Compare commits

..

1 Commits

Author SHA1 Message Date
Andrew Stoltz
0ed9b989fa monitoring: mirror Sprint 57 coverage rules 2026-06-03 22:46:33 -05:00
9 changed files with 190 additions and 1111 deletions

View File

@@ -74,14 +74,6 @@ metadata:
spec:
itemPath: "vaults/IAmWorkin/items/FlowerCore Edition Signing Key - edition:aistation-field"
---
apiVersion: onepassword.com/v1
kind: OnePasswordItem
metadata:
name: distribution-oidc-client
namespace: fc-distribution
spec:
itemPath: "vaults/IAmWorkin/items/distribution-oidc-client"
---
apiVersion: apps/v1
kind: Deployment
metadata:
@@ -109,7 +101,6 @@ spec:
prometheus.io/scrape: "true"
prometheus.io/port: "8080"
prometheus.io/path: "/metrics"
flowercore.io/healthz-auth-policy: "allow-anonymous"
spec:
# Synology NFS export `/volume1/kubernetes` ACL only allows rke2-server
# (10.0.56.11) right now. Until the ACL is widened in DSM (admin only),
@@ -127,7 +118,7 @@ spec:
# dotnet.exe publish -c Release -o deploy/app \
# src/FlowerCore.Distribution.Web/FlowerCore.Distribution.Web.csproj
# podman build -t localhost/fc-distribution:v<tag> -f deploy/Dockerfile.deploy deploy
image: localhost/fc-distribution:v20260604-oidc-root-anon
image: localhost/fc-distribution:v202605061948
imagePullPolicy: Never
ports:
- containerPort: 8080
@@ -139,25 +130,6 @@ spec:
value: "Production"
- name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
value: "false"
# Authentik/OIDC enforcement. Public read/entitlement + the
# dist.flowercore.io Method() allowlist stay open; OIDC gates the
# operator/admin surface while /healthz remains anonymous.
- name: FlowerCore__Auth__Enabled
value: "true"
- 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).
# Read by Data/DatabaseProviderExtensions.cs in precedence order; Sqlite key wins.
- name: FlowerCore__Database__Provider

