ci(deploy): publish the stack over TLS when PUBLIC_DOMAIN is set (refs #175)

The in-cluster edge (#178) is off unless the chart is given a domain, so pass
one through from a repository variable. Unset, the deploy is exactly what it was
— NodePorts, and the portals reachable only over the SSH forwards.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

.gitea/workflows/ci.yaml

@@ -41,6 +41,27 @@ jobs:
             nuget-${{ runner.os }}-
       - run: make lint
 
+  # The Helm chart's only automated gate: it renders and schema-checks the whole
+  # stack, and checks it still describes the same stack as the compose file
+  # (ADR-0033). No cluster involved — see docs/runbooks/kubernetes-talos.md.
+  k8s:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: https://github.com/actions/checkout@v4
+      # helm as its pinned static binary rather than a marketplace action: one URL,
+      # the same one the Talos runbook §0 gives a developer, and no third-party
+      # action to vet (CLAUDE.md §13). The drift check also needs `docker compose`,
+      # which the runner already has (see docs/runbooks/ci.md).
+      - name: Install helm
+        run: |
+          mkdir -p "$HOME/.local/bin"
+          curl -sSL https://get.helm.sh/helm-v3.16.4-linux-amd64.tar.gz \
+            | tar xz -O linux-amd64/helm > "$HOME/.local/bin/helm"
+          chmod +x "$HOME/.local/bin/helm"
+          echo "$HOME/.local/bin" >> "$GITHUB_PATH"
+      - run: make k8s-lint
+      - run: make k8s-drift
+
   build:
     runs-on: ubuntu-latest
     steps:

