelector:
    matchLabels:
@@ -34,7 +54,7 @@ apiVersion: cilium.io/v2
 kind: CiliumNetworkPolicy
 metadata:
  name: gitea-allow-review-bot-rotator
-  namespace: gitea
+  namespace: apps
 spec:
  endpointSelector:
    matchLabels:
@@ -13,7 +13,7 @@ apiVersion: policy/v1
 kind: PodDisruptionBudget
 metadata:
  name: gitea
-  namespace: gitea
+  namespace: apps
  labels:
    app.kubernetes.io/name: gitea
 spec:
@@ -2,7 +2,7 @@ apiVersion: v1
 kind: Service
 metadata:
  name: gitea
-  namespace: gitea
+  namespace: apps
  labels:
    app.kubernetes.io/name: gitea
 spec:
@@ -2,7 +2,7 @@ apiVersion: apps/v1
 kind: StatefulSet
 metadata:
  name: gitea
-  namespace: gitea
+  namespace: apps
  labels:
    app.kubernetes.io/name: gitea
 spec:
@@ -152,7 +152,7 @@ spec:
          # NOTE: volumeClaimTemplates is immutable on an existing StatefulSet,
          # so bumping this value cannot be `kubectl apply`-ed in place — Flux
          # will reject the whole object. Landing this size change requires a
-          # one-time `kubectl delete statefulset gitea -n gitea --cascade=orphan`
+          # one-time `kubectl delete statefulset gitea -n apps --cascade=orphan`
          # (pod + PVC keep running) so Flux re-creates the STS from this
          # template and re-adopts them. After the cleanup_packages GC reclaims
          # the ~10G of orphaned blobs, real usage is ~9G, so 40Gi is headroom.
@@ -111,23 +111,9 @@ statistics             max_id=13323904    max_start_ts=1787162400.0
 statistics_short_term  max_id=159205762   max_start_ts=1787166000.0
 ```

-## Phase 2c — cutover: DONE
+## Phase 2c — cutover (REMAINING)

-Verified 2026-09-02 against the live database:
-
-| table | rows | span |
-|---|---|---|
-| `statistics` | 11,092,586 | 2024-03-13 20:00 → current |
-| `statistics_short_term` | 1,883,709 | rolling ~7 days |
-| `statistics_meta` | 1,480 | |
-
-The 2024-03-13 origin is the proof that matters. It is unchanged from the
-pre-migration count in "What is at risk" above, so the history was copied
-across engines rather than started from zero — which is the failure this
-document exists to prevent. `states` carries current rows, so `db_url` points
-at Postgres.
-
-The procedure below is kept as the record of what was done.
+Do not start until phase 1 is verified.

 **Migrate statistics only.** Copying all 18M `states` rows is slow, needs a long
 HA outage, and buys a table that is discarded within 7 days anyway.
@@ -18,7 +18,7 @@ metadata:
    lb-pool: bgp
  annotations:
    lbipam.cilium.io/ips: "10.2.99.87,fd99::87"
-    external-dns.kubernetes.io/hostname: ha.renner.uno
+    external-dns.alpha.kubernetes.io/hostname: ha.renner.uno
 spec:
  type: LoadBalancer
  externalTrafficPolicy: Local
@@ -56,9 +56,10 @@ spec:
        # Re-rendered on every pod start, so a CNPG password rotation takes
        # effect rather than silently leaving a stale URI behind.
        #
-        # Load-bearing: `db_url: !secret recorder_db_url` in the homeassistant
-        # repo's configuration.yaml reads this key, so HA does not start
-        # without it. Removing this init container takes the recorder down.
+        # INERT until the recorder is repointed: nothing reads this key until
+        # `db_url: !secret recorder_db_url` lands in configuration.yaml in the
+        # homeassistant repo. That ordering is required — HA refuses to start
+        # when a referenced secret is missing.