View File

@@ -1,481 +0,0 @@
---
apiVersion: v1
kind: Namespace
metadata:
name: fc-dns
labels:
app.kubernetes.io/part-of: flowercore
---
# 1Password-backed Secret for the pfSense admin password.
# The operator watches this CRD, resolves the vault item, and produces a
# K8s Secret of the same name with each 1P field as a key. The `password`
# field of the "pfSense Admin" item becomes Secret key `password`.
apiVersion: onepassword.com/v1
kind: OnePasswordItem
metadata:
name: pfsense-admin
namespace: fc-dns
spec:
itemPath: "vaults/IAmWorkin/items/pfSense Admin"
---
apiVersion: onepassword.com/v1
kind: OnePasswordItem
metadata:
name: dns-oidc-client
namespace: fc-dns
spec:
itemPath: "vaults/IAmWorkin/items/dns-oidc-client"
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: dns-web-data
namespace: fc-dns
spec:
accessModes: [ReadWriteOnce]
storageClassName: longhorn
resources:
requests:
storage: 1Gi
---
apiVersion: v1
kind: ConfigMap
metadata:
name: dns-web-config
namespace: fc-dns
data:
appsettings.Production.json: |
{
"FlowerCore": {
"Auth": {
"Enabled": true,
"Oidc": {
"Enabled": true,
"Audience": "dns",
"RequireHttpsMetadata": true
}
},
"Database": {
"Provider": "Sqlite",
"ConnectionStrings": {
"Sqlite": "Data Source=/data/dns.db"
}
},
"Tenant": {
"DefaultTenantId": "default",
"JwtClaimsEnabled": false,
"DefaultTenantHosts": [
"dns.iamworkin.lan"
]
},
"Audit": {
"HashChain": {
"BridgeSensitivity": {
"Distribution": "Warn"
}
}
}
}
}
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: dns-web
namespace: fc-dns
labels:
app.kubernetes.io/name: dns-web
app.kubernetes.io/managed-by: flowercore
spec:
replicas: 1
strategy:
type: Recreate
selector:
matchLabels:
app.kubernetes.io/name: dns-web
template:
metadata:
labels:
app.kubernetes.io/name: dns-web
annotations:
prometheus.io/scrape: "true"
prometheus.io/port: "5320"
prometheus.io/path: "/metrics/prometheus"
flowercore.io/healthz-auth-policy: "allow-anonymous"
spec:
serviceAccountName: dns-web
securityContext:
runAsNonRoot: true
runAsUser: 1654
runAsGroup: 1654
fsGroup: 1654
containers:
- name: dns-web
image: localhost/fc-dns-web:v20260604-oidc-proper
imagePullPolicy: Never
securityContext:
readOnlyRootFilesystem: true
allowPrivilegeEscalation: false
capabilities:
drop: [ALL]
ports:
- containerPort: 5320
env:
# pfSense admin password resolved by the 1Password operator.
# `FallbackPassword` is the Slice A seam exposed by
# OptionsFallbackPasswordResolver; Slice B will replace it with
# a pull-at-runtime 1P Connect resolver once Shared.Vault ships.
- name: FlowerCore__Dns__Providers__PfSenseUnbound__FallbackPassword
valueFrom:
secretKeyRef:
name: pfsense-admin
key: password
- name: FlowerCore__Auth__Oidc__Authority
valueFrom:
secretKeyRef:
name: dns-oidc-client
key: issuer_url
optional: true
- name: FlowerCore__Auth__Oidc__ClientId
valueFrom:
secretKeyRef:
name: dns-oidc-client
key: client_id
optional: true
- name: FlowerCore__Auth__Oidc__ClientSecret
valueFrom:
secretKeyRef:
name: dns-oidc-client
key: client_secret
optional: true
- name: FlowerCore__Auth__Enabled
value: "true"
- name: FlowerCore__Auth__Oidc__Enabled
value: "true"
- name: FlowerCore__Auth__Oidc__Audience
value: "dns"
volumeMounts:
- name: data
mountPath: /data
- name: tmp
mountPath: /tmp
- name: logs
mountPath: /app/logs
- name: config
mountPath: /app/appsettings.Production.json
subPath: appsettings.Production.json
readOnly: true
resources:
requests:
cpu: 50m
memory: 96Mi
limits:
cpu: 300m
memory: 384Mi
readinessProbe:
httpGet:
path: /healthz
port: 5320
initialDelaySeconds: 10
periodSeconds: 10
livenessProbe:
httpGet:
path: /healthz
port: 5320
initialDelaySeconds: 20
periodSeconds: 30
volumes:
- name: data
persistentVolumeClaim:
claimName: dns-web-data
- name: tmp
emptyDir: {}
- name: logs
emptyDir: {}
- name: config
configMap:
name: dns-web-config
---
apiVersion: v1
kind: Service
metadata:
name: dns-web
namespace: fc-dns
spec:
selector:
app.kubernetes.io/name: dns-web
ports:
- port: 5320
targetPort: 5320
type: ClusterIP
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: dns-web
namespace: fc-dns
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: dns-web
rules:
- apiGroups: [""]
resources: ["namespaces", "pods", "services", "secrets", "configmaps"]
verbs: ["get", "list", "watch"]
- apiGroups: ["cert-manager.io"]
resources: ["certificates"]
verbs: ["get", "list", "watch"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: dns-web
subjects:
- kind: ServiceAccount
name: dns-web