.gitea/workflows/deploy.yaml

@@ -0,0 +1,126 @@
+name: Deploy to Talos
+
+# A merge to main ships the stack to the Talos cluster on the lab server
+# (docs/runbooks/kubernetes-talos.md §9). PR CI is the merge gate, so main is
+# green by construction — this workflow only deploys.
+on:
+  push:
+    branches: [main]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+# Queue deploys, never cancel one: a helm upgrade killed half-way leaves the
+# release in `pending-upgrade` and the next run has to be unwedged by hand.
+concurrency:
+  group: deploy-talos
+  cancel-in-progress: false
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    env:
+      # The Talos VM as seen from the Fedora host (libvirt guest IP), and the
+      # address a browser uses to reach the cluster. `localhost` is deliberate:
+      # the portals' PKCE needs a secure context, so they are reached over
+      # `kubectl port-forward` — runbook §5. Override with repo variables.
+      TALOS_VM_IP: ${{ vars.TALOS_VM_IP }}
+      TALOS_HOST: ${{ vars.TALOS_HOST }}
+      # Set it and the stack is published over TLS on <sub>.<domain> by the
+      # in-cluster edge (ADR-0035, runbook §10). Empty = NodePorts, as before.
+      PUBLIC_DOMAIN: ${{ vars.PUBLIC_DOMAIN }}
+      PUBLIC_EMAIL: ${{ vars.PUBLIC_EMAIL }}
+    steps:
+      - uses: https://github.com/actions/checkout@v4
+
+      # Pinned static binaries, the same URLs the Talos runbook §0 gives a
+      # developer and the same helm the `k8s` CI job uses — no action to vet.
+      - name: Install kubectl, helm and crane
+        run: |
+          set -euo pipefail
+          bin="$HOME/.local/bin"; mkdir -p "$bin"
+          curl -sSLo "$bin/kubectl" https://dl.k8s.io/release/v1.37.0/bin/linux/amd64/kubectl
+          curl -sSL https://get.helm.sh/helm-v3.16.4-linux-amd64.tar.gz | tar xz -O linux-amd64/helm > "$bin/helm"
+          curl -sSL https://github.com/google/go-containerregistry/releases/download/v0.20.2/go-containerregistry_Linux_x86_64.tar.gz | tar xz -O crane > "$bin/crane"
+          chmod +x "$bin"/{kubectl,helm,crane}
+          echo "$bin" >> "$GITHUB_PATH"
+
+      # The cluster's API and its registry are only reachable through the Fedora
+      # host, so forward both to the runner. 30141 is the openbaar portal, for
+      # the smoke at the end.
+      - name: Tunnel the Talos API + registry through the Fedora host
+        env:
+          SSH_KEY: ${{ secrets.TALOS_SSH_KEY }}
+        run: |
+          set -euo pipefail
+          : "${TALOS_VM_IP:=192.168.122.173}"
+          umask 077
+          printf '%s\n' "$SSH_KEY" > ~/.ssh_talos
+          ssh -i ~/.ssh_talos -o StrictHostKeyChecking=no -o IdentitiesOnly=yes \
+              -o ExitOnForwardFailure=yes -p 6667 -f -N \
+              -L 6443:$TALOS_VM_IP:6443 \
+              -L 30500:$TALOS_VM_IP:30500 \
+              -L 30141:$TALOS_VM_IP:30141 \
+              user@labs.respellion.tech
+
+      # The kubeconfig's server must be https://127.0.0.1:6443 — Talos puts
+      # 127.0.0.1 in the apiserver cert SANs, so TLS verification still holds
+      # through the tunnel.
+      - name: Write the kubeconfig
+        env:
+          KUBECONFIG_B64: ${{ secrets.TALOS_KUBECONFIG }}
+        run: |
+          set -euo pipefail
+          umask 077
+          base64 -d <<< "$KUBECONFIG_B64" > "$RUNNER_TEMP/kubeconfig"
+          echo "KUBECONFIG=$RUNNER_TEMP/kubeconfig" >> "$GITHUB_ENV"
+          kubectl --kubeconfig "$RUNNER_TEMP/kubeconfig" get nodes
+
+      # Idempotent; also makes a first deploy onto a bare cluster work. The
+      # registry's storage is an emptyDir, so a replaced pod loses the images —
+      # which the push in the next step puts back anyway.
+      - name: Ensure the in-cluster registry
+        run: make k8s-registry
+
+      # Push through the tunnel (localhost), pull from the node's own NodePort
+      # (the address in the Talos registry-mirror patch) — same registry, two
+      # names, so the two `make` calls get different K8S_REGISTRY values.
+      - name: Build and push the images
+        run: make k8s-images K8S_REGISTRY=localhost:30500
+
+      # k8s-reseed = seed configmaps + helm upgrade + re-run the bootstrap jobs.
+      # The jobs are idempotent, and deleting them first is what keeps a changed
+      # Job template from wedging the upgrade (`cannot patch … with kind Job`).
+      - name: Deploy the chart
+        run: |
+          set -euo pipefail
+          publish="${PUBLIC_DOMAIN:+--set public.domain=$PUBLIC_DOMAIN --set public.email=${PUBLIC_EMAIL:-}}"
+          make k8s-reseed \
+            TALOS_HOST=${TALOS_HOST:-localhost} \
+            K8S_REGISTRY=${TALOS_VM_IP:-192.168.122.173}:30500 \
+            K8S_SET="$publish"
+
+      # `dev` is a mutable tag and helm sees an unchanged pod template, so the
+      # new images only land on a restart (pullPolicy is already Always).
+      - name: Roll the services onto the new images
+        run: |
+          set -euo pipefail
+          svcs="acl domain bff event-subscriber projection-api self-service openbaar behandel beheer"
+          kubectl -n big rollout restart deploy $svcs
+          kubectl -n big rollout status --timeout=300s deploy $svcs
+
+      # Proves portal → Caddy → BFF → projection end to end. An empty register is
+      # a pass; a 502 or a timeout is not.
+      - name: Smoke the public register
+        run: curl -fsS --retry 10 --retry-delay 6 --retry-all-errors http://localhost:30141/openbaar/register
+
+      # Cluster-wide, not just `big`: the first thing that can fail is the registry
+      # in its own namespace, and a scheduling problem shows up in the events, not
+      # in `rollout status` — which only ever says "timed out waiting".
+      - name: Pods and events on failure
+        if: failure()
+        run: |
+          kubectl get pods -A -o wide || true
+          kubectl -n big get jobs || true
+          kubectl get events -A --sort-by=.lastTimestamp | tail -30 || true

