ci(kaniko): build-vmtest on the maintained fork like every other step

#797 added build-vmtest with gcr.io/kaniko-project/executor:v1.23.2-debug,
the archived Google image the other nine steps left in August (60f231f8).
It passed on master only because that image was still cached on the node;
the branch push of the controller PR scheduled it elsewhere and the step
died before its first command. Same fork pin as the rest.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

.woodpecker/build-ci-images.yml

@@ -89,7 +89,7 @@ steps:
           --destination gitea.renner.uno/gitea_admin/ci-k8s:latest
 
   - name: build-vmtest
-    image: gcr.io/kaniko-project/executor:v1.23.2-debug
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.18-debug
     directory: ci/images/vmtest
     depends_on: []
     when:
@@ -349,3 +349,30 @@ steps:
           --dockerfile Containerfile \
           --destination gitea.renner.uno/gitea_admin/heating-can:$TAG \
           --destination gitea.renner.uno/gitea_admin/heating-can:latest
+
+  # netbird-proxy-services: the controller that reconciles NetBird reverse-proxy
+  # services (public Ingress hosts -> TLS passthrough -> Traefik ClusterIP).
+  # Runtime artifact like heating-can; same registry so the audit tracks it.
+  - name: build-netbird-proxy-services
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.18-debug
+    directory: ci/images/netbird-proxy-services
+    depends_on: []
+    when:
+      - event: deployment
+      - event: push
+        path: ["ci/images/netbird-proxy-services/**", ".woodpecker/build-ci-images.yml"]
+    environment:
+      GITEA_USER: gitea_admin
+      GITEA_TOKEN:
+        from_secret: ci_images_token
+    commands:
+      - mkdir -p /kaniko/.docker
+      - AUTH=$(printf '%s:%s' "$GITEA_USER" "$GITEA_TOKEN" | base64 | tr -d '\n')
+      - printf '{"auths":{"gitea.renner.uno":{"auth":"%s"}}}' "$AUTH" > /kaniko/.docker/config.json
+      - TAG=$(date +%Y-%m-%d)
+      - |
+        /kaniko/executor \
+          --context . \
+          --dockerfile Containerfile \
+          --destination gitea.renner.uno/gitea_admin/netbird-proxy-services:$TAG \
+          --destination gitea.renner.uno/gitea_admin/netbird-proxy-services:latest

ci/images/netbird-proxy-services/Containerfile

@@ -0,0 +1,12 @@
+# netbird-proxy-services: reconciles NetBird reverse-proxy services (public
+# domains -> TLS passthrough -> Traefik ClusterIP) from Ingresses carrying the
+# public label. Standard library only, so the image is the interpreter plus one
+# file; runs unprivileged as its own user.
+FROM python:3.13-slim
+
+RUN useradd --system --no-create-home --shell /usr/sbin/nologin controller
+COPY controller.py /opt/controller.py
+
+ENV PYTHONUNBUFFERED=1
+USER controller
+ENTRYPOINT ["python3", "/opt/controller.py"]

