Compare commits

...

5 Commits

Author SHA1 Message Date
Andrew Stoltz
735f998197 fix(monitoring): probe OIDC-safe health routes 2026-06-04 00:23:48 -05:00
Andrew Stoltz
13f9bb7710 fix(distribution): revert OIDC enforcement — enabling it gated /healthz probe (service down)
Flipping Auth__Enabled=true gated the /healthz readiness probe (302->NotReady->
no endpoints->distribution.iamworkin.lan down, healthz=000). Classic
feedback_k8s_probes_behind_auth_middleware. Revert to false (OIDC env block kept,
gate off) to restore service. Proper fix (AllowAnonymous /healthz + CA-trust +
idempotent Editions seed + OIDC-challenge wiring + browser-proof) -> falcon OIDC lane.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-03 23:47:29 -05:00
Andrew Stoltz
9a58fd2af6 oidc: flip enforcement ON for knowledge + distribution (no-live-proof, fix-forward)
Operator 2026-06-04: nothing is production yet, flip OIDC + fix-forward (no
browser-proof gate). knowledge: Auth__Enabled false->true (OIDC env already
wired). distribution: add OIDC env block (Authority/Audience/ClientId=distribution,
ClientSecret from distribution-oidc-client) + Enabled=true; public read/entitlement
+ Method() allowlist stay open (OIDC gates admin only). Clients already provisioned
(secrets present). ArgoCD deploys both.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-03 23:38:48 -05:00
Andrew Stoltz
404d884863 Adopt live Library Retail AiStation web apps 2026-06-03 20:24:32 -05:00
f4bd90f805 Merge pull request #33 from codex/s56-monitoring-coverage
fix(monitoring): repoint pirelay scrape to signalcontrol
2026-06-04 01:22:49 +00:00
7 changed files with 648 additions and 13 deletions

View File

@@ -0,0 +1,169 @@
# FlowerCore.AiStation.Web GitOps adoption manifest.
#
# Authored from the already-live fc-aistation resources on 2026-06-04.
# Keep the live image tag, Service ClusterIP, and PVC volumeName unchanged so
# ArgoCD adopts in place instead of replacing the workload or data volume.
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: aistation-web-data
namespace: fc-aistation
labels:
app.kubernetes.io/name: aistation-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-aistation
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 1Gi
storageClassName: longhorn
volumeMode: Filesystem
volumeName: pvc-27448d6f-6e66-42a7-a293-73dd8bbd6b3e
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: aistation-web
namespace: fc-aistation
labels:
app.kubernetes.io/name: aistation-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-aistation
spec:
progressDeadlineSeconds: 600
replicas: 1
revisionHistoryLimit: 3
selector:
matchLabels:
app.kubernetes.io/name: aistation-web
strategy:
type: Recreate
template:
metadata:
annotations:
prometheus.io/path: /metrics/prometheus
prometheus.io/port: "5000"
prometheus.io/scrape: "true"
labels:
app.kubernetes.io/name: aistation-web
app.kubernetes.io/part-of: flowercore
spec:
containers:
- envFrom:
- configMapRef:
name: aistation-web-config
image: localhost/fc-aistation-web:v20260602-aistation-owned-deploy-fix2
imagePullPolicy: Never
livenessProbe:
failureThreshold: 3
httpGet:
path: /healthz
port: 5000
scheme: HTTP
initialDelaySeconds: 30
periodSeconds: 30
successThreshold: 1
timeoutSeconds: 5
name: aistation-web
ports:
- containerPort: 5000
name: http
protocol: TCP
readinessProbe:
failureThreshold: 6
httpGet:
path: /healthz
port: 5000
scheme: HTTP
initialDelaySeconds: 10
periodSeconds: 10
successThreshold: 1
timeoutSeconds: 5
resources: {}
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
volumeMounts:
- mountPath: /data
name: data
dnsPolicy: ClusterFirst
restartPolicy: Always
schedulerName: default-scheduler
securityContext: {}
terminationGracePeriodSeconds: 30
volumes:
- name: data
persistentVolumeClaim:
claimName: aistation-web-data
---
apiVersion: v1
kind: Service
metadata:
name: aistation-web
namespace: fc-aistation
labels:
app.kubernetes.io/name: aistation-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-aistation
spec:
clusterIP: 10.43.211.127
clusterIPs:
- 10.43.211.127
internalTrafficPolicy: Cluster
ipFamilies:
- IPv4
ipFamilyPolicy: SingleStack
ports:
- name: http
port: 80
protocol: TCP
targetPort: 5000
selector:
app.kubernetes.io/name: aistation-web
sessionAffinity: None
type: ClusterIP
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: aistation-web-tls
namespace: fc-aistation
labels:
app.kubernetes.io/name: aistation-web-tls
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-aistation
spec:
dnsNames:
- aistation.iamworkin.lan
issuerRef:
kind: ClusterIssuer
name: step-ca-acme
secretName: aistation-web-tls
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: aistation-web
namespace: fc-aistation
labels:
app.kubernetes.io/name: aistation-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-aistation
spec:
entryPoints:
- websecure
routes:
- kind: Rule
match: Host(`aistation.iamworkin.lan`)
services:
- name: aistation-web
port: 80
tls:
secretName: aistation-web-tls