Makefile

@@ -43,7 +43,7 @@ export DOCKER_HOST := unix://$(PODMAN_SOCK)
 endif
 endif
 
-.PHONY: ci lint build unit mutation frontend integration verify verify-up verify-acl verify-nrc verify-projection verify-bff verify-domain verify-observability verify-tracing verify-metrics verify-objecttypen verify-objecten verify-registerrecord verify-objecten-notifications verify-notifications smoke up down local verify-local local-down changelog openzaak-up openzaak-smoke openzaak-seed openzaak-down stack-up stack-smoke stack-down keycloak-up keycloak-smoke keycloak-down flowable-up flowable-smoke flowable-down k8s-lint k8s-registry k8s-images k8s-seed k8s-up k8s-reseed k8s-portals k8s-down k8s-purge help
+.PHONY: ci lint build unit mutation frontend integration verify verify-up verify-acl verify-nrc verify-projection verify-bff verify-domain verify-observability verify-tracing verify-metrics verify-objecttypen verify-objecten verify-registerrecord verify-objecten-notifications verify-notifications smoke up down local verify-local local-down changelog openzaak-up openzaak-smoke openzaak-seed openzaak-down stack-up stack-smoke stack-down keycloak-up keycloak-smoke keycloak-down flowable-up flowable-smoke flowable-down k8s-lint k8s-drift k8s-registry k8s-images k8s-seed k8s-up k8s-reseed k8s-portals k8s-down k8s-purge help
 
 ## ci: run the full pipeline — lint, build, unit, mutation, frontend, verify (mirrors Gitea Actions)
 ## `verify` is the live-stack stage (full stack up once → ACL + notification checks).
@@ -64,6 +64,9 @@ frontend:
 ## lint: verify formatting (no changes)
 lint:
 	dotnet format $(SLN) --verify-no-changes
+	# Only pages in mkdocs.yml's nav are published, and mkdocs keeps a build green
+	# when one is missing — so the nav is checked here rather than not at all.
+	python3 infra/check-docs-nav.py
 
 ## build: release build
 build:
@@ -350,6 +353,13 @@ k8s-lint:
 	helm lint $(K8S_CHART)
 	helm template big $(K8S_CHART) -n $(K8S_NS) --set images.registry=registry.invalid:5000 >/dev/null
 
+## k8s-drift: fail if compose and the Helm chart describe different stacks
+# Compose is CI-canonical (ADR-0033) and the chart is a transcription of it; this
+# compares what each one deploys — workload names and resolved images. Needs
+# `docker compose` and `helm`, no cluster.
+k8s-drift:
+	python3 infra/helm/check-drift.py
+
 ## k8s-registry: deploy the in-cluster image registry (NodePort 30500)
 k8s-registry:
 	kubectl apply -f infra/helm/registry.yaml

docs/architecture/adr-0033-kubernetes-via-one-helm-chart.md

@@ -3,8 +3,8 @@
 - **Status:** Accepted
 - **Date:** 2026-09-04
 - **Deciders:** Respellion engineering
-- **Slice:** _(none yet — raised directly as a deployment-target request; see
+- **Slice:** #25 (S-24) — raised directly as a deployment-target request and matched to
-  "Process note" at the end)_
+  that issue afterwards; see the "Process note" at the end
 
 ## Context
 
@@ -126,8 +126,9 @@ Consequences of that shape, each chosen deliberately:
 
 **Negative / costs**
 
-- A second deployment description to keep in step with compose. Nothing enforces that
+- A second deployment description to keep in step with compose. `make k8s-drift` (#168)
-  today; a drift check belongs in CI (follow-up).
+  now enforces the part that bites — the workload set and the resolved images, with the
+  four deviations below declared — but not per-workload env, ports or volumes.
 - `helm install` alone is not enough — the ConfigMaps must be seeded first, and a missing
   one surfaces as `ContainerCreating`, not as a clear error.
 - Generic templates mean a values typo can render valid-but-wrong YAML; `k8s-lint` catches

docs/index.md

@@ -14,6 +14,8 @@ should teach.
   In Dutch; the strategic framing lives in `Respellion/innovation-lab`.
 - **[Working in Gitea](gitea-workflow.md)** — issues, milestones, branches, PRs.
 - **[CI runbook](runbooks/ci.md)** — the pipeline and the `make ci` local gate.
+- **[Kubernetes on Talos](runbooks/kubernetes-talos.md)** — the second deployment target:
+  one Helm chart, a single-node cluster, and the parts that bite (ADR-0033).
 