        - name: render-db-url
          image: busybox:1.36
          command:
@@ -95,7 +96,7 @@ spec:
              memory: 32Mi
      containers:
        - name: home-assistant
-          image: ghcr.io/home-assistant/home-assistant:2026.9.3 # {"$imagepolicy": "flux-system:home-assistant"}
+          image: ghcr.io/home-assistant/home-assistant:2026.8.3 # {"$imagepolicy": "flux-system:home-assistant"}
          env:
            - name: TZ
              value: Europe/Berlin
@@ -209,28 +210,6 @@ spec:
            - name: vscode
              containerPort: 8080
              protocol: TCP
-          # /healthz answers 200 whenever the HTTP server is up; its body
-          # reports session heartbeat state, which is not health — an idle
-          # editor reports "expired" and is perfectly fine. So this asserts
-          # that code-server is serving, not that anyone is using it.
-          #
-          # Liveness matters here more than elsewhere in this pod: code-server
-          # shares the Home Assistant config volume, and a wedged editor is
-          # otherwise invisible until someone tries to open it.
-          livenessProbe:
-            httpGet:
-              path: /healthz
-              port: vscode
-            initialDelaySeconds: 30
-            periodSeconds: 30
-            timeoutSeconds: 5
-          readinessProbe:
-            httpGet:
-              path: /healthz
-              port: vscode
-            initialDelaySeconds: 10
-            periodSeconds: 10
-            timeoutSeconds: 5
          volumeMounts:
            - name: config
              mountPath: /config
@@ -18,12 +18,12 @@
 # That is the point of the move — it attacks the multiplier rather than trimming
 # what gets recorded, which would only hide the problem.
 #
-# This is the live recorder database. HA writes here; the SQLite file is no
-# longer the system of record. The 2.4 years of long-term statistics were
-# copied across engines rather than regenerated — HA does not migrate data
-# between database engines, so an empty Postgres would have silently started
-# from zero and taken the energy dashboard's history with it.
-# MIGRATION-recorder-postgres.md holds the sequence that was followed.
+# STAGING
+# Phase 1 (this manifest): the cluster comes up EMPTY and HA keeps using SQLite.
+# Nothing depends on it, so a failure here is inert. Verify Ready, WAL archiving
+# to Hetzner, and a successful base backup before going further.
+# Phase 2: migrate the statistics tables and repoint recorder.db_url.
+# See MIGRATION-recorder-postgres.md for the sequence and the rollback.
 apiVersion: postgresql.cnpg.io/v1
 kind: Cluster
 metadata:
@@ -1,8 +1,21 @@
 ---
 # Barman S3 credentials for ha-pg.
 #
-# One shared path for one shared credential — see the note in
-# ../paperless/hetzner-creds-externalsecret.yaml.
+# FOLLOW-UP (#397): sourced from seed/paperless/hetzner-creds, which is not where
+# they belong. woodpecker/hetzner-creds-externalsecret.yaml has the identical
+# problem and the same note. The values are the same today, so this is correct
+# but coupled: rotating paperless's Hetzner credentials would silently change
+# the backup credentials for Home Assistant and Woodpecker too.
+#
+# The fix is one dedicated path per consumer (seed/home-assistant/hetzner-creds)
+# and a one-line change to the `key:` below. Creating it needs an OpenBao write:
+#
+#   bao kv put homelab/seed/home-assistant/hetzner-creds \
+#     @<(bao kv get -format=json homelab/seed/paperless/hetzner-creds | jq '.data.data')
+#
+# Note the mount is `homelab`, so the path is homelab/seed/... — #397 records a
+# 403 on `bao kv list seed`, which was a wrong-path error rather than a
+# permissions problem.
 #
 # The namespace allowlist on the openbao ClusterSecretStore
 # (infrastructure/post-crds/openbao-clustersecretstore.yaml) must include this
@@ -22,4 +35,4 @@ spec:
    name: hetzner-s3-creds
  dataFrom:
    - extract:
-        key: infrastructure/hetzner-s3
+        key: seed/paperless/hetzner-creds
@@ -60,8 +60,9 @@ resources:
  - zigbee2mqtt-gate-service.yaml
  - zigbee2mqtt-ingress.yaml
  # Postgres backend for the recorder (MIGRATION-recorder-postgres.md).
-  # Live: recorder.db_url in the homeassistant repo points here, and the
-  # long-term statistics carry their full history from 2024.
+  # PHASE 1: this cluster comes up EMPTY and nothing consumes it — HA is still
+  # on SQLite. Deploying it is therefore inert; phase 2 migrates the statistics
+  # tables and repoints recorder.db_url in the homeassistant repo.