View File

@@ -130,6 +130,27 @@ spec:
value: "Production" value: "Production"
- name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT - name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
value: "false" value: "false"
# Authentik/OIDC enforcement (flipped ON 2026-06-04, no-live-proof per operator;
# public read/entitlement + Method() allowlist stay open — OIDC gates admin only).
# Auth__Enabled reverted to false 2026-06-04: enabling it gated the
# /healthz readiness probe (probe->302->NotReady->endpoints drop->down).
# Re-enable once /healthz is AllowAnonymous (falcon OIDC lane).
- name: FlowerCore__Auth__Enabled
value: "false"
- name: FlowerCore__Auth__Oidc__Enabled
value: "true"
- name: FlowerCore__Auth__Oidc__Authority
value: "https://id.iamworkin.lan/application/o/distribution/"
- name: FlowerCore__Auth__Oidc__Audience
value: "distribution"
- name: FlowerCore__Auth__Oidc__ClientId
value: "distribution"
- name: FlowerCore__Auth__Oidc__ClientSecret
valueFrom:
secretKeyRef:
name: distribution-oidc-client
key: client_secret
optional: true
# SQLite connection (catalog + data-protection keys via FlowerCoreDbContext). # SQLite connection (catalog + data-protection keys via FlowerCoreDbContext).
# Read by Data/DatabaseProviderExtensions.cs in precedence order; Sqlite key wins. # Read by Data/DatabaseProviderExtensions.cs in precedence order; Sqlite key wins.
- name: FlowerCore__Database__Provider - name: FlowerCore__Database__Provider

View File

@@ -0,0 +1,169 @@
# FlowerCore.Library.Web GitOps adoption manifest.
#
# Authored from the already-live fc-library resources on 2026-06-04.
# Keep the live image tag, Service ClusterIP, and PVC volumeName unchanged so
# ArgoCD adopts in place instead of replacing the workload or data volume.
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: library-web-data
namespace: fc-library
labels:
app.kubernetes.io/name: library-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-library
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 1Gi
storageClassName: longhorn
volumeMode: Filesystem
volumeName: pvc-2690bae2-4ee0-417a-b95f-50ec5c632b63
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: library-web
namespace: fc-library
labels:
app.kubernetes.io/name: library-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-library
spec:
progressDeadlineSeconds: 600
replicas: 1
revisionHistoryLimit: 3
selector:
matchLabels:
app.kubernetes.io/name: library-web
strategy:
type: Recreate
template:
metadata:
annotations:
prometheus.io/path: /metrics/prometheus
prometheus.io/port: "5000"
prometheus.io/scrape: "true"
labels:
app.kubernetes.io/name: library-web
app.kubernetes.io/part-of: flowercore
spec:
containers:
- envFrom:
- configMapRef:
name: library-web-config
image: localhost/fc-library-web:v20260602-library-owned-deploy-fix1
imagePullPolicy: Never
livenessProbe:
failureThreshold: 3
httpGet:
path: /health
port: 5000
scheme: HTTP
initialDelaySeconds: 30
periodSeconds: 30
successThreshold: 1
timeoutSeconds: 5
name: library-web
ports:
- containerPort: 5000
name: http
protocol: TCP
readinessProbe:
failureThreshold: 6
httpGet:
path: /health
port: 5000
scheme: HTTP
initialDelaySeconds: 10
periodSeconds: 10
successThreshold: 1
timeoutSeconds: 5
resources: {}
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
volumeMounts:
- mountPath: /data
name: data
dnsPolicy: ClusterFirst
restartPolicy: Always
schedulerName: default-scheduler
securityContext: {}
terminationGracePeriodSeconds: 30
volumes:
- name: data
persistentVolumeClaim:
claimName: library-web-data
---
apiVersion: v1
kind: Service
metadata:
name: library-web
namespace: fc-library
labels:
app.kubernetes.io/name: library-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-library
spec:
clusterIP: 10.43.179.63
clusterIPs:
- 10.43.179.63
internalTrafficPolicy: Cluster
ipFamilies:
- IPv4
ipFamilyPolicy: SingleStack
ports:
- name: http
port: 80
protocol: TCP
targetPort: 5000
selector:
app.kubernetes.io/name: library-web
sessionAffinity: None
type: ClusterIP
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: library-web-tls
namespace: fc-library
labels:
app.kubernetes.io/name: library-web-tls
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-library
spec:
dnsNames:
- library.iamworkin.lan
issuerRef:
kind: ClusterIssuer
name: step-ca-acme
secretName: library-web-tls
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: library-web
namespace: fc-library
labels:
app.kubernetes.io/name: library-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-library
spec:
entryPoints:
- websecure
routes:
- kind: Rule
match: Host(`library.iamworkin.lan`)
services:
- name: library-web
port: 80
tls:
secretName: library-web-tls