 ## Quickstart
 

docs/runbooks/ci.md

@@ -2,8 +2,10 @@
 
 > **Status: active.** The workflow `.gitea/workflows/ci.yaml` runs on Gitea's
 > hosted `ubuntu-latest` runner — no self-hosted runner required.
-> **`make ci` is still the local gate** — it runs the exact same checks
+> **`make ci` is still the local gate** — it runs the same checks via the same
-> (the workflow calls the same `make` targets).
+> `make` targets, with one exception: the `k8s` job's targets are not in `make ci`,
+> because `helm` is optional for everyone not deploying to Kubernetes. Run
+> `make k8s-lint k8s-drift` by hand after touching the chart or the compose file.
 
 ## The pipeline
 
@@ -16,6 +18,8 @@ and CI cannot drift:
 | `lint` | `make lint` → `dotnet format … --verify-no-changes` | .NET 10 SDK |
 | `build` | `make build` → `dotnet build … -c Release` | .NET 10 SDK |
 | `unit` | `make unit` → `dotnet test … -c Release --filter "Category!=Integration"` | .NET 10 SDK |
+| `frontend` | `make frontend` → Nx lint/test/build for the four portals | pnpm + Node |
+| `k8s` | `make k8s-lint` (render + schema-check the Helm chart) → `make k8s-drift` (chart still describes the same stack as `infra/docker-compose.yml`) | pinned `helm` binary + `docker compose` |
 | `mutation` | `make mutation` → `dotnet tool restore` → `dotnet stryker` (ACL); uploads the HTML report as an artifact | .NET 10 SDK |
 | `verify-stack` | the single live-stack stage — steps: `make verify-up` (full stack up + health, the DoD smoke) → `make verify-acl` (ACL ↔ OpenZaak) → `make verify-nrc` (OpenZaak → NRC delivery) → `make down` | container engine + egress (base images, nuget, `selectielijst.openzaak.nl`) |
 
@@ -27,6 +31,10 @@ and CI cannot drift:
 > services by **container IP** (the runner can't reach published ports — see
 > [gitea-actions-gotchas.md §5/§6](gitea-actions-gotchas.md)).
 
+A second workflow, `.gitea/workflows/deploy.yaml`, deploys the stack to the Talos
+cluster on the lab server when a PR is merged to `main` — see
+[kubernetes-talos.md §9](kubernetes-talos.md) for its secrets and the SSH tunnel it needs.
+
 All `uses:` references are absolute, tag-pinned URLs (`https://github.com/actions/checkout@v4`,
 `https://github.com/actions/setup-dotnet@v4`) per CLAUDE.md §8.7 and §15 — Gitea
 Actions resolves them from GitHub.

