254 lines
8.9 KiB
Python
254 lines
8.9 KiB
Python
|
"""Owner and Switchyard access-boundary contracts."""
|
||
|
|
|
||
|
|
from __future__ import annotations
|
||
|
|
|
||
|
|
from testing.tests.test_hermes_cli_support import (
|
||
|
|
HERMES,
|
||
|
|
SCRIPTS,
|
||
|
|
_agent_deployment,
|
||
|
|
yaml,
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
def test_owner_agent_has_pinned_dedicated_node_ssh_access():
|
||
|
|
deployment = _agent_deployment()
|
||
|
|
annotations = deployment["spec"]["template"]["metadata"]["annotations"]
|
||
|
|
assert annotations[
|
||
|
|
"vault.hashicorp.com/agent-inject-secret-node-ssh-private-key"
|
||
|
|
] == "kv/data/atlas/hermes/developer-ssh"
|
||
|
|
assert annotations[
|
||
|
|
"vault.hashicorp.com/agent-inject-secret-node-ssh-config"
|
||
|
|
] == "kv/data/atlas/hermes/developer-ssh"
|
||
|
|
assert annotations[
|
||
|
|
"vault.hashicorp.com/agent-inject-secret-node-ssh-known-hosts"
|
||
|
|
] == "kv/data/atlas/hermes/developer-ssh"
|
||
|
|
|
||
|
|
init = next(
|
||
|
|
item
|
||
|
|
for item in deployment["spec"]["template"]["spec"]["initContainers"]
|
||
|
|
if item["name"] == "init-config"
|
||
|
|
)
|
||
|
|
command = init["command"][2]
|
||
|
|
assert "ln -s /runtime-access/node-ssh-config /opt/data/home/.ssh/config" in command
|
||
|
|
assert (
|
||
|
|
"ln -s /runtime-access/node-ssh-known-hosts /opt/data/home/.ssh/known_hosts"
|
||
|
|
in command
|
||
|
|
)
|
||
|
|
assert "ln -s home/.ssh /opt/data/.ssh" in command
|
||
|
|
assert "chmod 0700 /opt/data/home/.ssh" in command
|
||
|
|
assert (
|
||
|
|
"ln -s /runtime-access/node-ssh-private-key "
|
||
|
|
"/opt/data/home/.ssh/id_ed25519_atlas_nodes"
|
||
|
|
) in command
|
||
|
|
|
||
|
|
config = yaml.safe_load((HERMES / "agent-configmap.yaml").read_text())["data"]
|
||
|
|
assert "ssh_config" not in config
|
||
|
|
assert "ssh_known_hosts" not in config
|
||
|
|
assert "ssh-ed25519" not in (HERMES / "agent-configmap.yaml").read_text()
|
||
|
|
|
||
|
|
resources = yaml.safe_load((HERMES / "kustomization.yaml").read_text())[
|
||
|
|
"resources"
|
||
|
|
]
|
||
|
|
assert "node-ssh-access.yaml" in resources
|
||
|
|
access = [
|
||
|
|
item
|
||
|
|
for item in yaml.safe_load_all((HERMES / "node-ssh-access.yaml").read_text())
|
||
|
|
if item
|
||
|
|
]
|
||
|
|
service_account = next(item for item in access if item["kind"] == "ServiceAccount")
|
||
|
|
assert service_account["metadata"]["name"] == "hermes-node-ssh-access"
|
||
|
|
provider = next(item for item in access if item["kind"] == "SecretProviderClass")
|
||
|
|
assert provider["metadata"]["name"] == "hermes-node-ssh-access"
|
||
|
|
assert provider["spec"]["provider"] == "vault"
|
||
|
|
parameters = provider["spec"]["parameters"]
|
||
|
|
assert parameters["roleName"] == "hermes-node-ssh"
|
||
|
|
assert 'secretPath: "kv/data/atlas/hermes/developer-ssh"' in parameters["objects"]
|
||
|
|
assert 'secretKey: "public_key"' in parameters["objects"]
|
||
|
|
daemonset = next(item for item in access if item["kind"] == "DaemonSet")
|
||
|
|
pod = daemonset["spec"]["template"]["spec"]
|
||
|
|
assert pod["serviceAccountName"] == "hermes-node-ssh-access"
|
||
|
|
assert pod["automountServiceAccountToken"] is True
|
||
|
|
host_home = next(item for item in pod["volumes"] if item["name"] == "host-home")
|
||
|
|
assert host_home["hostPath"] == {"path": "/home", "type": "Directory"}
|
||
|
|
vault_secrets = next(
|
||
|
|
item for item in pod["volumes"] if item["name"] == "vault-secrets"
|
||
|
|
)
|
||
|
|
assert vault_secrets["csi"]["driver"] == "secrets-store.csi.k8s.io"
|
||
|
|
assert vault_secrets["csi"]["volumeAttributes"] == {
|
||
|
|
"secretProviderClass": "hermes-node-ssh-access"
|
||
|
|
}
|
||
|
|
reconciler = pod["containers"][0]["args"][0]
|
||
|
|
assert "cat /vault/secrets/node-ssh-public-key" in reconciler
|
||
|
|
assert "grep -qxF" in reconciler
|
||
|
|
assert "for user in atlas oceanus" in reconciler
|
||
|
|
assert "/host-etc/passwd" in reconciler
|
||
|
|
assert "chown \"${uid}:${gid}\"" in reconciler
|
||
|
|
host_passwd = next(
|
||
|
|
item for item in pod["volumes"] if item["name"] == "host-passwd"
|
||
|
|
)
|
||
|
|
assert host_passwd["hostPath"] == {"path": "/etc/passwd", "type": "File"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_owner_agent_tracks_no_ssh_identity_or_host_key_material():
|
||
|
|
"""Vault references may be tracked; SSH identities and trust data may not."""