namespace: fc-dns
roleRef:
kind: ClusterRole
name: dns-web
apiGroup: rbac.authorization.k8s.io
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: dns-web-cert
namespace: fc-dns
spec:
secretName: dns-web-tls
issuerRef:
name: step-ca-dns01
kind: ClusterIssuer
dnsNames:
- dns.iamworkin.lan
duration: 720h
renewBefore: 240h
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: dns-web
namespace: fc-dns
spec:
entryPoints: [websecure]
routes:
- match: Host(`dns.iamworkin.lan`)
kind: Rule
services:
- name: dns-web
port: 5320
tls:
secretName: dns-web-tls
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: dns-acme-webhook
namespace: fc-dns
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: dns-acme-webhook
namespace: fc-dns
labels:
app.kubernetes.io/name: dns-acme-webhook
app.kubernetes.io/managed-by: flowercore
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: dns-acme-webhook
template:
metadata:
labels:
app.kubernetes.io/name: dns-acme-webhook
spec:
serviceAccountName: dns-acme-webhook
securityContext:
runAsNonRoot: true
runAsUser: 1654
runAsGroup: 1654
fsGroup: 1654
containers:
- name: dns-acme-webhook
image: localhost/fc-dns-acme-webhook:v202604290845
imagePullPolicy: Never
securityContext:
readOnlyRootFilesystem: true
allowPrivilegeEscalation: false
capabilities:
drop: [ALL]
ports:
- containerPort: 9443
name: https
env:
- name: ASPNETCORE_URLS
value: https://+:9443
- name: Kestrel__Certificates__Default__Path
value: /tls/tls.crt
- name: Kestrel__Certificates__Default__KeyPath
value: /tls/tls.key
- name: FlowerCore__Dns__AcmeWebhook__ServiceBaseUrl
value: http://dns-web:5320
- name: FlowerCore__Dns__AcmeWebhook__GroupName
value: acme.flowercore.io
- name: FlowerCore__Dns__AcmeWebhook__SolverName
value: flowercore-dns
- name: FlowerCore__Dns__AcmeWebhook__Version
value: v1alpha1
volumeMounts:
- name: tls
mountPath: /tls
readOnly: true
- name: tmp
mountPath: /tmp
- name: logs
mountPath: /app/logs
resources:
requests:
cpu: 25m
memory: 64Mi
limits:
cpu: 200m
memory: 256Mi
readinessProbe:
httpGet:
scheme: HTTPS
path: /readyz
port: https
initialDelaySeconds: 5
periodSeconds: 10
timeoutSeconds: 5
livenessProbe:
httpGet:
scheme: HTTPS
path: /healthz
port: https
initialDelaySeconds: 10
periodSeconds: 20
timeoutSeconds: 5
volumes:
- name: tls
secret:
secretName: dns-acme-webhook-tls
- name: tmp
emptyDir: {}
- name: logs
emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
name: dns-acme-webhook
namespace: fc-dns
spec:
selector:
app.kubernetes.io/name: dns-acme-webhook
ports:
- port: 443
targetPort: https
name: https
type: ClusterIP
---
apiVersion: cert-manager.io/v1
kind: Issuer
metadata:
name: dns-acme-webhook-selfsigned
namespace: fc-dns
spec:
selfSigned: {}
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: dns-acme-webhook-ca
namespace: fc-dns
spec:
secretName: dns-acme-webhook-ca
duration: 43800h
issuerRef:
name: dns-acme-webhook-selfsigned
commonName: ca.dns-acme-webhook.fc-dns
isCA: true
---
apiVersion: cert-manager.io/v1
kind: Issuer
metadata:
name: dns-acme-webhook-ca-issuer
namespace: fc-dns
spec:
ca:
secretName: dns-acme-webhook-ca
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: dns-acme-webhook-serving-cert
namespace: fc-dns
spec:
secretName: dns-acme-webhook-tls
duration: 8760h
issuerRef:
name: dns-acme-webhook-ca-issuer
dnsNames:
- dns-acme-webhook
- dns-acme-webhook.fc-dns
- dns-acme-webhook.fc-dns.svc
---
apiVersion: apiregistration.k8s.io/v1
kind: APIService
metadata:
name: v1alpha1.acme.flowercore.io
annotations:
cert-manager.io/inject-ca-from: fc-dns/dns-acme-webhook-serving-cert
spec:
group: acme.flowercore.io
groupPriorityMinimum: 1000
service:
name: dns-acme-webhook
namespace: fc-dns
version: v1alpha1
versionPriority: 15
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: dns-acme-webhook-solver
rules:
- apiGroups: ["acme.flowercore.io"]
resources: ["flowercore-dns"]
verbs: ["create"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: dns-acme-webhook-solver
subjects:
- kind: ServiceAccount
name: cert-manager
namespace: cert-manager
roleRef:
kind: ClusterRole
name: dns-acme-webhook-solver
apiGroup: rbac.authorization.k8s.io
---
apiVersion: cert-manager.io/v1
kind: ClusterIssuer
metadata:
name: step-ca-dns01
spec:
acme:
caBundle: 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
privateKeySecretRef:
name: step-ca-dns01-account-key
server: https://10.0.56.10:9443/acme/acme/directory
solvers:
- dns01:
webhook:
groupName: acme.flowercore.io
solverName: flowercore-dns