docs/runbooks/kubernetes-talos.md

@@ -322,6 +322,7 @@ The PVCs carry `helm.sh/resource-policy: keep`, so `make k8s-down` leaves the da
 
 ```bash
 make k8s-lint                      # render + schema-check the chart, no cluster needed
+make k8s-drift                     # fail if compose and the chart describe different stacks
 make k8s-portals                   # forward the portals + Keycloak to localhost (browser access)
 make k8s-images K8S_REGISTRY=...   # after changing a service or a portal
 make k8s-up TALOS_HOST=... K8S_REGISTRY=...
@@ -359,6 +360,97 @@ immutable, so `helm upgrade` is rejected with `cannot patch "…" with kind Job`
 | Pods `Evicted` / `OOMKilled` | the VM is too small (§0) |
 | A Job shows `BackoffLimitExceeded` | read it: `kubectl -n big logs job/<name>` |
 
+## 9. Deploying on merge to main
+
+`.gitea/workflows/deploy.yaml` runs the §3–§4 steps against the **lab server's** Talos VM
+every time a PR is squash-merged to `main` (and on demand via *Run workflow*). PR CI is the
+merge gate, so the workflow deploys without re-running the checks.
+
+**Prerequisite: the VM must have been installed with the §1 patch.** A stock Talos config
+gives you a node that still carries the control-plane taint and knows nothing about the
+plain-HTTP registry, and the deploy hits those in that order: the `registry` pod sits
+`Pending` until `rollout status` times out, and once that is fixed every repo image fails to
+pull. Two separate fixes:
+
+```bash
+# on the Fedora host — 1. let workloads onto the only node (§1)
+export KUBECONFIG=~/talos-kubeconfig-local
+kubectl taint node --all node-role.kubernetes.io/control-plane-
+
+# 2. trust the in-cluster registry over plain HTTP (§2)
+cat > /tmp/registry-patch.yaml <<'YAML'
+machine:
+  registries:
+    mirrors:
+      "<TALOS_VM_IP>:30500":
+        endpoints:
+          - http://<TALOS_VM_IP>:30500
+YAML
+talosctl -n <TALOS_VM_IP> -e <TALOS_VM_IP> patch mc --patch @/tmp/registry-patch.yaml
+```
+
+Keep those two apart. On Talos 1.14 a patch that also sets
+`cluster.allowSchedulingOnControlPlanes` is rejected with *".cluster.allowSchedulingOnControlPlanes
+is already set in v1alpha1 config"* — the field moved out of the v1alpha1 schema, the same way
+`machine.install` did (§1) — and the rejection takes the whole patch with it, so the mirror
+silently doesn't land either. `kubectl taint` is the documented way (§1); it is undone if the
+node ever re-registers, which is a reboot, not a deploy.
+
+The cluster's API and registry are not exposed publicly, so the job forwards them over the
+same SSH hop the Gitea-runner pipeline uses:
+
+```
+ssh -p 6667 user@labs.respellion.tech  -L 6443 -L 30500 -L 30141  →  <TALOS_VM_IP>
+```
+
+Consequences worth knowing:
+
+- Images are **pushed** to `localhost:30500` (the tunnel) and **pulled** by the node from
+  `<TALOS_VM_IP>:30500` (its own NodePort, the address in the Talos registry-mirror patch).
+  Same registry, two names — hence the two `K8S_REGISTRY` values in the workflow.
+- It calls `make k8s-reseed`, not `make k8s-up`: the bootstrap Jobs are idempotent, and
+  deleting them first is what stops a changed Job template from wedging `helm upgrade` (§7).
+- `dev` is a mutable tag, so a `rollout restart` of the nine repo deployments is what
+  actually puts the new images in the pods.
+- Deploys **queue** (`cancel-in-progress: false`): a helm upgrade killed half-way leaves the
+  release in `pending-upgrade`, which has to be unwedged by hand.
+
+Settings, all on the repository in Gitea:
+
+| Kind | Name | What |
+|---|---|---|
+| Secret | `TALOS_SSH_KEY` | private key for `user@labs.respellion.tech` (the Fedora host) |
+| Secret | `TALOS_KUBECONFIG` | base64 of the kubeconfig, **`server: https://127.0.0.1:6443`** — Talos puts `127.0.0.1` in the apiserver cert SANs, so TLS still verifies through the tunnel |
+| Variable | `TALOS_VM_IP` | the VM's libvirt address (default `192.168.122.173`) |
+| Variable | `TALOS_HOST` | the browser-facing host baked into Keycloak's issuer (default `localhost`, see §5) |