View File

@@ -0,0 +1,170 @@
# FlowerCore.Retail.Web GitOps adoption manifest.
#
# Authored from the already-live fc-retail resources on 2026-06-04.
# Keep the live image tag, Service ClusterIP, and PVC volumeName unchanged so
# ArgoCD adopts in place instead of replacing the workload or data volume.
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: retail-web-data
namespace: fc-retail
labels:
app.kubernetes.io/name: retail-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-retail
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 1Gi
storageClassName: longhorn
volumeMode: Filesystem
volumeName: pvc-3d40b336-eab4-41b3-812c-d5e9413ce0ab
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: retail-web
namespace: fc-retail
labels:
app.kubernetes.io/name: retail-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-retail
spec:
progressDeadlineSeconds: 600
replicas: 1
revisionHistoryLimit: 3
selector:
matchLabels:
app.kubernetes.io/name: retail-web
strategy:
type: Recreate
template:
metadata:
annotations:
kubectl.kubernetes.io/restartedAt: "2026-06-02T01:34:08-05:00"
prometheus.io/path: /metrics/prometheus
prometheus.io/port: "5000"
prometheus.io/scrape: "true"
labels:
app.kubernetes.io/name: retail-web
app.kubernetes.io/part-of: flowercore
spec:
containers:
- envFrom:
- configMapRef:
name: retail-web-config
image: localhost/fc-retail-web:v20260602-retail-owned-deploy-fix5
imagePullPolicy: Never
livenessProbe:
failureThreshold: 3
httpGet:
path: /health
port: 5000
scheme: HTTP
initialDelaySeconds: 30
periodSeconds: 30
successThreshold: 1
timeoutSeconds: 5
name: retail-web
ports:
- containerPort: 5000
name: http
protocol: TCP
readinessProbe:
failureThreshold: 6
httpGet:
path: /health
port: 5000
scheme: HTTP
initialDelaySeconds: 10
periodSeconds: 10
successThreshold: 1
timeoutSeconds: 5
resources: {}
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
volumeMounts:
- mountPath: /data
name: data
dnsPolicy: ClusterFirst
restartPolicy: Always
schedulerName: default-scheduler
securityContext: {}
terminationGracePeriodSeconds: 30
volumes:
- name: data
persistentVolumeClaim:
claimName: retail-web-data
---
apiVersion: v1
kind: Service
metadata:
name: retail-web
namespace: fc-retail
labels:
app.kubernetes.io/name: retail-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-retail
spec:
clusterIP: 10.43.239.8
clusterIPs:
- 10.43.239.8
internalTrafficPolicy: Cluster
ipFamilies:
- IPv4
ipFamilyPolicy: SingleStack
ports:
- name: http
port: 80
protocol: TCP
targetPort: 5000
selector:
app.kubernetes.io/name: retail-web
sessionAffinity: None
type: ClusterIP
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: retail-web-tls
namespace: fc-retail
labels:
app.kubernetes.io/name: retail-web-tls
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-retail
spec:
dnsNames:
- retail.iamworkin.lan
issuerRef:
kind: ClusterIssuer
name: step-ca-acme
secretName: retail-web-tls
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: retail-web
namespace: fc-retail
labels:
app.kubernetes.io/name: retail-web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
argocd.argoproj.io/instance: infra-fc-retail
spec:
entryPoints:
- websecure
routes:
- kind: Rule
match: Host(`retail.iamworkin.lan`)
services:
- name: retail-web
port: 80
tls:
secretName: retail-web-tls

