fix(review-bot): mint the review-bot PAT with read:issue

Since 9ec31f07 (PR #1503) review-bot's sweep lists the PRs that request its review via GET /repos/issues/search?review_requested=true. Gitea requires read:issue for that endpoint, and the rotator mints the review-bot PAT with write:repository only, so every 5-minute sweep fails with HTTP 403 and requested reviews are picked up only by the webhook. - review-bot-secret-rotate: GITEA_SCOPES = write:repository,read:issue. - One-shot Job review-bot-rotate-read-issue runs the CronJob's rotate-mint and sync-woodpecker steps once, so the new token is minted on merge instead of at the next quarterly run (2027-01-01). ESO (refresh 1h) picks it up and Reloader restarts review-bot. Remove the Job in a follow-up once it ran. Closes #1505
2026-10-27 23:25:12 +00:00
280 changed files with 2451 additions and 9659 deletions
@@ -41,14 +41,13 @@ when:
      - "ci/images/**"
      - "secret-rotator/**"
      - "review-bot/**"
-      - "wlan-setup/**"
      - ".woodpecker/build-ci-images.yml"
  - event: deployment
    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "build-ci-images"'

 steps:
  - name: build-ansible
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/ansible
    # Only rebuild when THIS image's source (or the pipeline file) changed, or
    # on a manual run. Without this every step ran on any matching push, so a
@@ -75,7 +74,7 @@ steps:
          --destination gitea.renner.uno/gitea_admin/ci-ansible:latest

  - name: build-k8s
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/k8s
    when:
      - event: deployment
@@ -98,7 +97,7 @@ steps:
          --destination gitea.renner.uno/gitea_admin/ci-k8s:latest

  - name: build-vmtest
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/vmtest
    when:
      - event: deployment
@@ -121,7 +120,7 @@ steps:
          --destination gitea.renner.uno/gitea_admin/ci-vmtest:latest

  - name: build-tofu
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/tofu
    when:
      - event: deployment
@@ -151,7 +150,7 @@ steps:
  # Runtime image, not CI tooling: a static musl binary in a FROM-scratch image,
  # used as the base for secret-rotation CronJobs. Replaces per-job inline Python.
  - name: build-secret-rotator
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: secret-rotator
    when:
      - event: deployment
@@ -176,7 +175,7 @@ steps:
  # review-bot: the Go service that reviews pull requests with a Mistral agent (webhook plus sweep).
  # Runs after Gitea is up, so no ghcr mirror.
  - name: build-review-bot
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: review-bot
    when:
      - event: deployment
@@ -198,31 +197,6 @@ steps:
          --destination gitea.renner.uno/gitea_admin/review-bot:$TAG \
          --destination gitea.renner.uno/gitea_admin/review-bot:latest

-  # wlan-setup: the Go service behind wlan.renner.uno (802.1X/Passpoint setup page with per-device
-  # authentik app passwords). Runs after Gitea is up, so no ghcr mirror.
-  - name: build-wlan-setup
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
-    directory: wlan-setup
-    when:
-      - event: deployment
-      - event: push
-        path: ["wlan-setup/**", ".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=$(date +%Y-%m-%d-%H%M)
-      - |
-        /kaniko/executor \
-          --context . \
-          --dockerfile Containerfile \
-          --destination gitea.renner.uno/gitea_admin/wlan-setup:$TAG \
-          --destination gitea.renner.uno/gitea_admin/wlan-setup:latest
-
  # Runtime image, not CI tooling: a general-purpose alpine + jq base for
  # workloads that need to read JSON from a shell script. Named for what it IS,
  # not for who uses it — its first consumer is the zigbee2mqtt seed-data init
@@ -251,7 +225,7 @@ steps:
  #
  # The gitea_admin/ copy stays until nothing references it any more.
  - name: build-alpine-jq
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/alpine-jq
    when:
      - event: deployment
@@ -269,8 +243,7 @@ steps:
      - 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
-      # konairius/ gets one tag per build: Gitea's cleanup rule counts tags.
-      - TAG=$(date +%Y-%m-%d-%H%M)
+      - TAG=$(date +%Y-%m-%d)
      - |
        /kaniko/executor \
          --context . \
@@ -278,7 +251,9 @@ steps:
          --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 ghcr.io/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

  # Runtime image, not CI tooling: upstream containernetworking/plugins binaries
  # baked in, consumed by the multus cni-plugins-installer DaemonSet. Replaces a
@@ -302,7 +277,7 @@ steps:
  # note on build-alpine-jq. Anything an app needs while the cluster is still
  # being built cannot live only in that cluster's own registry.
  - name: build-cni-plugins
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/cni-plugins
    when:
      - event: deployment
@@ -320,8 +295,7 @@ steps:
      - 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
-      # konairius/ gets one tag per build: Gitea's cleanup rule counts tags.
-      - TAG=$(date +%Y-%m-%d-%H%M)
+      - TAG=$(date +%Y-%m-%d)
      - |
        /kaniko/executor \
          --context . \
@@ -329,7 +303,9 @@ steps:
          --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 ghcr.io/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

  # 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
@@ -342,7 +318,7 @@ steps:
  # gitea.renner.uno is not there to serve it. A cold-rebuild rehearsal left
  # paperless in Init:ErrImagePull on exactly this image.
  - name: build-alpine-openssl
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/alpine-openssl
    when:
      - event: deployment
@@ -360,8 +336,7 @@ steps:
      - 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
-      # konairius/ gets one tag per build: Gitea's cleanup rule counts tags.
-      - TAG=$(date +%Y-%m-%d-%H%M)
+      - TAG=$(date +%Y-%m-%d)
      - |
        /kaniko/executor \
          --context . \
@@ -369,7 +344,9 @@ steps:
          --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 ghcr.io/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

  # 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
@@ -377,7 +354,7 @@ steps:
  # Ansible converge. Not a ci-* image -- it is a runtime artifact -- but it
  # builds the same way and lands in the same registry so the audit sees it.
  - name: build-heating-can
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/heating-can
    when:
      - event: deployment
@@ -403,7 +380,7 @@ steps:
  # services (public Ingress hosts -> TLS passthrough -> Traefik ClusterIP).
  # Runtime artifact like heating-can; same registry so the audit tracks it.
  - name: build-netbird-service-sync
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/netbird-service-sync
    when:
      - event: deployment
@@ -428,7 +405,7 @@ steps:
  # authentik-gate-sync: the authentik-gate ingress class (Ingress -> Authentik
  # proxy gate + Traefik route). Its unit tests run as a stage of the image build.
  - name: build-authentik-gate-sync
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/authentik-gate-sync
    when:
      - event: deployment
@@ -454,7 +431,7 @@ steps:
  # kuma-sync: reconciles KumaMonitor resources into Uptime Kuma. Its unit
  # tests run as a stage of the image build.
  - name: build-kuma-sync
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/kuma-sync
    when:
      - event: deployment
@@ -480,7 +457,7 @@ steps:
  # cloudflare-lb-sync: reconciles CloudflareLoadBalancer resources into
  # Cloudflare. Its unit tests run as a stage of the image build.
  - name: build-cloudflare-lb-sync
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/cloudflare-lb-sync
    when:
      - event: deployment
@@ -506,7 +483,7 @@ steps:
  # bird: BGP daemon for the pod-network mesh over pod0 (#576). Runtime
  # artifact like heating-can; same registry so the audit tracks it.
  - name: build-bird
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/bird
    when:
      - event: deployment
@@ -530,7 +507,7 @@ steps:

  # Orchestrator for the monthly backup-verify CronJob (velero ns).
  - name: build-backup-verify
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/backup-verify
    when:
      - event: deployment
@@ -131,7 +131,7 @@ steps:
  #    --build-arg to the resolved version (not "latest") guarantees the tag and
  #    the image content agree even if a new release lands mid-run.
  - name: build
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/claude
    depends_on: [decide]
    environment:
@@ -172,7 +172,7 @@ steps:
  # whenever it trails the deployed server. If you bump the server, bump here.
  - name: woodpecker-lint
    depends_on: [] # see note above `steps:`
-    image: woodpeckerci/woodpecker-cli:v3.20.1-alpine@sha256:74c576faf49cce699825d11c7d7bd38ab5f007dd4f57cdbdd55099d2c0f2621a
+    image: woodpeckerci/woodpecker-cli:v3.19.0-alpine@sha256:27a77117e38d7bbdc380f0e90ff3ee4871ab1eefa78b5d9136a2c969fbecd9f4
    commands:
      - |
        set -eu
@@ -35,25 +35,25 @@ when:
 steps:
  - name: model-selection-tests
    depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.318
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
    commands:
      - sh scripts/ci/test-model-selection.sh

  - name: pr-review-mistral-tests
    depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.318
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
    commands:
      - sh scripts/ci/test-pr-review-mistral.sh

  - name: promtool-rules-guard-tests
    depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.318
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
    commands:
      - sh scripts/ci/test-promtool-rules.sh

  - name: yaml-citations-guard-tests
    depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.318
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
    commands:
      - sh scripts/ci/test-yaml-citations.sh

@@ -63,7 +63,7 @@ steps:
  # bridge, and the secret guard.
  - name: hermes-skill-tests
    depends_on: []
-    image: python:3.15-alpine@sha256:20a82dbc2783112ddb91d1534603f802d222a3e63e593cd002eb2ac534e70211
+    image: python:3.15-alpine@sha256:d44b1254cb92329418d164b22b20d86bbd3869d48e80e09e476531a409a728bb
    environment:
      PYTHONDONTWRITEBYTECODE: "1"
    commands:
@@ -26,7 +26,7 @@ steps:
    # fetch-models.sh response mapping. No cluster, no secrets, no network — the
    # ci-claude image just provides sh + jq. Keeps the flag-injection regression
    # test from rotting (it exercises the exact injection shapes).
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.318
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
    commands:
      - sh scripts/ci/test-model-selection.sh

@@ -1,5 +1,5 @@
 # Builds ci/images/hermes (nousresearch/hermes-agent plus the agent's CLIs) as
-# gitea.renner.uno/konairius/hermes:YYYY-MM-DD-HHMM, one tag per build.
+# gitea.renner.uno/konairius/hermes:build.<unix-ts> and :latest.
 when:
  - event: push
    branch: main
@@ -10,7 +10,7 @@ when:

 steps:
  - name: build
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.20-debug@sha256:28af5a3bd9c51fedb353ad91de735eda53592b5c06a34e7f5a9550334725d7f7
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
    directory: ci/images/hermes
    environment:
      # registry-bot write:package PAT (konairius org secret).
@@ -20,9 +20,10 @@ steps:
      - mkdir -p /kaniko/.docker
      - AUTH=$(printf '%s:%s' registry-bot "$GITEA_TOKEN" | base64 | tr -d '\n')
      - printf '{"auths":{"gitea.renner.uno":{"auth":"%s"}}}' "$AUTH" > /kaniko/.docker/config.json
-      - TAG=$(date +%Y-%m-%d-%H%M)
+      - TAG="build.$(date +%s)"
      - |
        /kaniko/executor \
          --context . \
          --dockerfile Containerfile \
-          --destination gitea.renner.uno/konairius/hermes:$TAG
+          --destination gitea.renner.uno/konairius/hermes:$TAG \
+          --destination gitea.renner.uno/konairius/hermes:latest
@@ -6,7 +6,7 @@ when:

 steps:
  - name: go-test
-    image: golang:1.27.3-bookworm@sha256:d9b6a1beb9474adc2a1ce842573639b44b2a0dd49b6669f51d3821baf9ec37c9
+    image: golang:1.27.3-bookworm@sha256:972b4110ba0f47539a975c31e52c64765e1ff19f2d74469ae4a595c6676e80a5
    commands:
      - test -z "$(gofmt -l review-bot)"
      - go -C review-bot vet ./...
@@ -70,7 +70,7 @@ steps:
    # this step is skipped — otherwise we'd fork-bomb PRs.
    when:
      - branch: main
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.318
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
    environment:
      CLAUDE_CODE_OAUTH_TOKEN:
        from_secret: claude_code_oauth_token
@@ -30,7 +30,7 @@ when:

 steps:
  - name: update-audit-agent
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.318
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.311
    environment:
      CLAUDE_CODE_OAUTH_TOKEN:
        from_secret: claude_code_oauth_token
@@ -1,13 +0,0 @@
-# Tests for the wlan-setup Go service (wlan-setup/). Offline: the tests run against a fake
-# authentik server, so the step needs no secret and no network beyond the module cache.
-when:
-  - event: pull_request
-    path: ["wlan-setup/**", ".woodpecker/wlan-setup-test.yml"]
-
-steps:
-  - name: go-test
-    image: golang:1.27.3-bookworm@sha256:d9b6a1beb9474adc2a1ce842573639b44b2a0dd49b6669f51d3821baf9ec37c9
-    commands:
-      - test -z "$(gofmt -l wlan-setup)"
-      - go -C wlan-setup vet ./...
-      - go -C wlan-setup test -race ./...
@@ -1,17 +1,13 @@
 # edge-host — bare-metal Arch thin client (replaces the k8s-edge Talos VM)

 Runs the hardware-bound services that used to be pinned to the `k8s-edge`
-Talos node (opentofu `vm_153_k8s_edge.tf`):
+Talos node (opentofu `vm_153_k8s_edge.tf`), plus the new CAN bridge:

 | Service | How it runs | Hardware | Talks to |
 |---|---|---|---|
 | zwave-js-ui | docker compose | ZWA-2 Z-Wave USB radio | HA `zwave_js` via ws://:3000, UI :8091 |
 | sml2mqtt | docker compose | FTDI FT230X meter reader | Mosquitto (`sml2mqtt` user) |
-
-The Viessmann E3 CAN bus is not read by an edge host: the ESP32 gateway
-`vitocal-can` (open3e-esp32) at the Vitocal publishes `open3e/#` directly to
-the cluster broker. `plays/install-edge-host.yml` removes the former
-heating-can stack and the can0 configuration from edge hosts.
+| open3e | venv + systemd | Innomaker USB2CAN (gs_usb) | Mosquitto (`open3e` user) |

 Everything else that once lived on k8s-edge (HA core, matter-server, OTBR,
 music-assistant) already moved to the general node pool and stays in the
@@ -23,13 +19,17 @@ The deployed unit is a **Dell Wyse 3040** (Atom x5-Z8350, 2 GB RAM) on a
 flash-wear handling that hardware implies. The installer also supports an
 N100/NVMe box; it autodetects the target disk, so either works.

+Rationale for leaving Kubernetes for the CAN part: the stock Talos kernel
+ships with `CONFIG_CAN` unset (siderolabs/talos#7686), so SocketCAN cannot
+work in any pod without a custom kernel image per Talos release.
+
 ## Base install (once, from the edge-host installer ISO)

 Build and boot the dedicated installer image — see
 `images/edge-host-iso/README.md`. Short version:

 1. `sudo pacman -S archiso && sudo images/edge-host-iso/build.sh`
-2. Write ISO to a USB stick, boot the target box from it, run `edge-install <hostname>`
+2. Write ISO to a USB stick, boot the target box from it, run `edge-install`
   (partitions the internal disk — NVMe if present, else the eMMC; the
   installer autodetects — installs the ansible-ready base system with SSH
   keys, DHCP, docker — asks for confirmation before wiping).
@@ -58,18 +58,24 @@ inventory change.

 | device | group | playbook |
 |---|---|---|
+| Innomaker USB2CAN (Vitocal/VX3 + E380) | `heating_can` | `plays/install-heating-can.yml` |
 | Nabu Casa ZWA-2 Z-Wave radio | `zwave_gateway` | `plays/install-zwave-gateway.yml` |

-Add the host to the matching group, then run that playbook. It depends on
-the base play having run: it needs docker.
+Add the host to the matching group, then run that playbook. They depend on
+the base play having run: all three need the local MQTT bridge, and two of
+them need docker.

-A host with nothing attached is simply absent from these groups and needs
+A host with nothing attached is simply absent from all three groups and needs
 none of these commands.

 ## Secrets (before first play run)

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

 ```
 # zwave-js session secret
@@ -78,6 +84,7 @@ kubectl -n home-assistant get secret zwave-js-session -o jsonpath='{.data.sessio