ci/images/netbird-proxy-services/controller.py

@@ -0,0 +1,269 @@
+#!/usr/bin/env python3
+"""netbird-proxy-services: reconcile NetBird reverse-proxy services from Ingresses.
+
+Source of truth: every Ingress carrying the public label (dns.renner.uno/public).
+For each host on such an Ingress the NetBird management gets one reverse-proxy
+service in TLS-passthrough mode on :443, targeting Traefik's ClusterIP through a
+subnet resource that covers the cluster's service CIDR. SNI and Host reach
+Traefik untouched, the proxy terminates nothing, and no domain resource is
+involved -- the routing peers stay ordinary IP routers.
+
+Ownership is derived from NetBird itself, not from local state: a service is
+managed iff its mode is "tls" and its target is this controller's subnet
+resource. Services that do not match (the hand-made HTTP/domain ones) are never
+touched; a desired host held by such a service is reported and skipped until
+that service is removed by hand.
+
+Credentials: the NetBird PAT is read from OpenBao on every pass through the
+Kubernetes auth role, exactly like the setup-key rotator; it never lands in a
+Kubernetes Secret or in a log line.
+"""
+
+import json
+import logging
+import os
+import sys
+import time
+import urllib.error
+import urllib.parse
+import urllib.request
+
+LOG = logging.getLogger("netbird-proxy-services")
+
+NB = os.environ.get("NB_MANAGEMENT_URL", "https://netbird.renner.uno").rstrip("/")
+BAO_ADDR = os.environ.get("BAO_ADDR", "http://openbao.openbao.svc.cluster.local:8200").rstrip("/")
+BAO_ROLE = os.environ.get("BAO_ROLE", "netbird-proxy-services")
+BAO_PAT_PATH = os.environ.get("BAO_PAT_PATH", "homelab/data/infrastructure/secret-rotators-bootstrap/netbird")
+BAO_PAT_KEY = os.environ.get("BAO_PAT_KEY", "pat")
+SERVICE_CIDR = os.environ.get("SERVICE_CIDR", "10.96.0.0/12")
+NETWORK_NAME = os.environ.get("NETWORK_NAME", "k8s public ingress")
+ROUTER_GROUP = os.environ.get("ROUTER_GROUP_NAME", "k8s-ingress-router")
+SOURCE_GROUP = os.environ.get("SOURCE_GROUP_NAME", "All")
+TRAEFIK_NS, TRAEFIK_SVC = os.environ.get("TRAEFIK_SERVICE", "ingress/traefik").split("/", 1)
+PUBLIC_LABEL = os.environ.get("PUBLIC_LABEL", "dns.renner.uno/public")
+LISTEN_PORT = int(os.environ.get("LISTEN_PORT", "443"))
+INTERVAL = int(os.environ.get("INTERVAL_SECONDS", "60"))
+HTTP_TIMEOUT = 20
+
+K8S_API = "https://kubernetes.default.svc"
+K8S_TOKEN_FILE = "/var/run/secrets/kubernetes.io/serviceaccount/token"
+K8S_CA_FILE = "/var/run/secrets/kubernetes.io/serviceaccount/ca.crt"
+
+
+class ApiError(Exception):
+    pass
+
+
+def http(method, url, body=None, headers=None, cafile=None):
+    data = None if body is None else json.dumps(body).encode()
+    req = urllib.request.Request(url, data=data, method=method)
+    req.add_header("Accept", "application/json")
+    if data is not None:
+        req.add_header("Content-Type", "application/json")
+    for k, v in (headers or {}).items():
+        req.add_header(k, v)
+    ctx = None
+    if cafile:
+        import ssl
+        ctx = ssl.create_default_context(cafile=cafile)
+    try:
+        with urllib.request.urlopen(req, timeout=HTTP_TIMEOUT, context=ctx) as resp:
+            raw = resp.read()
+            return json.loads(raw) if raw else None
+    except urllib.error.HTTPError as e:
+        detail = e.read().decode(errors="replace")[:300]
+        raise ApiError(f"{method} {url} -> {e.code}: {detail}") from None
+
+
+# --- Kubernetes -------------------------------------------------------------
+
+def k8s(path):
+    with open(K8S_TOKEN_FILE) as f:
+        token = f.read().strip()
+    return http("GET", K8S_API + path, headers={"Authorization": f"Bearer {token}"}, cafile=K8S_CA_FILE)
+
+
+def desired_hosts():
+    sel = urllib.parse.quote(f"{PUBLIC_LABEL}=true")
+    ingresses = k8s(f"/apis/networking.k8s.io/v1/ingresses?labelSelector={sel}")
+    hosts = {}
+    for ing in ingresses.get("items", []):
+        ref = f'{ing["metadata"]["namespace"]}/{ing["metadata"]["name"]}'
+        for rule in ing.get("spec", {}).get("rules", []):
+            host = rule.get("host")
+            if not host or host.startswith("*"):
+                continue
+            hosts.setdefault(host, ref)
+    return hosts
+
+
+def traefik_cluster_ip():
+    svc = k8s(f"/api/v1/namespaces/{TRAEFIK_NS}/services/{TRAEFIK_SVC}")
+    for ip in svc["spec"].get("clusterIPs", []):
+        if ":" not in ip:
+            return ip
+    raise ApiError(f"{TRAEFIK_NS}/{TRAEFIK_SVC} has no IPv4 ClusterIP")
+
+
+# --- OpenBao ----------------------------------------------------------------
+
+def netbird_pat():
+    with open(K8S_TOKEN_FILE) as f:
+        jwt = f.read().strip()
+    login = http("POST", f"{BAO_ADDR}/v1/auth/kubernetes/login", {"role": BAO_ROLE, "jwt": jwt})
+    bao_token = login["auth"]["client_token"]
+    kv = http("GET", f"{BAO_ADDR}/v1/{BAO_PAT_PATH}", headers={"X-Vault-Token": bao_token})
+    pat = kv["data"]["data"].get(BAO_PAT_KEY)
+    if not pat:
+        raise ApiError(f"OpenBao {BAO_PAT_PATH} has no key {BAO_PAT_KEY}")
+    return pat
+
+
+# --- NetBird management -----------------------------------------------------
+
+class NetBird:
+    def __init__(self, pat):
+        self.h = {"Authorization": f"Token {pat}"}
+
+    def get(self, path):
+        return http("GET", f"{NB}/api/{path}", headers=self.h)
+
+    def list(self, path):
+        # An empty collection comes back as an empty body / null, not [].