+
+The last step smokes `GET /openbaar/register` through the openbaar portal, which exercises
+portal → Caddy → BFF → projection. An empty register passes; a 502 does not.
+
+### Reaching the portals from a laptop
+
+The deployed portals are pinned to `http://localhost:30180` for Keycloak (§5), so a browser
+needs **all five** browser-facing ports on its own localhost — the portal alone is not
+enough, and a missing Keycloak shows up as `ERR_CONNECTION_REFUSED` on
+`/realms/*/.well-known/openid-configuration` followed by an opaque `ERROR Error: [object Object]`.
+`make k8s-portals` does this when kubectl can reach the cluster; through the lab server one
+SSH does it without a kubeconfig at all:
+
+```bash
+ssh -N -p 6667 \
+  -L 30140:<TALOS_VM_IP>:30140 -L 30141:<TALOS_VM_IP>:30141 \
+  -L 30142:<TALOS_VM_IP>:30142 -L 30143:<TALOS_VM_IP>:30143 \
+  -L 30180:<TALOS_VM_IP>:30180 \
+  user@labs.respellion.tech
+```
+
+Then the §5 table's URLs work as written. The admin UIs (OpenZaak, Flowable, …) need no
+forward — they are server-rendered, so the VM's address is fine.
+
+Not covered: the portals still need `make k8s-portals` (or an SSH forward) to be usable in a
+browser, because PKCE needs a secure context (§5). Giving the server a hostname + TLS is the
+upgrade path.
+
 ## What is not ported
 
 - **Observability** (Tempo, Prometheus, Grafana) is defined but disabled — those are built
@@ -366,5 +458,7 @@ immutable, so `helm upgrade` is rejected with `cannot patch "…" with kind Job`
   `K8S_SET='--set workloads.tempo.enabled=true --set workloads.prometheus.enabled=true --set workloads.grafana.enabled=true'`.
   The .NET services still export OTLP; the exporter fails harmlessly when Tempo is absent.
 - **The verify/e2e lanes.** `make verify*` and the Playwright e2e drive compose, not the
-  chart. The Kubernetes path is verified with §5's smoke test.
+  chart. The Kubernetes path is verified with §5's smoke test. CI's `k8s` job runs the two
+  clusterless checks (`k8s-lint`, `k8s-drift`) on every PR — a values typo or a compose
+  image bump that skipped the chart fails there, but nothing deploys the chart in CI.
 - **Ingress, TLS, and resource requests.** See the ponytail ceiling in ADR-0033.

infra/check-docs-nav.py

@@ -0,0 +1,30 @@
+#!/usr/bin/env python3
+"""Fail when a page under docs/ is missing from mkdocs.yml's nav.
+
+docs/ is the source of truth (CLAUDE.md §12), but only the pages listed in the nav
+are published — and mkdocs' own `omitted_files: warn` keeps a build green while
+silently dropping them, which is how every ADR after 0010 and every runbook but
+ci.md fell off the site.
+
+ponytail: a substring test, not a YAML parse — a page's path either appears in
+mkdocs.yml or it doesn't, and that needs no dependency.
+"""
+
+import sys
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parents[1]
+nav = (ROOT / "mkdocs.yml").read_text()
+
+missing = sorted(
+    str(page.relative_to(ROOT / "docs"))
+    for page in (ROOT / "docs").rglob("*.md")
+    if str(page.relative_to(ROOT / "docs")) not in nav
+)
+
+if missing:
+    print(f"{len(missing)} page(s) under docs/ are not in mkdocs.yml's nav:")
+    print("\n".join(f"  {m}" for m in missing))
+    sys.exit(1)
+
+print("docs nav complete: every page under docs/ is published")

infra/helm/check-drift.py

@@ -0,0 +1,116 @@
+#!/usr/bin/env python3
+"""Fail when the compose stack and the Helm chart stop describing the same stack.
+
+`infra/docker-compose.yml` is CI-canonical; `infra/helm/big-reference` is a
+transcription of it (ADR-0033), and until now nothing kept the two in step — an
+upstream image bump or a new service applied to only one of them landed
+unnoticed. This compares what each side actually *deploys*, not the two files:
+the rendered chart against `docker compose config`. Both tools are already
+prerequisites of the `k8s-*` make targets.
+
+Run it with `make k8s-drift`. No cluster needed.
+
+ponytail: names and images only, as sets — no per-workload env/ports/volumes.