 ```yaml
 # vault.yml
+vault_edge_open3e_mqtt_password: "..."
 vault_edge_zwavejs_session_secret: "..."
 vault_edge_loki_password: "..."   # dedicated edge-1 Loki push cred (see "Logging & eMMC")
 ```
@@ -95,6 +102,9 @@ The Z-Wave network keys do NOT need separate handling — they live in

 Preparation:
 - [ ] `vault.yml` populated (above), play runs green against edge-1
+- [ ] CAN: Innomaker adapter connected to the VX3 external CAN port,
+      `ip -details link show can0` shows `state ERROR-ACTIVE bitrate 250000`,
+      `candump can0 -n 5` shows frames

 zwave-js (order matters — never two servers on one radio):
 - [ ] Copy the store out of the PVC while the pod still runs:
@@ -112,6 +122,11 @@ sml2mqtt:
      port, Wh stays Wh) → remove sml2mqtt from the home-assistant
      kustomization in the follow-up PR

+open3e:
+- [ ] Stop any workstation listener (ONE instance per bus, hard rule)
+- [ ] Move the USB2CAN adapter, `systemctl start open3e`
+- [ ] Topics under `open3e/#` update on the broker
+
 Afterwards:
 - [ ] Retire VM 153: remove `vm_153_k8s_edge.tf`, `talos/patches/k8s-edge.yaml`,
      node from the cluster (`kubectl delete node k8s-edge`, tofu apply)
@@ -119,13 +134,22 @@ Afterwards:

 ## Day-2 notes

- Image bumps: Renovate opens a PR for `edge_*_image` in
-  `roles/*/defaults/main.yml` (tag + digest, `customManagers` in
-  `renovate.json`). No pipeline deploys to edge-1, so after the merge run
-  `ansible-playbook plays/install-zwave-gateway.yml` from `ansible/` on a
-  mesh-connected workstation. The play reads the image's Alpine release
-  itself and rebuilds the preloaded `.so` when it changes (see
-  "Logging & eMMC" → zwave-js).
+- Image bumps: edit `edge_zwavejs_image` / `edge_sml2mqtt_image` in
+  defaults and re-run the play (no flux image-automation out here —
+  deliberate for sml2mqtt, acceptable for zwave-js). If a zwave-js bump
+  changes its Alpine major, also update `edge_zwave_alpine_base` and refresh
+  the preloaded `.so` (see "Logging & eMMC" → zwave-js).
+- open3e / E3onCAN updates: both are pinned to commits in
+  `roles/heating-can/defaults/main.yml`, so re-running the play does NOT pick
+  up upstream changes -- that is deliberate, these drive the heat pump. The
+  weekly update-audit reports when either falls behind (see
+  `ci/agents/update-audit/prompt.md`); bump the pin and re-run.
+  Pinning to a tag is not an option for open3e: it publishes none.
+- Ad-hoc CAN scans: `systemctl stop open3e` first (single-instance rule),
+  restart afterwards.
+- can-utils (`candump`) is AUR-only on Arch — install manually via
+  `pamac build can-utils` if needed for debugging; the role deliberately
+  doesn't manage AUR packages.

 ## Logging & eMMC

@@ -138,9 +162,7 @@ role keeps logs off local flash and monitors wear:
 - **Docker logs to journald** (`docker-daemon.json`, `log-driver: journald`)
  instead of unbounded json files under `/var/lib/docker/containers`. Both
  compose services inherit it; `docker logs` still works.
- **Grafana Alloy ships the journal to Loki** (`edge-alloy.service`, which
-  runs the upstream `grafana/alloy` image with `/run/log/journal` mounted
-  read-only; Arch's `grafana-alloy` package has no `loki.source.journal`). Its
+- **Grafana Alloy ships the journal to Loki** (`edge-alloy.service`). Its
  WAL/positions sit on `/run/alloy` (tmpfs), so the agent writes nothing to
  the eMMC either. Net effect: no log writes hit local flash — the trade-off
  is that logs are RAM-only and lost on reboot unless already shipped.
@@ -168,7 +190,7 @@ journal commit).

 - **Fix:** the `zwave-js` container preloads **`libeatmydata`**
  (`LD_PRELOAD=/usr/lib/libeatmydata.so`, mounted read-only from
-  `zwave-js/libeatmydata-alpine<X.Y>.so`). This makes `fsync`/`fdatasync` no-ops *for that
+  `zwave-js/libeatmydata.so`). This makes `fsync`/`fdatasync` no-ops *for that
  one process*, so the kernel batches the writes via normal writeback (~30 s)
  instead of forcing each one. The WS/MQTT value stream to Home Assistant and
  the on-disk cache are **unchanged** — full data resolution, no re-interview
@@ -177,9 +199,9 @@ journal commit).
  batch it); the only mount-level alternative is putting the cache on tmpfs,
  which makes the *whole* store volatile → re-interview on every restart.
 - **The `.so` is musl** (the image is Alpine-based), extracted from
-  `alpine:<X.Y>`, where `X.Y` is read from the image's `/etc/alpine-release`
-  on every run. A new Alpine release gives a new file name, so the play
-  extracts it, recreates the container and deletes the old file.
+  `edge_zwave_alpine_base` — keep that var in sync with the image's Alpine
+  version; to refresh after a major bump, `rm zwave-js/libeatmydata.so` and
+  re-run.
 - **Durability guard:** because `fsync` is neutralized, a hard power-loss
  during the (rare) settings write could truncate `settings.json`, which holds
  the **Z-Wave network keys**. `edge-zwave-settings-backup.timer` keeps a
@@ -189,3 +211,47 @@ journal commit).
 - Verify the drop with the eMMC-write sampling described above; roll back by
  removing the `LD_PRELOAD` env + `.so` mount from the compose file.

+## MQTT bridge (TLS to the cluster broker)
+
+open3e, e3oncan and sml2mqtt do **not** publish to the cluster broker directly.
+They connect to a **local mosquitto on loopback** (`127.0.0.1:1883`,
+`edge_mqtt_host`), which **bridges to the cluster broker over TLS**
+(`mqtt.renner.uno:8883`). Two reasons:
+
+- **Security:** open3e and e3oncan have no native MQTTS support (their MQTT
+  code does a plain `connect()`), so they can't use the broker's 8883 TLS
+  listener. Terminating TLS in the local broker keeps their plaintext MQTT on
+  loopback only — off the untrusted IoT VLAN — while the actual network hop is
+  encrypted. The public Let's Encrypt cert is validated against the system CA
+  bundle (`edge_mqtt_bridge_cafile`); no cert distribution needed.
+- **Availability:** the local broker buffers telemetry (in RAM) if the cluster
+  broker is briefly unreachable, and flushes on reconnect — edge-1 no longer
+  hard-depends on cluster/network uptime for every publish.
+
+The local broker is `allow_anonymous` on loopback — the trust boundary is the
+host; nothing off-host can reach it.
+
+**Bridge credential (REN-1307).** One bridge `connection` logs in as the
+register account `edge-1` (`kubernetes/apps/home-assistant/mqtt-accounts.yaml`)
+and carries `open3e/#` out and `open3e/cmnd` back. The cluster broker does not
+accept the vault-password bridges in `bridge.d/legacy.conf`, which exists only
+until the first push. Its password is pushed
+by mqtt-account-controller to `edge-mqtt-cred` (`:8443`, the controller's
+esp32 API over HTTPS). That endpoint accepts only a client certificate from
+the MQTT CA with CN `mqtt-account-controller`; edge-1 holds the public CA and
+its own server key, nothing else. On a push it writes
+`/etc/mosquitto/bridge.d/edge-1.conf`, deletes `bridge.d/legacy.conf` and
+restarts the local mosquitto. The controller sets a new password whenever the
+bridge reports "not connected" (also after a reinstall), so no play run is
+needed for a rotation. Diagnosis: `journalctl -u
+edge-mqtt-cred`, and `mosquitto_sub -t '$SYS/broker/connection/edge-1/state'`
+(retained `1` = connected).
+
+**eMMC:** the local broker writes **nothing** to flash — `persistence false`
+(retained/queued messages in RAM) and `log_dest stdout` (to the volatile
+journal → Loki). Do not add persistence or log-file settings to
+`edge-mqtt-bridge.conf.j2`.
+
+Rollback: point `edge_mqtt_host` back to `mqtt.renner.uno` and re-run (clients
+reconnect directly on 1883). Config: `edge-mqtt-bridge.conf.j2` →
+`/etc/mosquitto/mosquitto.conf`.
@@ -2,6 +2,7 @@
 # Secret indirection — real values live in vault.yml (ansible-vault) next
 # to this file; see docs/edge-host.md for how to populate it from
 # the cluster secrets.
+edge_open3e_mqtt_password: "{{ vault_edge_open3e_mqtt_password }}"
 edge_zwavejs_session_secret: "{{ vault_edge_zwavejs_session_secret }}"
 # Loki push credential (dedicated 'edge-1' user, Traefik basic-auth on the
 # loki.renner.uno ingress; the matching htpasswd line lives in the cluster
@@ -35,8 +36,25 @@ keepalived_ntp_sysctl:
 # Realtek NIC on the Wyse 3040 has no hardware timestamping.
 chrony_hwtimestamp: false

+# --- Local MQTT contract -------------------------------------------------
+# Shared between the broker and its clients, so it belongs to the inventory
+# rather than to either side's role. mqtt-bridge listens here; heating-can
+# publishes here; and the bridge authenticates to the cluster
+# broker AS the open3e user, so it needs that identity too.
+#
+# Keeping these in one role's defaults only worked while a single play loaded
+# every role at once. Splitting the plays by capability exposed it: the bridge
+# could not render without a heating-can default, and the CAN services could
+# not render without an mqtt-bridge default.
+edge_mqtt_host: 127.0.0.1
+edge_mqtt_port: 1883
+edge_open3e_mqtt_user: open3e
+edge_open3e_mqtt_topic: open3e
+
 # Units claude-bot may restart (ssh-ca role); the containers go through docker.
 ssh_ca_claude_sudo_units:
+  - mosquitto
+  - edge-mqtt-cred
  - edge-alloy
  - keepalived
  - chronyd
@@ -8,7 +8,7 @@
 # two plays over this group -- withdraw the static assignments fleet-wide, then
 # hand the address to keepalived -- and both need the same value. Duplicating a
 # service address across plays is exactly the sort of thing that drifts.
-ntp_vip6: "fd02:40::123/128"
+ntp_vip6: "fd40::123/128"

 # Link-local address carried as the FIRST virtual_ipaddress of the IPv6 VRRP
 # instance. RFC 5798 gives an IPv6 virtual router a link-local primary, and
@@ -1,8 +0,0 @@
---
-# DSM's own python3 is 3.8; plays/configure-synology-python.yml installs this.
-ansible_python_interpreter: /var/packages/Python3.9/target/usr/bin/python3.9
-# DSM offers no sftp/scp.
-ansible_ssh_transfer_method: piped
-
-# claude-bot is a DSM administrator here; its password is unknown.
-ssh_ca_claude_sudo_all: true
@@ -8,6 +8,8 @@
 #   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]
@@ -18,16 +20,10 @@ proxy-1.renner.uno ansible_host=proxy-1.nb.renner.uno ansible_user=root
 proxy-2.renner.uno ansible_host=proxy-2.nb.renner.uno ansible_user=root

 # Every bare-metal edge thin client. Gets the host-generic roles only:
-# flash-wear handling, the log shipper, the VLAN sub-interface. Nothing here
-# assumes any peripheral is attached.
+# flash-wear handling, the log shipper, the MQTT bridge, the VLAN
+# sub-interface. Nothing here assumes any peripheral is attached.
 [edge_host]
 edge-1.iot.renner.uno ansible_user=root
-edge-2.iot.renner.uno ansible_user=root
-
-# Synology NAS (DSM): nas-1 RS1221+ on site, nas-2 DS1522+ off site.
-[synology_nas]
-nas-1.renner.uno ansible_user=root
-nas-2.renner.uno ansible_user=root

 # Capability groups. Membership states which hardware a host physically has,
 # and each service playbook targets the group for its own concern. No flags and
@@ -37,18 +33,32 @@ nas-2.renner.uno ansible_user=root
 # These are children of [edge_host], declared below: a peripheral is added to an
 # edge client, it does not replace the base. Making that a :children relation
 # rather than a comment means a host added only to a capability group still
-# resolves group_vars/edge_host.
+# resolves group_vars/edge_host -- where the local MQTT contract lives -- so it
+# cannot silently come up without edge_mqtt_host and friends.
 [zwave_gateway]
 edge-1.iot.renner.uno

+[heating_can]
+edge-1.iot.renner.uno
+
 [edge_host:children]
 zwave_gateway
+heating_can

-# NTP servers: every edge host (edge-1 BACKUP prio 70, edge-2 BACKUP prio 60;
-# see the ntp_servers map in plays/install-ntp-ha.yml). Talos nodes cannot run
-# chrony or keepalived. The jupiter/saturn/neptune entries in that map
-# describe retired PVE hosts. See plays/install-ntp-ha.yml for why keepalived
-# is scoped more narrowly than chrony within this group.
+# NTP servers. edge-1 was added here so the role would survive the PVE hosts
+# being retired for bare-metal Talos, which cannot run chrony or keepalived
+# itself. That retirement has now happened, so edge-1 is the ONLY member.
+#
+# THIS IS NO LONGER HIGHLY AVAILABLE. The group was jupiter (MASTER, prio 100),
+# saturn (90), neptune (80) and edge-1 (BACKUP, 70); the first three are gone.
+# A single VRRP member takes the address regardless of its configured state, so
+# fd40::123 is still served — verified answering — but by one thin client with
+# no failover behind it. install-ntp-ha.yml still carries the four-host
+# ntp_servers priority map, which now describes hosts that do not exist.
+#
+# Restoring redundancy needs a second chrony host that is not a Talos node.
+# See plays/install-ntp-ha.yml for why keepalived is scoped more narrowly than
+# chrony within this group.
 [ntp_cluster:children]
 edge_host

@@ -60,9 +70,6 @@ proxy-1.renner.uno
 proxy-2.renner.uno
 netbird.renner.uno
 edge-1.iot.renner.uno
-edge-2.iot.renner.uno
-nas-1.renner.uno
-nas-2.renner.uno

 # Hosts whose admin logins accept only ssh_admin_authorized_keys (break-glass);
 # everything else needs a CA certificate. Members must be in [ssh_ca].
@@ -1,19 +0,0 @@
---
-# Ansible needs Python >= 3.9 on the target; DSM ships 3.8. Synology's
-# Python3.9 package installs beside it. raw, because the modules cannot run
-# before it is there; raw is skipped in check mode.
- name: Install Python 3.9 on the Synology NAS
-  hosts: synology_nas
-  become: true
-  gather_facts: false
-  tasks:
-    - name: Install the Python3.9 package
-      ansible.builtin.raw: >-
-        if [ -x {{ ansible_python_interpreter }} ]; then echo present;
-        else /usr/syno/bin/synopkg install_from_server Python3.9; fi
-      register: synology_python_install
-      changed_when: "'present' not in synology_python_install.stdout"
-
-    - name: Check the interpreter exists
-      ansible.builtin.raw: test -x {{ ansible_python_interpreter }}
-      changed_when: false
@@ -0,0 +1,70 @@
+---
+# Configure VMs to use host time sync via kvm-clock
+# Disables systemd-timesyncd to prevent NTP conflicts
+#
+# VMs get time from Proxmox host via kvm-clock paravirtualized clock
+# This is more accurate and reliable than network NTP for VMs
+
+- name: Configure VM time synchronization from host
+  hosts: all
+  become: yes
+  gather_facts: yes
+
+  tasks:
+    - name: Check if running as VM (not LXC)
+      stat:
+        path: /sys/devices/system/clocksource/clocksource0/current_clocksource
+      register: clocksource_file
+
+    - name: Get current clock source
+      slurp:
+        src: /sys/devices/system/clocksource/clocksource0/current_clocksource
+      register: clocksource
+      when: clocksource_file.stat.exists
+
+    - name: Display clock source
+      debug:
+        msg: "Clock source: {{ (clocksource.content | b64decode | trim) if clocksource_file.stat.exists else 'N/A (LXC)' }}"
+
+    - name: Check if systemd-timesyncd is installed
+      command: systemctl list-unit-files systemd-timesyncd.service
+      register: timesyncd_installed
+      check_mode: false
+      failed_when: false
+      changed_when: false
+
+    - name: Stop and disable systemd-timesyncd on VMs using kvm-clock
+      systemd:
+        name: systemd-timesyncd
+        state: stopped
+        enabled: no
+      when:
+        - clocksource_file.stat.exists
+        - clocksource.content is defined
+        - "'kvm-clock' in (clocksource.content | b64decode)"
+        - "'systemd-timesyncd.service' in timesyncd_installed.stdout"
+
+    - name: Mask systemd-timesyncd to prevent re-enabling
+      systemd:
+        name: systemd-timesyncd
+        masked: yes
+      when:
+        - clocksource_file.stat.exists
+        - clocksource.content is defined
+        - "'kvm-clock' in (clocksource.content | b64decode)"
+        - "'systemd-timesyncd.service' in timesyncd_installed.stdout"
+
+    - name: Verify time sync status
+      command: timedatectl show --property=NTPSynchronized
+      register: timesync_status
+      check_mode: false
+      changed_when: false
+      failed_when: false
+
+    - name: Display final status
+      debug:
+        msg: |
+          Host: {{ inventory_hostname }}
+          Type: {{ 'VM (kvm-clock)' if (clocksource_file.stat.exists and 'kvm-clock' in (clocksource.content | b64decode | default(''))) else 'LXC/Other' }}
+          Time sync: {{ timesync_status.stdout | default('unknown') }}
+          Note: VMs sync time from Proxmox host, LXCs inherit host time automatically
@@ -8,6 +8,7 @@
 # their own inventory groups:
 #
 #   plays/install-zwave-gateway.yml   [zwave_gateway]   ZWA-2 radio
+#   plays/install-heating-can.yml     [heating_can]     Innomaker USB2CAN
 #
 # Splitting the roles without splitting the plays would have kept the coupling:
 # one play applying every role to one group is the monolith again, a layer up.
@@ -30,96 +31,11 @@
  # do not silently depend on the connection user staying privileged.
  become: true

-  # The Viessmann E3 CAN bus is read by vitocal-can (open3e-esp32 at the
-  # Vitocal), which publishes to the cluster broker itself, not by an edge
-  # host. These remove the former heating-can stack, the can0 configuration
-  # and the open3e MQTT bridge (loopback mosquitto + edge-mqtt-cred); each is
-  # a no-op where they are absent.
-  pre_tasks:
-    - name: Read the service list
-      ansible.builtin.service_facts:
-
-    - name: Stop and disable the retired MQTT bridge services
-      ansible.builtin.systemd:
-        name: "{{ item }}"
-        state: stopped
-        enabled: false
-      loop:
-        - edge-mqtt-cred
-        - mosquitto
-      when: (item ~ '.service') in ansible_facts.services
-
-    - name: Remove the retired MQTT bridge files
-      ansible.builtin.file:
-        path: "{{ item }}"
-        state: absent
-      loop:
-        - /etc/systemd/system/edge-mqtt-cred.service
-        - /usr/local/sbin/edge-mqtt-cred
-        - /etc/edge-mqtt-cred
-        - /etc/mosquitto
-      register: edge_mqtt_bridge_files
-
-    - name: Reload systemd without the edge-mqtt-cred unit
-      ansible.builtin.systemd:
-        daemon_reload: true
-      when: edge_mqtt_bridge_files.changed
-
-    - name: Uninstall mosquitto
-      ansible.builtin.package:
-        name: mosquitto
-        state: absent
-
-    - name: Check for the retired heating-can compose project
-      ansible.builtin.stat:
-        path: /opt/edge-host/heating-can/docker-compose.yml
-      register: edge_heating_can_compose
-
-    - name: Stop and remove the retired heating-can containers and image
-      ansible.builtin.command:
-        cmd: docker compose down --remove-orphans --rmi all
-        chdir: /opt/edge-host/heating-can
-      when: edge_heating_can_compose.stat.exists
-      changed_when: true
-
-    - name: Remove the retired heating-can directory
-      ansible.builtin.file:
-        path: /opt/edge-host/heating-can
-        state: absent
-
-    - name: Remove the can0 networkd configuration
-      ansible.builtin.file:
-        path: /etc/systemd/network/80-can0.network
-        state: absent
-      register: edge_can0_network
-
-    - name: Reload networkd without the can0 configuration
-      ansible.builtin.command:
-        cmd: networkctl reload
-      when: edge_can0_network.changed
-      changed_when: true
-
-    - name: Read the can0 link flags
-      ansible.builtin.command:
-        cmd: ip -o link show can0
-      register: edge_can0_link
-      check_mode: false
-      changed_when: false
-      failed_when: false
-
-    - name: Take can0 down
-      ansible.builtin.command:
-        cmd: ip link set can0 down
-      when:
-        - edge_can0_link.rc == 0
-        - edge_can0_link.stdout is search('[<,]UP[,>]')
-      changed_when: true
-
  roles:
    - certificates
    - common
-    - pacman-cache
    - edge-flash-wear
    - docker-install
    - edge-log-shipper
+    - mqtt-bridge
    - edge-vlan
@@ -0,0 +1,18 @@
+---
+# Heating system over the Viessmann E3 CAN bus, for hosts with the Innomaker
+# USB2CAN adapter attached.
+#
+# Targets [heating_can]: membership means the adapter is physically present.
+# Two roles because they are two concerns -- the interface is host network
+# state, the services consume it -- but one group, because both need the same
+# hardware.
+#
+# Requires the base play (plays/install-edge-host.yml) to have run: these
+# services publish to the local MQTT bridge it sets up.
+- name: Install heating CAN services
+  hosts: heating_can
+  become: true
+
+  roles:
+    - socketcan
+    - heating-can
@@ -22,7 +22,6 @@
  become: true
  roles:
    - common
-    - timesyncd
    - docker-install
    - netbird-proxy
    - netbird-proxy-watchdog
@@ -16,6 +16,5 @@
  become: true
  roles:
    - common
-    - timesyncd
    - docker-install
    - netbird-server
@@ -62,7 +62,7 @@
  # One node at a time. The keepalived role withdraws the statically assigned
  # IPv6 service address and restarts keepalived so the address is re-taken
  # under VRRP control; doing that across every NTP server at once would leave
-  # the whole fleet with nobody holding the service address until the elections settle.
+  # the whole fleet with nobody holding fd40::123 until the elections settle.
  # Serialised, the remaining members keep answering throughout.
  serial: 1

@@ -83,9 +83,6 @@
      edge-1.iot.renner.uno:
        priority: 70
        state: "BACKUP"
-      edge-2.iot.renner.uno:
-        priority: 60
-        state: "BACKUP"

  roles:
    - role: chrony-ntp-server
@@ -4,7 +4,7 @@
 # Networks allowed to use this server as NTP source.
 #
 # BOTH families are required. IPv6 is the primary address family here -- the
-# service address ntp.srv.renner.uno resolves to fd02:40::123 -- so an IPv4-only
+# service address ntp.srv.renner.uno resolves to fd40::123 -- so an IPv4-only
 # allow list refuses every client that uses the documented name.
 #
 # The hosts carried `allow fd00::/8` for a long time without it ever being in
@@ -8,11 +8,12 @@
  lineinfile:
    path: /etc/hosts
    regexp: '^127\.0\.1\.1\s+{{ inventory_hostname }}'
-    line: "{{ ansible_facts['default_ipv4']['address'] }} {{ inventory_hostname }} {{ inventory_hostname_short | default(inventory_hostname.split('.')[0]) }}"
+    line: "{{ ansible_default_ipv4.address }} {{ inventory_hostname }} {{ inventory_hostname_short | default(inventory_hostname.split('.')[0]) }}"
    state: present
  when:
-    - ansible_facts['virtualization_type'] == 'lxc'
-    - ansible_facts['default_ipv4']['address'] is defined
+    - ansible_virtualization_type is defined
+    - ansible_virtualization_type == 'lxc'
+    - ansible_default_ipv4.address is defined

 # -------------------------------------------------------
 # 1. Install Common Packages
@@ -54,9 +55,18 @@
 # via plays/configure-ssh-ca.yml.

 # -------------------------------------------------------
-# 5. Time sync
+# 5. Disable NTP on VMs/LXC (use host time)
 # -------------------------------------------------------
-# Moved to separate roles: timesyncd (internet VPS), chrony-ntp-server (edge).
+- name: Stop and disable systemd-timesyncd on VMs/LXC
+  systemd:
+    name: systemd-timesyncd
+    state: stopped
+    enabled: no
+    masked: yes
+  when:
+    - ansible_virtualization_type is defined
+    - ansible_virtualization_type in ['kvm', 'lxc']
+  ignore_errors: yes

 # -------------------------------------------------------
 # 6. Certificates
@@ -15,8 +15,6 @@
 # amd64 asset for exactly this tag.
 crowdsec_bouncer_version: v0.0.36
 crowdsec_bouncer_sha256: f86e4b72693549d99f40a9402abefb894108f047a3fbe6e72fada25ee17ce88b
-# Controller cache for the release archive; it outlives /tmp cleanups.
-crowdsec_bouncer_download_dir: "{{ lookup('ansible.builtin.env', 'HOME') }}/.cache/ansible/crowdsec"

 # The LAPI over the public path these hosts already serve, see
 # kubernetes/infrastructure/crowdsec/lapi-ingress.yaml. The proxies cannot
@@ -32,23 +32,13 @@
 # The controller has v4, so it does the fetching. The checksum is verified
 # there, before anything is copied to a host. Also in check mode: the fetch
 # only writes on the controller, and the copy below needs the file.
- name: Create the controller download directory
-  ansible.builtin.file:
-    path: "{{ crowdsec_bouncer_download_dir }}"
-    state: directory
-    mode: "0755"
-  delegate_to: localhost
-  become: false
-  run_once: true
-  check_mode: false
-
 - name: Fetch the pinned bouncer release on the controller
  check_mode: false
  ansible.builtin.get_url:
    url: >-
      https://github.com/crowdsecurity/cs-firewall-bouncer/releases/download/{{
      crowdsec_bouncer_version }}/crowdsec-firewall-bouncer-linux-amd64.tgz
-    dest: "{{ crowdsec_bouncer_download_dir }}/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}.tgz"
+    dest: /tmp/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}.tgz
    checksum: sha256:{{ crowdsec_bouncer_sha256 }}
    mode: "0644"
  delegate_to: localhost
@@ -63,7 +53,7 @@
 # host.
 - name: Copy the bouncer archive to the host
  ansible.builtin.copy:
-    src: "{{ crowdsec_bouncer_download_dir }}/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}.tgz"
+    src: /tmp/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}.tgz