View File

@@ -1,6 +0,0 @@
# ArgoCD's bluejay-infra ApplicationSet discovers apps/* directories on main.
# The kustomization is included for local previews and single-app validation.
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
resources:
- fc-dns.yaml

View File

@@ -1,296 +0,0 @@
---
apiVersion: v1
kind: Namespace
metadata:
name: fc-media
labels:
app.kubernetes.io/name: fc-media
app.kubernetes.io/part-of: flowercore
---
apiVersion: onepassword.com/v1
kind: OnePasswordItem
metadata:
name: media-oidc-client
namespace: fc-media
labels:
app.kubernetes.io/name: fc-media-web
app.kubernetes.io/part-of: flowercore
spec:
itemPath: "vaults/IAmWorkin/items/media-oidc-client"
---
apiVersion: v1
kind: ConfigMap
metadata:
name: fc-media-config
namespace: fc-media
labels:
app.kubernetes.io/name: fc-media-web
app.kubernetes.io/part-of: flowercore
data:
appsettings.Production.json: |
{
"DatabaseProvider": "Sqlite",
"ConnectionStrings": {
"Sqlite": "Data Source=/data/media.db"
},
"FlowerCore": {
"Auth": {
"Enabled": true,
"Oidc": {
"Authority": "https://id.iamworkin.lan/application/o/media/",
"ClientId": "media",
"ClientSecret": "",
"Audience": "media",
"RequireHttpsMetadata": true
}
},
"Tenant": {
"JwtClaimsEnabled": false,
"DefaultTenantHosts": [ "media.iamworkin.lan" ]
}
},
"Media": {
"LibraryRoot": "/media/library",
"Sources": [
{
"Name": "BlueJayNAS Video",
"Driver": "Nfs",
"MountedPath": "/media/library",
"RemotePath": "nfs://10.0.58.3/volume1/video",
"IsEnabled": true,
"IsDefault": true,
"Notes": "Synology NFS media share mounted read-only inside the cluster."
}
],
"GeneratedRoot": "/data/generated",
"TranscodeRoot": "/data/transcodes",
"InboxPath": "/media/inbox",
"InboxScanIntervalMinutes": 5,
"ScanOnStartup": false,
"ComputeChecksums": false,
"FfmpegCommand": "ffmpeg",
"FfprobeCommand": "ffprobe",
"Hls": {
"MaxConcurrentJobs": 1
},
"DefaultViewerName": "BlueJay",
"Dlna": {
"IsEnabled": true,
"MulticastAddress": "239.255.255.250",
"Port": 1900,
"DiscoveryTimeoutSeconds": 2,
"DescriptionFetchTimeoutSeconds": 2,
"MaxResponsesPerSearchTarget": 32,
"SearchTargets": [
"urn:schemas-upnp-org:device:MediaRenderer:1",
"urn:schemas-upnp-org:device:MediaServer:1"
]
}
}
}
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: fc-media-data
namespace: fc-media
labels:
app.kubernetes.io/name: fc-media-web
app.kubernetes.io/part-of: flowercore
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 20Gi
storageClassName: longhorn
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: fc-media-web
namespace: fc-media
labels:
app: fc-media-web
app.kubernetes.io/name: fc-media-web
app.kubernetes.io/part-of: flowercore
spec:
replicas: 1
strategy:
type: Recreate
selector:
matchLabels:
app: fc-media-web
template:
metadata:
labels:
app: fc-media-web
app.kubernetes.io/name: fc-media-web
app.kubernetes.io/part-of: flowercore
annotations:
prometheus.io/scrape: "true"
prometheus.io/port: "5200"
prometheus.io/path: "/metrics"