+Those differ by design in four documented places (ADR-0033), so comparing them
+would mean re-encoding every deviation field by field; a tag bump and a missing
+service are the drift that actually bites.
+"""
+
+import json
+import re
+import subprocess
+import sys
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parents[2]
+COMPOSE = ROOT / "infra/docker-compose.yml"
+CHART = ROOT / "infra/helm/big-reference"
+
+# The busybox init container that every `waitFor` workload gets exists only in
+# the chart (compose has `depends_on`). Rendering it under a sentinel makes it
+# filterable without teaching the check what busybox is.
+BUSYBOX = "drift-check-ignored-init-image"
+
+# Differences that Kubernetes forces, not drift (ADR-0033). A name listed here is
+# expected to be on exactly one side; anything else fails.
+DEVIATIONS = {
+    # The four Django services apply their own setup_configuration in the web pod
+    # (`args: [sh, -c, "/setup_configuration.sh && exec /start.sh"]`) rather than in a
+    # separate init Job. Both that script and /start.sh run `manage.py migrate`, and
+    # Kubernetes has no `depends_on: service_completed_successfully` to serialise them,
+    # so the Job and its web pod migrated the same database concurrently.
+    "oz-init": "folded into the openzaak pod",
+    "nrc-init": "folded into the nrc-web pod",
+    "objecttypen-init": "folded into the objecttypen pod",
+    "objecten-init": "folded into the objecten pod",
+    # Compose seeds these from the host — the verify scripts `docker cp` the two
+    # scripts into a running container, and docker-compose.local.yml carries
+    # `local-seed` + `nrc-subscribe` for `make local`. A cluster has no host to seed
+    # from, so both became Jobs in the chart.
+    "seed-zaaktype": "compose seeds the catalogus from the host (infra/openzaak/seed_catalogus.py)",
+    "nrc-subscribe": "compose registers the abonnement from the host (infra/local/register-abonnement.py)",
+}
+
+# Workloads the observability backplane adds. Off by default in both stacks'
+# defaults, so they are rendered on purpose here — otherwise their images drift
+# unwatched.
+OBSERVABILITY = ["tempo", "prometheus", "grafana"]
+
+
+def compose_services() -> dict[str, str]:
+    """Service name -> image, with ${TAG:-default} interpolation already applied."""
+    out = run(["docker", "compose", "-f", str(COMPOSE), "config", "--format", "json"])
+    return {name: svc.get("image", "") for name, svc in json.loads(out)["services"].items()}
+
+
+def chart_workloads() -> dict[str, str]:
+    """Workload name -> image, read back out of the rendered manifests."""
+    out = run(
+        ["helm", "template", "big", str(CHART), "-n", "big", "--set", f"images.busybox={BUSYBOX}"]
+        + [f"--set=workloads.{w}.enabled=true" for w in OBSERVABILITY]
+    )
+    workloads = {}
+    for doc in out.split("\n---"):
+        if not re.search(r"^kind: (Deployment|Job)$", doc, re.M):
+            continue
+        name = re.search(r"^  name: (\S+)$", doc, re.M)[1]
+        images = [i for i in re.findall(r"^\s+image: (\S+)$", doc, re.M) if i != BUSYBOX]
+        workloads[name] = images[0]
+    return workloads
+
+
+def run(argv: list[str]) -> str:
+    proc = subprocess.run(argv, capture_output=True, text=True)
+    if proc.returncode != 0:
+        sys.exit(f"{argv[0]} failed:\n{proc.stderr}")
+    return proc.stdout
+
+
+def main() -> int:
+    compose, chart = compose_services(), chart_workloads()
+    problems = []
+
+    for name in sorted(set(compose) - set(chart) - set(DEVIATIONS)):
+        problems.append(f"  {name}: in docker-compose.yml, not in the chart")
+    for name in sorted(set(chart) - set(compose) - set(DEVIATIONS)):
+        problems.append(f"  {name}: in the chart, not in docker-compose.yml")
+    for name in sorted(set(compose) & set(chart)):
+        if compose[name] != chart[name]:
+            problems.append(f"  {name}: compose runs {compose[name]}, the chart runs {chart[name]}")