    dest: /opt/crowdsec-firewall-bouncer-{{ crowdsec_bouncer_version }}.tgz
    mode: "0644"

@@ -7,9 +7,7 @@

 edge_alloy_config_file: /etc/alloy/edge.alloy
 edge_alloy_http_port: 12345
-# Upstream image: Arch's grafana-alloy 1.21 is built without
-# loki.source.journal. Renovate-tracked (customManagers in renovate.json).
-edge_alloy_image: grafana/alloy:v1.21.3@sha256:8ab871206bd2d8f89277f53abffee5f452a293980788d52f85fa183a87a505a4
+edge_alloy_bin: /usr/bin/grafana-alloy   # Arch `grafana-alloy` pkg names the binary this, not `alloy`
 edge_loki_push_url: "https://loki.renner.uno/loki/api/v1/push"
 edge_loki_username: edge-1
 edge_alloy_labels:
@@ -6,18 +6,15 @@
 # directly, so one journal source covers everything. Alloy s storage/WAL sits
 # on /run (tmpfs) so it does not write to flash either.

-# Alloy runs from the upstream image (see edge-alloy.service); the Arch package
-# lacks journal support.
- name: Remove the grafana-alloy package
+- name: Install grafana-alloy
  ansible.builtin.package:
    name: grafana-alloy
-    state: absent
+    state: present

 - name: Create alloy system group
  ansible.builtin.group:
    name: alloy
    system: true
-  register: edge_alloy_group

 - name: Create alloy system user
  ansible.builtin.user:
@@ -27,25 +24,6 @@
    system: true
    create_home: false
    shell: /usr/bin/nologin
-  register: edge_alloy_user
-
- name: Look up the systemd-journal group
-  ansible.builtin.getent:
-    database: group
-    key: systemd-journal
-
- name: Set the container identity
-  ansible.builtin.set_fact:
-    edge_alloy_uid: "{{ edge_alloy_user.uid }}"
-    edge_alloy_gid: "{{ edge_alloy_group.gid }}"
-    edge_alloy_journal_gid: "{{ ansible_facts.getent_group['systemd-journal'][1] }}"
-
- name: Pull the alloy image
-  ansible.builtin.command:
-    argv: [docker, pull, "{{ edge_alloy_image }}"]
-  register: edge_alloy_pull
-  changed_when: "'Downloaded newer image' in edge_alloy_pull.stdout"
-  notify: Restart alloy

 - name: Create alloy config directory
  ansible.builtin.file:
@@ -1,35 +1,32 @@
 [Unit]
-Description=Grafana Alloy (journal -> Loki)
+Description=Grafana Alloy (edge-1 log shipper -> Loki)
 Documentation=https://grafana.com/docs/alloy/
-After=docker.service network-online.target
-Requires=docker.service
+After=network-online.target
 Wants=network-online.target

 [Service]
 Type=simple
-# WAL + positions on tmpfs so the agent never writes to the eMMC.
-ExecStartPre=/usr/bin/install -d -o alloy -g alloy -m 0750 /run/alloy
-ExecStartPre=-/usr/bin/docker rm -f edge-alloy
-# Attached run with --log-driver none: the container's output reaches the
-# journal once, through this unit.
-ExecStart=/usr/bin/docker run --rm --name edge-alloy \
-  --log-driver none \
-  --network host \
-  --user {{ edge_alloy_uid }}:{{ edge_alloy_gid }} \
-  --group-add {{ edge_alloy_journal_gid }} \
-  --read-only --tmpfs /tmp \
-  --cap-drop ALL --security-opt no-new-privileges \
-  -v /run/log/journal:/run/log/journal:ro \
-  -v /etc/machine-id:/etc/machine-id:ro \
-  -v {{ edge_alloy_config_file }}:/etc/alloy/config.alloy:ro \
-  -v /run/alloy:/var/lib/alloy \
-  {{ edge_alloy_image }} run \
+User=alloy
+Group=alloy
+# Read the (volatile) systemd journal.
+SupplementaryGroups=systemd-journal
+# WAL + positions on tmpfs so the agent never writes to the eMMC. %t is the
+# runtime dir root (/run); RuntimeDirectory creates /run/alloy owned by us.
+RuntimeDirectory=alloy
+ExecStart={{ edge_alloy_bin }} run \
  --server.http.listen-addr=127.0.0.1:{{ edge_alloy_http_port }} \
-  --storage.path=/var/lib/alloy \
-  /etc/alloy/config.alloy
-ExecStop=/usr/bin/docker stop edge-alloy
-Restart=always
+  --storage.path=%t/alloy \
+  {{ edge_alloy_config_file }}
+ExecReload=/bin/kill -HUP $MAINPID
+Restart=on-failure
 RestartSec=10s
+LimitNOFILE=65536
+
+# Hardening (bare metal, no LXC namespace limits here).
+NoNewPrivileges=yes
+ProtectSystem=strict
+ProtectHome=yes
+PrivateTmp=yes

 [Install]
 WantedBy=multi-user.target
@@ -0,0 +1,71 @@
+---
+# Heating system over the Viessmann E3 CAN bus: open3e (heat pump) and
+# e3oncan (E380 energy meter). The can0 interface itself is the socketcan
+# role.
+
+# Service root. Kept per-role so the role is usable on its own.
+edge_base_dir: /opt/edge-host
+
+edge_open3e_mqtt_user: open3e
+edge_open3e_mqtt_topic: open3e
+edge_open3e_mqtt_format: "{device}_{didNumber:04d}_{didName}"
+edge_open3e_poll_seconds: 30
+# Read-only datapoint set (Phase 1 extended set, established 2026-07-02 on
+# the commissioning workstation; see vican repo CLAUDE.md for the rationale).
+# NO -w / write DIDs here — live heating + battery, writes are Phase 3.
+# vx3.266 = ErrorDtcHistory (O3EList) — the VX3 fault log; polled to catch
+# recurrences of FailureCommunicationEnergyMeter (the E380 energy-meter link
+# the internal PV-surplus EMS depends on). Decodes via the master O3EList
+# codec inherited through the vx3plus overlay.
+# vitocal.543/2350/2543/2560: SmartGrid-/EMS-Status-Beobachtung (2026-07-06)
+# — klärt, ob die Eigenstromoptimierung (EMS) bei PV-Überschuss von selbst
+# den WW-Boost auslöst (2543.2 steht laut Scan bereits auf +10 K), bevor
+# SG-Ready-Verdrahtung oder andere Trigger gebaut werden. Alle vier ro.
+# vitocal.259/260 = InfoDtcList/InfoDtcHistory (O3EList) — the HPMU event log,
+# the Vitocal-side counterpart to vx3.266. Both are capped lists (2 and 9
+# 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
+# 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,
+# which decodes all polled VCMU DIDs.
+edge_open3e_devices:
+  vitocal: { tx: "0x680", dpList: "vcal" }
+  # dpList als Pfad: Overlay-Datei mit den Batteriemodul-DIDs (siehe
+  # 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}"
+
+# Secrets come from inventory/group_vars/edge_host/vault.yml:
+#   edge_open3e_mqtt_password
+
+# The image carrying both readers, built and pinned in CI
+# (ci/images/heating-can/Containerfile). The source pins live in the
+# Containerfile, in the artifact -- not here -- so what is deployed is a tag,
+# and `docker compose up -d` on an unchanged tag is a genuine no-op.
+#
+# Tracked by the weekly update-audit as an ordinary image, which is why this is
+# simpler to keep current than the two git refs it replaced: one publishes no
+# tags at all, the other was pinned to an untagged commit between releases.
+heating_can_image: gitea.renner.uno/gitea_admin/heating-can:latest
+
+# Compose project directory. Separate from the old native layout under
+# {{ edge_base_dir }}/open3e, which this role removes.
+heating_can_base_dir: "{{ edge_base_dir }}/heating-can"
@@ -0,0 +1,54 @@
+# 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},
+    }
+}
@@ -0,0 +1,20 @@
+# Managed by ansible (roles/heating-can). Datapoint overlay for the VX3:
+# the stock vx3 list acts as a FILTER (DIDs missing from it are popped
+# from the master table, Open3Eclass.py), so the per-battery-module DIDs
+# were never pollable with dpList "vx3". This overlay re-adds them with
+# codec None (= keep the master/general codec, RawCodec hex strings).
+#
+# Module DIDs (verified answering on ECU 0x6a1, 2026-07-03):
+#   1577-1582  ElectricalEnergyStorageModule{One..Six}OperatingData
+#              (139 B: 8x temperature 0.1 °C + 15x cell voltage mV)
+#   3085-3090  ElectricalEnergyStorageModule{One..Six}Information
+#              (18 B: module voltage 0.01 V, SoH?, counters)
+from open3e.Open3EdatapointsVx3 import dataIdentifiers as _vx3
+
+dataIdentifiers = {
+    "dids": {
+        **_vx3["dids"],
+        1577: None, 1578: None, 1579: None, 1580: None, 1581: None, 1582: None,
+        3085: None, 3086: None, 3087: None, 3088: None, 3089: None, 3090: None,
+    }
+}
@@ -0,0 +1,10 @@
+---
+- name: Reload systemd
+  ansible.builtin.systemd:
+    daemon_reload: true
+
+- name: Restart heating-can
+  ansible.builtin.command:
+    cmd: docker compose up -d --force-recreate
+    chdir: "{{ heating_can_base_dir }}"
+  changed_when: true
@@ -0,0 +1,172 @@
+---
+# Heating system over the Viessmann E3 CAN bus.
+#
+# Two readers of the same heating installation, supervised inside one container
+# from one image (ci/images/heating-can):
+#   open3e    UDS request/response to the Vitocal heat pump and Vitocharge VX3
+#   e3oncan   passive CANopen listener for the E380 grid energy meter, which
+#             feeds the heat pump's own energy management
+#
+# They coexist because e3oncan issues no bus writes.
+#
+# Nothing is installed here. The image is built in CI with both sources pinned,
+# published to the registry, and this host only pulls and runs it. That is what
+# removes the churn: these were pip-installed into venvs on the node, and pip
+# re-cloned and rebuilt a VCS requirement on every converge -- restarting the
+# heating bridge each time -- which pinning the SHA did not fix.
+#
+# network_mode: host is required, not incidental: SocketCAN interfaces live in
+# the host network namespace, so can0 is only reachable that way. It is also how
+# the local MQTT broker on 127.0.0.1 is reached. CAN_RAW needs no capabilities,
+# so both run unprivileged.
+#
+# The can0 interface itself belongs to the socketcan role; this role consumes it.
+
+- name: Create heating-can directory
+  ansible.builtin.file:
+    path: "{{ heating_can_base_dir }}"
+    state: directory
+    mode: "0755"
+
+# --- Migration off the native install ---------------------------------------
+# Must happen before the containers start. Two open3e instances issuing UDS
+# requests on one CAN bus is the failure mode to avoid, so the old units are
+# stopped and masked rather than merely disabled -- masked so a stray
+# `systemctl start` or a leftover dependency cannot bring them back alongside
+# the containers.
+- name: Find which native CAN units still exist
+  ansible.builtin.stat:
+    path: "/etc/systemd/system/{{ item }}.service"
+  loop:
+    - open3e
+    - e3oncan
+  register: heating_can_native_units
+
+# Stop and disable BEFORE anything else, and do NOT swallow the result.
+#
+# The first version did stop + disable + mask in one call with
+# failed_when: false, then deleted the unit files. Masking a unit whose file
+# still exists conflicts, so the call failed, failed_when hid it, nothing was
+# stopped -- and the next task deleted the unit files out from under two
+# running processes. systemctl is-enabled then reported "not-found" and looked
+# clean while is-active still said "active".
+#
+# The result on 2026-08-10 was two open3e instances issuing UDS requests on the
+# same CAN bus for nine minutes, fighting over the open3e-edge client ID and
+# kicking each other off the broker.
+#
+# Only units that actually exist are touched, so a fresh host does not need an
+# error swallowed to get through this.
+- name: Stop and disable the native CAN services
+  ansible.builtin.systemd:
+    name: "{{ item.item }}"
+    state: stopped
+    enabled: false
+  loop: "{{ heating_can_native_units.results }}"
+  loop_control:
+    label: "{{ item.item }}"
+  when: item.stat.exists
+
+# Masking is deliberately NOT used. It writes a symlink at the same path the
+# next task removes, so the two cancel out -- which is half of how the original
+# failed. With the unit files gone there is nothing left to start.
+- name: Remove the native unit files
+  ansible.builtin.file:
+    path: "/etc/systemd/system/{{ item }}.service"
+    state: absent
+  loop:
+    - open3e
+    - e3oncan
+  notify: Reload systemd
+
+# The invariant that actually matters is "no native process is on the CAN bus",
+# and systemd reporting success is not the same claim. Two open3e instances
+# polling one bus is the failure this whole block exists to prevent, so it is
+# asserted directly rather than inferred from the calls above.
+- name: Check for surviving native CAN processes
+  ansible.builtin.command:
+    argv: [pgrep, -af, "edge-host/(open3e|e3oncan)"]
+  register: heating_can_survivors
+  check_mode: false
+  changed_when: false
+  failed_when: false
+
+- name: Assert no native CAN process survived
+  ansible.builtin.assert:
+    that:
+      - heating_can_survivors.stdout | default('') | length == 0
+    fail_msg: >-
+      A native open3e/e3oncan process is still running after the units were
+      stopped and removed:
+      {{ heating_can_survivors.stdout_lines | default([]) | join('; ') }}.
+      Starting the container now would put two readers on the same CAN bus --
+      two open3e instances issue competing UDS requests and take over each
+      other's MQTT session. Kill the survivors, then re-run.
+    success_msg: No native CAN processes remain; safe to start the container.
+
+- name: Remove the native venvs
+  ansible.builtin.file:
+    path: "{{ item }}"
+    state: absent
+  loop:
+    - "{{ edge_base_dir }}/open3e/venv"
+    - "{{ edge_base_dir }}/e3oncan/venv"
+    - "{{ edge_base_dir }}/e3oncan/src"
+    - "{{ edge_base_dir }}/open3e"
+    - "{{ edge_base_dir }}/e3oncan"
+
+# --- Configuration (bind-mounted into the containers) ------------------------
+- name: Deploy open3e devices.json
+  ansible.builtin.copy:
+    content: "{{ edge_open3e_devices | to_nice_json }}\n"
+    dest: "{{ heating_can_base_dir }}/devices.json"
+    mode: "0644"
+  notify: Restart heating-can
+
+- name: Deploy open3e vx3 datapoint overlay (battery-module DIDs)
+  ansible.builtin.copy:
+    src: open3e-vx3plus.py
+    dest: "{{ heating_can_base_dir }}/vx3plus.py"
+    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:
+    src: heating-can.env.j2
+    dest: "{{ heating_can_base_dir }}/heating-can.env"
+    mode: "0600"
+  notify: Restart heating-can
+
+- name: Deploy heating-can compose project
+  ansible.builtin.template:
+    src: docker-compose.yml.j2
+    dest: "{{ heating_can_base_dir }}/docker-compose.yml"
+    mode: "0644"
+  notify: Restart heating-can
+
+- name: Pull the heating-can image
+  ansible.builtin.command:
+    cmd: docker compose pull
+    chdir: "{{ heating_can_base_dir }}"
+  changed_when: false
+
+# Unlike the zwave and meter services there is no missing-device tolerance here:
+# can0 is created by the socketcan role from a USB adapter that is part of this
+# host's purpose. If it is absent the heating telemetry is down and the run
+# should say so rather than pass quietly.
+- name: Start heating-can services
+  ansible.builtin.command:
+    cmd: docker compose up -d
+    chdir: "{{ heating_can_base_dir }}"
+  register: heating_can_up
+  changed_when: >-
+    'Started' in heating_can_up.stderr or 'Created' in heating_can_up.stderr
+    or 'Started' in heating_can_up.stdout or 'Creating' in heating_can_up.stdout
@@ -0,0 +1,36 @@
+# Managed by ansible (roles/heating-can).
+#
+# One container. Both CAN readers live in the image and are supervised inside
+# it -- this file supplies configuration and nothing else. It does not know
+# open3e's or E3onCAN's command line.
+#
+# network_mode: host is required: SocketCAN interfaces live in the host network
+# namespace, so {{ edge_can_interface }} is only reachable this way, and it is
+# also how the local MQTT broker is reached. CAN_RAW needs no capabilities, so
+# the image runs unprivileged.
+services:
+  heating-can:
+    image: {{ heating_can_image }}
+    container_name: heating-can
+    restart: unless-stopped
+    network_mode: host
+    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
+    environment:
+      CAN_INTERFACE: "{{ edge_can_interface }}"
+      MQTT_HOST: "{{ edge_mqtt_host }}"
+      MQTT_PORT: "{{ edge_mqtt_port }}"
+      MQTT_TOPIC: "{{ edge_open3e_mqtt_topic }}"
+      MQTT_FORMAT: "{{ edge_open3e_mqtt_format }}"
+      E3ONCAN_MQTT_FORMAT: "{{ edge_e3oncan_mqtt_format }}"
+      OPEN3E_CONFIG: /config/devices.json
+      OPEN3E_CLIENT_ID: open3e-edge
+      OPEN3E_POLL_SECONDS: "{{ edge_open3e_poll_seconds }}"
+      OPEN3E_DATAPOINTS: "{{ edge_open3e_datapoints }}"
+      E3ONCAN_DEVICE: e380
+      E3ONCAN_GAP_SECONDS: "{{ edge_e3oncan_gap_seconds }}"
@@ -0,0 +1,8 @@
+# Managed by ansible (roles/heating-can). 0600 -- carries the broker credential.
+#
+# Kept out of docker-compose.yml, which is 0644: the sibling roles on this host
+# do the same (power-meter-sml renders its config at 0600 while its compose file
+# stays world-readable), and the native unit this replaced used a 0600 env file
+# for exactly this value.
+MQTT_USER={{ edge_open3e_mqtt_user }}
+MQTT_PASSWORD={{ edge_open3e_mqtt_password }}
@@ -99,7 +99,7 @@
 # quietly proceed either. install-edge-host.yml is a separate play with no
 # ordering relationship to this one, so nothing guarantees it has been re-run
 # to drop the [Address] block. If it has not, edge-1 would end up holding
-# the service address statically AND running a VRRP instance for the same address:
+# fd40::123 statically AND running a VRRP instance for the same address:
 # keepalived would believe it had withdrawn the address while networkd kept it
 # assigned, and the host would go on answering NTP with a clock the health
 # check had already rejected.
@@ -107,9 +107,9 @@
 # That is the precise failure of 2026-08-04, on the host it happened to, so it
 # fails fast rather than being left to inspection.
 # Matched on the bare address, not the full address/prefixlen, and anchored
-# with \b so it cannot also hit a longer address sharing the prefix (fd02:40::1234).
+# with \b so it cannot also hit a longer address sharing the prefix (fd40::1234).
 #
-# Searching for the literal "fd02:40::123/128" would fail open: a hand-written
+# Searching for the literal "fd40::123/128" would fail open: a hand-written
 # [Address] using any other mask -- /64, say -- would not match, the assert
 # below would pass, and keepalived would be handed an address networkd is
 # still assigning. Since this check is detect-only, with no delete afterwards
@@ -2,7 +2,7 @@
 # Managed by Ansible - Do not edit manually

 global_defs {
-    router_id {{ ansible_facts['hostname'] }}_ntp
+    router_id {{ ansible_hostname }}_ntp
    enable_script_security
    script_user root
 }
@@ -0,0 +1,23 @@
+---
+# --- MQTT: edge clients (open3e, e3oncan, sml2mqtt) publish to a LOCAL
+# mosquitto on loopback, which bridges to the central cluster broker over TLS
+# (open3e/e3oncan have no native MQTTS). This keeps plaintext on loopback only
+# — off the untrusted IoT VLAN — and buffers telemetry in RAM during cluster
+# blips. The local broker writes nothing to the eMMC (persistence off, logs to
+# the volatile journal). See edge-mqtt-bridge.conf.j2 and README "MQTT bridge".
+# Upstream cluster broker the local bridge connects to (TLS; the public
+# Let's Encrypt cert is validated against the system CA bundle).
+edge_mqtt_cluster_host: mqtt.renner.uno
+edge_mqtt_cluster_tls_port: 8883
+edge_mqtt_bridge_cafile: /etc/ssl/certs/ca-certificates.crt
+
+# --- Bridge credential from mqtt-account-controller (REN-1307) ------------
+# The cluster account the bridge logs in as (register entry in
+# kubernetes/apps/home-assistant/mqtt-accounts.yaml). The controller pushes
+# its password to edge-mqtt-cred and rotates it when the bridge reports
+# "not connected"; there is no copy in ansible-vault.
+edge_mqtt_bridge_account: edge-1
+# HTTPS port of edge-mqtt-cred (esp32 device API, mTLS). Only a client
+# certificate from the MQTT CA with this CN is accepted.
+edge_mqtt_cred_port: 8443
+edge_mqtt_cred_allowed_cn: mqtt-account-controller
@@ -0,0 +1,141 @@
+#!/usr/bin/env python3
+# Managed by ansible (roles/mqtt-bridge). Receives the cluster bridge password
+# from mqtt-account-controller (REN-1307) so no plaintext copy lives in
+# ansible-vault and no play run is needed to rotate it.
+#
+# Speaks the controller's esp32 device API over HTTPS:
+#   GET /api/status   -> {"mqtt": {"connected": bool}}
+#   PUT /api/settings <- {"mqtt": {"user": "...", "pass": "..."}}
+# A client certificate from the MQTT CA with CN mqtt-account-controller is
+# required; nothing else may call it. The server key is generated on this
+# host and never leaves it (the controller pins it on first contact).
+#
+# PUT writes the bridge file (template + credentials), removes the legacy
+# vault-password bridges and restarts the local mosquitto. The password is
+# kept only in that 0640 root:mosquitto file.
+import grp
+import json
+import os
+import socket
+import ssl
+import subprocess
+import sys
+import tempfile
+import threading
+from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
+
+CONF = json.load(open(sys.argv[1]))
+WRITE = threading.Lock()
+
+
+def connected():
+    try:
+        out = subprocess.run(
+            ["mosquitto_sub", "-h", "127.0.0.1", "-p", str(CONF["local_port"]),
+             "-t", CONF["state_topic"], "-C", "1", "-W", "3"],
+            capture_output=True, text=True, timeout=10).stdout
+    except (OSError, subprocess.TimeoutExpired):
+        return False
+    return out.strip() == "1"
+
+
+def write_bridge(user, password):
+    with open(CONF["template"]) as f:
+        body = f.read()
+    body += f"remote_username {user}\nremote_password {password}\n"
+    d = os.path.dirname(CONF["bridge_file"])
+    fd, tmp = tempfile.mkstemp(dir=d, prefix=".edge-mqtt-cred.")
+    with os.fdopen(fd, "w") as f:
+        f.write(body)
+    os.chown(tmp, 0, grp.getgrnam("mosquitto").gr_gid)
+    os.chmod(tmp, 0o640)
+    os.replace(tmp, CONF["bridge_file"])
+    for legacy in CONF["legacy_files"]:
+        if os.path.exists(legacy):
+            os.remove(legacy)
+    subprocess.run(["systemctl", "restart", "mosquitto"], check=True, timeout=60)
+
+
+def valid(s):
+    # Controller passwords are random URL-safe tokens; anything with
+    # whitespace or a control character would break the config line.
+    return isinstance(s, str) and 0 < len(s) <= 256 and s.isprintable() and not any(c.isspace() for c in s)
+
+
+class Handler(BaseHTTPRequestHandler):
+    def authorized(self):
+        cert = self.connection.getpeercert() or {}
+        cns = [v for rdn in cert.get("subject", ()) for k, v in rdn if k == "commonName"]
+        if cns != [CONF["allowed_cn"]]:
+            self.send_error(403)
+            return False
+        return True
+
+    def reply(self, code, obj=None):
+        data = b"" if obj is None else json.dumps(obj).encode()
+        self.send_response(code)
+        if data:
+            self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(data)))
+        self.end_headers()
+        self.wfile.write(data)
+
+    def do_GET(self):
+        if not self.authorized():
+            return
+        if self.path != "/api/status":
+            return self.send_error(404)
+        self.reply(200, {"mqtt": {"connected": connected()}})
+
+    def do_PUT(self):
+        if not self.authorized():
+            return
+        if self.path != "/api/settings":
+            return self.send_error(404)
+        try:
+            n = int(self.headers.get("Content-Length", "0"))
+            if not 0 < n <= 4096:
+                raise ValueError("body size")
+            m = json.loads(self.rfile.read(n))["mqtt"]
+            user, password = m["user"], m["pass"]
+        except (ValueError, KeyError, TypeError):
+            return self.send_error(400)
+        if user != CONF["user"] or not valid(password):
+            return self.send_error(400)
+        with WRITE:
+            write_bridge(user, password)
+        self.log_message("bridge credentials for %s replaced, mosquitto restarted", user)
+        self.reply(204)
+
+    def log_message(self, fmt, *args):
+        sys.stderr.write("%s %s\n" % (self.address_string(), fmt % args))
+
+
+class Server(ThreadingHTTPServer):
+    address_family = socket.AF_INET6
+
+    def server_bind(self):
+        self.socket.setsockopt(socket.IPPROTO_IPV6, socket.IPV6_V6ONLY, 0)
+        super().server_bind()
+
+    def get_request(self):
+        # The TLS handshake runs in the request thread, with a timeout, so a
+        # stalled peer cannot block the accept loop.
+        sock, addr = self.socket.accept()
+        sock.settimeout(10)
+        return self.ctx.wrap_socket(sock, server_side=True, do_handshake_on_connect=False), addr
+
+
+def main():
+    ctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
+    ctx.minimum_version = ssl.TLSVersion.TLSv1_2
+    ctx.load_cert_chain(CONF["cert"], CONF["key"])
+    ctx.load_verify_locations(CONF["ca"])
+    ctx.verify_mode = ssl.CERT_REQUIRED
+    srv = Server(("::", CONF["port"]), Handler)
+    srv.ctx = ctx
+    srv.serve_forever()
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,10 @@
+-----BEGIN CERTIFICATE-----
+MIIBdTCCARygAwIBAgIUN8ne4k4Wif9O83GDyKiBP0Ma7EIwCgYIKoZIzj0EAwIw
+GTEXMBUGA1UEAxMOUmVubmVyIE1RVFQgQ0EwHhcNMjYxMDA2MTUzMDE1WhcNMzYx
+MDAzMTUzMDE1WjAZMRcwFQYDVQQDEw5SZW5uZXIgTVFUVCBDQTBZMBMGByqGSM49
+AgEGCCqGSM49AwEHA0IABOZhZF2JDoyvVg2oIXSbJAuAWDcoG22RxPA4oMKRMA/b
+XzIY566D2k6cVnWqbil9s/q4O2mj+Epo7plBw8NwuOOjQjBAMA4GA1UdDwEB/wQE
+AwICpDAPBgNVHRMBAf8EBTADAQH/MB0GA1UdDgQWBBQcqSDDiLZzhrvqq9f16Y08
+CO7QfzAKBggqhkjOPQQDAgNHADBEAiBFkxd9pXnqIcjReEcOTvCBZ3HxKu2jNQGL
+/le7gunTGgIgZapWAcu4awa+wmZcR/z2luOjD2GhIT15um14Z+sstJk=
+-----END CERTIFICATE-----
@@ -0,0 +1,13 @@
+---
+# The MQTT clients (zwave-js, sml2mqtt, open3e, e3oncan) reconnect on their
+# own once the local broker is back.
+- name: Restart mosquitto
+  ansible.builtin.service:
+    name: mosquitto