flowercore.io/healthz-auth-policy: "allow-anonymous"
spec:
nodeSelector:
kubernetes.io/hostname: rke2-server
containers:
- name: fc-media-web
image: localhost/fc-media-web:v20260604-oidc-proper
imagePullPolicy: Never
ports:
- containerPort: 5200
name: http
env:
- name: ASPNETCORE_ENVIRONMENT
value: Production
- name: ASPNETCORE_URLS
value: http://+:5200
- name: FlowerCore__Auth__Enabled
value: "true"
- name: FlowerCore__Auth__Oidc__Enabled
value: "true"
- name: FlowerCore__Auth__Oidc__Audience
value: "media"
- name: FlowerCore__Auth__Oidc__ClientId
valueFrom:
secretKeyRef:
name: media-oidc-client
key: client_id
optional: true
- name: FlowerCore__Auth__Oidc__ClientSecret
valueFrom:
secretKeyRef:
name: media-oidc-client
key: client_secret
optional: true
- name: FlowerCore__Auth__Oidc__Authority
valueFrom:
secretKeyRef:
name: media-oidc-client
key: issuer_url
optional: true
resources:
requests:
cpu: 500m
memory: 1Gi
limits:
cpu: "4"
memory: 4Gi
volumeMounts:
- name: config
mountPath: /app/appsettings.Production.json
subPath: appsettings.Production.json
readOnly: true
- name: data
mountPath: /data
- name: transcodes
mountPath: /data/transcodes
- name: media-library
mountPath: /media/library
readOnly: true
- name: media-inbox
mountPath: /media/inbox
startupProbe:
httpGet:
path: /healthz
port: 5200
httpHeaders:
- name: X-Forwarded-Proto
value: https
failureThreshold: 18
periodSeconds: 10
readinessProbe:
httpGet:
path: /healthz
port: 5200
httpHeaders:
- name: X-Forwarded-Proto
value: https
initialDelaySeconds: 5
periodSeconds: 10
livenessProbe:
httpGet:
path: /healthz
port: 5200
httpHeaders:
- name: X-Forwarded-Proto
value: https
initialDelaySeconds: 30
periodSeconds: 30
volumes:
- name: config
configMap:
name: fc-media-config
- name: data
persistentVolumeClaim:
claimName: fc-media-data
- name: transcodes
nfs:
server: 10.0.58.3
path: /volume1/kubernetes/fc-media-transcodes
- name: media-inbox
nfs:
server: 10.0.58.3
path: /volume1/kubernetes/fc-media-inbox
- name: media-library
nfs:
server: 10.0.58.3
path: /volume1/video
readOnly: true
---
apiVersion: v1
kind: Service
metadata:
name: fc-media-web
namespace: fc-media
labels:
app: fc-media-web
app.kubernetes.io/name: fc-media-web
app.kubernetes.io/part-of: flowercore
spec:
type: ClusterIP
selector:
app: fc-media-web
ports:
- port: 5200
targetPort: 5200
protocol: TCP
name: http
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: fc-media-tls
namespace: fc-media
labels:
app.kubernetes.io/name: fc-media-web
app.kubernetes.io/part-of: flowercore
spec:
secretName: fc-media-tls
issuerRef:
name: step-ca-acme
kind: ClusterIssuer
dnsNames:
- media.iamworkin.lan
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: fc-media-web
namespace: fc-media
labels:
app.kubernetes.io/name: fc-media-web
app.kubernetes.io/part-of: flowercore
spec:
entryPoints:
- websecure
routes:
- match: Host(`media.iamworkin.lan`)
kind: Rule
services:
- name: fc-media-web
port: 5200
tls:
secretName: fc-media-tls