  - ha-pg-hetzner-creds-externalsecret.yaml
  - ha-pg-objectstore.yaml
  - ha-pg-cluster.yaml
@@ -1,22 +1,80 @@
 ---
-# mDNS relay: holds the multicast membership on the IoT VLAN through its own
-# macvlan and forwards each datagram to Home Assistant as ordinary UNICAST UDP.
+# mDNS relay: gives Home Assistant sight of the IoT VLAN's mDNS announcements
+# without putting a macvlan on the HA pod itself.
 #
-# It must stay unicast. An avahi-style reflector cannot work here — Cilium runs
-# in tunnel mode without enable-multicast, so re-emitted multicast is dropped by
-# the CNI. Unicast is carried, and python-zeroconf accepts it: its datagram
-# handler checks size and duplicates but never the destination or source
-# address. RFC 6762's QU bit makes this protocol-legal rather than a trick.
+# THE PROBLEM
 #
-# This restores passive reception only — announcements, including the
-# re-announce a device sends when its address changes. HA-initiated browsing
-# still dies on eth0; that would need a querier on the VLAN side, which this
-# deliberately is not.
+# HA's zeroconf listener joins both mDNS groups on eth0 — 224.0.0.251 and
+# ff02::fb — and never hears anything on either.
+# Multicast is link-local, so IoT-VLAN announcements do not reach the pod
+# CIDR; and Cilium runs in tunnel mode (VXLAN) without `enable-multicast`, so
+# it does not replicate multicast between pods either. Both halves of the path
+# are dead, which is why an avahi-style reflector — receive on one interface,
+# re-emit as multicast on the other — cannot work here: the re-emitted packets
+# would be dropped by the CNI.
 #
-# so-bindtodevice=net1 on both receive sockets is load-bearing: without it
-# socat binds the wildcard, and the namespace CNP lets any sibling pod reach
-# :5353 and inject records into HA's zeroconf cache. Binding net1's address
-# instead is impossible — it is DHCP-leased and unknown at exec time.
+# Consequence for HA: the ESPHome integration dials devices at the address
+# cached in its config entry. When a lease rotates, every attempt fails with
+# `[Errno 113] Connect call failed` and the device stays unreachable, because
+# the mDNS announcement that would carry the new address never arrives. New
+# devices are never discovered at all.
+#
+# THE MECHANISM
+#
+# This relay holds the multicast membership on the IoT VLAN through its own
+# macvlan (mdns-relay-network-attachment.yaml) and forwards each datagram it
+# receives to HA as ordinary UNICAST UDP. That is the one direction of travel
+# the CNI will carry.
+#
+# It works because python-zeroconf does not filter on how a packet arrived:
+# its datagram handler validates size, deduplicates, and parses, but performs
+# no check on destination address, source address, or source port. A unicast
+# datagram delivered to :5353 is processed exactly like a multicast one. (mDNS
+# unicast responses are part of RFC 6762 — the QU bit — so this is within the
+# protocol, not a trick.)
+#
+# WHAT THIS DOES AND DOES NOT RESTORE
+#
+# Restored: passive reception. RFC 6762 requires a responder to re-announce
+# when its address changes, so a device that moves to a new lease announces
+# the move, HA sees it, and the ESPHome integration updates the config entry.
+# That is the failure this exists to fix. New devices announcing themselves
+# are likewise seen.
+#
+# NOT restored: HA-initiated browsing. Queries HA sends leave on eth0 as
+# multicast and die there, so HA cannot actively solicit a response. Anything
+# depending on a query rather than an announcement stays broken. Making that
+# work needs a querier on the VLAN side, which this relay deliberately is not.
+#
+# EXPOSURE
+#
+# The receive sockets carry so-bindtodevice=net1, so only datagrams that
+# actually arrived on the IoT VLAN interface are delivered. Binding to net1's
+# address instead is not possible — it is DHCP-leased and unknown at exec time
+# — but binding to the device achieves the same confinement without needing to
+# know the address, and needs no capability: SO_BINDTODEVICE succeeds as an
+# unprivileged uid here.