+    state: restarted
+
+- name: Restart edge-mqtt-cred
+  ansible.builtin.systemd:
+    name: edge-mqtt-cred
+    state: restarted
+    daemon_reload: true
@@ -0,0 +1,109 @@
+---
+# Local MQTT bridge broker.
+#
+# Edge clients (open3e, e3oncan, sml2mqtt) publish here over loopback; this
+# broker bridges to the cluster broker over TLS, because those clients have no
+# native MQTTS. Persistence is off and logging goes to stdout so it writes
+# nothing to local flash.
+
+- name: Install mosquitto
+  ansible.builtin.package:
+    name: mosquitto
+    state: present
+
+- name: Create the bridge directory
+  ansible.builtin.file:
+    path: /etc/mosquitto/bridge.d
+    state: directory
+    owner: root
+    group: mosquitto
+    mode: "0750"
+
+- name: Check for the controller-managed bridge file
+  ansible.builtin.stat:
+    path: "/etc/mosquitto/bridge.d/{{ edge_mqtt_bridge_account }}.conf"
+  register: edge_mqtt_bridge_managed
+
+# Until mqtt-account-controller has pushed the first password, keep the
+# vault-password bridges so the cluster never loses edge-1's data. Once the
+# managed file exists, never render them again (edge-mqtt-cred removed them).
+- name: Deploy legacy vault-password bridges
+  ansible.builtin.template:
+    src: edge-mqtt-bridge-legacy.conf.j2
+    dest: /etc/mosquitto/bridge.d/legacy.conf
+    owner: root
+    group: mosquitto
+    mode: "0640"   # carries the legacy cluster bridge credentials
+  when: not edge_mqtt_bridge_managed.stat.exists
+  notify: Restart mosquitto
+
+- name: Deploy local mosquitto config
+  ansible.builtin.template:
+    src: edge-mqtt-bridge.conf.j2
+    dest: /etc/mosquitto/mosquitto.conf
+    owner: root
+    group: mosquitto
+    mode: "0640"
+  notify: Restart mosquitto
+
+- name: Enable local mosquitto bridge
+  ansible.builtin.systemd:
+    name: mosquitto
+    enabled: true
+    state: started
+
+# --- edge-mqtt-cred (REN-1307): receives the bridge password from
+# mqtt-account-controller. edge-1 holds only the public MQTT CA and its own
+# server key, generated here and never copied off the host.
+- name: Create edge-mqtt-cred config directory
+  ansible.builtin.file:
+    path: /etc/edge-mqtt-cred
+    state: directory
+    owner: root
+    group: root
+    mode: "0700"
+
+- name: Generate edge-mqtt-cred server key and certificate
+  ansible.builtin.command:
+    cmd: >-
+      openssl req -x509 -newkey ec -pkeyopt ec_paramgen_curve:prime256v1
+      -nodes -days 36500 -subj "/CN={{ inventory_hostname }}"
+      -keyout /etc/edge-mqtt-cred/tls.key -out /etc/edge-mqtt-cred/tls.crt
+    creates: /etc/edge-mqtt-cred/tls.key
+  notify: Restart edge-mqtt-cred
+
+- name: Deploy edge-mqtt-cred files
+  ansible.builtin.copy:
+    src: "{{ item.src }}"
+    dest: "{{ item.dest }}"
+    owner: root
+    group: root
+    mode: "{{ item.mode }}"
+  loop:
+    - {src: edge-mqtt-cred.py, dest: /usr/local/sbin/edge-mqtt-cred, mode: "0755"}
+    # Public CA of the cluster's MQTT client certificates
+    # (kubernetes/infrastructure/post-crds/mqtt-ca.yaml), valid until 2036-10-03.
+    - {src: mqtt-ca.crt, dest: /etc/edge-mqtt-cred/mqtt-ca.crt, mode: "0644"}
+  notify: Restart edge-mqtt-cred
+
+- name: Deploy edge-mqtt-cred config and bridge template
+  ansible.builtin.template:
+    src: "{{ item.src }}"
+    dest: "{{ item.dest }}"
+    owner: root
+    group: root
+    mode: "{{ item.mode }}"
+  loop:
+    - {src: edge-mqtt-cred.json.j2, dest: /etc/edge-mqtt-cred/config.json, mode: "0600"}
+    # Read only on the controller's next push: a change here reaches the
+    # running bridge when the password is next set.
+    - {src: edge-1-bridge.conf.in.j2, dest: /etc/edge-mqtt-cred/bridge.conf.in, mode: "0600"}
+    - {src: edge-mqtt-cred.service.j2, dest: /etc/systemd/system/edge-mqtt-cred.service, mode: "0644"}
+  notify: Restart edge-mqtt-cred
+
+- name: Enable edge-mqtt-cred
+  ansible.builtin.systemd:
+    name: edge-mqtt-cred
+    enabled: true
+    state: started
+    daemon_reload: true
@@ -0,0 +1,21 @@
+# Managed by roles/mqtt-bridge (REN-1307). edge-mqtt-cred appends
+# remote_username/remote_password to this and writes the result to
+# /etc/mosquitto/bridge.d/{{ edge_mqtt_bridge_account }}.conf. One bridge for
+# open3e, as the register account `{{ edge_mqtt_bridge_account }}`
+# (ACL readwrite open3e/#). sml2mqtt is retired (SML reader, 2026-09-19).
+connection {{ edge_mqtt_bridge_account }}
+address {{ edge_mqtt_cluster_host }}:{{ edge_mqtt_cluster_tls_port }}
+bridge_cafile {{ edge_mqtt_bridge_cafile }}
+bridge_insecure false
+remote_clientid edge1-bridge
+cleansession false
+try_private true
+restart_timeout 5 30
+queue_qos0_messages true
+# The bridge state goes to the LOCAL broker only (retained 1/0); edge-mqtt-cred
+# reads it to answer the controller's "connected?".
+notifications true
+notifications_local_only true
+notification_topic $SYS/broker/connection/{{ edge_mqtt_bridge_account }}/state
+topic open3e/# out 0
+topic open3e/cmnd in 0
@@ -0,0 +1,21 @@
+# Managed by roles/mqtt-bridge. Legacy vault-password bridges, rendered only
+# while /etc/mosquitto/bridge.d/{{ edge_mqtt_bridge_account }}.conf does not
+# exist; edge-mqtt-cred deletes this file on the controller's first push
+# (REN-1307). Remove with the vault keys once edge-1 is on the register account.
+# --- Bridge 1: open3e datapoints + command topic, as the cluster `open3e`
+# user (its ACL is `readwrite open3e/#`, which covers publishing datapoints
+# and subscribing to open3e/cmnd). e3oncan also publishes under open3e/#.
+connection edge1-open3e
+address {{ edge_mqtt_cluster_host }}:{{ edge_mqtt_cluster_tls_port }}
+bridge_cafile {{ edge_mqtt_bridge_cafile }}
+bridge_insecure false
+remote_username {{ edge_open3e_mqtt_user }}
+remote_password {{ edge_open3e_mqtt_password }}
+remote_clientid edge1-bridge-open3e
+cleansession false
+try_private true
+notifications false
+restart_timeout 5 30
+queue_qos0_messages true
+topic open3e/# out 0
+topic open3e/cmnd in 0
@@ -0,0 +1,30 @@
+# Managed by roles/mqtt-bridge. Local mosquitto that the edge clients (open3e,
+# e3oncan, sml2mqtt) publish to over loopback; it bridges to the central
+# cluster broker over TLS. open3e/e3oncan have no native MQTTS, so this is how
+# edge-1's MQTT gets off plaintext on the untrusted IoT VLAN, and it buffers
+# telemetry in RAM if the cluster broker is briefly unreachable.
+#
+# eMMC: this host runs on a small internal eMMC, so the local broker writes
+# NOTHING to flash — `persistence false` keeps retained/queued messages in RAM
+# only, and `log_dest stdout` goes to the (volatile, RAM) journal that Alloy
+# ships to Loki. Do not add persistence/log-file settings here.
+persistence false
+log_dest stdout
+log_type error
+log_type warning
+log_type notice
+
+# Loopback only — the trust boundary is the host itself. Any process on edge-1
+# may publish here (same trust as the bridged services); nothing off-host can
+# reach it. Real authentication to the cluster happens on the bridge below.
+# Single v4-loopback listener: all edge clients dial 127.0.0.1 (edge_mqtt_host),
+# and a second same-port listener can make some builds refuse to start.
+listener 1883 127.0.0.1
+allow_anonymous true
+
+# --- Bridges to the cluster broker (REN-1307). bridge.d holds either
+# {{ edge_mqtt_bridge_account }}.conf, written by edge-mqtt-cred with the password
+# mqtt-account-controller pushed, or, until that first push, legacy.conf with
+# the two vault-password bridges. edge-mqtt-cred deletes legacy.conf when it
+# writes the new file.
+include_dir /etc/mosquitto/bridge.d
@@ -0,0 +1,13 @@
+{{ {
+  "port": edge_mqtt_cred_port,
+  "allowed_cn": edge_mqtt_cred_allowed_cn,
+  "user": edge_mqtt_bridge_account,
+  "cert": "/etc/edge-mqtt-cred/tls.crt",
+  "key": "/etc/edge-mqtt-cred/tls.key",
+  "ca": "/etc/edge-mqtt-cred/mqtt-ca.crt",
+  "template": "/etc/edge-mqtt-cred/bridge.conf.in",
+  "bridge_file": "/etc/mosquitto/bridge.d/" ~ edge_mqtt_bridge_account ~ ".conf",
+  "legacy_files": ["/etc/mosquitto/bridge.d/legacy.conf"],
+  "local_port": edge_mqtt_port,
+  "state_topic": "$SYS/broker/connection/" ~ edge_mqtt_bridge_account ~ "/state",
+} | to_nice_json }}
@@ -0,0 +1,19 @@
+# Managed by roles/mqtt-bridge (REN-1307). See /usr/local/sbin/edge-mqtt-cred.
+[Unit]
+Description=Receives the MQTT bridge credential from mqtt-account-controller
+After=network-online.target mosquitto.service
+Wants=network-online.target
+
+[Service]
+ExecStart=/usr/bin/python3 /usr/local/sbin/edge-mqtt-cred /etc/edge-mqtt-cred/config.json
+Restart=always
+RestartSec=5
+# Root only to write the bridge file and restart mosquitto.
+ProtectSystem=strict
+ReadWritePaths=/etc/mosquitto/bridge.d
+ProtectHome=true
+PrivateTmp=true
+NoNewPrivileges=true
+
+[Install]
+WantedBy=multi-user.target
@@ -11,8 +11,6 @@
          - curl
          - ca-certificates
          - gnupg
-          # deb822_repository
-          - python3-debian
        state: present
        update_cache: true

@@ -23,19 +21,10 @@
        creates: /usr/share/keyrings/netbird-archive-keyring.gpg

    - name: Add NetBird repository
-      ansible.builtin.deb822_repository:
-        name: netbird
-        types: deb
-        uris: https://pkgs.netbird.io/debian
-        suites: stable
-        components: main
-        signed_by: /usr/share/keyrings/netbird-archive-keyring.gpg
-
-    # A one-line netbird.list beside netbird.sources lists the repository twice.
-    - name: Remove the one-line NetBird repository
-      ansible.builtin.file:
-        path: /etc/apt/sources.list.d/netbird.list
-        state: absent
+      ansible.builtin.apt_repository:
+        repo: "deb [signed-by=/usr/share/keyrings/netbird-archive-keyring.gpg] https://pkgs.netbird.io/debian stable main"
+        state: present
+        filename: netbird

    - name: Install NetBird client
      ansible.builtin.apt:
@@ -1,14 +0,0 @@
-# Managed by ansible (roles/pacman-cache).
-# Downloaded packages are not kept; older versions come from the Arch Linux
-# Archive.
-[Trigger]
-Operation = Install
-Operation = Upgrade
-Operation = Remove
-Type = Package
-Target = *
-
-[Action]
-Description = Removing downloaded packages from the cache...
-When = PostTransaction
-Exec = /usr/bin/find /var/cache/pacman/pkg -mindepth 1 -delete
@@ -1,21 +0,0 @@
---
-# Keep the pacman package cache empty. pacman keeps every downloaded package;
-# on a 7 GB eMMC root the cache grows to gigabytes. Arch hosts only.
-
- name: Ensure the pacman hook directory exists
-  ansible.builtin.file:
-    path: /etc/pacman.d/hooks
-    state: directory
-    mode: "0755"
-
- name: Empty the package cache after every transaction
-  ansible.builtin.copy:
-    src: pacman-cache.hook
-    dest: /etc/pacman.d/hooks/pacman-cache.hook
-    mode: "0644"
-
- name: Empty the package cache
-  ansible.builtin.command:
-    argv: [find, /var/cache/pacman/pkg, -mindepth, "1", -delete, -print]
-  register: pacman_cache_clean
-  changed_when: pacman_cache_clean.stdout | length > 0
@@ -6,15 +6,15 @@
  apt:
    name: qemu-guest-agent
    state: present
-  when:
-    - ansible_facts['os_family'] == 'Debian'
+  when: 
+    - ansible_os_family is defined and ansible_os_family == 'Debian'

 - name: Install QEMU Guest Agent (RHEL/Rocky VMs)
  dnf:
    name: qemu-guest-agent
    state: present
-  when:
-    - ansible_facts['os_family'] == 'RedHat'
+  when: 
+    - ansible_os_family is defined and ansible_os_family == 'RedHat'

 - name: Ensure qemu-guest-agent is started and enabled
  service:
@@ -0,0 +1,5 @@
+---
+# SocketCAN interface. Consumed by heating-can.
+# --- CAN / open3e (Viessmann E3 external bus) ---
+edge_can_interface: can0
+edge_can_bitrate: 250000
@@ -0,0 +1,7 @@
+---
+# reload alone only re-reads config files; existing links keep their old state
+# until reconfigured.
+- name: Reload networkd
+  ansible.builtin.shell:
+    cmd: networkctl reload && networkctl reconfigure {{ edge_can_interface }}
+  changed_when: true
@@ -0,0 +1,20 @@
+---
+# SocketCAN interface, owned by systemd-networkd.
+#
+# gs_usb is an in-tree module and autoloads when the adapter enumerates;
+# networkd then matches the interface and applies bitrate + up. Separate from
+# the services that consume the bus (heating-can, e380-can-meter) because the
+# interface is host network state shared by both.
+
+- name: Configure can0 via systemd-networkd
+  ansible.builtin.template:
+    src: 80-can0.network.j2
+    dest: /etc/systemd/network/80-can0.network
+    mode: "0644"
+  notify: Reload networkd
+
+- name: Enable systemd-networkd
+  ansible.builtin.service:
+    name: systemd-networkd
+    state: started
+    enabled: true
@@ -0,0 +1,17 @@
+# Managed by ansible (roles/socketcan).
+# Viessmann E3 external CAN bus via Innomaker USB2CAN (gs_usb).
+# The adapter is a stub tap on an already-terminated bus (120R jumper OFF).
+[Match]
+Name={{ edge_can_interface }}
+
+[Link]
+# networkd applies [CAN] settings but does not raise a CAN link on its
+# own (observed on edge-1); force it up, and back up after any down.
+ActivationPolicy=always-up
+
+[CAN]
+BitRate={{ edge_can_bitrate }}
+# NO RestartSec here: gs_usb does not support hardware bus-off restart,
+# and networkd fails the ENTIRE link configuration on the unsupported
+# option ("off (failed)", link never raised — found by reboot test).
+# Bus-off recovery falls to the open3e service restart loop.
@@ -16,6 +16,3 @@ ssh_ca_claude_principal: claude-bot

 # Units claude-bot may restart/reload via sudo on this host, e.g. [netbird].
 ssh_ca_claude_sudo_units: []
-
-# Full passwordless sudo for claude-bot on this host.
-ssh_ca_claude_sudo_all: false
@@ -1,15 +1,23 @@
 ---
 # Replaces the admin logins' authorized_keys with ssh_admin_authorized_keys
 # (break-glass + CI). Everything else logs in with a CA certificate.
-# ssh_ca_admin_logins comes from main.yml, which runs first in the same play.
+- name: Look up the admin logins
+  ansible.builtin.getent:
+    database: passwd
+    key: "{{ item }}"
+    fail_key: false
+  loop: "{{ ssh_ca_owner_users }}"
+  register: ssh_ca_admin_lookup
+
 - name: Set the admin logins' authorized_keys to the managed list
  ansible.posix.authorized_key:
-    user: "{{ item[0] }}"
+    user: "{{ item.item }}"
    key: |
      {% for k in ssh_admin_authorized_keys %}
      {{ (k.options ~ ' ') if (k.options | default('')) else '' }}{{ k.key }}
      {% endfor %}
    exclusive: true
-  loop: "{{ ssh_ca_admin_logins }}"
+  loop: "{{ ssh_ca_admin_lookup.results }}"
  loop_control:
-    label: "{{ item[0] }}"
+    label: "{{ item.item }}"
+  when: (item.ansible_facts.getent_passwd | default({})).get(item.item) is not none
@@ -23,7 +23,6 @@
    owner: root
    group: root
    mode: "0644"
-  register: ssh_ca_trusted_file

 # sshd refuses all public key logins when RevokedKeys is set but unreadable,
 # so the file is always deployed, even when empty.
@@ -35,26 +34,6 @@
    group: root
    mode: "0644"

-# /etc/passwd, not getent: DSM has no getent binary. The admin logins are
-# local accounts. Each entry is the split passwd line (0 name, 5 home).
- name: Read the local accounts
-  ansible.builtin.slurp:
-    src: /etc/passwd
-  register: ssh_ca_passwd_file
-
- name: Find the existing admin logins
-  vars:
-    ssh_ca_passwd: "{{ ssh_ca_passwd_file.content | b64decode | trim | split('\n') | map('split', ':') | list }}"
-  ansible.builtin.set_fact:
-    ssh_ca_admin_logins: "{{ ssh_ca_passwd | selectattr('0', 'in', ssh_ca_owner_users) | list }}"
-    ssh_ca_claude_exists: "{{ ssh_ca_claude_user in ssh_ca_passwd | map('first') }}"
-
-# DSM manages accounts with synouser/synogroup and has no useradd.
- name: Detect DSM
-  ansible.builtin.stat:
-    path: /usr/syno/sbin/synouser
-  register: ssh_ca_synouser
-
 # systemd-journal: read every journal without sudo (see sudoers-claude.j2).
 - name: Create the Claude account
  ansible.builtin.user:
@@ -64,57 +43,14 @@
    password: "!"
    groups: systemd-journal
    append: true
-  when: not ssh_ca_synouser.stat.exists

- name: Create the Claude account on DSM
-  when: ssh_ca_synouser.stat.exists
-  block:
-    # synouser requires a password; nobody knows it and sshd refuses passwords.
-    - name: Create the DSM account
-      ansible.builtin.command:
-        argv:
-          - /usr/syno/sbin/synouser
-          - --add
-          - "{{ ssh_ca_claude_user }}"
-          - "{{ lookup('ansible.builtin.password', '/dev/null', length=40, chars=['ascii_letters', 'digits']) }}"
-          - Claude Bot
-          - "0"
-          - ""
-          - "0"
-      # command runs in check mode here.
-      when:
-        - not ssh_ca_claude_exists
-        - not ansible_check_mode
-      no_log: true
-
-    # Members are listed as "<n>:[<name>]".
-    - name: Read the administrators members
-      ansible.builtin.command: /usr/syno/sbin/synogroup --get administrators
-      register: ssh_ca_dsm_admins_out
-      changed_when: false
-      check_mode: false
-
-    - name: Find the administrators members
-      ansible.builtin.set_fact:
-        ssh_ca_dsm_admins: >-
-          {{ ssh_ca_dsm_admins_out.stdout_lines | select('match', '^[0-9]+:\[.*\]$')
-             | map('regex_replace', '^[0-9]+:\[(.*)\]$', '\1') | list }}
-
-    # synogroup --member replaces the member list; a parse that lost the owner
-    # admin login would drop it.
-    - name: Check the member list holds the owner admin login
-      ansible.builtin.assert:
-        that:
-          - ssh_ca_dsm_admins | intersect(ssh_ca_owner_users) | length > 0
-        fail_msg: "administrators members lack {{ ssh_ca_owner_users }}: {{ ssh_ca_dsm_admins }}"
-
-    # DSM allows SSH for administrators only.
-    - name: Add the Claude account to administrators
-      ansible.builtin.command:
-        argv: "{{ ['/usr/syno/sbin/synogroup', '--member', 'administrators'] + ssh_ca_dsm_admins + [ssh_ca_claude_user] }}"
-      when:
-        - ssh_ca_claude_user not in ssh_ca_dsm_admins
-        - not ansible_check_mode
+- name: Look up the owner admin logins
+  ansible.builtin.getent:
+    database: passwd
+    key: "{{ item }}"
+    fail_key: false
+  loop: "{{ ssh_ca_owner_users }}"
+  register: ssh_ca_owner_lookup

 - name: Create the principals directory
  ansible.builtin.file:
@@ -127,13 +63,14 @@
 - name: Accept the owner principal for the existing admin logins
  ansible.builtin.copy:
    content: "{{ ssh_ca_owner_principal }}\n"
-    dest: "/etc/ssh/auth_principals/{{ item[0] }}"
+    dest: "/etc/ssh/auth_principals/{{ item.item }}"
    owner: root
    group: root
    mode: "0644"
-  loop: "{{ ssh_ca_admin_logins }}"
+  loop: "{{ ssh_ca_owner_lookup.results }}"
  loop_control:
-    label: "{{ item[0] }}"
+    label: "{{ item.item }}"
+  when: (item.ansible_facts.getent_passwd | default({})).get(item.item) is not none

 - name: Accept the Claude principal for the Claude account
  ansible.builtin.copy:
@@ -143,12 +80,6 @@
    group: root
    mode: "0644"

- name: Install sudo
-  ansible.builtin.package:
-    name: sudo
-    state: present
-  when: not ssh_ca_synouser.stat.exists
-
 - name: Install the Claude sudo rules
  ansible.builtin.template:
    src: sudoers-claude.j2
@@ -157,48 +88,6 @@
    group: root
    mode: "0440"
    validate: visudo -cf %s
-  when: not ssh_ca_synouser.stat.exists
-
-# DSM has no visudo, so the rules are checked on the controller.
- name: Install the Claude sudo rules on DSM
-  when: ssh_ca_synouser.stat.exists
-  vars:
-    ssh_ca_sudoers: "{{ lookup('ansible.builtin.template', 'sudoers-claude.j2') | trim }}"
-  block:
-    - name: Check the sudo rules on the controller
-      ansible.builtin.command:
-        cmd: visudo -c -f -
-        stdin: "{{ ssh_ca_sudoers }}"
-      delegate_to: localhost
-      become: false
-      changed_when: false
-      check_mode: false
-
-    - name: Install the checked sudo rules
-      ansible.builtin.copy:
-        content: "{{ ssh_ca_sudoers }}\n"
-        dest: "/etc/sudoers.d/{{ ssh_ca_claude_user }}"
-        owner: root
-        group: root
-        mode: "0440"
-
- name: Create the sshd drop-in directory
-  ansible.builtin.file:
-    path: /etc/ssh/sshd_config.d
-    state: directory
-    owner: root
-    group: root
-    mode: "0755"
-
-# DSM's sshd_config has no Include. sshd keeps the first value it reads, so
-# the Include goes first for the drop-ins to win.
- name: Include the sshd drop-in directory
-  ansible.builtin.lineinfile:
-    path: /etc/ssh/sshd_config
-    line: Include /etc/ssh/sshd_config.d/*.conf
-    insertbefore: BOF
-    validate: sshd -t -f %s
-  register: ssh_ca_include_line

 # A broken drop-in only bites on the next sshd restart, so it is tested here
 # and removed again if the full config does not parse.
@@ -211,7 +100,6 @@
        owner: root
        group: root
        mode: "0644"
-      register: ssh_ca_dropin_file

    - name: Test the full sshd config
      ansible.builtin.command: sshd -t
@@ -248,11 +136,10 @@
    fail_msg: "sshd -T does not show the SSH CA settings; another config line takes precedence"

 # The unit is sshd.service on Arch and RedHat, ssh.service on Debian/Ubuntu,
-# where sshd.service is an alias that resolves to it. The running daemon is
-# reloaded when a file it reads at start changed; a reload keeps open
+# where sshd.service is an alias that resolves to it. sshd -T only parses the
+# files, so the running daemon is reloaded on every run; a reload keeps open
 # sessions. None runs when sshd is socket activated and stopped, or per
 # connection (ssh-mesh-only role); the next start reads the config.
-# Principals and revoked keys are read per login and need no reload.
 # systemctl directly: service_facts took 3-12 s per host.
 - name: Find the running sshd unit
  ansible.builtin.command: systemctl list-units --state=running --plain --no-legend --type=service sshd.service ssh.service
@@ -274,9 +161,7 @@
      ansible.builtin.systemd:
        name: "{{ ssh_ca_sshd_units | first }}"
        state: reloaded
-      when:
-        - ssh_ca_sshd_units | length == 1
-        - ssh_ca_trusted_file is changed or ssh_ca_include_line is changed or ssh_ca_dropin_file is changed
+      when: ssh_ca_sshd_units | length == 1

 - name: Report the admin logins' authorized keys
  ansible.builtin.include_tasks: report.yml
@@ -3,10 +3,11 @@
 # [ssh_keys_managed] have this reduced to ssh_admin_authorized_keys.
 - name: Find the admin logins' authorized_keys
  ansible.builtin.stat:
-    path: "{{ item[5] }}/.ssh/authorized_keys"
-  loop: "{{ ssh_ca_admin_logins }}"
+    path: "{{ item.ansible_facts.getent_passwd[item.item][4] }}/.ssh/authorized_keys"
+  loop: "{{ ssh_ca_owner_lookup.results }}"
  loop_control:
-    label: "{{ item[0] }}"
+    label: "{{ item.item }}"
+  when: (item.ansible_facts.getent_passwd | default({})).get(item.item) is not none
  register: ssh_ca_keyfiles

 - name: Fingerprint the admin logins' authorized keys
@@ -10,6 +10,3 @@
 {% for unit in ssh_ca_claude_sudo_units %}
 {{ ssh_ca_claude_user }} ALL=(root) NOPASSWD:NOEXEC: /usr/bin/systemctl restart {{ unit }}, /usr/bin/systemctl reload {{ unit }}
 {% endfor %}
-{% if ssh_ca_claude_sudo_all %}
-{{ ssh_ca_claude_user }} ALL=(ALL) NOPASSWD: ALL
-{% endif %}
@@ -1,26 +0,0 @@
---
-# Keep the system clock on NTP with systemd-timesyncd, on hosts that run no
-# chrony. A KVM guest's clocksource does not steer wall-clock time; without an
-# NTP client the clock drifts until JWT iat/exp checks fail.
-
- name: Install systemd-timesyncd
-  ansible.builtin.apt:
-    name: systemd-timesyncd
-    state: present
-  when: ansible_facts['os_family'] == 'Debian'
-
- name: Run systemd-timesyncd
-  ansible.builtin.systemd_service:
-    name: systemd-timesyncd
-    masked: false
-    enabled: true
-    state: started
-
- name: Wait for the clock to synchronize
-  ansible.builtin.command:
-    argv: [timedatectl, show, --property=NTPSynchronized, --value]
-  register: timesyncd_synchronized
-  changed_when: false
-  until: timesyncd_synchronized.stdout == "yes"
-  retries: 12
-  delay: 5
@@ -5,9 +5,14 @@ uptime_kuma_base_url: "https://{{ uptime_kuma_host }}"
 uptime_kuma_dir: /opt/uptime-kuma
 uptime_kuma_traefik_network: netbird_netbird

+uptime_kuma_smtp_from: uptime@renner.uno
+# Alertmanager email receiver in kubernetes/apps/monitoring/helmrelease-prometheus.yaml.
+uptime_kuma_smtp_to: admin@renner.uno
+
 uptime_kuma_openbao_url: https://openbao.renner.uno
 uptime_kuma_openbao_mount: homelab
 uptime_kuma_openbao_path: infrastructure/uptime-kuma
+uptime_kuma_openbao_smtp_path: infrastructure/uptime-kuma/smtp
 uptime_kuma_openbao_metrics_path: infrastructure/uptime-kuma-metrics
 # Token with policy uptime-kuma-vps, looked up like the bao CLI does:
 # VAULT_TOKEN, else the token helper file written by `bao login -method=oidc`.
@@ -1,4 +1,4 @@
-// Bootstraps Uptime Kuma: admin user, general settings,
+// Bootstraps Uptime Kuma: admin user, general settings, SMTP notification,
 // and (when KUMA_METRICS_ROTATE=true) a fresh Prometheus API key written to KUMA_METRICS_KEY_FILE.
 // All input comes from environment variables; secrets are never printed.
 // Output lines: "admin user created" / "already set up", then "changed: <step>" or "ok: <step>".
@@ -20,7 +20,17 @@ const SETTINGS_DEFAULTS = {
    trustProxy: false,
 };

-const REQUIRED = ["KUMA_SETUP_USERNAME", "KUMA_SETUP_PASSWORD", "KUMA_BASE_URL"];