View File

@@ -93,6 +93,7 @@ spec:
prometheus.io/scrape: "true" prometheus.io/scrape: "true"
prometheus.io/port: "8080" prometheus.io/port: "8080"
prometheus.io/path: "/metrics" prometheus.io/path: "/metrics"
flowercore.io/healthz-auth-policy: "allow-anonymous"
spec: spec:
securityContext: securityContext:
runAsNonRoot: true runAsNonRoot: true
@@ -123,11 +124,11 @@ spec:
value: "Production" value: "Production"
- name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT - name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
value: "false" value: "false"
# AuthentiK/OIDC is wired but not enforced until the # AuthentiK/OIDC is enforced. /healthz stays anonymous by contract;
# knowledge-oidc-client Secret is provisioned and # see flowercore.io/healthz-auth-policy above and the Sprint 58
# FlowerCore__Auth__Enabled is flipped to true. # OIDC readiness probe audit.
- name: FlowerCore__Auth__Enabled - name: FlowerCore__Auth__Enabled
value: "false" value: "true"
- name: FlowerCore__Auth__Oidc__Enabled - name: FlowerCore__Auth__Oidc__Enabled
value: "true" value: "true"
- name: FlowerCore__Auth__Oidc__Authority - name: FlowerCore__Auth__Oidc__Authority