+#
+# Without it socat would bind the wildcard, and since the namespace CNP grants
+# every pod in home-assistant unrestricted access to every other pod on every
+# port, any sibling pod could reach :5353 over the cluster network and have
+# records forwarded into HA's zeroconf cache.
+#
+# What remains, and cannot be closed here: any host on the IoT VLAN can send
+# this port a datagram. That is the same trust already extended to genuine
+# mDNS from that segment, which any device there can equally forge — the relay
+# widens who can reach HA's listener, not what can be claimed. macvlan traffic
+# bypasses Cilium policy entirely, so the namespace CNP does not constrain
+# this interface either way.
+#
+# Note that the relay is not what makes HA's zeroconf reachable from inside
+# the cluster: HA binds :5353 on the pod address (v4) and the wildcard (v6),
+# and the namespace CNP already permits any sibling pod to reach it directly.
+# Confining the relay removes a second route to that listener; it does not
+# remove the first.
+#
+# Nothing else is exposed: the containers run socat and only socat, with no
+# second listener to reach.
 apiVersion: apps/v1
 kind: Deployment
 metadata:
@@ -60,7 +118,7 @@ spec:
      # Two processes rather than one: socat carries a single address pair per
      # invocation, and the families need different receive and send addresses.
      # They are independent — one crashing does not blind the other — and each
-      # carries its own supervisor loop.
+      # is restarted by the kubelet on its own.
      containers:
        # -u is load-bearing on both: unidirectional, left to right. Without it
        # socat would also carry HA's replies back out, and this must stay a
@@ -77,29 +135,17 @@ spec:
        # UDP4-SENDTO takes its A record and UDP6-SENDTO its AAAA. See
        # mdns-relay-service.yaml for why that indirection is required and why
        # the Service is dual-stack.
-        #
-        # Supervisor loop: socat exits 1 on the first datagram it cannot
-        # deliver, and the ClusterIP has no backend while HA restarts. The
-        # trap forwards SIGTERM so the pod still terminates promptly.
        - name: socat-ipv4
          image: alpine/socat:1.8.0.3@sha256:beb4a68d9e4fe6b0f21ea774a0fde6c31f580dde6368939ed70100c5385b015e
          imagePullPolicy: IfNotPresent
-          command:
-            - /bin/sh
-            - -c
-            - |
-              trap 'kill "$pid"; exit 0' TERM INT
-              while :; do
-                socat -u \
-                  "UDP4-RECV:5353,ip-add-membership=224.0.0.251:net1,so-bindtodevice=net1,reuseaddr" \
-                  "UDP4-SENDTO:home-assistant-mdns.home-assistant.svc.cluster.local:5353" &
-                pid=$!
-                wait "$pid"
-                echo "mdns-relay: socat-ipv4 exited ($?); restarting in 2s" >&2
-                sleep 2
-              done
-          # No probes. The supervisor loop is the liveness story; a probe here
-          # could only re-assert that PID 1 is running.
+          args:
+            - -u
+            - "UDP4-RECV:5353,ip-add-membership=224.0.0.251:net1,so-bindtodevice=net1,reuseaddr"
+            - "UDP4-SENDTO:home-assistant-mdns.home-assistant.svc.cluster.local:5353"
+          # No probes. socat is a single process with no health surface: if it
+          # exits, the container exits and the kubelet restarts it, which is the
+          # entire liveness story. A probe here could only re-assert that PID 1
+          # is running.
          resources:
            requests:
              cpu: 10m
@@ -126,20 +172,10 @@ spec:
        - name: socat-ipv6
          image: alpine/socat:1.8.0.3@sha256:beb4a68d9e4fe6b0f21ea774a0fde6c31f580dde6368939ed70100c5385b015e
          imagePullPolicy: IfNotPresent
-          command:
-            - /bin/sh
-            - -c
-            - |
-              trap 'kill "$pid"; exit 0' TERM INT
-              while :; do
-                socat -u \
-                  "UDP6-RECV:5353,ipv6-join-group=[ff02::fb]:net1,so-bindtodevice=net1,ipv6-v6only=1,reuseaddr" \
-                  "UDP6-SENDTO:home-assistant-mdns.home-assistant.svc.cluster.local:5353" &
-                pid=$!