+const REQUIRED = [
+    "KUMA_SETUP_USERNAME",
+    "KUMA_SETUP_PASSWORD",
+    "KUMA_BASE_URL",
+    "KUMA_SMTP_HOST",
+    "KUMA_SMTP_PORT",
+    "KUMA_SMTP_USERNAME",
+    "KUMA_SMTP_PASSWORD",
+    "KUMA_SMTP_FROM",
+    "KUMA_SMTP_TO",
+];
 const missing = REQUIRED.filter((name) => !process.env[name]);
 const rotateMetricsKey = process.env.KUMA_METRICS_ROTATE === "true";
 if (rotateMetricsKey && !process.env.KUMA_METRICS_KEY_FILE) {
@@ -34,7 +44,7 @@ const env = process.env;

 const socket = io(KUMA_URL, { transports: ["websocket"], reconnection: false });
 const lists = {};
-const LIST_EVENTS = ["apiKeyList"];
+const LIST_EVENTS = ["notificationList", "apiKeyList"];
 for (const event of LIST_EVENTS) {
    socket.on(event, (data) => {
        lists[event] = data;
@@ -113,6 +123,34 @@ async function ensureSettings() {
    report("settings", true);
 }

+async function ensureNotification() {
+    const port = Number(env.KUMA_SMTP_PORT);
+    const desired = {
+        name: "email",
+        type: "smtp",
+        isDefault: true,
+        smtpHost: env.KUMA_SMTP_HOST,
+        smtpPort: port,
+        // 465 is implicit TLS; any other port uses STARTTLS.
+        smtpSecure: port === 465,
+        smtpIgnoreSTARTTLS: false,
+        smtpUsername: env.KUMA_SMTP_USERNAME,
+        smtpPassword: env.KUMA_SMTP_PASSWORD,
+        smtpFrom: env.KUMA_SMTP_FROM,
+        smtpTo: env.KUMA_SMTP_TO,
+    };
+    const existing = (lists.notificationList || []).filter((n) => n.name === desired.name).sort((a, b) => a.id - b.id)[0];
+    const current = existing ? JSON.parse(existing.config || "{}") : {};
+    const upToDate =
+        existing && existing.isDefault === true && Object.keys(desired).every((key) => current[key] === desired[key]);
+    if (upToDate) {
+        report("notification", false);
+        return;
+    }
+    await callOk("addNotification", { ...current, ...desired, applyExisting: true }, existing ? existing.id : null);
+    report("notification", true);
+}
+
 async function rotateMetricsApiKey() {
    if (!rotateMetricsKey) {
        report("metrics api key", false);
@@ -131,6 +169,7 @@ async function main() {
    await setupAdmin();
    await login();
    await ensureSettings();
+    await ensureNotification();
    await rotateMetricsApiKey();
 }

@@ -23,6 +23,18 @@
  register: _uptime_kuma_secret_read
  no_log: true

+- name: Read SMTP credentials from OpenBao
+  ansible.builtin.uri:
+    url: "{{ uptime_kuma_openbao_url }}/v1/{{ uptime_kuma_openbao_mount }}/data/{{ uptime_kuma_openbao_smtp_path }}"
+    headers:
+      X-Vault-Token: "{{ uptime_kuma_openbao_token }}"
+  delegate_to: localhost
+  become: false
+  run_once: true
+  check_mode: false
+  register: _uptime_kuma_smtp_read
+  no_log: true
+
 # 404 until the role has stored a key for the first time.
 - name: Read metrics API key from OpenBao
  ansible.builtin.uri:
@@ -40,6 +52,7 @@
 - name: Extract the OpenBao secrets
  ansible.builtin.set_fact:
    _uptime_kuma_secret: "{{ _uptime_kuma_secret_read.json.data.data }}"
+    _uptime_kuma_smtp: "{{ _uptime_kuma_smtp_read.json.data.data }}"
    _uptime_kuma_metrics_key: "{{ _uptime_kuma_metrics_read.json.data.data.api_key if _uptime_kuma_metrics_read.status == 200 else '' }}"
  no_log: true

@@ -127,6 +140,18 @@
      - -e
      - KUMA_BASE_URL
      - -e
+      - KUMA_SMTP_HOST
+      - -e
+      - KUMA_SMTP_PORT
+      - -e
+      - KUMA_SMTP_USERNAME
+      - -e
+      - KUMA_SMTP_PASSWORD
+      - -e
+      - KUMA_SMTP_FROM
+      - -e
+      - KUMA_SMTP_TO
+      - -e
      - KUMA_METRICS_ROTATE
      - -e
      - KUMA_METRICS_KEY_FILE
@@ -139,6 +164,12 @@
    KUMA_SETUP_USERNAME: "{{ _uptime_kuma_secret.username }}"
    KUMA_SETUP_PASSWORD: "{{ _uptime_kuma_secret.password }}"
    KUMA_BASE_URL: "{{ uptime_kuma_base_url }}"
+    KUMA_SMTP_HOST: "{{ _uptime_kuma_smtp.server }}"
+    KUMA_SMTP_PORT: "{{ _uptime_kuma_smtp.port }}"
+    KUMA_SMTP_USERNAME: "{{ _uptime_kuma_smtp.username }}"
+    KUMA_SMTP_PASSWORD: "{{ _uptime_kuma_smtp.token }}"
+    KUMA_SMTP_FROM: "{{ uptime_kuma_smtp_from }}"
+    KUMA_SMTP_TO: "{{ uptime_kuma_smtp_to }}"
    KUMA_METRICS_ROTATE: "{{ 'false' if (_uptime_kuma_metrics_check.status | default(0)) == 200 else 'true' }}"
    KUMA_METRICS_KEY_FILE: /app/data/.metrics-api-key
  register: _uptime_kuma_setup
@@ -13,8 +13,12 @@ zwave_base_dir: "{{ edge_base_dir }}/zwave-js"
 # survives moving the stick between machines.
 edge_zwave_device: /dev/serial/by-id/usb-Nabu_Casa_ZWA-2_80B54EE15720-if00

-# Renovate-tracked (customManagers in renovate.json).
-edge_zwavejs_image: ghcr.io/zwave-js/zwave-js-ui:11.25.2@sha256:ac4874a3cbea61c0c60002a8fd8ae05104cc8eb2eae91aa05bd184972aa06853
+edge_zwavejs_image: ghcr.io/zwave-js/zwave-js-ui:11.21.1
+
+# Alpine version the zwave-js-ui image is built on -- the source for the musl
+# libeatmydata.so preloaded into that container. Keep in sync if the image
+# bumps its Alpine major (check: docker exec zwave-js cat /etc/os-release).
+edge_zwave_alpine_base: alpine:3.22

 # Secret from inventory/group_vars/edge_host/vault.yml:
 #   edge_zwavejs_session_secret
@@ -15,31 +15,17 @@
    - "{{ zwave_base_dir }}"
    - "{{ zwave_base_dir }}/store"

-# The preloaded .so is musl and must come from the image's own Alpine release.
- name: Read the Alpine release of the zwave-js-ui image
-  ansible.builtin.command:
-    cmd: docker run --rm --entrypoint cat {{ edge_zwavejs_image }} /etc/alpine-release
-  register: zwave_alpine_release
-  changed_when: false
-  check_mode: false
-
- name: Name libeatmydata.so after that Alpine release
-  ansible.builtin.set_fact:
-    zwave_alpine_minor: "{{ zwave_alpine_release.stdout.split('.')[:2] | join('.') }}"
-    zwave_libeatmydata: "libeatmydata-alpine{{ zwave_alpine_release.stdout.split('.')[:2] | join('.') }}.so"
-
 - name: Extract musl libeatmydata.so (matches the zwave-js-ui Alpine base)
  ansible.builtin.shell:
    cmd: |
      set -euo pipefail
      tmp="$(mktemp)"
      trap 'rm -f "$tmp"' EXIT
-      docker run --rm --network=host alpine:{{ zwave_alpine_minor }} \
+      docker run --rm --network=host {{ edge_zwave_alpine_base }} \
        sh -c 'apk add --no-cache libeatmydata >/dev/null 2>&1 && cat /usr/lib/libeatmydata.so' > "$tmp"
      test "$(stat -c%s "$tmp")" -ge 8000   # sanity: real .so is ~14 KB, guards against a failed/empty pull
-      install -m 0644 "$tmp" {{ zwave_base_dir }}/{{ zwave_libeatmydata }}
-    creates: "{{ zwave_base_dir }}/{{ zwave_libeatmydata }}"
-    executable: /bin/bash
+      install -m 0644 "$tmp" {{ zwave_base_dir }}/libeatmydata.so
+    creates: "{{ zwave_base_dir }}/libeatmydata.so"
  notify: Restart zwave-js

 # Because fsync is neutralized, a hard power-loss during the (rare) settings
@@ -107,18 +93,3 @@
      zwave-js could not start -- the ZWA-2 radio is not present:
      {{ zwave_compose_up.stderr_lines | select('search', 'device') | list }}
  when: zwave_compose_up.rc != 0
-
- name: Find libeatmydata.so builds of other Alpine releases
-  ansible.builtin.find:
-    paths: "{{ zwave_base_dir }}"
-    patterns: "libeatmydata*.so"
-    excludes: "{{ zwave_libeatmydata }}"
-  register: zwave_stale_libeatmydata
-
- name: Remove libeatmydata.so builds of other Alpine releases
-  ansible.builtin.file:
-    path: "{{ item.path }}"
-    state: absent
-  loop: "{{ zwave_stale_libeatmydata.files }}"
-  loop_control:
-    label: "{{ item.path }}"
@@ -31,7 +31,7 @@ services:
      - "{{ edge_zwave_device }}:/dev/zwave"
    volumes:
      # musl libeatmydata.so extracted from the image's Alpine base (ro)
-      - ./{{ zwave_libeatmydata }}:/usr/lib/libeatmydata.so:ro
+      - ./libeatmydata.so:/usr/lib/libeatmydata.so:ro
      # Persistent store: settings.json, device DB, network keys. Path is
      # unchanged from the previous shared project, so nothing is migrated.
      - ./store:/usr/src/app/store
@@ -8,10 +8,10 @@
 # One-off actions are not state and stay separate: plays/update-os.yml,
 # plays/update-dist-upgrade.yml, plays/rotate-netbird-secrets.yml.

- name: Synology Python
-  ansible.builtin.import_playbook: plays/configure-synology-python.yml
 - name: Base system
  ansible.builtin.import_playbook: plays/common.yml
+- name: VM time sync
+  ansible.builtin.import_playbook: plays/configure-vm-time-sync.yml

 - name: SSH user CA
  ansible.builtin.import_playbook: plays/configure-ssh-ca.yml
@@ -31,6 +31,8 @@
  ansible.builtin.import_playbook: plays/install-edge-host.yml
 - name: Z-Wave gateway
  ansible.builtin.import_playbook: plays/install-zwave-gateway.yml
+- name: Heating CAN
+  ansible.builtin.import_playbook: plays/install-heating-can.yml
 - name: NTP service
  ansible.builtin.import_playbook: plays/install-ntp-ha.yml

@@ -5,12 +5,12 @@

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

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

 RUN useradd --system --no-create-home --shell /usr/sbin/nologin controller
 COPY --from=test /src/controller.py /opt/controller.py
@@ -1,4 +1,4 @@
-FROM node:26-alpine@sha256:c6ad9e9c1d80f6eb607c26b4b0a132ff7a2344fad1c78ea3baa2a7d4c8de6d94
+FROM node:24-alpine@sha256:06d7adf3e0ef61a13f1d28682726366f97a15aa1888c934d3ecec86c33918b53

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

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

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


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

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

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

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

-FROM gcr.io/distroless/static:nonroot@sha256:25ac8f0c3b2334a9eb05452266bd4697864a8c8ef0ef71e5e6480d7f92868329
+FROM gcr.io/distroless/static:nonroot@sha256:18f4cc26c9ffa7f20a359298be7deadac5c607c8e03a02b8119f1a5fc2f82c99
 COPY --from=build /out/kuma-sync /kuma-sync
 USER 65532
 ENTRYPOINT ["/kuma-sync"]
@@ -97,10 +97,6 @@ type KumaMonitorSpec struct {
 	// +kubebuilder:validation:Minimum=0
 	// +kubebuilder:default=0
 	MaxRetries int32 `json:"maxRetries,omitempty"`
-	// Consecutive DOWN heartbeats after which Kuma sends the DOWN notification
-	// again, not minutes; 0 sends it once per outage.
-	// +kubebuilder:validation:Minimum=0
-	ResendInterval int32 `json:"resendInterval,omitempty"`
 	// Seconds.
 	// +kubebuilder:validation:Minimum=1
 	Timeout     *int32 `json:"timeout,omitempty"`
@@ -112,17 +108,6 @@ type KumaMonitorSpec struct {
 	JSONQuery *JSONQuerySpec `json:"jsonQuery,omitempty"`
 	DNS       *DNSSpec       `json:"dns,omitempty"`
 	Port      *PortSpec      `json:"port,omitempty"`
-
-	// KumaNotifications attached to the monitor; none attaches no notification.
-	// +listType=map
-	// +listMapKey=name
-	NotificationRefs []NotificationRef `json:"notificationRefs,omitempty"`
-}
-
-// NotificationRef references a KumaNotification.
-type NotificationRef struct {
-	// +kubebuilder:validation:MinLength=1
-	Name string `json:"name"`
 }

 type KumaMonitorStatus struct {
@@ -1,66 +0,0 @@
-package v1alpha1
-
-import (
-	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
-)
-
-// SecretRef references a Secret in any namespace.
-type SecretRef struct {
-	// +kubebuilder:validation:MinLength=1
-	Namespace string `json:"namespace"`
-	// +kubebuilder:validation:MinLength=1
-	Name string `json:"name"`
-}
-
-// SMTPSpec configures an smtp notification. The server and its credentials
-// come from the Secret: keys host, port, username and password, all required.
-// Port 465 uses implicit TLS, any other port STARTTLS.
-type SMTPSpec struct {
-	// +kubebuilder:validation:MinLength=1
-	From string `json:"from"`
-	// +kubebuilder:validation:MinLength=1
-	To        string    `json:"to"`
-	SecretRef SecretRef `json:"secretRef"`
-}
-
-// +kubebuilder:validation:XValidation:rule="(self.type == 'smtp') == has(self.smtp)",message="smtp is required for type smtp and forbidden otherwise"
-type KumaNotificationSpec struct {
-	// +kubebuilder:validation:Enum=smtp
-	Type string    `json:"type"`
-	SMTP *SMTPSpec `json:"smtp,omitempty"`
-}
-
-type KumaNotificationStatus struct {
-	NotificationID     int64 `json:"notificationID,omitempty"`
-	ObservedGeneration int64 `json:"observedGeneration,omitempty"`
-	// +listType=map
-	// +listMapKey=type
-	Conditions []metav1.Condition `json:"conditions,omitempty"`
-}
-
-// KumaNotification is the Kuma notification named like the resource. It is
-// never a default notification and never applied to existing monitors;
-// KumaMonitors attach it through notificationRefs.
-// +kubebuilder:object:root=true
-// +kubebuilder:subresource:status
-// +kubebuilder:resource:path=kumanotifications,scope=Cluster
-// +kubebuilder:printcolumn:name="Type",type=string,JSONPath=`.spec.type`
-// +kubebuilder:printcolumn:name="Ready",type=string,JSONPath=`.status.conditions[?(@.type=="Ready")].status`
-type KumaNotification struct {
-	metav1.TypeMeta   `json:",inline"`
-	metav1.ObjectMeta `json:"metadata,omitempty"`
-
-	Spec   KumaNotificationSpec   `json:"spec"`
-	Status KumaNotificationStatus `json:"status,omitempty"`
-}
-
-// +kubebuilder:object:root=true
-type KumaNotificationList struct {
-	metav1.TypeMeta `json:",inline"`
-	metav1.ListMeta `json:"metadata,omitempty"`
-	Items           []KumaNotification `json:"items"`
-}
-
-func init() {
-	SchemeBuilder.Register(&KumaNotification{}, &KumaNotificationList{})
-}
@@ -1,78 +0,0 @@
-//go:build envtest
-
-package v1alpha1
-
-import (
-	"context"
-	"strings"
-	"testing"
-
-	"k8s.io/apimachinery/pkg/api/errors"
-	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
-)
-
-func smtpNotification(name string) *KumaNotification {
-	return &KumaNotification{
-		ObjectMeta: metav1.ObjectMeta{Name: name},
-		Spec: KumaNotificationSpec{Type: "smtp", SMTP: &SMTPSpec{
-			From: "kuma@renner.uno", To: "ops@renner.uno",
-			SecretRef: SecretRef{Namespace: "kuma-sync", Name: "smtp"},
-		}},
-	}
-}
-
-func expectNotificationInvalid(t *testing.T, n *KumaNotification, wants ...string) {
-	t.Helper()
-	err := k8s.Create(context.Background(), n)
-	if err == nil || !errors.IsInvalid(err) {
-		t.Fatalf("expected invalid, got %v", err)
-	}
-	for _, w := range wants {
-		if !strings.Contains(err.Error(), w) {
-			t.Fatalf("error %q does not contain %q", err.Error(), w)
-		}
-	}
-}
-
-func TestValidNotification(t *testing.T) {
-	if err := k8s.Create(context.Background(), smtpNotification("valid-smtp")); err != nil {
-		t.Fatalf("expected accept, got %v", err)
-	}
-}
-
-func TestNotificationInvalidSpecs(t *testing.T) {
-	noSMTP := smtpNotification("no-smtp")
-	noSMTP.Spec.SMTP = nil
-	expectNotificationInvalid(t, noSMTP, "smtp is required for type smtp")
-
-	webhook := smtpNotification("webhook")
-	webhook.Spec.Type = "webhook"
-	expectNotificationInvalid(t, webhook, "spec.type")
-
-	noTo := smtpNotification("no-to")
-	noTo.Spec.SMTP.To = ""
-	expectNotificationInvalid(t, noTo, "spec.smtp.to")
-
-	noSecret := smtpNotification("no-secret")
-	noSecret.Spec.SMTP.SecretRef.Namespace = ""
-	expectNotificationInvalid(t, noSecret, "spec.smtp.secretRef.namespace")
-}
-
-func TestMonitorNotificationRefs(t *testing.T) {
-	m := monitor("with-refs", KumaMonitorSpec{
-		Type: "group", DisplayName: "g",
-		NotificationRefs: []NotificationRef{{Name: "mail"}, {Name: "ops"}},
-	})
-	if err := k8s.Create(context.Background(), m); err != nil {
-		t.Fatalf("expected accept, got %v", err)
-	}
-	dup := monitor("dup-refs", KumaMonitorSpec{
-		Type: "group", DisplayName: "g",
-		NotificationRefs: []NotificationRef{{Name: "mail"}, {Name: "mail"}},
-	})
-	expectInvalid(t, dup, "Duplicate value")
-	empty := monitor("empty-ref", KumaMonitorSpec{
-		Type: "group", DisplayName: "g", NotificationRefs: []NotificationRef{{Name: ""}},
-	})
-	expectInvalid(t, empty, "spec.notificationRefs[0].name")
-}
@@ -131,15 +131,6 @@ func TestNegativeMaxRetriesRejected(t *testing.T) {
 	expectInvalid(t, m, "spec.maxRetries")
 }

-func TestNegativeResendIntervalRejected(t *testing.T) {
-	m := monitor("neg-resend", KumaMonitorSpec{
-		Type:           "group",
-		DisplayName:    "g",
-		ResendInterval: -1,
-	})
-	expectInvalid(t, m, "spec.resendInterval")
-}
-
 func TestJSONQueryBadOperator(t *testing.T) {
 	m := monitor("jq-bad-op", KumaMonitorSpec{
 		Type:        "json-query",
@@ -203,11 +203,6 @@ func (in *KumaMonitorSpec) DeepCopyInto(out *KumaMonitorSpec) {
 		*out = new(PortSpec)
 		**out = **in
 	}
-	if in.NotificationRefs != nil {
-		in, out := &in.NotificationRefs, &out.NotificationRefs
-		*out = make([]NotificationRef, len(*in))
-		copy(*out, *in)
-	}
 }

 // DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new KumaMonitorSpec.
@@ -242,107 +237,6 @@ func (in *KumaMonitorStatus) DeepCopy() *KumaMonitorStatus {
 	return out
 }

-// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
-func (in *KumaNotification) DeepCopyInto(out *KumaNotification) {
-	*out = *in
-	out.TypeMeta = in.TypeMeta
-	in.ObjectMeta.DeepCopyInto(&out.ObjectMeta)
-	in.Spec.DeepCopyInto(&out.Spec)
-	in.Status.DeepCopyInto(&out.Status)
-}
-
-// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new KumaNotification.
-func (in *KumaNotification) DeepCopy() *KumaNotification {
-	if in == nil {
-		return nil
-	}
-	out := new(KumaNotification)
-	in.DeepCopyInto(out)
-	return out
-}
-
-// DeepCopyObject is an autogenerated deepcopy function, copying the receiver, creating a new runtime.Object.
-func (in *KumaNotification) DeepCopyObject() runtime.Object {
-	if c := in.DeepCopy(); c != nil {
-		return c
-	}
-	return nil
-}
-
-// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
-func (in *KumaNotificationList) DeepCopyInto(out *KumaNotificationList) {
-	*out = *in
-	out.TypeMeta = in.TypeMeta
-	in.ListMeta.DeepCopyInto(&out.ListMeta)
-	if in.Items != nil {
-		in, out := &in.Items, &out.Items
-		*out = make([]KumaNotification, len(*in))
-		for i := range *in {
-			(*in)[i].DeepCopyInto(&(*out)[i])
-		}
-	}
-}
-
-// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new KumaNotificationList.
-func (in *KumaNotificationList) DeepCopy() *KumaNotificationList {
-	if in == nil {
-		return nil
-	}
-	out := new(KumaNotificationList)
-	in.DeepCopyInto(out)
-	return out
-}
-
-// DeepCopyObject is an autogenerated deepcopy function, copying the receiver, creating a new runtime.Object.
-func (in *KumaNotificationList) DeepCopyObject() runtime.Object {
-	if c := in.DeepCopy(); c != nil {
-		return c
-	}
-	return nil
-}
-
-// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
-func (in *KumaNotificationSpec) DeepCopyInto(out *KumaNotificationSpec) {
-	*out = *in
-	if in.SMTP != nil {
-		in, out := &in.SMTP, &out.SMTP
-		*out = new(SMTPSpec)
-		**out = **in
-	}
-}
-
-// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new KumaNotificationSpec.
-func (in *KumaNotificationSpec) DeepCopy() *KumaNotificationSpec {
-	if in == nil {
-		return nil
-	}
-	out := new(KumaNotificationSpec)
-	in.DeepCopyInto(out)
-	return out
-}
-
-// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
-func (in *KumaNotificationStatus) DeepCopyInto(out *KumaNotificationStatus) {
-	*out = *in
-	if in.Conditions != nil {
-		in, out := &in.Conditions, &out.Conditions
-		*out = make([]v1.Condition, len(*in))
-		for i := range *in {
-			(*in)[i].DeepCopyInto(&(*out)[i])
-		}
-	}
-}
-
-// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new KumaNotificationStatus.
-func (in *KumaNotificationStatus) DeepCopy() *KumaNotificationStatus {
-	if in == nil {
-		return nil
-	}
-	out := new(KumaNotificationStatus)
-	in.DeepCopyInto(out)
-	return out
-}
-
 // DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
 func (in *KumaStatusPage) DeepCopyInto(out *KumaStatusPage) {
 	*out = *in
@@ -471,21 +365,6 @@ func (in *LocalRef) DeepCopy() *LocalRef {
 	return out
 }

-// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
-func (in *NotificationRef) DeepCopyInto(out *NotificationRef) {
-	*out = *in
-}
-
-// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new NotificationRef.
-func (in *NotificationRef) DeepCopy() *NotificationRef {
-	if in == nil {
-		return nil
-	}
-	out := new(NotificationRef)
-	in.DeepCopyInto(out)
-	return out
-}
-
 // DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
 func (in *PortSpec) DeepCopyInto(out *PortSpec) {
 	*out = *in
@@ -501,37 +380,6 @@ func (in *PortSpec) DeepCopy() *PortSpec {
 	return out
 }

-// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
-func (in *SMTPSpec) DeepCopyInto(out *SMTPSpec) {
-	*out = *in
-	out.SecretRef = in.SecretRef
-}
-
-// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new SMTPSpec.
-func (in *SMTPSpec) DeepCopy() *SMTPSpec {
-	if in == nil {
-		return nil
-	}
-	out := new(SMTPSpec)
-	in.DeepCopyInto(out)
-	return out
-}
-
-// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
-func (in *SecretRef) DeepCopyInto(out *SecretRef) {
-	*out = *in
-}
-
-// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new SecretRef.
-func (in *SecretRef) DeepCopy() *SecretRef {
-	if in == nil {
-		return nil
-	}
-	out := new(SecretRef)
-	in.DeepCopyInto(out)
-	return out
-}
-
 // DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
 func (in *SectionStatus) DeepCopyInto(out *SectionStatus) {
 	*out = *in
@@ -3,25 +3,19 @@ package main
 import (
 	"errors"
 	"fmt"
-	"strings"
-
-	"k8s.io/apimachinery/pkg/types"
-	"k8s.io/apimachinery/pkg/util/validation"
 )

 type config struct {
 	URL      string
 	Username string
 	Password string
-	// RootGroup is the zero value when KUMA_ROOT_GROUP is unset.
-	RootGroup types.NamespacedName
 }

 // loadConfig reads the Kuma connection settings from the environment. It
-// names every missing or invalid variable.
+// names every missing variable.
 func loadConfig(getenv func(string) string) (config, error) {
 	var cfg config
-	var errs []error
+	var missing []error
 	for _, v := range []struct {
 		name string
 		dst  *string
@@ -31,30 +25,8 @@ func loadConfig(getenv func(string) string) (config, error) {
 		{"KUMA_PASSWORD", &cfg.Password},
 	} {
 		if *v.dst = getenv(v.name); *v.dst == "" {
-			errs = append(errs, fmt.Errorf("missing required environment variable %s", v.name))
+			missing = append(missing, fmt.Errorf("missing required environment variable %s", v.name))
 		}
 	}
-	if raw := getenv("KUMA_ROOT_GROUP"); raw != "" {
-		root, err := parseRootGroup(raw)
-		if err != nil {
-			errs = append(errs, fmt.Errorf("KUMA_ROOT_GROUP: %w", err))
-		}
-		cfg.RootGroup = root
-	}
-	return cfg, errors.Join(errs...)
-}
-
-// parseRootGroup parses namespace/name of a KumaMonitor.
-func parseRootGroup(raw string) (types.NamespacedName, error) {
-	ns, name, ok := strings.Cut(raw, "/")
-	if !ok || strings.Contains(name, "/") {
-		return types.NamespacedName{}, fmt.Errorf("%q is not namespace/name", raw)
-	}
-	if msgs := validation.IsDNS1123Label(ns); len(msgs) > 0 {
-		return types.NamespacedName{}, fmt.Errorf("namespace %q: %s", ns, strings.Join(msgs, "; "))
-	}
-	if msgs := validation.IsDNS1123Subdomain(name); len(msgs) > 0 {
-		return types.NamespacedName{}, fmt.Errorf("name %q: %s", name, strings.Join(msgs, "; "))
-	}
-	return types.NamespacedName{Namespace: ns, Name: name}, nil
+	return cfg, errors.Join(missing...)
 }
@@ -3,8 +3,6 @@ package main
 import (
 	"strings"
 	"testing"
-
-	"k8s.io/apimachinery/pkg/types"
 )

 func TestLoadConfig(t *testing.T) {
@@ -38,21 +36,3 @@ func TestLoadConfig(t *testing.T) {
 		}
 	}
 }
-
-func TestLoadConfigRootGroup(t *testing.T) {
-	env := func(root string) func(string) string {
-		m := map[string]string{"KUMA_URL": "http://kuma", "KUMA_USERNAME": "u", "KUMA_PASSWORD": "p", "KUMA_ROOT_GROUP": root}
-		return func(k string) string { return m[k] }
-	}
-
-	cfg, err := loadConfig(env("kuma-sync/renner-uno"))
-	if err != nil || cfg.RootGroup != (types.NamespacedName{Namespace: "kuma-sync", Name: "renner-uno"}) {
-		t.Fatalf("cfg=%+v err=%v", cfg, err)
-	}
-
-	for _, bad := range []string{"renner-uno", "/renner-uno", "kuma-sync/", "a/b/c", "Kuma/x", "ns/UPPER", " ns/x"} {
-		if _, err := loadConfig(env(bad)); err == nil || !strings.Contains(err.Error(), "KUMA_ROOT_GROUP") {
-			t.Errorf("%q: err = %v, want KUMA_ROOT_GROUP rejected", bad, err)
-		}
-	}
-}
@@ -48,7 +48,6 @@ func run() error {
 		GCInterval:  5 * time.Minute,
 		OrphanGrace: time.Hour,
 		Resync:      5 * time.Minute,
-		RootGroup:   cfg.RootGroup,
 	})
 	if err != nil {
 		return err
@@ -182,22 +182,6 @@ spec:
                format: int32
                minimum: 0
                type: integer
-              notificationRefs:
-                description: KumaNotifications attached to the monitor; none attaches
-                  no notification.
-                items:
-                  description: NotificationRef references a KumaNotification.
-                  properties:
-                    name:
-                      minLength: 1
-                      type: string
-                  required:
-                  - name
-                  type: object
-                type: array
-                x-kubernetes-list-map-keys:
-                - name
-                x-kubernetes-list-type: map
              parentRef:
                description: LocalRef references a KumaMonitor in the same namespace.
                properties:
@@ -222,13 +206,6 @@ spec:
                - hostname
                - port
                type: object
-              resendInterval:
-                description: |-
-                  Consecutive DOWN heartbeats after which Kuma sends the DOWN notification
-                  again, not minutes; 0 sends it once per outage.
-                format: int32
-                minimum: 0
-                type: integer
              retryInterval:
                default: 60
                description: Seconds.
@@ -1,165 +0,0 @@
---
-apiVersion: apiextensions.k8s.io/v1
-kind: CustomResourceDefinition
-metadata:
-  annotations:
-    controller-gen.kubebuilder.io/version: v0.23.0
-  name: kumanotifications.uptime.renner.uno
-spec:
-  group: uptime.renner.uno
-  names:
-    kind: KumaNotification
-    listKind: KumaNotificationList
-    plural: kumanotifications
-    singular: kumanotification
-  scope: Cluster
-  versions:
-  - additionalPrinterColumns:
-    - jsonPath: .spec.type
-      name: Type
-      type: string
-    - jsonPath: .status.conditions[?(@.type=="Ready")].status
-      name: Ready
-      type: string
-    name: v1alpha1
-    schema:
-      openAPIV3Schema:
-        description: |-
-          KumaNotification is the Kuma notification named like the resource. It is
-          never a default notification and never applied to existing monitors;
-          KumaMonitors attach it through notificationRefs.
-        properties:
-          apiVersion:
-            description: |-
-              APIVersion defines the versioned schema of this representation of an object.
-              Servers should convert recognized schemas to the latest internal value, and
-              may reject unrecognized values.
-              More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
-            type: string
-          kind:
-            description: |-
-              Kind is a string value representing the REST resource this object represents.
-              Servers may infer this from the endpoint the client submits requests to.
-              Cannot be updated.
-              In CamelCase.
-              More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
-            type: string
-          metadata:
-            type: object
-          spec:
-            properties:
-              smtp:
-                description: |-
-                  SMTPSpec configures an smtp notification. The server and its credentials
-                  come from the Secret: keys host, port, username and password, all required.
-                  Port 465 uses implicit TLS, any other port STARTTLS.
-                properties:
-                  from:
-                    minLength: 1
-                    type: string
-                  secretRef:
-                    description: SecretRef references a Secret in any namespace.
-                    properties:
-                      name:
-                        minLength: 1
-                        type: string
-                      namespace:
-                        minLength: 1
-                        type: string
-                    required:
-                    - name
-                    - namespace
-                    type: object
-                  to:
-                    minLength: 1
-                    type: string
-                required:
-                - from
-                - secretRef
-                - to
-                type: object
-              type:
-                enum:
-                - smtp
-                type: string
-            required:
-            - type
-            type: object
-            x-kubernetes-validations:
-            - message: smtp is required for type smtp and forbidden otherwise
-              rule: (self.type == 'smtp') == has(self.smtp)
-          status:
-            properties:
-              conditions:
-                items:
-                  description: Condition contains details for one aspect of the current
-                    state of this API Resource.
-                  properties:
-                    lastTransitionTime:
-                      description: |-
-                        lastTransitionTime is the last time the condition transitioned from one status to another.
-                        This should be when the underlying condition changed.  If that is not known, then using the time when the API field changed is acceptable.
-                      format: date-time
-                      type: string
-                    message:
-                      description: |-
-                        message is a human readable message indicating details about the transition.
-                        This may be an empty string.
-                      maxLength: 32768
-                      type: string
-                    observedGeneration:
-                      description: |-
-                        observedGeneration represents the .metadata.generation that the condition was set based upon.
-                        For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date
-                        with respect to the current state of the instance.
-                      format: int64
-                      minimum: 0
-                      type: integer
-                    reason:
-                      description: |-
-                        reason contains a programmatic identifier indicating the reason for the condition's last transition.
-                        Producers of specific condition types may define expected values and meanings for this field,
-                        and whether the values are considered a guaranteed API.
-                        The value should be a CamelCase string.
-                        This field may not be empty.
-                      maxLength: 1024
-                      minLength: 1
-                      pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$
-                      type: string
-                    status:
-                      description: status of the condition, one of True, False, Unknown.
-                      enum:
-                      - "True"
-                      - "False"
-                      - Unknown
-                      type: string
-                    type:
-                      description: type of condition in CamelCase or in foo.example.com/CamelCase.
-                      maxLength: 316
-                      pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$
-                      type: string
-                  required:
-                  - lastTransitionTime
-                  - message
-                  - reason
-                  - status
-                  - type
-                  type: object
-                type: array
-                x-kubernetes-list-map-keys:
-                - type
-                x-kubernetes-list-type: map
-              notificationID:
-                format: int64
-                type: integer
-              observedGeneration:
-                format: int64
-                type: integer
-            type: object
-        required:
-        - spec
-        type: object
-    served: true
-    storage: true
-    subresources:
-      status: {}
@@ -21,7 +21,6 @@ rules:
  - uptime.renner.uno
  resources:
  - kumamonitors
-  - kumanotifications
  - kumastatuspages
  verbs:
  - get
@@ -33,7 +32,6 @@ rules:
  - uptime.renner.uno
  resources:
  - kumamonitors/finalizers
-  - kumanotifications/finalizers
  - kumastatuspages/finalizers
  verbs:
  - update
@@ -41,7 +39,6 @@ rules:
  - uptime.renner.uno
  resources:
  - kumamonitors/status
-  - kumanotifications/status
  - kumastatuspages/status
  verbs:
  - get
@@ -10,7 +10,6 @@ import (
 	"time"

 	"k8s.io/apimachinery/pkg/runtime"
-	"k8s.io/apimachinery/pkg/types"
 	clientgoscheme "k8s.io/client-go/kubernetes/scheme"
 	"k8s.io/client-go/rest"
 	"k8s.io/utils/ptr"
@@ -42,9 +41,6 @@ type Options struct {
 	// Resync is how often a healthy resource is reconciled again, which is
 	// what repairs drift made in Kuma; 0 means 5 minutes.
 	Resync time.Duration
-	// RootGroup is the group KumaMonitor that monitors without a parentRef are
-	// placed under; the zero value leaves them at the top level.
-	RootGroup types.NamespacedName

 	// SkipNameValidation allows several managers in one process, as in tests
 	// that restart the manager.
@@ -76,19 +72,12 @@ func NewManager(o Options) (manager.Manager, error) {
 		return nil, fmt.Errorf("create manager: %w", err)
 	}

-	if err := (&controller.Reconciler{
-		Client: mgr.GetClient(), Kuma: o.Kuma, Resync: o.Resync, RootGroup: o.RootGroup,
-	}).SetupWithManager(mgr); err != nil {
+	if err := (&controller.Reconciler{Client: mgr.GetClient(), Kuma: o.Kuma, Resync: o.Resync}).SetupWithManager(mgr); err != nil {
 		return nil, fmt.Errorf("set up reconciler: %w", err)
 	}
 	if err := (&controller.StatusPageReconciler{Client: mgr.GetClient(), Kuma: o.Kuma, Resync: o.Resync}).SetupWithManager(mgr); err != nil {
 		return nil, fmt.Errorf("set up status page reconciler: %w", err)
 	}
-	if err := (&controller.NotificationReconciler{
-		Client: mgr.GetClient(), APIReader: mgr.GetAPIReader(), Kuma: o.Kuma, Resync: o.Resync,
-	}).SetupWithManager(mgr); err != nil {
-		return nil, fmt.Errorf("set up notification reconciler: %w", err)
-	}
 	if err := mgr.Add(&controller.GC{
 		Client:      mgr.GetClient(),
 		Kuma:        o.Kuma,
@@ -7,6 +7,7 @@ import (
 	"fmt"
 	"io"
 	"path/filepath"
+	"slices"
 	"sync"
 	"testing"
 	"time"
@@ -20,7 +21,6 @@ import (
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/runtime"
 	"k8s.io/apimachinery/pkg/types"
-	clientgoscheme "k8s.io/client-go/kubernetes/scheme"
 	"k8s.io/client-go/util/retry"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 	"sigs.k8s.io/controller-runtime/pkg/envtest"
@@ -85,9 +85,6 @@ func newE2E(t *testing.T) (*e2e, *envtest.Environment) {
 	t.Cleanup(func() { _ = env.Stop() })

 	scheme := runtime.NewScheme()
-	if err := clientgoscheme.AddToScheme(scheme); err != nil {
-		t.Fatal(err)
-	}
 	if err := v1.AddToScheme(scheme); err != nil {
 		t.Fatal(err)
 	}
@@ -414,6 +411,46 @@ func (f *e2e) webhook(name string, isDefault bool) int64 {
 	return id
 }

+func TestE2EDefaultNotifications(t *testing.T) {
+	f, env := newE2E(t)
+	first := f.webhook("first", true)
+	f.webhook("opt-in", false)
+	f.start(env)
+	f.apply(group("g", ""), dns("probe", "g"))
+
+	carry := func(want ...int64) func() (bool, string) {
+		return func() (bool, string) {
+			m := byKey(f.owned())
+			for _, k := range []string{"default/g", "default/probe"} {
+				got, ok := m[k]
+				if !ok {
+					return false, k + " missing"
+				}
+				if !slices.Equal(got.NotificationIDs, want) {
+					return false, fmt.Sprintf("%s carries %v, want %v", k, got.NotificationIDs, want)
+				}
+			}
+			return true, ""
+		}
+	}
+	eventually(t, 30*time.Second, "monitors created with the default notification", carry(first))
+
+	second := f.webhook("second", true)
+	want := []int64{first, second}
+	slices.Sort(want)
+	eventually(t, 30*time.Second, "new default notification attached by a resync", carry(want...))
+
+	var live monitor.DNS
+	if err := f.raw.GetMonitorAs(t.Context(), byKey(f.owned())["default/probe"].ID, &live); err != nil {
+		t.Fatal(err)
+	}
+	live.NotificationIDs = nil
+	if err := f.raw.UpdateMonitor(t.Context(), &live); err != nil {
+		t.Fatal(err)
+	}
+	eventually(t, 30*time.Second, "notifications removed by hand restored by a resync", carry(want...))
+}
+
 // A monitor that lost its ownership tag in the UI must not get a twin when the
 // controller restarts: the resource reports NotOwned and nothing is created.
 func TestE2ETagRemovedNeverDuplicates(t *testing.T) {
@@ -17,11 +17,8 @@ import (
 	"sigs.k8s.io/controller-runtime/pkg/builder"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 	"sigs.k8s.io/controller-runtime/pkg/controller/controllerutil"
-	"sigs.k8s.io/controller-runtime/pkg/event"
-	"sigs.k8s.io/controller-runtime/pkg/handler"
 	"sigs.k8s.io/controller-runtime/pkg/log"
 	"sigs.k8s.io/controller-runtime/pkg/predicate"
-	"sigs.k8s.io/controller-runtime/pkg/reconcile"

 	v1 "gitea.renner.uno/konairius/homelab/kuma-sync/api/v1alpha1"
 	"gitea.renner.uno/konairius/homelab/kuma-sync/internal/kumaclient"
@@ -30,16 +27,15 @@ import (
 const (
 	Finalizer = "uptime.renner.uno/kuma-sync"

-	ReasonSynced              = "Synced"
-	ReasonParentPending       = "ParentPending"
-	ReasonInvalidParent       = "InvalidParent"
-	ReasonOwnerTagMissing     = "OwnerTagMissing"
-	ReasonOwnerConflict       = "OwnerConflict"
-	ReasonDuplicateOwner      = "DuplicateOwner"
-	ReasonKumaUnavailable     = "KumaUnavailable"
-	ReasonPossibleOrphan      = "PossibleOrphan"
-	ReasonNotOwned            = "NotOwned"
-	ReasonNotificationPending = "NotificationPending"
+	ReasonSynced          = "Synced"
+	ReasonParentPending   = "ParentPending"
+	ReasonInvalidParent   = "InvalidParent"
+	ReasonOwnerTagMissing = "OwnerTagMissing"
+	ReasonOwnerConflict   = "OwnerConflict"
+	ReasonDuplicateOwner  = "DuplicateOwner"
+	ReasonKumaUnavailable = "KumaUnavailable"
+	ReasonPossibleOrphan  = "PossibleOrphan"
+	ReasonNotOwned        = "NotOwned"

 	parentRetry    = 10 * time.Second
 	resyncPeriod   = 5 * time.Minute
@@ -58,15 +54,6 @@ type Reconciler struct {
 	// Resync is how often a healthy resource is reconciled again, which repairs
 	// drift made in Kuma. 0 means 5 minutes.
 	Resync time.Duration
-	// RootGroup is the group KumaMonitor every monitor without a parentRef is
-	// placed under in Kuma; the zero value places them at the top level.
-	RootGroup types.NamespacedName
-}
-
-func (r *Reconciler) hasRoot() bool { return r.RootGroup.Name != "" }
-
-func (r *Reconciler) isRoot(o client.Object) bool {
-	return r.hasRoot() && o.GetNamespace() == r.RootGroup.Namespace && o.GetName() == r.RootGroup.Name
 }

 func (r *Reconciler) resync() time.Duration {
@@ -78,19 +65,12 @@ func (r *Reconciler) resync() time.Duration {

 // SetupWithManager ignores status-only updates, which keeps failure backoff
 // intact. Deletion still reconciles: setting deletionTimestamp bumps
-// metadata.generation. A KumaNotification whose ID changes enqueues the
-// monitors referencing it; a change to the root group enqueues the monitors
-// without a parentRef.
+// metadata.generation.
 func (r *Reconciler) SetupWithManager(mgr ctrl.Manager) error {
-	b := ctrl.NewControllerManagedBy(mgr).
+	return ctrl.NewControllerManagedBy(mgr).
 		For(&v1.KumaMonitor{}, builder.WithPredicates(predicate.GenerationChangedPredicate{})).
-		Watches(&v1.KumaNotification{}, handler.EnqueueRequestsFromMapFunc(r.referencingMonitors),
-			builder.WithPredicates(predicate.Funcs{UpdateFunc: notificationIDChanged}))
-	if r.hasRoot() {
-		b = b.Watches(&v1.KumaMonitor{}, handler.EnqueueRequestsFromMapFunc(r.rootChildren),
-			builder.WithPredicates(r.rootPredicate()))
-	}
-	return b.Named("kumamonitor").Complete(r)
+		Named("kumamonitor").
+		Complete(r)
 }

 // failure is a Ready=False outcome. The message is fixed per reason; the cause
@@ -102,22 +82,18 @@ type failure struct {
 }

 const (
-	msgKumaUnavailable     = "Kuma request failed"
-	msgListIncomplete      = "monitor list incomplete: owner conflict on another monitor"
-	msgOwnerTagMissing     = "kuma-sync tag missing in Kuma"
-	msgOwnerConflict       = "monitor carries conflicting kuma-sync tag values"
-	msgPossibleOrphan      = "create outcome unknown, an untagged monitor may exist in Kuma"
-	msgDuplicateOwner      = "several monitors carry this owner key; syncing the lowest ID"
-	msgParentPending       = "parent has no monitor ID yet"
-	msgParentNotGroup      = "parent must be of type group"
-	msgParentCycle         = "parentRef forms a cycle"
-	msgParentTooDeep       = "parentRef chain is too deep"
-	msgRootPending         = "root group has no monitor ID yet"
-	msgRootNotGroup        = "root group must be of type group"
-	msgRootHasParent       = "root group must not have a parentRef"
-	msgNotificationPending = "a referenced notification has no notification ID yet"
-	msgSynced              = "monitor in sync"
-	msgNotOwned            = "previous monitor exists without our ownership tag; restore the tag or delete it in Kuma"
+	msgKumaUnavailable = "Kuma request failed"
+	msgListIncomplete  = "monitor list incomplete: owner conflict on another monitor"
+	msgOwnerTagMissing = "kuma-sync tag missing in Kuma"
+	msgOwnerConflict   = "monitor carries conflicting kuma-sync tag values"
+	msgPossibleOrphan  = "create outcome unknown, an untagged monitor may exist in Kuma"
+	msgDuplicateOwner  = "several monitors carry this owner key; syncing the lowest ID"
+	msgParentPending   = "parent has no monitor ID yet"
+	msgParentNotGroup  = "parent must be of type group"
+	msgParentCycle     = "parentRef forms a cycle"
+	msgParentTooDeep   = "parentRef chain is too deep"
+	msgSynced          = "monitor in sync"
+	msgNotOwned        = "previous monitor exists without our ownership tag; restore the tag or delete it in Kuma"
 )

 func (r *Reconciler) Reconcile(ctx context.Context, req ctrl.Request) (ctrl.Result, error) {
@@ -135,43 +111,29 @@ func (r *Reconciler) Reconcile(ctx context.Context, req ctrl.Request) (ctrl.Resu
 	}

 	desired := Desired(km)
-	var p parentOutcome
-	var err error
-	switch {
-	case km.Spec.ParentRef != nil:
-		p, err = r.resolveParent(ctx, km)
-	case r.hasRoot() && !r.isRoot(km):
-		p, err = r.resolveRoot(ctx)
-	}
-	if err != nil {
-		return ctrl.Result{}, err
-	}
-	if p.reason != "" {
-		if err := r.setReady(ctx, km, metav1.ConditionFalse, p.reason, p.message, nil); err != nil {
+	if km.Spec.ParentRef != nil {
+		p, err := r.resolveParent(ctx, km)
+		if err != nil {
 			return ctrl.Result{}, err
 		}
-		return ctrl.Result{RequeueAfter: p.requeue}, nil
-	}
-	if p.id != 0 {
+		if p.reason != "" {
+			if err := r.setReady(ctx, km, metav1.ConditionFalse, p.reason, p.message, nil); err != nil {
+				return ctrl.Result{}, err
+			}
+			return ctrl.Result{RequeueAfter: p.requeue}, nil
+		}
 		desired.Parent = &p.id
 	}

-	notifications, pending, err := r.resolveNotifications(ctx, km)
-	if err != nil {
-		return ctrl.Result{}, err
-	}
-	if pending {
-		if err := r.setReady(ctx, km, metav1.ConditionFalse, ReasonNotificationPending, msgNotificationPending, nil); err != nil {
-			return ctrl.Result{}, err
-		}
-		return ctrl.Result{RequeueAfter: parentRetry}, nil
-	}
-	desired.NotificationIDs = notifications
-
 	res, fail := r.lookup(ctx, desired.OwnerKey)
 	if fail != nil {
 		return r.fail(ctx, km, fail)
 	}
+	notifications, err := r.Kuma.DefaultNotifications(ctx)
+	if err != nil {
+		return r.fail(ctx, km, &failure{ReasonKumaUnavailable, msgKumaUnavailable, err})
+	}
+	desired.NotificationIDs = notifications

 	var id int64
 	if res.mon == nil {
@@ -288,57 +250,6 @@ func (r *Reconciler) lookup(ctx context.Context, key string) (lookupResult, *fai
 	return res, &failure{ReasonKumaUnavailable, msgListIncomplete, err}
 }

-// resolveNotifications returns the Kuma IDs of the referenced
-// KumaNotifications. pending reports a reference that does not exist, has no
-// notification ID yet or is being deleted. No references yield nil, which
-// detaches every notification in Kuma.
-func (r *Reconciler) resolveNotifications(ctx context.Context, km *v1.KumaMonitor) (ids []int64, pending bool, err error) {
-	for _, ref := range km.Spec.NotificationRefs {
-		kn := &v1.KumaNotification{}
-		err := r.Client.Get(ctx, types.NamespacedName{Name: ref.Name}, kn)
-		if apierrors.IsNotFound(err) {
-			return nil, true, nil
-		}
-		if err != nil {
-			return nil, false, err
-		}
-		if kn.Status.NotificationID == 0 || !kn.DeletionTimestamp.IsZero() {
-			return nil, true, nil
-		}
-		ids = append(ids, kn.Status.NotificationID)
-	}
-	return ids, false, nil
-}
-
-// notificationIDChanged reports changes that alter what a referencing
-// monitor attaches.
-func notificationIDChanged(e event.UpdateEvent) bool {
-	o, ok1 := e.ObjectOld.(*v1.KumaNotification)
-	n, ok2 := e.ObjectNew.(*v1.KumaNotification)
-	if !ok1 || !ok2 {
-		return true
-	}
-	return o.Status.NotificationID != n.Status.NotificationID ||
-		o.DeletionTimestamp.IsZero() != n.DeletionTimestamp.IsZero()
-}
-
-// referencingMonitors enqueues the KumaMonitors of all namespaces that
-// reference the notification.
-func (r *Reconciler) referencingMonitors(ctx context.Context, o client.Object) []reconcile.Request {
-	var list v1.KumaMonitorList
-	if err := r.Client.List(ctx, &list); err != nil {
-		log.FromContext(ctx).Error(err, "list KumaMonitors to enqueue")
-		return nil
-	}
-	var reqs []reconcile.Request
-	for _, km := range list.Items {
-		if slices.ContainsFunc(km.Spec.NotificationRefs, func(ref v1.NotificationRef) bool { return ref.Name == o.GetName() }) {
-			reqs = append(reqs, reconcile.Request{NamespacedName: types.NamespacedName{Namespace: km.Namespace, Name: km.Name}})
-		}
-	}
-	return reqs
-}
-
 type parentOutcome struct {
 	id      int64
 	reason  string // empty: resolved
@@ -346,75 +257,8 @@ type parentOutcome struct {
 	requeue time.Duration
 }

-// rootChanged reports changes to the root group that alter what the monitors
-// without a parentRef resolve to.
-func rootChanged(e event.UpdateEvent) bool {
-	o, ok1 := e.ObjectOld.(*v1.KumaMonitor)
-	n, ok2 := e.ObjectNew.(*v1.KumaMonitor)
-	if !ok1 || !ok2 {
-		return true
-	}
-	return o.Status.MonitorID != n.Status.MonitorID ||
-		o.Spec.Type != n.Spec.Type ||
-		(o.Spec.ParentRef == nil) != (n.Spec.ParentRef == nil) ||
-		o.DeletionTimestamp.IsZero() != n.DeletionTimestamp.IsZero()
-}
-
-// rootPredicate passes events of the root group only.
-func (r *Reconciler) rootPredicate() predicate.Funcs {
-	return predicate.Funcs{
-		CreateFunc:  func(e event.CreateEvent) bool { return r.isRoot(e.Object) },
-		DeleteFunc:  func(e event.DeleteEvent) bool { return r.isRoot(e.Object) },
-		GenericFunc: func(e event.GenericEvent) bool { return r.isRoot(e.Object) },
-		UpdateFunc:  func(e event.UpdateEvent) bool { return r.isRoot(e.ObjectNew) && rootChanged(e) },
-	}
-}
-
-// rootChildren enqueues the KumaMonitors of all namespaces that have no
-// parentRef, except the root group itself.
-func (r *Reconciler) rootChildren(ctx context.Context, _ client.Object) []reconcile.Request {
-	var list v1.KumaMonitorList
-	if err := r.Client.List(ctx, &list); err != nil {
-		log.FromContext(ctx).Error(err, "list KumaMonitors to enqueue")
-		return nil
-	}
-	var reqs []reconcile.Request
-	for i := range list.Items {
-		km := &list.Items[i]
-		if km.Spec.ParentRef == nil && !r.isRoot(km) {
-			reqs = append(reqs, reconcile.Request{NamespacedName: types.NamespacedName{Namespace: km.Namespace, Name: km.Name}})
-		}
-	}
-	return reqs
-}
-
-// resolveRoot returns the Kuma ID of the root group for a monitor without a
-// parentRef. The root must be a group without a parentRef: under one of its
-// own ancestors it would close a cycle in Kuma.
-func (r *Reconciler) resolveRoot(ctx context.Context) (parentOutcome, error) {
-	pending := parentOutcome{reason: ReasonParentPending, message: msgRootPending, requeue: parentRetry}
-	root := &v1.KumaMonitor{}
-	err := r.Client.Get(ctx, r.RootGroup, root)
-	if apierrors.IsNotFound(err) {
-		return pending, nil
-	}
-	if err != nil {
-		return parentOutcome{}, err
-	}
-	switch {
-	case root.Spec.Type != "group":
-		return parentOutcome{reason: ReasonInvalidParent, message: msgRootNotGroup, requeue: r.resync()}, nil
-	case root.Spec.ParentRef != nil:
-		return parentOutcome{reason: ReasonInvalidParent, message: msgRootHasParent, requeue: r.resync()}, nil
-	case root.Status.MonitorID == 0 || !root.DeletionTimestamp.IsZero():
-		return pending, nil
-	}
-	return parentOutcome{id: root.Status.MonitorID}, nil
-}
-
 // resolveParent checks the whole parentRef chain: every ancestor must exist
-// and be a group, without cycles or more than maxParentDepth levels. The root
-// group, which the topmost ancestor is placed under, counts as a level.
+// and be a group, without cycles or more than maxParentDepth levels.
 func (r *Reconciler) resolveParent(ctx context.Context, km *v1.KumaMonitor) (parentOutcome, error) {
 	invalid := func(msg string) (parentOutcome, error) {
 		return parentOutcome{reason: ReasonInvalidParent, message: msg, requeue: r.resync()}, nil
@@ -424,8 +268,7 @@ func (r *Reconciler) resolveParent(ctx context.Context, km *v1.KumaMonitor) (par
 	visited := map[string]bool{km.Name: true}
 	cur := km
 	var directID int64
-	depth := 0
-	for ; cur.Spec.ParentRef != nil; depth++ {
+	for depth := 0; cur.Spec.ParentRef != nil; depth++ {
 		if depth >= maxParentDepth {
 			return invalid(msgParentTooDeep)
 		}
@@ -450,9 +293,6 @@ func (r *Reconciler) resolveParent(ctx context.Context, km *v1.KumaMonitor) (par
 		}
 		cur = parent
 	}
-	if r.hasRoot() && !r.isRoot(cur) && depth >= maxParentDepth {
-		return invalid(msgParentTooDeep)
-	}
 	if directID == 0 {
 		return pending, nil
 	}
@@ -4,6 +4,7 @@ import (
 	"context"
 	"errors"
 	"fmt"
+	"slices"
 	"testing"
 	"time"

@@ -310,6 +311,79 @@ func TestReconcileListErrorNoCreate(t *testing.T) {
 	}
 }

+func TestReconcileCreateGetsDefaultNotifications(t *testing.T) {
+	group := &v1.KumaMonitor{
+		ObjectMeta: metav1.ObjectMeta{Namespace: "default", Name: "grp"},
+		Spec:       v1.KumaMonitorSpec{Type: "group", DisplayName: "grp", Interval: 60, RetryInterval: 60},
+	}
+	e := newEnv(t, httpMonitor("a"), group)