View File

@@ -481,22 +481,25 @@ data:
- "https://intranet.iamworkin.lan/" - "https://intranet.iamworkin.lan/"
- "https://signage.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200 - "https://signage.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200
- "https://kiosk.iamworkin.lan/" - "https://kiosk.iamworkin.lan/"
- "https://media.iamworkin.lan/" - "https://media.iamworkin.lan/" # OIDC lane must add /healthz before flipping auth; live /healthz 404 on 2026-06-04
- "https://mysql.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200 - "https://mysql.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200
- "https://php.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200 - "https://php.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200
- "https://zabbix.iamworkin.lan/" - "https://zabbix.iamworkin.lan/"
- "https://desktop.iamworkin.lan/" - "https://desktop.iamworkin.lan/"
- "https://print.iamworkin.lan/" - "https://print.iamworkin.lan/healthz" # root 401 behind API key auth; /healthz anonymous 200
- "https://dns.iamworkin.lan/" - "https://dns.iamworkin.lan/" # OIDC lane must add /healthz before flipping auth; live /healthz 404 on 2026-06-04
- "https://chat.iamworkin.lan/" - "https://chat.iamworkin.lan/healthz" # OIDC staged; keep blackbox off root before enforcement flips
- "https://dist.iamworkin.lan/" - "https://dist.iamworkin.lan/healthz" # distribution OIDC flip outage was /healthz gating; probe the anonymous health route
- "https://dms.iamworkin.lan/" - "https://dms.iamworkin.lan/healthz" # future OIDC posture; health route is already anonymous/live
- "https://menuboard.iamworkin.lan/" - "https://menuboard.iamworkin.lan/"
- "https://messageboard.iamworkin.lan/" - "https://messageboard.iamworkin.lan/"
- "https://presentations.iamworkin.lan/" - "https://presentations.iamworkin.lan/"
- "https://retail.iamworkin.lan/" - "https://retail.iamworkin.lan/"
- "https://ttsreader.iamworkin.lan/" - "https://ttsreader.iamworkin.lan/"
# Explicit healthcheck paths # Explicit healthcheck paths
- "https://library.iamworkin.lan/health"
- "https://aistation.iamworkin.lan/healthz"
- "https://knowledge.iamworkin.lan/healthz"
- "https://fc-llm-bridge.iamworkin.lan/healthz" - "https://fc-llm-bridge.iamworkin.lan/healthz"
- "https://acme.iamworkin.lan/health" - "https://acme.iamworkin.lan/health"
# NOTE: services intentionally NOT in this probe surface # NOTE: services intentionally NOT in this probe surface
@@ -1020,7 +1023,12 @@ data:
- name: kubernetes-state - name: kubernetes-state
rules: rules:
- alert: KubeContainerRestartingFrequently - alert: KubeContainerRestartingFrequently
expr: increase(kube_pod_container_status_restarts_total[1h]) > 5 # Exclude github-runner: ephemeral runners register, run one job,
# exit cleanly, and restart by design. Also require kube_pod_info so
# deleted rollout pods do not keep firing from retained restart series.
expr: |
increase(kube_pod_container_status_restarts_total{namespace!="github-runner"}[1h]) > 5
and on(namespace, pod) kube_pod_info
for: 15m for: 15m
labels: labels:
severity: warning severity: warning
@@ -1029,7 +1037,12 @@ data:
description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has restarted {{ $value | printf \"%.0f\" }} times in the last hour. Check 'kubectl describe pod' + last-state termination reason." description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has restarted {{ $value | printf \"%.0f\" }} times in the last hour. Check 'kubectl describe pod' + last-state termination reason."
- alert: KubeContainerCrashLooping - alert: KubeContainerCrashLooping
expr: increase(kube_pod_container_status_restarts_total[15m]) > 3 # Same github-runner/delete-retention exclusions as the hourly
# restart rule above; real runner failures are covered by the
# dedicated LinuxRunnerOffline/MacMiniRunnerOffline alerts.
expr: |
increase(kube_pod_container_status_restarts_total{namespace!="github-runner"}[15m]) > 3
and on(namespace, pod) kube_pod_info
for: 5m for: 5m
labels: labels:
severity: critical severity: critical
@@ -1057,7 +1070,10 @@ data:
description: "Pod can't pull image. Check the image ref (often a stale tag or unreachable registry) and clean up if it's an orphan." description: "Pod can't pull image. Check the image ref (often a stale tag or unreachable registry) and clean up if it's an orphan."
- alert: KubeDeploymentReplicasMismatch - alert: KubeDeploymentReplicasMismatch
expr: kube_deployment_spec_replicas != kube_deployment_status_replicas_available # github-runner has explicit runner-offline alerts; the generic
# replica-mismatch rule should not page on intentionally ephemeral
# 0/1 runner churn between CI jobs.
expr: kube_deployment_spec_replicas{namespace!="github-runner"} != kube_deployment_status_replicas_available{namespace!="github-runner"}
for: 15m for: 15m
labels: labels:
severity: warning severity: warning