+        return self.get(path) or []
+
+    def post(self, path, body):
+        return http("POST", f"{NB}/api/{path}", body, headers=self.h)
+
+    def put(self, path, body):
+        return http("PUT", f"{NB}/api/{path}", body, headers=self.h)
+
+    def delete(self, path):
+        return http("DELETE", f"{NB}/api/{path}", headers=self.h)
+
+
+def group_id(nb, name):
+    for g in nb.list("groups"):
+        if g["name"] == name:
+            return g["id"]
+    raise ApiError(f"NetBird group {name!r} not found")
+
+
+def ensure_network(nb):
+    for n in nb.list("networks"):
+        if n["name"] == NETWORK_NAME:
+            return n["id"]
+    n = nb.post("networks", {"name": NETWORK_NAME,
+                             "description": "managed by netbird-proxy-services; public ingress via TLS passthrough"})
+    LOG.info("created network %s (%s)", NETWORK_NAME, n["id"])
+    return n["id"]
+
+
+def ensure_resource(nb, net):
+    for r in nb.list(f"networks/{net}/resources"):
+        if r.get("address") == SERVICE_CIDR:
+            return r["id"]
+    r = nb.post(f"networks/{net}/resources", {"name": "cluster service CIDR", "address": SERVICE_CIDR,
+                                              "description": "managed by netbird-proxy-services",
+                                              "enabled": True, "groups": []})
+    LOG.info("created subnet resource %s (%s)", SERVICE_CIDR, r["id"])
+    return r["id"]
+
+
+def ensure_router(nb, net, router_group):
+    for r in nb.list(f"networks/{net}/routers"):
+        if router_group in (r.get("peer_groups") or []):
+            return r["id"]
+    r = nb.post(f"networks/{net}/routers", {"peer_groups": [router_group], "metric": 9999,
+                                            "masquerade": True, "enabled": True})
+    LOG.info("created router on group %s (%s)", ROUTER_GROUP, r["id"])
+    return r["id"]
+
+
+def ensure_policy(nb, resource, source_group):
+    name = f"{NETWORK_NAME} access"
+    for p in nb.list("policies"):
+        if p["name"] == name:
+            return p["id"]
+    p = nb.post("policies", {"name": name, "enabled": True, "rules": [{
+        "name": name, "enabled": True, "action": "accept", "protocol": "tcp",
+        "ports": [str(LISTEN_PORT)], "bidirectional": False, "sources": [source_group],
+        "destinationResource": {"id": resource, "type": "subnet"}}]})
+    LOG.info("created policy %s (%s)", name, p["id"])
+    return p["id"]
+
+
+def service_body(host, resource, target_ip):
+    return {"name": host, "domain": host, "mode": "tls", "listen_port": LISTEN_PORT, "enabled": True,
+            "targets": [{"target_type": "subnet", "target_id": resource, "protocol": "tcp",
+                         "host": target_ip, "port": 443, "enabled": True}]}
+
+
+def is_managed(svc, resource):
+    return svc.get("mode") == "tls" and any(t.get("target_id") == resource for t in svc.get("targets") or [])
+
+
+def target_matches(svc, target_ip):
+    if svc.get("listen_port") != LISTEN_PORT or not svc.get("enabled"):
+        return False
+    ts = svc.get("targets") or []
+    return len(ts) == 1 and ts[0].get("host") == target_ip and ts[0].get("port") == 443 \
+        and ts[0].get("protocol") == "tcp" and ts[0].get("enabled")
+
+
+def reconcile():
+    hosts = desired_hosts()
+    target_ip = traefik_cluster_ip()
+    nb = NetBird(netbird_pat())
+
+    router_group = group_id(nb, ROUTER_GROUP)
+    source_group = group_id(nb, SOURCE_GROUP)
+    net = ensure_network(nb)
+    resource = ensure_resource(nb, net)
+    ensure_router(nb, net, router_group)
+    ensure_policy(nb, resource, source_group)
+
+    by_domain = {s["domain"]: s for s in nb.list("reverse-proxies/services")}
+    created = updated = deleted = held = 0
+
+    for host, ref in sorted(hosts.items()):
+        svc = by_domain.get(host)
+        if svc is None:
+            nb.post("reverse-proxies/services", service_body(host, resource, target_ip))
+            LOG.info("created %s (from %s) -> %s:443", host, ref, target_ip)
+            created += 1
+        elif not is_managed(svc, resource):
+            LOG.warning("%s is held by unmanaged service %s (mode %s); remove it to migrate",
+                        host, svc["id"], svc.get("mode"))
+            held += 1
+        elif not target_matches(svc, target_ip):
+            nb.put(f"reverse-proxies/services/{svc['id']}", service_body(host, resource, target_ip))
+            LOG.info("updated %s -> %s:443", host, target_ip)
+            updated += 1
+
+    for domain, svc in by_domain.items():
+        if is_managed(svc, resource) and domain not in hosts:
+            nb.delete(f"reverse-proxies/services/{svc['id']}")
+            LOG.info("deleted %s (no public Ingress carries it any more)", domain)
+            deleted += 1
+
+    LOG.info("reconciled: %d hosts desired, %d created, %d updated, %d deleted, %d held by unmanaged services",
+             len(hosts), created, updated, deleted, held)
+
+
+def main():
+    logging.basicConfig(level=os.environ.get("LOG_LEVEL", "INFO"), stream=sys.stdout,
+                        format="%(asctime)s %(levelname)s %(message)s")
+    if os.environ.get("ONCE") == "1":
+        reconcile()
+        return
+    while True:
+        try:
+            reconcile()
+        except Exception as e:  # keep running; the next pass retries
+            LOG.error("reconcile failed: %s", e)
+        time.sleep(INTERVAL)
+
+
+if __name__ == "__main__":
+    main()