+	e.kuma.SetDefaultNotifications(7, 3)
+	for _, name := range []string{"a", "grp"} {
+		if _, err := e.reconcile(t, name); err != nil {
+			t.Fatal(err)
+		}
+		got := e.kuma.Get(e.get(t, name).Status.MonitorID)
+		if got == nil || !slices.Equal(got.NotificationIDs, []int64{3, 7}) {
+			t.Errorf("%s: kuma monitor = %+v, want notifications [3 7]", name, got)
+		}
+	}
+}
+
+func TestReconcileRevertsNotificationDrift(t *testing.T) {
+	km := httpMonitor("a")
+	e := newEnv(t, km)
+	e.kuma.SetDefaultNotifications(1, 2)
+	drifted := Desired(km)
+	drifted.NotificationIDs = []int64{2, 9}
+	id, _ := e.kuma.Create(t.Context(), drifted)
+	if _, err := e.reconcile(t, "a"); err != nil {
+		t.Fatal(err)
+	}
+	if e.cnt.updates != 1 || e.cnt.creates != 0 {
+		t.Fatalf("updates=%d creates=%d", e.cnt.updates, e.cnt.creates)
+	}
+	if got := e.kuma.Get(id).NotificationIDs; !slices.Equal(got, []int64{1, 2}) {
+		t.Errorf("notifications = %v, want [1 2]", got)
+	}
+}
+
+func TestReconcileUnchangedNotificationsNoUpdate(t *testing.T) {
+	km := httpMonitor("a")
+	e := newEnv(t, km)
+	e.kuma.SetDefaultNotifications(4, 2)
+	existing := Desired(km)
+	existing.NotificationIDs = []int64{4, 2}
+	e.kuma.Create(t.Context(), existing)
+	for range 2 {
+		if _, err := e.reconcile(t, "a"); err != nil {
+			t.Fatal(err)
+		}
+	}
+	if e.cnt.updates != 0 || e.cnt.creates != 0 {
+		t.Fatalf("updates=%d creates=%d, want 0 and 0", e.cnt.updates, e.cnt.creates)
+	}
+}
+
+func TestReconcileNotificationListErrorNoWrite(t *testing.T) {
+	adopt := httpMonitor("b")
+	e := newEnv(t, httpMonitor("a"), adopt)
+	drifted := Desired(adopt)
+	drifted.Interval = 30
+	e.kuma.Create(t.Context(), drifted)
+	e.kuma.SetNotificationsErr(errors.New("boom"))
+	for _, name := range []string{"a", "b"} {
+		if _, err := e.reconcile(t, name); err == nil {
+			t.Fatalf("%s: expected error", name)
+		}
+		if c := ready(t, e.get(t, name)); c.Status != metav1.ConditionFalse || c.Reason != ReasonKumaUnavailable {
+			t.Errorf("%s: Ready = %+v", name, c)
+		}
+	}
+	if e.cnt.creates != 0 || e.cnt.updates != 0 {
+		t.Errorf("creates=%d updates=%d", e.cnt.creates, e.cnt.updates)
+	}
+}
+
 func TestReconcileOwnerTagMissing(t *testing.T) {
 	e := newEnv(t, httpMonitor("a"))
 	e.kuma.SetErrs(kumaclient.ErrOwnerTagMissing, nil, nil, nil)
@@ -24,15 +24,14 @@ func OwnerKey(km *v1.KumaMonitor) string {
 func Desired(km *v1.KumaMonitor) kumaclient.Monitor {
 	s := km.Spec
 	m := kumaclient.Monitor{
-		Type:           s.Type,
-		Name:           s.DisplayName,
-		Description:    s.Description,
-		Active:         !s.Paused,
-		Interval:       s.Interval,
-		RetryInterval:  s.RetryInterval,
-		MaxRetries:     s.MaxRetries,
-		ResendInterval: s.ResendInterval,
-		OwnerKey:       OwnerKey(km),
+		Type:          s.Type,
+		Name:          s.DisplayName,
+		Description:   s.Description,
+		Active:        !s.Paused,
+		Interval:      s.Interval,
+		RetryInterval: s.RetryInterval,
+		MaxRetries:    s.MaxRetries,
+		OwnerKey:      OwnerKey(km),
 	}
 	if s.Timeout != nil {
 		m.Timeout = *s.Timeout
@@ -57,8 +57,6 @@ func TestMappingAllTypes(t *testing.T) {
 	port.Port = &v1.PortSpec{Hostname: "p.com", Port: 443}
 	paused := base("group")
 	paused.Paused = true
-	resend := base("group")
-	resend.ResendInterval = 60

 	wantKW := withHTTP(common("keyword"))
 	wantKW.Keyword, wantKW.InvertKeyword = "ok", true
@@ -76,8 +74,6 @@ func TestMappingAllTypes(t *testing.T) {
 	wantPort.Hostname, wantPort.Port = "p.com", 443
 	wantPaused := common("group")
 	wantPaused.Active = false
-	wantResend := common("group")
-	wantResend.ResendInterval = 60

 	cases := []struct {
 		name string
@@ -92,7 +88,6 @@ func TestMappingAllTypes(t *testing.T) {
 		{"dns with conditions", dnsCond, wantDNSCond},
 		{"port", port, wantPort},
 		{"paused maps to inactive", paused, wantPaused},
-		{"resend interval", resend, wantResend},
 	}
 	for _, c := range cases {
 		got := Desired(mk(c.spec))
@@ -1,240 +0,0 @@
-package controller
-
-import (
-	"context"
-	"errors"
-	"reflect"
-	"strconv"
-	"strings"
-	"time"
-
-	corev1 "k8s.io/api/core/v1"
-	apierrors "k8s.io/apimachinery/pkg/api/errors"
-	"k8s.io/apimachinery/pkg/api/meta"
-	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
-	"k8s.io/apimachinery/pkg/types"
-	ctrl "sigs.k8s.io/controller-runtime"
-	"sigs.k8s.io/controller-runtime/pkg/builder"
-	"sigs.k8s.io/controller-runtime/pkg/client"
-	"sigs.k8s.io/controller-runtime/pkg/controller/controllerutil"
-	"sigs.k8s.io/controller-runtime/pkg/log"
-	"sigs.k8s.io/controller-runtime/pkg/predicate"
-
-	v1 "gitea.renner.uno/konairius/homelab/kuma-sync/api/v1alpha1"
-	"gitea.renner.uno/konairius/homelab/kuma-sync/internal/kumaclient"
-)
-
-const (
-	ReasonSecretMissing = "SecretMissing"
-	ReasonInvalidSecret = "InvalidSecret"
-	ReasonInvalidSpec   = "InvalidSpec"
-
-	msgNotificationSynced    = "notification in sync"
-	msgDuplicateNotification = "several notifications carry this name; syncing the lowest ID"
-	msgSecretMissing         = "secret not found or not readable"
-	msgSecretKeyMissing      = "secret lacks host, port, username or password"
-	msgInvalidSecretPort     = "secret port is not a number from 1 to 65535"
-	msgInvalidType           = "notification type is not supported"
-
-	// smtpsPort is the port that uses implicit TLS; any other uses STARTTLS.
-	smtpsPort = 465
-)
-
-// smtpSecretKeys are the keys the SMTP Secret must hold, none empty.
-var smtpSecretKeys = []string{"host", "port", "username", "password"}
-
-// +kubebuilder:rbac:groups=uptime.renner.uno,resources=kumanotifications,verbs=get;list;watch;update;patch
-// +kubebuilder:rbac:groups=uptime.renner.uno,resources=kumanotifications/status,verbs=get;update;patch
-// +kubebuilder:rbac:groups=uptime.renner.uno,resources=kumanotifications/finalizers,verbs=update
-
-// NotificationReconciler syncs KumaNotification resources to Kuma. The Kuma
-// notification is owned by name: the lowest-ID notification with the
-// resource's name is adopted, whoever made it.
-type NotificationReconciler struct {
-	Client client.Client
-	// APIReader reads the SMTP Secret uncached, so no Secret watch is needed:
-	// only get on the referenced Secret.
-	APIReader client.Reader
-	Kuma      kumaclient.Notifications
-	// Resync is how often a resource is reconciled again, which reverts edits
-	// made in Kuma and picks up Secret changes. 0 means 5 minutes.
-	Resync time.Duration
-}
-
-func (r *NotificationReconciler) resync() time.Duration {
-	if r.Resync > 0 {
-		return r.Resync
-	}
-	return resyncPeriod
-}
-
-// SetupWithManager ignores status-only updates. Secrets are not watched.
-func (r *NotificationReconciler) SetupWithManager(mgr ctrl.Manager) error {
-	return ctrl.NewControllerManagedBy(mgr).
-		For(&v1.KumaNotification{}, builder.WithPredicates(predicate.GenerationChangedPredicate{})).
-		Named("kumanotification").
-		Complete(r)
-}
-
-// specProblem is a Ready=False outcome that waits for a resync.
-type specProblem struct {
-	reason  string
-	message string
-}
-
-func (r *NotificationReconciler) Reconcile(ctx context.Context, req ctrl.Request) (ctrl.Result, error) {
-	kn := &v1.KumaNotification{}
-	if err := r.Client.Get(ctx, req.NamespacedName, kn); err != nil {
-		return ctrl.Result{}, client.IgnoreNotFound(err)
-	}
-	if !kn.DeletionTimestamp.IsZero() {
-		return r.reconcileDelete(ctx, kn)
-	}
-	if controllerutil.AddFinalizer(kn, Finalizer) {
-		if err := r.Client.Update(ctx, kn); err != nil {
-			return ctrl.Result{}, err
-		}
-	}
-
-	desired, problem, err := r.desired(ctx, kn)
-	if err != nil {
-		return ctrl.Result{}, err
-	}
-	if problem != nil {
-		err := r.setReady(ctx, kn, metav1.ConditionFalse, problem.reason, problem.message, nil)
-		return ctrl.Result{RequeueAfter: r.resync()}, err
-	}
-
-	list, err := r.Kuma.ListNotifications(ctx, kn.Name)
-	if err != nil {
-		return r.fail(ctx, kn, &failure{ReasonKumaUnavailable, msgKumaUnavailable, err})
-	}
-	var id int64
-	if len(list) == 0 {
-		id, err = r.Kuma.CreateNotification(ctx, desired)
-		if err != nil {
-			return r.fail(ctx, kn, &failure{ReasonKumaUnavailable, msgKumaUnavailable, err})
-		}
-	} else {
-		id = list[0].ID
-		desired.ID = id
-		if !desired.SameContent(list[0]) {
-			log.FromContext(ctx).Info("notification differs from spec, updating", "notificationID", id)
-			if err := r.Kuma.UpdateNotification(ctx, desired); err != nil {
-				return r.fail(ctx, kn, &failure{ReasonKumaUnavailable, msgKumaUnavailable, err})
-			}
-		}
-	}
-
-	if len(list) > 1 {
-		ids := make([]int64, 0, len(list))
-		for _, n := range list {
-			ids = append(ids, n.ID)
-		}
-		log.FromContext(ctx).Error(nil, "several Kuma notifications carry the same name, syncing the lowest ID",
-			"name", kn.Name, "notificationIDs", ids)
-		err := r.setReady(ctx, kn, metav1.ConditionFalse, ReasonDuplicateOwner, msgDuplicateNotification, &id)
-		return ctrl.Result{RequeueAfter: r.resync()}, err
-	}
-	if err := r.setReady(ctx, kn, metav1.ConditionTrue, ReasonSynced, msgNotificationSynced, &id); err != nil {
-		return ctrl.Result{}, err
-	}
-	return ctrl.Result{RequeueAfter: r.resync()}, nil
-}
-
-// reconcileDelete removes every notification carrying the name, duplicates
-// included. Kuma detaches them from the monitors.
-func (r *NotificationReconciler) reconcileDelete(ctx context.Context, kn *v1.KumaNotification) (ctrl.Result, error) {
-	if !controllerutil.ContainsFinalizer(kn, Finalizer) {
-		return ctrl.Result{}, nil
-	}
-	list, err := r.Kuma.ListNotifications(ctx, kn.Name)
-	if err != nil {
-		return r.fail(ctx, kn, &failure{ReasonKumaUnavailable, msgKumaUnavailable, err})
-	}
-	for _, n := range list {
-		err := r.Kuma.DeleteNotification(ctx, n.ID)
-		if err != nil && !errors.Is(err, kumaclient.ErrNotificationNotFound) {
-			return r.fail(ctx, kn, &failure{ReasonKumaUnavailable, msgKumaUnavailable, err})
-		}
-	}
-	controllerutil.RemoveFinalizer(kn, Finalizer)
-	return ctrl.Result{}, r.Client.Update(ctx, kn)
-}
-
-// desired builds the notification from the spec and the SMTP Secret. A
-// missing or invalid Secret is a problem, not an error; the cause is never
-// logged, as it may carry Secret data.
-func (r *NotificationReconciler) desired(
-	ctx context.Context, kn *v1.KumaNotification,
-) (kumaclient.Notification, *specProblem, error) {
-	s := kn.Spec.SMTP
-	if kn.Spec.Type != "smtp" || s == nil {
-		return kumaclient.Notification{}, &specProblem{ReasonInvalidSpec, msgInvalidType}, nil
-	}
-	secret := &corev1.Secret{}
-	err := r.APIReader.Get(ctx, types.NamespacedName{Namespace: s.SecretRef.Namespace, Name: s.SecretRef.Name}, secret)
-	if apierrors.IsNotFound(err) || apierrors.IsForbidden(err) {
-		return kumaclient.Notification{}, &specProblem{ReasonSecretMissing, msgSecretMissing}, nil
-	}
-	if err != nil {
-		return kumaclient.Notification{}, nil, err
-	}
-	for _, k := range smtpSecretKeys {
-		if len(secret.Data[k]) == 0 {
-			return kumaclient.Notification{}, &specProblem{ReasonSecretMissing, msgSecretKeyMissing}, nil
-		}
-	}
-	port, err := strconv.Atoi(strings.TrimSpace(string(secret.Data["port"])))
-	if err != nil || port < 1 || port > 65535 {
-		return kumaclient.Notification{}, &specProblem{ReasonInvalidSecret, msgInvalidSecretPort}, nil
-	}
-	return kumaclient.Notification{
-		Name:   kn.Name,
-		Type:   "smtp",
-		Active: true,
-		SMTP: kumaclient.SMTP{
-			Host:     strings.TrimSpace(string(secret.Data["host"])),
-			Port:     int32(port),
-			Secure:   port == smtpsPort,
-			Username: string(secret.Data["username"]),
-			Password: string(secret.Data["password"]),
-			From:     s.From,
-			To:       s.To,
-		},
-	}, nil, nil
-}
-
-// fail records a Ready=False outcome and returns its cause so the request is
-// requeued with backoff.
-func (r *NotificationReconciler) fail(ctx context.Context, kn *v1.KumaNotification, f *failure) (ctrl.Result, error) {
-	log.FromContext(ctx).Info("reconcile failed", "reason", f.reason, "error", f.err.Error())
-	if serr := r.setReady(ctx, kn, metav1.ConditionFalse, f.reason, f.message, nil); serr != nil {
-		return ctrl.Result{}, errors.Join(f.err, serr)
-	}
-	return ctrl.Result{}, f.err
-}
-
-// setReady writes the Ready condition, and the notification ID when given,
-// through the status subresource. It writes nothing if the status is
-// unchanged.
-func (r *NotificationReconciler) setReady(
-	ctx context.Context, kn *v1.KumaNotification, status metav1.ConditionStatus, reason, msg string, id *int64,
-) error {
-	orig := kn.Status.DeepCopy()
-	if id != nil {
-		kn.Status.NotificationID = *id
-		kn.Status.ObservedGeneration = kn.Generation
-	}
-	meta.SetStatusCondition(&kn.Status.Conditions, metav1.Condition{
-		Type:               v1.ConditionReady,
-		Status:             status,
-		Reason:             reason,
-		Message:            msg,
-		ObservedGeneration: kn.Generation,
-	})
-	if reflect.DeepEqual(*orig, kn.Status) {
-		return nil
-	}
-	return r.Client.Status().Update(ctx, kn)
-}
@@ -1,278 +0,0 @@
-package controller
-
-import (
-	"context"
-	"errors"
-	"testing"
-	"time"
-
-	corev1 "k8s.io/api/core/v1"
-	apierrors "k8s.io/apimachinery/pkg/api/errors"
-	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
-	"k8s.io/apimachinery/pkg/runtime"
-	"k8s.io/apimachinery/pkg/types"
-	clientgoscheme "k8s.io/client-go/kubernetes/scheme"
-	ctrl "sigs.k8s.io/controller-runtime"
-	"sigs.k8s.io/controller-runtime/pkg/client"
-	"sigs.k8s.io/controller-runtime/pkg/client/fake"
-
-	v1 "gitea.renner.uno/konairius/homelab/kuma-sync/api/v1alpha1"
-	"gitea.renner.uno/konairius/homelab/kuma-sync/internal/kumaclient"
-)
-
-// countingNotifs records notification writes on top of the Kuma fake.
-type countingNotifs struct {
-	kumaclient.Notifications
-	creates, updates, deletes int
-}
-
-func (c *countingNotifs) CreateNotification(ctx context.Context, n kumaclient.Notification) (int64, error) {
-	c.creates++
-	return c.Notifications.CreateNotification(ctx, n)
-}
-
-func (c *countingNotifs) UpdateNotification(ctx context.Context, n kumaclient.Notification) error {
-	c.updates++
-	return c.Notifications.UpdateNotification(ctx, n)
-}
-
-func (c *countingNotifs) DeleteNotification(ctx context.Context, id int64) error {
-	c.deletes++
-	return c.Notifications.DeleteNotification(ctx, id)
-}
-
-type notifEnv struct {
-	r    *NotificationReconciler
-	k8s  client.Client
-	kuma *kumaclient.Fake
-	cnt  *countingNotifs
-}
-
-func newNotifEnv(t *testing.T, objs ...client.Object) *notifEnv {
-	t.Helper()
-	s := runtime.NewScheme()
-	if err := clientgoscheme.AddToScheme(s); err != nil {
-		t.Fatal(err)
-	}
-	if err := v1.AddToScheme(s); err != nil {
-		t.Fatal(err)
-	}
-	k8s := fake.NewClientBuilder().WithScheme(s).WithObjects(objs...).
-		WithStatusSubresource(&v1.KumaNotification{}).Build()
-	kf := kumaclient.NewFake()
-	cnt := &countingNotifs{Notifications: kf}
-	return &notifEnv{
-		r:   &NotificationReconciler{Client: k8s, APIReader: k8s, Kuma: cnt},
-		k8s: k8s, kuma: kf, cnt: cnt,
-	}
-}
-
-func smtpNotification(name string) *v1.KumaNotification {
-	return &v1.KumaNotification{
-		ObjectMeta: metav1.ObjectMeta{Name: name},
-		Spec: v1.KumaNotificationSpec{Type: "smtp", SMTP: &v1.SMTPSpec{
-			From: "kuma@renner.uno", To: "ops@renner.uno",
-			SecretRef: v1.SecretRef{Namespace: "kuma-sync", Name: "smtp"},
-		}},
-	}
-}
-
-func smtpSecret(port string) *corev1.Secret {
-	return &corev1.Secret{
-		ObjectMeta: metav1.ObjectMeta{Namespace: "kuma-sync", Name: "smtp"},
-		Data: map[string][]byte{
-			"host": []byte("mail.example.com\n"), "port": []byte(port),
-			"username": []byte("kuma"), "password": []byte("s3cret"),
-		},
-	}
-}
-
-func wantSMTP(name string, port int32, secure bool) kumaclient.Notification {
-	return kumaclient.Notification{
-		Name: name, Type: "smtp", Active: true,
-		SMTP: kumaclient.SMTP{
-			Host: "mail.example.com", Port: port, Secure: secure,
-			Username: "kuma", Password: "s3cret", From: "kuma@renner.uno", To: "ops@renner.uno",
-		},
-	}
-}
-
-func (e *notifEnv) reconcile(t *testing.T, name string) (ctrl.Result, error) {
-	t.Helper()
-	return e.r.Reconcile(t.Context(), ctrl.Request{NamespacedName: types.NamespacedName{Name: name}})
-}
-
-func (e *notifEnv) get(t *testing.T, name string) *v1.KumaNotification {
-	t.Helper()
-	kn := &v1.KumaNotification{}
-	if err := e.k8s.Get(t.Context(), types.NamespacedName{Name: name}, kn); err != nil {
-		t.Fatal(err)
-	}
-	return kn
-}
-
-func notifReady(t *testing.T, kn *v1.KumaNotification) *metav1.Condition {
-	t.Helper()
-	for i := range kn.Status.Conditions {
-		if kn.Status.Conditions[i].Type == v1.ConditionReady {
-			return &kn.Status.Conditions[i]
-		}
-	}
-	t.Fatal("no Ready condition")
-	return nil
-}
-
-func TestNotificationCreates(t *testing.T) {
-	for port, secure := range map[string]bool{"587": false, "465": true, " 25\n": false} {
-		e := newNotifEnv(t, smtpNotification("mail"), smtpSecret(port))
-		res, err := e.reconcile(t, "mail")
-		if err != nil {
-			t.Fatal(err)
-		}
-		if res.RequeueAfter != 5*time.Minute {
-			t.Errorf("RequeueAfter = %v", res.RequeueAfter)
-		}
-		kn := e.get(t, "mail")
-		if kn.Status.NotificationID == 0 || kn.Status.ObservedGeneration != kn.Generation || len(kn.Finalizers) != 1 {
-			t.Fatalf("resource = %+v", kn)
-		}
-		if c := notifReady(t, kn); c.Status != metav1.ConditionTrue || c.Reason != ReasonSynced {
-			t.Errorf("Ready = %+v", c)
-		}
-		want := wantSMTP("mail", map[string]int32{"587": 587, "465": 465, " 25\n": 25}[port], secure)
-		want.ID = kn.Status.NotificationID
-		if got := e.kuma.Notification(kn.Status.NotificationID); got == nil || *got != want {
-			t.Errorf("port %q: kuma notification = %+v, want %+v", port, got, want)
-		}
-	}
-}
-
-func TestNotificationAdoptsLowestAndRevertsDrift(t *testing.T) {
-	e := newNotifEnv(t, smtpNotification("email"), smtpSecret("587"))
-	drifted := wantSMTP("email", 25, false)
-	drifted.IsDefault = true
-	drifted.SMTP.Password = "old"
-	first := e.kuma.PutNotification(drifted)
-	if _, err := e.reconcile(t, "email"); err != nil {
-		t.Fatal(err)
-	}
-	if e.cnt.creates != 0 || e.cnt.updates != 1 {
-		t.Fatalf("creates=%d updates=%d, want 0 and 1", e.cnt.creates, e.cnt.updates)
-	}
-	want := wantSMTP("email", 587, false)
-	want.ID = first
-	if got := e.kuma.Notification(first); *got != want {
-		t.Errorf("kuma notification = %+v, want %+v", *got, want)
-	}
-	if got := e.get(t, "email").Status.NotificationID; got != first {
-		t.Errorf("notificationID = %d, want %d", got, first)
-	}
-	if _, err := e.reconcile(t, "email"); err != nil {
-		t.Fatal(err)
-	}
-	if e.cnt.updates != 1 {
-		t.Errorf("updates = %d after a second reconcile, want 1", e.cnt.updates)
-	}
-}
-
-func TestNotificationDuplicateName(t *testing.T) {
-	e := newNotifEnv(t, smtpNotification("email"), smtpSecret("587"))
-	first := e.kuma.PutNotification(wantSMTP("email", 587, false))
-	second := e.kuma.PutNotification(wantSMTP("email", 25, false))
-	if _, err := e.reconcile(t, "email"); err != nil {
-		t.Fatal(err)
-	}
-	kn := e.get(t, "email")
-	if kn.Status.NotificationID != first {
-		t.Errorf("notificationID = %d, want lowest %d", kn.Status.NotificationID, first)
-	}
-	if c := notifReady(t, kn); c.Status != metav1.ConditionFalse || c.Reason != ReasonDuplicateOwner {
-		t.Errorf("Ready = %+v", c)
-	}
-	if e.cnt.updates != 0 || e.kuma.Notification(second).SMTP.Port != 25 {
-		t.Error("only the lowest ID may be synced")
-	}
-}
-
-func TestNotificationSecretProblems(t *testing.T) {
-	noKey := smtpSecret("587")
-	delete(noKey.Data, "password")
-	for name, tc := range map[string]struct {
-		secret  client.Object
-		reason  string
-		message string
-	}{
-		"missing secret": {nil, ReasonSecretMissing, "secret not found or not readable"},
-		"missing key":    {noKey, ReasonSecretMissing, "secret lacks host, port, username or password"},
-		"bad port":       {smtpSecret("smtp"), ReasonInvalidSecret, "secret port is not a number from 1 to 65535"},
-		"port too large": {smtpSecret("70000"), ReasonInvalidSecret, "secret port is not a number from 1 to 65535"},
-	} {
-		objs := []client.Object{smtpNotification("mail")}
-		if tc.secret != nil {
-			objs = append(objs, tc.secret)
-		}
-		e := newNotifEnv(t, objs...)
-		res, err := e.reconcile(t, "mail")
-		if err != nil {
-			t.Fatalf("%s: %v", name, err)
-		}
-		if res.RequeueAfter != 5*time.Minute {
-			t.Errorf("%s: RequeueAfter = %v", name, res.RequeueAfter)
-		}
-		if c := notifReady(t, e.get(t, "mail")); c.Status != metav1.ConditionFalse || c.Reason != tc.reason || c.Message != tc.message {
-			t.Errorf("%s: Ready = %+v", name, c)
-		}
-		if e.cnt.creates != 0 || e.cnt.updates != 0 {
-			t.Errorf("%s: creates=%d updates=%d", name, e.cnt.creates, e.cnt.updates)
-		}
-	}
-}
-
-func TestNotificationKumaErrorNoWrite(t *testing.T) {
-	e := newNotifEnv(t, smtpNotification("mail"), smtpSecret("587"))
-	e.kuma.SetNotifErr(errors.New("boom"))
-	if _, err := e.reconcile(t, "mail"); err == nil {
-		t.Fatal("expected error")
-	}
-	if c := notifReady(t, e.get(t, "mail")); c.Reason != ReasonKumaUnavailable || c.Message != msgKumaUnavailable {
-		t.Errorf("Ready = %+v", c)
-	}
-}
-
-func TestNotificationDeleteRemovesAll(t *testing.T) {
-	kn := smtpNotification("email")
-	now := metav1.Now()
-	kn.DeletionTimestamp = &now
-	kn.Finalizers = []string{Finalizer}
-	e := newNotifEnv(t, kn)
-	first := e.kuma.PutNotification(wantSMTP("email", 587, false))
-	second := e.kuma.PutNotification(wantSMTP("email", 25, false))
-	other := e.kuma.PutNotification(wantSMTP("other", 25, false))
-	if _, err := e.reconcile(t, "email"); err != nil {
-		t.Fatal(err)
-	}
-	if e.kuma.Notification(first) != nil || e.kuma.Notification(second) != nil {
-		t.Error("every notification with the name must be deleted")
-	}
-	if e.kuma.Notification(other) == nil {
-		t.Error("other notification deleted")
-	}
-	if err := e.k8s.Get(t.Context(), client.ObjectKeyFromObject(kn), &v1.KumaNotification{}); !apierrors.IsNotFound(err) {
-		t.Errorf("finalizer not removed: %v", err)
-	}
-}
-
-func TestNotificationDeleteKumaErrorKeepsFinalizer(t *testing.T) {
-	kn := smtpNotification("email")
-	now := metav1.Now()
-	kn.DeletionTimestamp = &now
-	kn.Finalizers = []string{Finalizer}
-	e := newNotifEnv(t, kn)
-	e.kuma.SetNotifErr(errors.New("boom"))
-	if _, err := e.reconcile(t, "email"); err == nil {
-		t.Fatal("expected error")
-	}
-	if got := e.get(t, "email").Finalizers; len(got) != 1 {
-		t.Errorf("finalizers = %v", got)
-	}
-}
@@ -1,98 +0,0 @@
-//go:build integration
-
-package controller_test
-
-import (
-	"fmt"
-	"slices"
-	"testing"
-	"time"
-
-	"github.com/breml/go-uptime-kuma-client/monitor"
-	corev1 "k8s.io/api/core/v1"
-	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
-	"k8s.io/apimachinery/pkg/types"
-
-	v1 "gitea.renner.uno/konairius/homelab/kuma-sync/api/v1alpha1"
-	"gitea.renner.uno/konairius/homelab/kuma-sync/internal/kumaclient"
-)
-
-// A KumaNotification adopts the hand-made notification of its name, and only
-// monitors referencing it carry it; a default notification is never attached.
-func TestE2ENotificationRefs(t *testing.T) {
-	f, env := newE2E(t)
-	legacy := f.webhook("legacy", true)
-	adopted := f.webhook("mail", false)
-	f.start(env)
-
-	secret := &corev1.Secret{
-		ObjectMeta: metav1.ObjectMeta{Namespace: "default", Name: "smtp"},
-		Data: map[string][]byte{
-			"host": []byte("mail.example.com"), "port": []byte("587"),
-			"username": []byte("kuma"), "password": []byte("s3cret"),
-		},
-	}
-	kn := &v1.KumaNotification{
-		ObjectMeta: metav1.ObjectMeta{Name: "mail"},
-		Spec: v1.KumaNotificationSpec{Type: "smtp", SMTP: &v1.SMTPSpec{
-			From: "kuma@example.com", To: "ops@example.com",
-			SecretRef: v1.SecretRef{Namespace: "default", Name: "smtp"},
-		}},
-	}
-	if err := f.k8s.Create(t.Context(), secret); err != nil {
-		t.Fatal(err)
-	}
-	if err := f.k8s.Create(t.Context(), kn); err != nil {
-		t.Fatal(err)
-	}
-	g := group("g", "")
-	g.Spec.NotificationRefs = []v1.NotificationRef{{Name: "mail"}}
-	f.apply(g, dns("probe", "g"))
-
-	want := kumaclient.Notification{
-		ID: adopted, Name: "mail", Type: "smtp", Active: true,
-		SMTP: kumaclient.SMTP{
-			Host: "mail.example.com", Port: 587, Username: "kuma", Password: "s3cret",
-			From: "kuma@example.com", To: "ops@example.com",
-		},
-	}
-	eventually(t, 30*time.Second, "notification adopted and converted", func() (bool, string) {
-		got, err := f.census.ListNotifications(t.Context(), "mail")
-		if err != nil {
-			return false, err.Error()
-		}
-		cur := &v1.KumaNotification{}
-		if err := f.k8s.Get(t.Context(), types.NamespacedName{Name: "mail"}, cur); err != nil {
-			return false, err.Error()
-		}
-		if len(got) != 1 || got[0] != want || cur.Status.NotificationID != adopted {
-			return false, fmt.Sprintf("kuma %+v, status ID %d", got, cur.Status.NotificationID)
-		}
-		return true, ""
-	})
-
-	carry := func(key string, want ...int64) func() (bool, string) {
-		return func() (bool, string) {
-			got, ok := byKey(f.owned())[key]
-			if !ok {
-				return false, key + " missing"
-			}
-			if !slices.Equal(got.NotificationIDs, want) {
-				return false, fmt.Sprintf("%s carries %v, want %v", key, got.NotificationIDs, want)
-			}
-			return true, ""
-		}
-	}
-	eventually(t, 30*time.Second, "group carries the referenced notification", carry("default/g", adopted))
-	eventually(t, 30*time.Second, "child carries none", carry("default/probe"))
-