|
||
|
|
forbidden = (
|
||
|
|
"BEGIN OPENSSH PRIVATE KEY",
|
||
|
|
"ssh-ed25519 AAAA",
|
||
|
|
"ssh-rsa AAAA",
|
||
|
|
"IdentityFile ",
|
||
|
|
"UserKnownHostsFile ",
|
||
|
|
"StrictHostKeyChecking ",
|
||
|
|
"ssh_config:",
|
||
|
|
"ssh_known_hosts:",
|
||
|
|
)
|
||
|
|
text_suffixes = {
|
||
|
|
".conf",
|
||
|
|
".json",
|
||
|
|
".md",
|
||
|
|
".py",
|
||
|
|
".sh",
|
||
|
|
".toml",
|
||
|
|
".yaml",
|
||
|
|
".yml",
|
||
|
|
}
|
||
|
|
tracked = "\n".join(
|
||
|
|
path.read_text(encoding="utf-8")
|
||
|
|
for path in HERMES.rglob("*")
|
||
|
|
if path.is_file() and path.suffix in text_suffixes
|
||
|
|
)
|
||
|
|
for marker in forbidden:
|
||
|
|
assert marker not in tracked
|
||
|
|
|
||
|
|
|
||
|
|
def test_switchyard_has_a_dedicated_non_owner_identity_and_read_only_catalog():
|
||
|
|
"""Routing must not inherit the owner agent's cluster-admin capability."""
|
||
|
|
service_accounts = [
|
||
|
|
item
|
||
|
|
for item in yaml.safe_load_all(
|
||
|
|
(HERMES / "vault-serviceaccount.yaml").read_text()
|
||
|
|
)
|
||
|
|
if item
|
||
|
|
]
|
||
|
|
assert any(
|
||
|
|
item["kind"] == "ServiceAccount"
|
||
|
|
and item["metadata"]["name"] == "hermes-switchyard"
|
||
|
|
for item in service_accounts
|
||
|
|
)
|
||
|
|
|
||
|
|
switchyard = yaml.safe_load(
|
||
|
|
(HERMES / "switchyard-deployment.yaml").read_text()
|
||
|
|
)
|
||
|
|
switchyard_pod = switchyard["spec"]["template"]["spec"]
|
||
|
|
assert switchyard_pod["serviceAccountName"] == "hermes-switchyard"
|
||
|
|
agent_pod = _agent_deployment()["spec"]["template"]["spec"]
|
||
|
|
for pod, container_name in (
|
||
|
|
(switchyard_pod, "worker-route-broker"),
|
||
|
|
(agent_pod, "claude-broker"),
|
||
|
|
):
|
||
|
|
container = next(item for item in pod["containers"] if item["name"] == container_name)
|
||
|
|
catalog = next(
|
||
|
|
item
|
||
|
|
for item in container["volumeMounts"]
|
||
|
|
if item["mountPath"] == "/routing-catalog"
|
||
|
|
)
|
||
|
|
assert catalog["readOnly"] is True
|
||
|
|
|
||
|
|
rbac = [
|
||
|
|
item
|
||
|
|
for item in yaml.safe_load_all((HERMES / "agent-rbac.yaml").read_text())
|
||
|
|
if item
|
||
|
|
]
|
||
|
|
binding = next(item for item in rbac if item["kind"] == "ClusterRoleBinding")
|
||
|
|
assert binding["subjects"] == [
|
||
|
|
{"kind": "ServiceAccount", "name": "hermes-agent", "namespace": "hermes"}
|
||
|
|
]
|
||
|
|
|
||
|
|
|
||
|
|
def test_switchyard_active_state_uses_a_relocatable_rwx_claim():
|
||
|
|
"""A stale node attachment must not strand the routing authority."""