+
+    if problems:
+        print("compose and the Helm chart describe different stacks:\n" + "\n".join(problems))
+        print(
+            "\nPort the change to the other stack, or — if the difference is forced by\n"
+            "Kubernetes — declare it in DEVIATIONS in this file, with the reason."
+        )
+        return 1
+
+    print(f"no drift: {len(chart)} workloads, images identical on both stacks")
+    for name, why in sorted(DEVIATIONS.items()):
+        print(f"  deviation (declared): {name} — {why}")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

mkdocs.yml

@@ -32,6 +32,30 @@ nav:
       - "ADR-0008: Read projection store": architecture/adr-0008-read-projection-store.md
       - "ADR-0009: External-task job worker": architecture/adr-0009-external-task-job-worker.md
       - "ADR-0010: BFF OIDC validation": architecture/adr-0010-bff-oidc.md
+      - "ADR-0011: Approval status flow": architecture/adr-0011-approval-status-flow.md
+      - "ADR-0012: Citizen reference correlation": architecture/adr-0012-citizen-reference-correlation.md
+      - "ADR-0013: Behandel-portal wiring": architecture/adr-0013-behandel-portal-wiring.md
+      - "ADR-0014: Withdrawal cancels the process": architecture/adr-0014-withdrawal-cancels-the-process.md
+      - "ADR-0015: Beoordeling escalation": architecture/adr-0015-beoordeling-escalation.md
+      - "ADR-0016: Diploma eligibility DMN": architecture/adr-0016-diploma-eligibility-dmn.md
+      - "ADR-0017: Document-wait timeout": architecture/adr-0017-document-wait-timeout-cancellation.md
+      - "ADR-0018: Diploma upload via the ACL": architecture/adr-0018-diploma-upload-via-acl-documenten.md
+      - "ADR-0019: Zaak cancellation on timeout": architecture/adr-0019-zaak-cancellation-on-timeout.md
+      - "ADR-0020: Local stack self-seeds": architecture/adr-0020-local-stack-self-seeds.md
+      - "ADR-0021: Zaaktype by identificatie": architecture/adr-0021-acl-resolves-zaaktype-by-identificatie.md
+      - "ADR-0022: Quartz scheduler": architecture/adr-0022-quartz-scheduler.md
+      - "ADR-0023: Observability stack": architecture/adr-0023-observability-stack.md
+      - "ADR-0024: Prometheus AspNetCore exporter": architecture/adr-0024-prometheus-aspnetcore-exporter.md
+      - "ADR-0025: BFF reads catalogus via the ACL": architecture/adr-0025-bff-reads-catalogus-via-acl.md
+      - "ADR-0026: Mutable default-fill store": architecture/adr-0026-mutable-default-fill-store.md
+      - "ADR-0027: RegisterRecord objecttype": architecture/adr-0027-registerrecord-objecttype-schema.md
+      - "ADR-0028: Objecten holds the register": architecture/adr-0028-objecten-holds-the-register.md
+      - "ADR-0029: Objecten publishes to NRC": architecture/adr-0029-objecten-publishes-to-nrc.md
+      - "ADR-0030: Projection sourced from the register": architecture/adr-0030-projection-sourced-from-the-register.md
+      - "ADR-0031: MFA on the medewerker realm": architecture/adr-0031-mfa-on-the-medewerker-realm.md
+      - "ADR-0032: Werkbak live refresh": architecture/adr-0032-werkbak-live-refresh.md
+      - "ADR-0033: Kubernetes via one Helm chart": architecture/adr-0033-kubernetes-via-one-helm-chart.md
+      - "ADR-0034: Caddy serves the portals": architecture/adr-0034-caddy-serves-the-portals.md
   - FDS-architectuur:
       - Overzicht: architecture/fds/README.md
       - Componentview (L3): architecture/fds/c4-component-view.md
@@ -46,8 +70,15 @@ nav:
   - Working in Gitea: gitea-workflow.md
   - Frontend decisions: frontend-decisions.md
   - Demo script: demo-script.md
+  - Synthetic data: synthetic-data.md
   - Runbooks:
       - CI: runbooks/ci.md
+      - OpenZaak: runbooks/openzaak.md
+      - Open Notificaties (NRC): runbooks/opennotificaties.md
+      - Keycloak: runbooks/keycloak.md
+      - Flowable: runbooks/flowable.md
+      - Kubernetes on Talos: runbooks/kubernetes-talos.md
+      - Gitea Actions gotchas: runbooks/gitea-actions-gotchas.md
 
 markdown_extensions:
   - admonition