-	var live monitor.Group
-	if err := f.raw.GetMonitorAs(t.Context(), byKey(f.owned())["default/g"].ID, &live); err != nil {
-		t.Fatal(err)
-	}
-	live.NotificationIDs = []int64{legacy}
-	if err := f.raw.UpdateMonitor(t.Context(), &live); err != nil {
-		t.Fatal(err)
-	}
-	eventually(t, 30*time.Second, "notifications changed by hand restored by a resync", carry("default/g", adopted))
-}
@@ -1,160 +0,0 @@
-package controller
-
-import (
-	"slices"
-	"testing"
-	"time"
-
-	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
-	"k8s.io/apimachinery/pkg/types"
-	"sigs.k8s.io/controller-runtime/pkg/event"
-	"sigs.k8s.io/controller-runtime/pkg/reconcile"
-
-	v1 "gitea.renner.uno/konairius/homelab/kuma-sync/api/v1alpha1"
-)
-
-func kumaNotification(name string, id int64) *v1.KumaNotification {
-	return &v1.KumaNotification{
-		ObjectMeta: metav1.ObjectMeta{Name: name},
-		Spec:       v1.KumaNotificationSpec{Type: "smtp"},
-		Status:     v1.KumaNotificationStatus{NotificationID: id},
-	}
-}
-
-func withRefs(km *v1.KumaMonitor, names ...string) *v1.KumaMonitor {
-	for _, n := range names {
-		km.Spec.NotificationRefs = append(km.Spec.NotificationRefs, v1.NotificationRef{Name: n})
-	}
-	return km
-}
-
-func TestReconcileAttachesReferencedNotifications(t *testing.T) {
-	group := withRefs(&v1.KumaMonitor{
-		ObjectMeta: metav1.ObjectMeta{Namespace: "default", Name: "grp"},
-		Spec:       v1.KumaMonitorSpec{Type: "group", DisplayName: "grp", Interval: 60, RetryInterval: 60},
-	}, "mail", "ops")
-	e := newEnv(t, withRefs(httpMonitor("a"), "ops"), group, kumaNotification("mail", 7), kumaNotification("ops", 3))
-	for name, want := range map[string][]int64{"a": {3}, "grp": {3, 7}} {
-		if _, err := e.reconcile(t, name); err != nil {
-			t.Fatal(err)
-		}
-		got := e.kuma.Get(e.get(t, name).Status.MonitorID)
-		if got == nil || !slices.Equal(got.NotificationIDs, want) {
-			t.Errorf("%s: kuma monitor = %+v, want notifications %v", name, got, want)
-		}
-	}
-}
-
-func TestReconcileNotificationPending(t *testing.T) {
-	deleted := kumaNotification("going", 5)
-	now := metav1.Now()
-	deleted.DeletionTimestamp = &now
-	deleted.Finalizers = []string{Finalizer}
-	e := newEnv(t,
-		withRefs(httpMonitor("missing"), "nope"),
-		withRefs(httpMonitor("unsynced"), "new"), kumaNotification("new", 0),
-		withRefs(httpMonitor("deleting"), "going"), deleted,
-	)
-	for _, name := range []string{"missing", "unsynced", "deleting"} {
-		res, err := e.reconcile(t, name)
-		if err != nil {
-			t.Fatalf("%s: %v", name, err)
-		}
-		if res.RequeueAfter != 10*time.Second {
-			t.Errorf("%s: RequeueAfter = %v", name, res.RequeueAfter)
-		}
-		c := ready(t, e.get(t, name))
-		if c.Status != metav1.ConditionFalse || c.Reason != ReasonNotificationPending ||
-			c.Message != "a referenced notification has no notification ID yet" {
-			t.Errorf("%s: Ready = %+v", name, c)
-		}
-	}
-	if e.cnt.creates != 0 || e.cnt.updates != 0 {
-		t.Errorf("creates=%d updates=%d", e.cnt.creates, e.cnt.updates)
-	}
-}
-
-func TestReconcileNoRefsDetachesNotifications(t *testing.T) {
-	km := httpMonitor("a")
-	e := newEnv(t, km)
-	attached := Desired(km)
-	attached.NotificationIDs = []int64{2, 9}
-	id, _ := e.kuma.Create(t.Context(), attached)
-	if _, err := e.reconcile(t, "a"); err != nil {
-		t.Fatal(err)
-	}
-	if e.cnt.updates != 1 {
-		t.Fatalf("updates = %d", e.cnt.updates)
-	}
-	if got := e.kuma.Get(id).NotificationIDs; got != nil {
-		t.Errorf("notifications = %v, want none", got)
-	}
-}
-
-func TestReconcileRevertsNotificationDrift(t *testing.T) {
-	km := withRefs(httpMonitor("a"), "mail")
-	e := newEnv(t, km, kumaNotification("mail", 1))
-	drifted := Desired(km)
-	drifted.NotificationIDs = []int64{2, 9}
-	id, _ := e.kuma.Create(t.Context(), drifted)
-	if _, err := e.reconcile(t, "a"); err != nil {
-		t.Fatal(err)
-	}
-	if e.cnt.updates != 1 || e.cnt.creates != 0 {
-		t.Fatalf("updates=%d creates=%d", e.cnt.updates, e.cnt.creates)
-	}
-	if got := e.kuma.Get(id).NotificationIDs; !slices.Equal(got, []int64{1}) {
-		t.Errorf("notifications = %v, want [1]", got)
-	}
-}
-
-func TestReconcileUnchangedNotificationsNoUpdate(t *testing.T) {
-	km := withRefs(httpMonitor("a"), "mail", "ops")
-	e := newEnv(t, km, kumaNotification("mail", 4), kumaNotification("ops", 2))
-	existing := Desired(km)
-	existing.NotificationIDs = []int64{4, 2}
-	e.kuma.Create(t.Context(), existing)
-	for range 2 {
-		if _, err := e.reconcile(t, "a"); err != nil {
-			t.Fatal(err)
-		}
-	}
-	if e.cnt.updates != 0 || e.cnt.creates != 0 {
-		t.Fatalf("updates=%d creates=%d, want 0 and 0", e.cnt.updates, e.cnt.creates)
-	}
-}
-
-func TestReferencingMonitors(t *testing.T) {
-	other := withRefs(httpMonitor("b"), "mail")
-	other.Namespace = "other"
-	e := newEnv(t, withRefs(httpMonitor("a"), "ops", "mail"), other, httpMonitor("none"), withRefs(httpMonitor("c"), "ops"))
-	got := e.r.referencingMonitors(t.Context(), kumaNotification("mail", 1))
-	want := []reconcile.Request{
-		{NamespacedName: types.NamespacedName{Namespace: "default", Name: "a"}},
-		{NamespacedName: types.NamespacedName{Namespace: "other", Name: "b"}},
-	}
-	if !slices.Equal(got, want) {
-		t.Errorf("requests = %v, want %v", got, want)
-	}
-}
-
-func TestNotificationIDChanged(t *testing.T) {
-	base := kumaNotification("mail", 1)
-	changed := base.DeepCopy()
-	changed.Status.NotificationID = 2
-	cond := base.DeepCopy()
-	cond.Status.Conditions = []metav1.Condition{{Type: v1.ConditionReady, Status: metav1.ConditionTrue}}
-	deleting := base.DeepCopy()
-	now := metav1.Now()
-	deleting.DeletionTimestamp = &now
-	for name, tc := range map[string]struct {
-		n    *v1.KumaNotification
-		want bool
-	}{
-		"id changed": {changed, true}, "condition only": {cond, false}, "deleting": {deleting, true},
-	} {
-		if got := notificationIDChanged(event.UpdateEvent{ObjectOld: base, ObjectNew: tc.n}); got != tc.want {
-			t.Errorf("%s: %v, want %v", name, got, tc.want)
-		}
-	}
-}
@@ -1,209 +0,0 @@
-package controller
-
-import (
-	"fmt"
-	"slices"
-	"testing"
-	"time"
-
-	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
-	"k8s.io/apimachinery/pkg/types"
-	"sigs.k8s.io/controller-runtime/pkg/client"
-	"sigs.k8s.io/controller-runtime/pkg/event"
-
-	v1 "gitea.renner.uno/konairius/homelab/kuma-sync/api/v1alpha1"
-)
-
-const rootID = 7
-
-var rootName = types.NamespacedName{Namespace: "default", Name: "root"}
-
-func rootGroup() *v1.KumaMonitor {
-	g := group("root", "")
-	g.Status.MonitorID = rootID
-	return g
-}
-
-func newRootEnv(t *testing.T, objs ...client.Object) *env {
-	t.Helper()
-	e := newEnv(t, objs...)
-	e.r.RootGroup = rootName
-	return e
-}
-
-func (e *env) parentOf(t *testing.T, name string) *int64 {
-	t.Helper()
-	got := e.kuma.Get(e.get(t, name).Status.MonitorID)
-	if got == nil {
-		t.Fatalf("%s: no Kuma monitor", name)
-	}
-	return got.Parent
-}
-
-func TestRootGroupParentsParentless(t *testing.T) {
-	e := newRootEnv(t, rootGroup(), httpMonitor("a"))
-	if _, err := e.reconcile(t, "a"); err != nil {
-		t.Fatal(err)
-	}
-	if p := e.parentOf(t, "a"); p == nil || *p != rootID {
-		t.Errorf("parent = %v, want %d", p, rootID)
-	}
-}
-
-func TestRootGroupKeepsParentRef(t *testing.T) {
-	grp := group("grp", "")
-	grp.Status.MonitorID = 42
-	child := httpMonitor("child")
-	child.Spec.ParentRef = &v1.LocalRef{Name: "grp"}
-	e := newRootEnv(t, rootGroup(), grp, child)
-	if _, err := e.reconcile(t, "child"); err != nil {
-		t.Fatal(err)
-	}
-	if p := e.parentOf(t, "child"); p == nil || *p != 42 {
-		t.Errorf("parent = %v, want 42", p)
-	}
-}
-
-func TestRootGroupItselfHasNoParent(t *testing.T) {
-	root := rootGroup()
-	root.Status.MonitorID = 0
-	e := newRootEnv(t, root)
-	if _, err := e.reconcile(t, "root"); err != nil {
-		t.Fatal(err)
-	}
-	if p := e.parentOf(t, "root"); p != nil {
-		t.Errorf("parent = %d, want none", *p)
-	}
-}
-
-func TestRootGroupUnsetLeavesTopLevel(t *testing.T) {
-	e := newEnv(t, rootGroup(), httpMonitor("a"))
-	if _, err := e.reconcile(t, "a"); err != nil {
-		t.Fatal(err)
-	}
-	if p := e.parentOf(t, "a"); p != nil {
-		t.Errorf("parent = %d, want none", *p)
-	}
-}
-
-func TestRootGroupPending(t *testing.T) {
-	noID := rootGroup()
-	noID.Status.MonitorID = 0
-	deletingRoot := deleting(rootGroup())
-	cases := map[string][]client.Object{
-		"missing":   nil,
-		"no ID":     {noID},
-		"deleting":  {deletingRoot},
-		"not group": {func() *v1.KumaMonitor { m := httpMonitor("root"); m.Status.MonitorID = rootID; return m }()},
-		"has parent": {func() *v1.KumaMonitor {
-			m := rootGroup()
-			m.Spec.ParentRef = &v1.LocalRef{Name: "x"}
-			return m
-		}()},
-	}
-	want := map[string]struct {
-		reason  string
-		requeue time.Duration
-	}{
-		"missing":    {ReasonParentPending, 10 * time.Second},
-		"no ID":      {ReasonParentPending, 10 * time.Second},
-		"deleting":   {ReasonParentPending, 10 * time.Second},
-		"not group":  {ReasonInvalidParent, 5 * time.Minute},
-		"has parent": {ReasonInvalidParent, 5 * time.Minute},
-	}
-	for name, objs := range cases {
-		e := newRootEnv(t, append(objs, httpMonitor("a"))...)
-		res, err := e.reconcile(t, "a")
-		if err != nil {
-			t.Fatalf("%s: %v", name, err)
-		}
-		if res.RequeueAfter != want[name].requeue {
-			t.Errorf("%s: RequeueAfter = %v, want %v", name, res.RequeueAfter, want[name].requeue)
-		}
-		if c := ready(t, e.get(t, "a")); c.Status != metav1.ConditionFalse || c.Reason != want[name].reason {
-			t.Errorf("%s: Ready = %+v", name, c)
-		}
-		if e.cnt.creates != 0 {
-			t.Errorf("%s: creates = %d", name, e.cnt.creates)
-		}
-	}
-}
-
-// A chain of maxParentDepth groups is allowed on its own, but the root group
-// adds one more level above it.
-func TestRootGroupCountsTowardsDepth(t *testing.T) {
-	var objs []client.Object
-	for i := range maxParentDepth {
-		parent := ""
-		if i < maxParentDepth-1 {
-			parent = fmt.Sprintf("c%d", i+1)
-		}
-		objs = append(objs, group(fmt.Sprintf("c%d", i), parent))
-	}
-	deep := httpMonitor("deep")
-	deep.Spec.ParentRef = &v1.LocalRef{Name: "c0"}
-	objs = append(objs, deep)
-
-	if _, err := newEnv(t, objs...).reconcile(t, "deep"); err != nil {
-		t.Fatal(err)
-	}
-
-	e := newRootEnv(t, append(objs, rootGroup())...)
-	if _, err := e.reconcile(t, "deep"); err != nil {
-		t.Fatal(err)
-	}
-	if c := ready(t, e.get(t, "deep")); c.Reason != ReasonInvalidParent || c.Message != msgParentTooDeep {
-		t.Errorf("Ready = %+v", c)
-	}
-
-	// A chain ending in the root itself gets no extra level.
-	objs[maxParentDepth-1] = func() *v1.KumaMonitor { g := rootGroup(); g.Name = "c9"; return g }()
-	e = newEnv(t, objs...)
-	e.r.RootGroup = types.NamespacedName{Namespace: "default", Name: "c9"}
-	if _, err := e.reconcile(t, "deep"); err != nil {
-		t.Fatal(err)
-	}
-	if c := ready(t, e.get(t, "deep")); c.Status != metav1.ConditionTrue {
-		t.Errorf("chain ending in root: Ready = %+v", c)
-	}
-}
-
-func TestRootChildrenEnqueuesParentless(t *testing.T) {
-	child := httpMonitor("child")
-	child.Spec.ParentRef = &v1.LocalRef{Name: "grp"}
-	other := httpMonitor("other")
-	other.Namespace = "elsewhere"
-	e := newRootEnv(t, rootGroup(), group("grp", ""), child, httpMonitor("a"), other)
-
-	var got []string
-	for _, req := range e.r.rootChildren(t.Context(), rootGroup()) {
-		got = append(got, req.String())
-	}
-	slices.Sort(got)
-	want := []string{"default/a", "default/grp", "elsewhere/other"}
-	if !slices.Equal(got, want) {
-		t.Errorf("enqueued %v, want %v", got, want)
-	}
-}
-
-func TestRootPredicate(t *testing.T) {
-	r := &Reconciler{RootGroup: rootName}
-	p := r.rootPredicate()
-	old := rootGroup()
-	old.Status.MonitorID = 0
-	withID := rootGroup()
-	other := group("other", "")
-
-	if !p.Update(event.UpdateEvent{ObjectOld: old, ObjectNew: withID}) {
-		t.Error("root ID change must pass")
-	}
-	if p.Update(event.UpdateEvent{ObjectOld: withID, ObjectNew: withID.DeepCopy()}) {
-		t.Error("unchanged root must not pass")
-	}
-	if p.Update(event.UpdateEvent{ObjectOld: other, ObjectNew: other.DeepCopy()}) || p.Create(event.CreateEvent{Object: other}) {
-		t.Error("other monitors must not pass")
-	}
-	if !p.Create(event.CreateEvent{Object: withID}) || !p.Delete(event.DeleteEvent{Object: withID}) {
-		t.Error("root create and delete must pass")
-	}
-}
@@ -13,6 +13,7 @@ import (

 	kuma "github.com/breml/go-uptime-kuma-client"
 	"github.com/breml/go-uptime-kuma-client/monitor"
+	"github.com/breml/go-uptime-kuma-client/notification"
 	"github.com/breml/go-uptime-kuma-client/tag"
 )

@@ -46,9 +47,6 @@ type Breml struct {
 	opts     []kuma.Option
 	token    string
 	backoff0 time.Duration
-	// notifStale means a notification write may be missing from the
-	// session's cached list.
-	notifStale bool
 }

 var _ Client = (*Breml)(nil)
@@ -160,7 +158,7 @@ func (b *Breml) checkSession(ctx context.Context, err error) (rebuilt, dead bool
 	if ctx.Err() != nil {
 		return false, false
 	}
-	for _, app := range []error{ErrNotFound, ErrNotOwned, ErrOwnerTagMissing, ErrOwnerConflict, ErrStatusPageNotFound, ErrNotificationNotFound} {
+	for _, app := range []error{ErrNotFound, ErrNotOwned, ErrOwnerTagMissing, ErrOwnerConflict, ErrStatusPageNotFound} {
 		if errors.Is(err, app) {
 			return false, false
 		}
@@ -198,8 +196,6 @@ func (b *Breml) reconnect(ctx context.Context) error {
 		}
 		_ = b.c.Disconnect()
 		b.c = c
-		// A new session starts with a fresh notification list.
-		b.notifStale = false
 		if t := c.SessionToken(); t != "" {
 			b.token = t
 		}
@@ -378,7 +374,7 @@ func (b *Breml) update(ctx context.Context, m Monitor) error {
 		return fmt.Errorf("update %d: monitor carries owner key %q, not %q: %w", m.ID, key, m.OwnerKey, ErrNotOwned)
 	}
 	// Start from the full current object, also across a type change, so
-	// fields we do not manage (proxy, upside down, auth)
+	// fields we do not manage (proxy, resend interval, upside down, auth)
 	// survive the overwrite.
 	wire, err := toWire(m, &cur)
 	if err != nil {
@@ -409,6 +405,29 @@ func (b *Breml) Delete(ctx context.Context, id int64) error {
 	return err
 }

+// DefaultNotifications reads the notification list cached by the session.
+// Kuma has no command to request it: it pushes the list at login and to every
+// session of the user after each change.
+func (b *Breml) DefaultNotifications(ctx context.Context) ([]int64, error) {
+	if err := ctx.Err(); err != nil {
+		return nil, err
+	}
+	b.mu.Lock()
+	defer b.mu.Unlock()
+	return defaultIDs(b.c.GetNotifications(ctx)), nil
+}
+
+func defaultIDs(list []notification.Base) []int64 {
+	var ids []int64
+	for _, n := range list {
+		if n.IsDefault {
+			ids = append(ids, n.ID)
+		}
+	}
+	slices.Sort(ids)
+	return ids
+}
+
 // toDomain converts a monitor from the Kuma monitor list.
 func toDomain(base monitor.Base, ownerKey string) (Monitor, error) {
 	m := Monitor{
@@ -420,7 +439,6 @@ func toDomain(base monitor.Base, ownerKey string) (Monitor, error) {
 		Interval:        int32(base.Interval),
 		RetryInterval:   int32(base.RetryInterval),
 		MaxRetries:      int32(base.MaxRetries),
-		ResendInterval:  int32(base.ResendInterval),
 		NotificationIDs: slices.Clone(base.NotificationIDs),
 		OwnerKey:        ownerKey,
 	}
@@ -582,7 +600,6 @@ func writeBase(b *monitor.Base, m Monitor) {
 	b.Interval = int64(m.Interval)
 	b.RetryInterval = int64(m.RetryInterval)
 	b.MaxRetries = int64(m.MaxRetries)
-	b.ResendInterval = int64(m.ResendInterval)
 	b.IsActive = m.Active
 	b.NotificationIDs = slices.Clone(m.NotificationIDs)
 }
@@ -127,7 +127,7 @@ func TestCreateFieldsIntact(t *testing.T) {

 	group := Monitor{
 		Type: "group", Name: "grp", Description: "a group", Active: true,
-		Interval: 60, RetryInterval: 60, MaxRetries: 0, ResendInterval: 60, OwnerKey: "default/grp",
+		Interval: 60, RetryInterval: 60, MaxRetries: 0, OwnerKey: "default/grp",
 	}
 	gid, err := b.Create(ctx, group)
 	if err != nil {
@@ -313,6 +313,7 @@ func setUnmanaged(t *testing.T, b *Breml, id int64) (notificationID int64) {
 		t.Fatal(err)
 	}
 	kw.UpsideDown = true
+	kw.ResendInterval = 7
 	kw.NotificationIDs = []int64{nid}
 	if err := b.c.UpdateMonitor(ctx, &kw); err != nil {
 		t.Fatal(err)
@@ -327,8 +328,8 @@ func assertUnmanaged(t *testing.T, c *Breml, id int64, when string) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	if !base.UpsideDown {
-		t.Errorf("%s: unmanaged state lost: upsideDown=%v", when, base.UpsideDown)
+	if !base.UpsideDown || base.ResendInterval != 7 {
+		t.Errorf("%s: unmanaged state lost: upsideDown=%v resend=%d", when, base.UpsideDown, base.ResendInterval)
 	}
 }

@@ -343,7 +344,7 @@ func TestUpdatePreservesUnmanagedAndClearsManaged(t *testing.T) {
 	}
 	orig := Monitor{
 		Type: "keyword", Name: "kw", Active: true, Parent: &gid,
-		Interval: 60, RetryInterval: 60, ResendInterval: 7, URL: "https://example.com",
+		Interval: 60, RetryInterval: 60, URL: "https://example.com",
 		Headers: map[string]string{"A": "1"}, Keyword: "up", OwnerKey: "default/kw",
 	}
 	id, err := b.Create(ctx, orig)
@@ -359,7 +360,6 @@ func TestUpdatePreservesUnmanagedAndClearsManaged(t *testing.T) {
 	cleared.Headers = nil
 	cleared.Keyword = ""
 	cleared.Interval = 90
-	cleared.ResendInterval = 0
 	if err := b.Update(ctx, cleared); err != nil {
 		t.Fatal(err)
 	}
@@ -369,7 +369,7 @@ func TestUpdatePreservesUnmanagedAndClearsManaged(t *testing.T) {
 		t.Fatal(err)
 	}
 	m := byID(got)[id]
-	if m.Parent != nil || m.Headers != nil || m.Keyword != "" || m.Interval != 90 || m.ResendInterval != 0 || m.NotificationIDs != nil {
+	if m.Parent != nil || m.Headers != nil || m.Keyword != "" || m.Interval != 90 || m.NotificationIDs != nil {
 		t.Errorf("managed fields not cleared: %+v", m)
 	}
 	assertUnmanaged(t, fresh, id, "after plain update")
@@ -391,6 +391,51 @@ func TestUpdatePreservesUnmanagedAndClearsManaged(t *testing.T) {
 	assertUnmanaged(t, fresh, id, "after type change")
 }

+func TestDefaultNotificationsAndWrite(t *testing.T) {
+	ctx := context.Background()
+	url := startKuma(t)
+	b := setupClient(t, url)
+	other := freshClient(t, url)
+
+	if ids, err := other.DefaultNotifications(ctx); err != nil || ids != nil {
+		t.Fatalf("no notifications: ids=%v err=%v", ids, err)
+	}
+	def := createWebhook(t, b, "default", true)
+	createWebhook(t, b, "opt-in", false)
+	// Kuma pushes the list to every session of the user, not only the writer.
+	deadline := time.Now().Add(10 * time.Second)
+	for {
+		ids, err := other.DefaultNotifications(ctx)
+		if err != nil {
+			t.Fatal(err)
+		}
+		if reflect.DeepEqual(ids, []int64{def}) {
+			break
+		}
+		if time.Now().After(deadline) {
+			t.Fatalf("other session sees defaults %v, want [%d]", ids, def)
+		}
+		time.Sleep(100 * time.Millisecond)
+	}
+
+	m := Monitor{
+		Type: "group", Name: "grp", Active: true, Interval: 60, RetryInterval: 60,
+		NotificationIDs: []int64{def}, OwnerKey: "default/grp",
+	}
+	id, err := b.Create(ctx, m)
+	if err != nil {
+		t.Fatal(err)
+	}
+	got, err := freshClient(t, url).ListOwned(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	m.ID = id
+	if !reflect.DeepEqual(byID(got)[id], m.Normalized()) {
+		t.Errorf("read-back differs:\n got  %+v\n want %+v", byID(got)[id], m.Normalized())
+	}
+}
+
 func TestRestartAdoptsByTag(t *testing.T) {
 	ctx := context.Background()
 	url := startKuma(t)
@@ -1,202 +0,0 @@
-package kumaclient
-
-import (
-	"cmp"
-	"context"
-	"errors"
-	"fmt"
-	"maps"
-	"slices"
-	"strconv"
-
-	kuma "github.com/breml/go-uptime-kuma-client"
-	"github.com/breml/go-uptime-kuma-client/notification"
-)
-
-const typeSMTP = "smtp"
-
-// ListNotifications reads the notification list cached by the session. Kuma
-// has no command to request it: it pushes the list at login and to every
-// session of the user after each change. After a write whose broadcast was
-// missed the cache is rebuilt first, so a created notification is never
-// reported absent.
-func (b *Breml) ListNotifications(ctx context.Context, name string) ([]Notification, error) {
-	if err := ctx.Err(); err != nil {
-		return nil, err
-	}
-	b.mu.Lock()
-	defer b.mu.Unlock()
-	if b.notifStale {
-		if err := b.c.Resync(ctx); err != nil && !b.recoverSession(ctx, err) {
-			return nil, fmt.Errorf("resync notifications: %w", err)
-		}
-		b.notifStale = false
-	}
-	var out []Notification
-	for _, base := range b.c.GetNotifications(ctx) {
-		if base.Name != name {
-			continue
-		}
-		n, err := toNotification(base)
-		if err != nil {
-			return nil, err
-		}
-		out = append(out, n)
-	}
-	slices.SortFunc(out, func(a, b Notification) int { return cmp.Compare(a.ID, b.ID) })
-	return out, nil
-}
-
-// CreateNotification is never retried: Kuma may have stored the notification
-// although the ack was lost; the next list finds it by name.
-func (b *Breml) CreateNotification(ctx context.Context, n Notification) (int64, error) {
-	if n.Type != typeSMTP {
-		return 0, fmt.Errorf("create notification: unsupported type %q", n.Type)
-	}
-	b.mu.Lock()
-	defer b.mu.Unlock()
-	wire := &notification.SMTP{
-		Base: notification.Base{Name: n.Name, IsActive: n.Active, IsDefault: n.IsDefault},
-	}
-	writeSMTP(&wire.SMTPDetails, n.SMTP)
-	id, err := b.c.CreateNotification(ctx, wire)
-	if err != nil {
-		b.notifStale = true
-	}
-	if createdDespite(id, err) {
-		return id, nil
-	}
-	b.recoverSession(ctx, err)
-	return 0, err
-}
-
-func (b *Breml) UpdateNotification(ctx context.Context, n Notification) error {
-	if n.Type != typeSMTP {
-		return fmt.Errorf("update notification %d: unsupported type %q", n.ID, n.Type)
-	}
-	b.mu.Lock()
-	defer b.mu.Unlock()
-	_, err := withRecovery(ctx, b, func() (struct{}, error) { return struct{}{}, b.updateNotification(ctx, n) })
-	return err
-}
-
-// updateNotification starts from the notification's current config, so keys
-// kuma-sync does not manage are written back unchanged, also across a type
-// change.
-func (b *Breml) updateNotification(ctx context.Context, n Notification) error {
-	cur, err := b.c.GetNotification(ctx, n.ID)
-	if errors.Is(err, kuma.ErrNotFound) {
-		return fmt.Errorf("update notification %d: %w", n.ID, ErrNotificationNotFound)
-	}
-	if err != nil {
-		return err
-	}
-	var g notification.Generic
-	if err := cur.As(&g); err != nil {
-		return fmt.Errorf("notification %d: %w", n.ID, err)
-	}
-	g.Name = n.Name
-	g.IsActive = n.Active
-	g.IsDefault = n.IsDefault
-	g.ApplyExisting = false
-	g.TypeName = typeSMTP
-	g.GenericDetails = maps.Clone(g.GenericDetails)
-	if g.GenericDetails == nil {
-		g.GenericDetails = notification.GenericDetails{}
-	}
-	var d notification.SMTPDetails
-	writeSMTP(&d, n.SMTP)
-	g.GenericDetails["smtpHost"] = d.Host
-	g.GenericDetails["smtpPort"] = d.Port
-	g.GenericDetails["smtpSecure"] = d.Secure
-	g.GenericDetails["smtpIgnoreSTARTTLS"] = d.IgnoreSTARTTLS
-	g.GenericDetails["smtpUsername"] = d.Username
-	g.GenericDetails["smtpPassword"] = d.Password
-	g.GenericDetails["smtpFrom"] = d.From
-	g.GenericDetails["smtpTo"] = d.To
-	err = b.c.UpdateNotification(ctx, g)
-	if errors.Is(err, kuma.ErrUpdateEventTimeout) {
-		// Applied; only the broadcast is missing.
-		b.notifStale = true
-		return nil
-	}
-	return err
-}
-
-func (b *Breml) DeleteNotification(ctx context.Context, id int64) error {
-	b.mu.Lock()
-	defer b.mu.Unlock()
-	_, err := withRecovery(ctx, b, func() (struct{}, error) {
-		if _, err := b.c.GetNotification(ctx, id); errors.Is(err, kuma.ErrNotFound) {
-			return struct{}{}, fmt.Errorf("delete notification %d: %w", id, ErrNotificationNotFound)
-		}
-		err := b.c.DeleteNotification(ctx, id)
-		if errors.Is(err, kuma.ErrUpdateEventTimeout) {
-			b.notifStale = true
-			return struct{}{}, nil
-		}
-		return struct{}{}, err
-	})
-	return err
-}
-
-func writeSMTP(d *notification.SMTPDetails, s SMTP) {
-	d.Host = s.Host
-	d.Port = int(s.Port)
-	d.Secure = s.Secure
-	d.IgnoreSTARTTLS = s.IgnoreSTARTTLS
-	d.Username = s.Username
-	d.Password = s.Password
-	d.From = s.From
-	d.To = s.To
-}
-
-// toNotification reads the config loosely: a notification made in the Kuma UI
-// may hold the port as a string.
-func toNotification(base notification.Base) (Notification, error) {
-	n := Notification{
-		ID: base.ID, Name: base.Name, Type: base.Type(), IsDefault: base.IsDefault, Active: base.IsActive,
-	}
-	if n.Type != typeSMTP {
-		return n, nil
-	}
-	var g notification.Generic
-	if err := base.As(&g); err != nil {
-		return Notification{}, fmt.Errorf("notification %d: %w", base.ID, err)
-	}
-	d := g.GenericDetails
-	n.SMTP = SMTP{
-		Host:           configString(d, "smtpHost"),
-		Port:           configPort(d, "smtpPort"),
-		Secure:         configBool(d, "smtpSecure"),
-		IgnoreSTARTTLS: configBool(d, "smtpIgnoreSTARTTLS"),
-		Username:       configString(d, "smtpUsername"),
-		Password:       configString(d, "smtpPassword"),
-		From:           configString(d, "smtpFrom"),
-		To:             configString(d, "smtpTo"),
-	}
-	return n, nil
-}
-
-func configString(d notification.GenericDetails, key string) string {
-	s, _ := d[key].(string)
-	return s
-}
-
-func configBool(d notification.GenericDetails, key string) bool {
-	v, _ := d[key].(bool)
-	return v
-}
-
-// configPort returns 0 for a missing or unreadable port, which never matches a
-// desired one.
-func configPort(d notification.GenericDetails, key string) int32 {
-	switch v := d[key].(type) {
-	case float64:
-		return int32(v)
-	case string:
-		p, _ := strconv.ParseInt(v, 10, 32)
-		return int32(p)
-	}
-	return 0
-}
--- a/Show More
+++ b/Show More