View File

@@ -424,6 +424,82 @@ public sealed class FleetManifestLintTests
monitoring.Should().Contain("alert_channel: irc"); monitoring.Should().Contain("alert_channel: irc");
} }
[Fact]
public void Monitoring_GenericKubernetesAlerts_MustExcludeEphemeralGithubRunnerNamespace()
{
var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
monitoring.Should().Contain("kube_pod_container_status_restarts_total{namespace!=\"github-runner\"}");
monitoring.Should().Contain("and on(namespace, pod) kube_pod_info");
monitoring.Should().Contain("kube_deployment_spec_replicas{namespace!=\"github-runner\"} != kube_deployment_status_replicas_available{namespace!=\"github-runner\"}");
monitoring.Should().Contain("dedicated LinuxRunnerOffline/MacMiniRunnerOffline alerts");
}
[Fact]
public void Monitoring_BlackboxTargetsForOidcSensitiveServices_MustUseAnonymousHealthRoutesWhenAvailable()
{
var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
monitoring.Should().Contain("https://chat.iamworkin.lan/healthz");
monitoring.Should().Contain("https://dist.iamworkin.lan/healthz");
monitoring.Should().Contain("https://dms.iamworkin.lan/healthz");
monitoring.Should().Contain("https://print.iamworkin.lan/healthz");
monitoring.Should().Contain("https://knowledge.iamworkin.lan/healthz");
monitoring.Should().Contain("https://library.iamworkin.lan/health");
monitoring.Should().Contain("https://aistation.iamworkin.lan/healthz");
monitoring.Should().NotContain("https://print.iamworkin.lan/\"");
}
[Fact]
public void OidcEnforcedDeployments_WithHttpHealthzProbes_MustDeclareAnonymousHealthzContract()
{
var violations = Inventory.Documents
.Where(document => document.Kind == "Deployment")
.SelectMany(document => document.MainContainerMappings()
.Where(container => string.Equals(EnvValue(container, "FlowerCore__Auth__Enabled"), "true", StringComparison.OrdinalIgnoreCase))
.Where(container => string.Equals(EnvValue(container, "FlowerCore__Auth__Oidc__Enabled"), "true", StringComparison.OrdinalIgnoreCase))
.Where(container => ProbeHttpGetPath(container, "readinessProbe") == "/healthz"
|| ProbeHttpGetPath(container, "startupProbe") == "/healthz")
.Where(_ => !string.Equals(
PodAnnotation(document, "flowercore.io/healthz-auth-policy"),
"allow-anonymous",
StringComparison.Ordinal))
.Select(container =>
{
var containerName = ManifestNodeExtensions.Scalar(container, "name") ?? "<unnamed>";
return $"{document.Descriptor} container '{containerName}' enforces OIDC while probing /healthz but lacks flowercore.io/healthz-auth-policy: allow-anonymous.";
}))
.ToList();
violations.Should().BeEmpty();
}
[Fact]
public void Knowledge_OidcEnforcement_MustKeepHealthzAnonymousContractVisibleInManifest()
{
var knowledge = Inventory.Documents
.Single(document => document.Kind == "Deployment" && document.Namespace == "knowledge" && document.Name == "knowledge-web");
var container = knowledge.MainContainerMappings().Should().ContainSingle().Subject;
EnvValue(container, "FlowerCore__Auth__Enabled").Should().Be("true");
EnvValue(container, "FlowerCore__Auth__Oidc__Enabled").Should().Be("true");
ProbeHttpGetPath(container, "readinessProbe").Should().Be("/healthz");
PodAnnotation(knowledge, "flowercore.io/healthz-auth-policy").Should().Be("allow-anonymous");
}
[Fact]
public void Distribution_OidcEnforcement_MustStayOffUntilHealthzAllowAnonymousProofLands()
{
var distribution = Inventory.Documents
.Single(document => document.Kind == "Deployment" && document.Namespace == "fc-distribution" && document.Name == "fc-distribution");
var container = distribution.MainContainerMappings().Should().ContainSingle().Subject;
EnvValue(container, "FlowerCore__Auth__Oidc__Enabled").Should().Be("true");
EnvValue(container, "FlowerCore__Auth__Enabled").Should().Be("false");
ProbeHttpGetPath(container, "readinessProbe").Should().Be("/healthz");
PodAnnotation(distribution, "flowercore.io/healthz-auth-policy").Should().NotBe("allow-anonymous");
}
[Fact] [Fact]
public void StatefulSets_WithVolumeClaimTemplates_MustDeclareFilesystemDefaults() public void StatefulSets_WithVolumeClaimTemplates_MustDeclareFilesystemDefaults()
{ {
@@ -768,6 +844,19 @@ public sealed class FleetManifestLintTests
.SingleOrDefault(env => string.Equals(ManifestNodeExtensions.Scalar(env, "name"), name, StringComparison.Ordinal)); .SingleOrDefault(env => string.Equals(ManifestNodeExtensions.Scalar(env, "name"), name, StringComparison.Ordinal));
} }
private static string? PodAnnotation(ManifestDocument document, string name)
{
return document.Scalar("spec", "template", "metadata", "annotations", name);
}
private static string? ProbeHttpGetPath(YamlMappingNode container, string probeKey)
{
return ManifestNodeExtensions.TryGetMapping(container, probeKey, out var probe)
&& ManifestNodeExtensions.TryGetMapping(probe, "httpGet", out var httpGet)
? ManifestNodeExtensions.Scalar(httpGet, "path")
: null;
}
private static IReadOnlyList<ManifestDocument> FcDeviceManagementDocuments() private static IReadOnlyList<ManifestDocument> FcDeviceManagementDocuments()
{ {
return Inventory.Documents return Inventory.Documents