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).
@@ -350,6 +350,13 @@ 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

infra/helm/check-drift.py

@@ -0,0 +1,94 @@
+#!/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"
+
+# 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)):
+        problems.append(f"  {name}: in docker-compose.yml, not in the chart")
+    for name in sorted(set(chart) - set(compose)):
+        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")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())