-                wait "$pid"
-                echo "mdns-relay: socat-ipv6 exited ($?); restarting in 2s" >&2
-                sleep 2
-              done
+          args:
+            - -u
+            - "UDP6-RECV:5353,ipv6-join-group=[ff02::fb]:net1,so-bindtodevice=net1,ipv6-v6only=1,reuseaddr"
+            - "UDP6-SENDTO:home-assistant-mdns.home-assistant.svc.cluster.local:5353"
          resources:
            requests:
              cpu: 10m
@@ -6,23 +6,32 @@ metadata:
  labels:
    app.kubernetes.io/name: mosquitto
  annotations:
-    # REQUIRED for credential rotation to take effect. The startup shim rebuilds
-    # the password file only on pod start, so without this a rotated Secret sits
-    # inert while the old password stays valid indefinitely.
+    # REQUIRED for credential rotation to take effect at all. The startup shim
+    # rebuilds /mosquitto/auth/passwd from these Secrets on every pod start, so
+    # a rotated Secret is inert until the pod restarts — without this the new
+    # password would sit unused until some unrelated restart, while the old one
+    # stayed valid indefinitely.
    #
-    # Listed per-Secret rather than with the blanket auto annotation, so that
-    # enrolling another broker user is a visible edit to this line.
+    # Listed per-Secret rather than using the blanket `reloader.stakater.com/
+    # auto: "true"`, so that enrolling each remaining broker user in rotation is
+    # a visible, reviewable edit to this line rather than something that starts
+    # happening implicitly.
    secret.reloader.stakater.com/reload: mosquitto-health-credentials
 spec:
  replicas: 1
  strategy:
-    # No PVC, so nothing to fence — the new broker can serve before the old one
-    # is torn down. Two stateless brokers overlapping behind the LB is fine.
+    # No PVC anymore, so nothing to fence: the new broker can come up and pass
+    # its readiness probe before the old one is torn down. maxUnavailable:0 keeps
+    # a broker serving throughout an image bump / reschedule (clients on the old
+    # pod just reconnect to the new one); maxSurge:1 permits the brief two-pod
+    # overlap — two independent stateless brokers behind the LB, fine since there
+    # is no shared state.
    #
-    # Connectivity survives a roll but RETAINED STATE DOES NOT: the new pod
-    # starts with an empty retained store, so every roll is a broker restart
-    # for clients that depend on retention. Zigbee2MQTT does not recover from
-    # that on its own (#381).
+    # NOTE: connectivity survives the roll, but RETAINED STATE DOES NOT — the
+    # new pod starts with an empty retained store, so a roll is equivalent to a
+    # broker restart for every client that depends on retention. Zigbee2MQTT
+    # does not recover from that on its own; see mosquitto-config.yaml and
+    # gitea issue #381.
    type: RollingUpdate
    rollingUpdate:
      maxUnavailable: 0
@@ -35,10 +44,14 @@ spec:
      labels:
        app.kubernetes.io/name: mosquitto
    spec:
-      # Runs anywhere; the mosquitto-iot LB finds it. Short fault tolerations
-      # reschedule the broker in ~30s rather than the default ~5min, which is
-      # only possible because there is no PVC to fence — so it also does not
-      # depend on Ceph being healthy.
+      # Runs on any node (no nodeSelector); the mosquitto-iot LB forwards
+      # IoT-VLAN traffic to the broker wherever it lands.
+      # Availability: home-critical priority (never preempted, reschedules
+      # first) + short fault tolerations so a node failure reschedules the
+      # broker in ~30s instead of the default ~5min. With persistence off there
+      # is no PVC to fence/detach/reattach, so the broker can (re)start anywhere
+      # instantly, no longer depends on Ceph being healthy, and rolls without a
+      # tear-down-first gap (see the RollingUpdate strategy above).
      priorityClassName: home-critical
      terminationGracePeriodSeconds: 10
      tolerations:
@@ -19,7 +19,7 @@ metadata:
    # LAN can connect with `mqtt.renner.uno` (matches the broker cert
    # SAN) instead of the bare IP. No Cloudflare label — kept off the
    # public DNS; UniFi serves a split-DNS answer for LAN clients.
-    external-dns.kubernetes.io/hostname: mqtt.renner.uno
+    external-dns.alpha.kubernetes.io/hostname: mqtt.renner.uno
 spec:
  type: LoadBalancer
  externalTrafficPolicy: Local
@@ -6,9 +6,12 @@ metadata:
  labels:
    app.kubernetes.io/name: zigbee2mqtt
 spec:
-  # Z2M is the live Zigbee stack. Never run it alongside ZHA: they contend for
-  # the coordinator's single TCP session, and a Z2M start without the restored
-  # coordinator backup forms a NEW network and drops every paired device.
