.gitea/workflows/ci.yaml

@@ -333,7 +333,7 @@ jobs:
       # Log dump must precede teardown (which removes the containers).
       - name: Dump container logs on failure
         if: failure()
-        run: docker compose -f infra/docker-compose.yml logs --no-color --tail=100 oz-init openzaak nrc-init nrc-web nrc-celery nrc-beat flowable-db flowable-rest flowable-init keycloak acl bff domain projection-db event-subscriber projection-api self-service openbaar behandel beheer objecttypen-db objecttypen-redis objecttypen-init objecttypen objecten-db objecten-redis objecten-init objecten objecten-celery registerrecord-init tempo prometheus grafana 2>&1 || true
+        run: docker compose -f infra/docker-compose.yml logs --no-color --tail=100 oz-init openzaak nrc-init nrc-web nrc-celery nrc-beat flowable-db flowable-rest flowable-init keycloak acl bff domain projection-db event-subscriber projection-api self-service openbaar behandel beheer objecttypen-db objecttypen-redis objecttypen-init objecttypen objecten-db objecten-redis objecten-init objecten objecten-celery registerrecord-init clamav tempo prometheus grafana 2>&1 || true
       - name: Tear down
         if: always()
         run: make down

Makefile

@@ -10,7 +10,7 @@ COMPOSE    := infra/docker-compose.yml
 # Long-running services with a healthcheck — the smoke polls these for readiness
 # (infra/wait-healthy.sh). One-shot init jobs (oz-init, nrc-init, flowable-init)
 # are not polled; they only need to have run. See docs/runbooks/gitea-actions-gotchas.md.
-WAIT_SVCS  := openzaak nrc-web acl bff domain event-subscriber projection-api self-service openbaar behandel beheer objecttypen objecten
+WAIT_SVCS  := openzaak nrc-web acl bff domain event-subscriber projection-api self-service openbaar behandel beheer objecttypen objecten clamav
 # Config files (OpenZaak data.yaml, Keycloak realms, Flowable BPMN) are streamed
 # into external named volumes via `docker cp` (infra/seed-config.sh) instead of
 # bind-mounted, because bind mounts don't reach sibling containers on the

infra/docker-compose.yml

@@ -785,6 +785,26 @@ services:
         condition: service_completed_successfully
     networks: [cg]
 
+  # ClamAV daemon (S-28, ADR-0036): the domain scans uploaded diplomas over clamd's INSTREAM
+  # protocol on :3310 before they reach OpenZaak (S-29). The first start downloads ~300 MB of
+  # signatures with freshclam; the volume keeps them across restarts. clamd holds them in memory
+  # (~1.2 GB), and a reload would briefly hold two copies — ConcurrentDatabaseReload off prevents
+  # that, at the cost of clamd pausing scans during a signature reload.
+  clamav:
+    image: docker.io/clamav/clamav:1.4.6
+    environment:
+      CLAMD_CONF_ConcurrentDatabaseReload: "no"
+    # The image's own healthcheck (clamdcheck.sh: PING → PONG) polls every 30s; poll faster so
+    # wait-healthy sees it as soon as the signatures are loaded.
+    healthcheck:
+      test: ["CMD-SHELL", "clamdcheck.sh"]
+      interval: 5s
+      start_period: 360s
+    mem_limit: 2g
+    volumes:
+      - clamav-db:/var/lib/clamav
+    networks: [cg]
+
   # ── Observability backplane (S-16a, ADR-0023) ──────────────────────────────
   # Grafana-native stack: Tempo ingests OTLP traces (the .NET services export
   # straight to it — no collector hop, S-16b), Prometheus scrapes service
@@ -836,6 +856,7 @@ volumes:
   projection-db:
   objecttypen-db:
   objecten-db:
+  clamav-db:
   # Config volumes — created and populated out-of-band by infra/seed-config.sh
   # (docker cp), because bind mounts don't reach sibling containers on the CI
   # runner. `external` keeps the names deterministic; the seed step manages them.

infra/helm/big-reference/values.yaml

@@ -588,6 +588,24 @@ workloads:
     envFrom: [objecten]
     waitFor: [objecten-db:5432, objecten-redis:6379]
 
+  # ── ClamAV (S-28, ADR-0036) ─────────────────────────────────────────────────
+  # The domain scans uploaded diplomas over clamd's INSTREAM protocol (S-29).
+  # First start pulls ~300 MB of signatures, so the node needs outbound internet
+  # (like seed-zaaktype); the data volume keeps them when persistence is on.
+  clamav:
+    image: docker.io/clamav/clamav:1.4.6
+    env:
+      CLAMD_CONF_ConcurrentDatabaseReload: "no"
+    ports: [{ name: clamd, port: 3310 }]
+    data: { mountPath: /var/lib/clamav, size: 1Gi }
+    probe:
+      exec: { command: [clamdcheck.sh] }
+      periodSeconds: 5
+      failureThreshold: 72
+    resources:
+      requests: { memory: 1200Mi }
+      limits: { memory: 2Gi }
+
   # ── Bootstrap the flow, like the local compose stack does (S-B04, ADR-0020) ──
   # Seeds + publishes the BIG zaaktype through the same FQDN the ACL uses, so the
   # server-assigned URLs are host-consistent. The ACL then resolves them by