|
||
|
|
claims = [
|
||
|
|
item
|
||
|
|
for item in yaml.safe_load_all((HERMES / "switchyard-pvc.yaml").read_text())
|
||
|
|
if item
|
||
|
|
]
|
||
|
|
active_claim = next(
|
||
|
|
item
|
||
|
|
for item in claims
|
||
|
|
if item["metadata"]["name"] == "hermes-switchyard-state-rwx"
|
||
|
|
)
|
||
|
|
assert active_claim["spec"]["accessModes"] == ["ReadWriteMany"]
|
||
|
|
|
||
|
|
deployment = yaml.safe_load((HERMES / "switchyard-deployment.yaml").read_text())
|
||
|
|
strategy = deployment["spec"]["strategy"]
|
||
|
|
assert strategy == {
|
||
|
|
"type": "RollingUpdate",
|
||
|
|
"rollingUpdate": {"maxSurge": 1, "maxUnavailable": 0},
|
||
|
|
}
|
||
|
|
pod = deployment["spec"]["template"]["spec"]
|
||
|
|
state = next(item for item in pod["volumes"] if item["name"] == "state")
|
||
|
|
assert state["persistentVolumeClaim"]["claimName"] == active_claim["metadata"][
|
||
|
|
"name"
|
||
|
|
]
|
||
|
|
|
||
|
|
|
||
|
|
def test_worker_route_broker_accepts_pod_network_health_checks():
|
||
|
|
"""Kubelet probes the pod IP, so the broker cannot bind to loopback only."""
|
||
|
|
script = (SCRIPTS / "worker_route_broker.py").read_text()
|
||
|
|
assert 'ThreadingHTTPServer(("0.0.0.0", PORT), Handler)' in script
|
||
|
|
|
||
|
|
|
||
|
|
def test_switchyard_network_boundary_allows_vault_bootstrap():
|
||
|
|
"""The pre-populate init container must reach Vault before routing starts."""
|
||
|
|
documents = [
|
||
|
|
item
|
||
|
|
for item in yaml.safe_load_all((HERMES / "networkpolicy.yaml").read_text())
|
||
|
|
if item
|
||
|
|
]
|
||
|
|
isolation = next(
|
||
|
|
item
|
||
|
|
for item in documents
|
||
|
|
if item.get("metadata", {}).get("name") == "hermes-switchyard-isolation"
|
||
|
|
)
|
||
|
|
assert any(
|
||
|
|
rule.get("to")
|
||
|
|
== [
|
||
|
|
{
|
||
|
|
"namespaceSelector": {
|
||
|
|
"matchLabels": {"kubernetes.io/metadata.name": "vault"}
|
||
|
|
},
|
||
|
|
"podSelector": {"matchLabels": {"app": "vault"}},
|
||
|
|
}
|
||
|
|
]
|
||
|
|
and rule.get("ports") == [{"protocol": "TCP", "port": 8200}]
|
||
|
|
for rule in isolation["spec"]["egress"]
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
def test_switchyard_network_boundary_allows_metrics_scraping():
|
||
|
|
"""VictoriaMetrics may scrape Switchyard without widening its API boundary."""
|
||
|
|
documents = [
|
||
|
|
item
|
||
|
|
for item in yaml.safe_load_all((HERMES / "networkpolicy.yaml").read_text())
|
||
|
|
if item
|
||
|
|
]
|
||
|
|
isolation = next(
|
||
|
|
item
|
||
|
|
for item in documents
|
||
|
|
if item.get("metadata", {}).get("name") == "hermes-switchyard-isolation"
|
||
|
|
)
|
||
|
|
assert any(
|
||
|
|
rule.get("from")
|
||
|
|
== [
|
||
|
|
{
|
||
|
|
"namespaceSelector": {
|
||
|
|
"matchLabels": {
|
||
|
|
"kubernetes.io/metadata.name": "monitoring"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"podSelector": {"matchLabels": {"app": "server"}},
|
||
|
|
}
|
||
|
|
]
|
||
|
|
and rule.get("ports") == [{"protocol": "TCP", "port": 9005}]
|
||
|
|
for rule in isolation["spec"]["ingress"]
|
||
|
|
)
|