+  # CUTOVER DONE (2026-07-23): ZHA disabled, the coordinator-backup Secret is
+  # populated in OpenBao, and Z2M is now the live Zigbee stack — so replicas is
+  # 1. It shipped at 0 as a safety interlock (Z2M contends with ZHA for the
+  # coordinator's single TCP session, and starting without the restored backup
+  # would form a NEW network and drop every device); that interlock is spent
+  # once the migration is committed. To roll back, set 0 and re-enable ZHA.
  replicas: 1
  # RWO PVC → single writer; never run two pods against the same /app/data.
  strategy:
@@ -36,10 +39,14 @@ spec:
        # network_key, the latter extracted from the OpenBao coordinator backup
        # as a natural-byte-order int array.
        - name: seed-data
-          # Our own alpine + jq image, built by build-ci-images.yml. DATED tag,
-          # never :latest — rebuilding this base for an unrelated consumer
-          # would otherwise silently change what this init container runs on
-          # its next pod
+          # alpine + jq, built by .woodpecker/build-ci-images.yml from
+          # ci/images/alpine-jq/. Replaces `apk add --no-cache jq` on every pod
+          # start: tools belong in the image, not installed at runtime.
+          # Referenced by tag rather than digest — these are our own images.
+          # DATED tag, not :latest, matching the ci-ansible:2026-04-29 precedent
+          # in kubernetes/infrastructure/netbird-backup/cronjob.yaml. With
+          # :latest, rebuilding this base for some unrelated consumer would
+          # silently change what this init container runs on its next pod
          # restart, with no diff here to review — and this is the container that
          # renders the Zigbee network key. Bumping the tag is a deliberate,
          # reviewable act; the cost is remembering to bump it.
@@ -57,14 +64,7 @@ spec:
          # and leaves this one untouched (tags are not deleted), so this keeps
          # resolving — but the image then came from the branch build rather than
          # master. Re-point it at a master-built tag when convenient.
-          #
-          # konairius/, not gitea_admin/: this init container runs during a cold
-          # rebuild, when Gitea does not exist because it runs inside the
-          # cluster being rebuilt. The node then falls back to a ghcr.io copy
-          # (machine.registries.mirrors, applied by bootstrap.sh), and containerd
-          # keeps the repository path when it falls through — so the path has to
-          # exist on both registries. Steady state still pulls from Gitea.
-          image: gitea.renner.uno/konairius/alpine-jq:2026-09-04
+          image: gitea.renner.uno/gitea_admin/alpine-jq:2026-07-30
          command:
            - sh
            - -c
@@ -0,0 +1,18 @@
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: barman-cloud-creds
+  namespace: immich
+  annotations:
+    # Prune-disabled — a standing guard kept from the seed->immich-KS handoff (barman creds).
+    kustomize.toolkit.fluxcd.io/prune: disabled
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    kind: ClusterSecretStore
+    name: openbao
+  target:
+    name: barman-cloud-creds # keeps the old Secret's name — consumers unchanged
+  dataFrom:
+    - extract:
+        key: seed/immich/barman-creds
@@ -10,15 +10,15 @@ metadata:
    # Kept permanently as a standing guard.
    kustomize.toolkit.fluxcd.io/prune: disabled
 spec:
-  # A replica is viable because nothing here writes pg_vectors any more. Both
-  # vector indexes run on vchordrq and the vectors extension is gone, so the
-  # long pg_vectors/indexes/<uuid> paths are absent — pg_basebackup's tar
-  # format cannot represent them, and that is what blocks a replica join.
-  instances: 2
-  # See ak-pg cluster.yaml for rationale. The barman-plugin shutdown wedge
-  # (cloudnative-pg#9770) holds an instance up until SIGKILL, so bounding
-  # terminationGracePeriod (stopDelay) is what keeps a failover from waiting
-  # on it. smartShutdownTimeout keeps pod restarts quick.