kubernetes/infrastructure/openbao/policies/netbird-proxy-services.hcl

@@ -0,0 +1,23 @@
+# OpenBao policy: netbird-proxy-services
+#
+# The reverse-proxy-services controller (Deployment netbird-proxy-services in
+# the openbao namespace) reads the NetBird PAT on every reconcile pass and
+# calls the management API with it. Read-only on that one path; it shares the
+# bootstrap credential with rotator-netbird but not that role's PATCH rights.
+#
+# NOT applied by Flux. Apply ONCE with an admin token:
+#
+#   bao policy write netbird-proxy-services kubernetes/infrastructure/openbao/policies/netbird-proxy-services.hcl
+#   bao write auth/kubernetes/role/netbird-proxy-services \
+#     bound_service_account_names=netbird-proxy-services \
+#     bound_service_account_namespaces=openbao \
+#     policies=netbird-proxy-services ttl=15m
+#
+# The PAT itself is the one rotator-netbird already uses
+# (homelab/infrastructure/secret-rotators-bootstrap/netbird, key `pat`).
+#
+# Do NOT set token_no_default_policy=true (kv-v2 preflight needs the default policy).
+
+path "homelab/data/infrastructure/secret-rotators-bootstrap/netbird" {
+  capabilities = ["read"]
+}