+  # Single instance during pgvecto.rs → VectorChord migration window;
+  # pg_basebackup tar format chokes on the long pg_vectors/indexes/<uuid>
+  # paths, blocking replica join. Bump back to 2 once Immich's in-app
+  # vchord migration drops the vectors extension.
+  instances: 1
+  # See ak-pg cluster.yaml for rationale. Single-instance, so no failover, but
+  # the barman-plugin shutdown wedge (cloudnative-pg#9770) takes the whole DB
+  # down until SIGKILL — bounding terminationGracePeriod (stopDelay) matters
+  # even without a standby. smartShutdownTimeout keeps pod restarts quick.
  smartShutdownTimeout: 10
  stopDelay: 60
  imageName: ghcr.io/corentingiraud/cnpg-pgvector-vectorchord:16-migration
@@ -36,10 +36,8 @@ spec:
      database: immich
      owner: immich
  postgresql:
-    # vchord only. The image also ships pgvecto.rs (vectors.so), but its
-    # extension is not installed and preloading it would recreate pg_vectors
-    # in PGDATA for nothing. pgvector needs no preloading.
    shared_preload_libraries:
+      - vectors.so
      - vchord.so
    parameters:
      shared_buffers: "512MB"
@@ -15,4 +15,4 @@ spec:
    name: hetzner-s3-creds # keeps the old Secret's name — consumers unchanged
  dataFrom:
    - extract:
-        key: infrastructure/hetzner-s3
+        key: seed/immich/hetzner-creds
@@ -13,5 +13,6 @@ resources:
  - cluster.yaml
  - objectstore.yaml
  - scheduled-backup.yaml
+  - barman-creds-externalsecret.yaml
  - hetzner-creds-externalsecret.yaml
  - pvcs.yaml
@@ -32,7 +32,7 @@ spec:
          type: RuntimeDefault
      containers:
        - name: immich-machine-learning
-          image: ghcr.io/immich-app/immich-machine-learning:v3.2.2 # {"$imagepolicy": "flux-system:immich-machine-learning"}
+          image: ghcr.io/immich-app/immich-machine-learning:v3.1.0 # {"$imagepolicy": "flux-system:immich-machine-learning"}
          ports:
            - name: http
              containerPort: 3003
@@ -35,9 +35,6 @@ metadata:
  namespace: immich
  labels:
    app.kubernetes.io/name: immich-server
-  annotations:
-    # envFrom does not restart the pod when the ConfigMap changes; Reloader does.
-    configmap.reloader.stakater.com/reload: immich-config
 spec:
  # Scaled to 0 alongside immich-machine-learning during single-node
  # maintenance; see the note there. The CNPG Postgres cluster stays running,
@@ -87,7 +84,7 @@ spec:
              mountPath: /ca
      containers:
        - name: immich-server
-          image: ghcr.io/immich-app/immich-server:v3.2.2 # {"$imagepolicy": "flux-system:immich-server"}
+          image: ghcr.io/immich-app/immich-server:v3.1.0 # {"$imagepolicy": "flux-system:immich-server"}
          ports:
            - name: http
              containerPort: 3001
@@ -0,0 +1,20 @@
+# Shared Traefik ServersTransport for ingresses that re-encrypt to a
+# backend serving HTTPS with a self-signed / hostname-mismatched cert:
+#
+#   apps/file       — NAS web UI on a self-signed cert
+#
+# Replaces the nginx `backend-protocol: HTTPS` + `proxy-ssl-verify: off`
+# annotation pair. Each Ingress that wants this behaviour sets
+#   traefik.ingress.kubernetes.io/service.serversscheme: https
+#   traefik.ingress.kubernetes.io/service.serverstransport: insecure-backend
+#
+# (bare name — kubernetesIngress provider resolves ServersTransport in
+# the same namespace as the Ingress; the `<ns>-<name>@kubernetescrd`
+# qualified form is for IngressRoute CRDs only).
+apiVersion: traefik.io/v1alpha1
+kind: ServersTransport
+metadata:
+  name: insecure-backend
+  namespace: apps
+spec:
+  insecureSkipVerify: true
--- a/Show More
+++ b/Show More