View File

@@ -1,6 +0,0 @@
# ArgoCD's bluejay-infra ApplicationSet discovers apps/* directories on main.
# The kustomization is included for local previews and single-app validation.
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
resources:
- fc-media.yaml

View File

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

View File

@@ -216,24 +216,19 @@ data:
- job_name: "pimanager-app"
scrape_interval: 15s
metrics_path: /metrics
scheme: https
tls_config:
insecure_skip_verify: true
static_configs:
- targets: ["piez.iamworkin.lan"]
- targets: ["10.0.58.25:5000"]
labels:
instance: "piez"
service: "signalcontrol"
service: "pimanager"
vlan: "home"
device: "pi4-ezconnect"
rig: "signal-b"
- targets: ["pirelay.iamworkin.lan"]
- targets: ["10.0.58.113:5200"]
labels:
instance: "pirelay"
service: "signalcontrol"
service: "pimanager"
vlan: "home"
device: "pi3-ks0212"
rig: "signal-a"
# Epson ET-3750 EcoTank Printer SNMP
- job_name: "snmp-printer"
@@ -485,34 +480,33 @@ data:
- "https://argocd.iamworkin.lan/"
- "https://intranet.iamworkin.lan/"
- "https://signage.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200
- "https://signalcontrol.iamworkin.lan/health" # FlowerCore.SignalControl explicit health route
- "https://kiosk.iamworkin.lan/"
- "https://media.iamworkin.lan/healthz" # root auth-gated by OIDC; /healthz anonymous 200
- "https://media.iamworkin.lan/"
- "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://dns.iamworkin.lan/"
- "https://zabbix.iamworkin.lan/"
- "https://flowercore.iamworkin.lan/healthz"
- "https://desktop.iamworkin.lan/"
- "https://print.iamworkin.lan/healthz" # root 401 behind API key auth; /healthz anonymous 200
- "https://dns.iamworkin.lan/healthz" # root auth-gated by OIDC; /healthz anonymous 200
- "https://signalcontrol.iamworkin.lan/health" # FlowerCore.SignalControl Pi control plane
- "https://flowercore.iamworkin.lan/healthz" # FlowerCore landing
- "https://replay.iamworkin.lan/healthz" # FlowerCore.Signage replay surface
- "https://worldbuilder.iamworkin.lan/healthz" # FlowerCore.WorldBuilder
- "https://updates.iamworkin.lan/api/v1/manifests/_schema" # UpdateCenter plural LAN alias
- "https://updatecenter-internal.iamworkin.lan/api/v1/manifests/_schema" # internal UC schema route
- "https://chat.iamworkin.lan/healthz" # OIDC staged; keep blackbox off root before enforcement flips
- "https://dist.iamworkin.lan/healthz" # root/admin auth-gated by OIDC; /healthz anonymous 200
- "https://dms.iamworkin.lan/healthz" # future OIDC posture; health route is already anonymous/live
- "https://print.iamworkin.lan/"
- "https://chat.iamworkin.lan/"
- "https://dist.iamworkin.lan/"
- "https://dms.iamworkin.lan/"
- "https://menuboard.iamworkin.lan/"
- "https://messageboard.iamworkin.lan/"
- "https://presentations.iamworkin.lan/"
- "https://retail.iamworkin.lan/"
- "https://ttsreader.iamworkin.lan/"
- "https://updates.iamworkin.lan/api/v1/manifests/_schema"
# 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://acme.iamworkin.lan/health"
- "https://replay.iamworkin.lan/healthz"
- "https://updatecenter-internal.iamworkin.lan/api/v1/manifests/_schema"
- "https://worldbuilder.iamworkin.lan/healthz"
# Coverage gaps logged Q-MR-129/Q-MR-130: devices.iamworkin.lan
# returns 503 and e2e-test-pma/wpdemo only return 404.
# NOTE: services intentionally NOT in this probe surface
# - grafana.iamworkin.lan: every endpoint (incl. /api/health
# and /login) returns 401 behind Traefik basic-auth.
@@ -921,14 +915,16 @@ data:
# for: 30m absorbs sleep cycles. The EcoTank sleeps after ~5 min
# of idle and SNMP times out, so 5m for: would page nightly. A
# genuine printer outage (jam, disconnected) lasts well over 30m.
# Use a range-window expression: instant up{} can go stale/absent
# after repeated snmp-exporter 500s.
- alert: EpsonPrinterDown
expr: (max_over_time(up{job="snmp-printer"}[35m]) == bool 0) == 1 and (hour() >= 13 or hour() < 1)
for: 30m
labels:
severity: info
severity: warning
alert_channel: irc
annotations:
summary: "Epson ET-3750 SNMP unreachable during waking hours (30m)"
summary: "Epson ET-3750 SNMP unreachable for >30m (likely actual fault, not sleep)"
- alert: SynologyDiskLow
expr: hrStorageUsed{job="snmp-nas"} / hrStorageSize{job="snmp-nas"} * 100 > 85
@@ -1036,11 +1032,8 @@ data:
rules:
- alert: KubeContainerRestartingFrequently
# 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
# exit cleanly, then restart by design.
expr: increase(kube_pod_container_status_restarts_total{namespace!="github-runner"}[1h]) > 5
for: 15m
labels:
severity: warning
@@ -1049,12 +1042,9 @@ 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."
- alert: KubeContainerCrashLooping
# 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
# Exclude github-runner: ephemeral runners register, run one job,
# exit cleanly, then restart by design.
expr: increase(kube_pod_container_status_restarts_total{namespace!="github-runner"}[15m]) > 3
for: 5m
labels:
severity: critical
@@ -1082,9 +1072,7 @@ 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."
- alert: KubeDeploymentReplicasMismatch
# 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.
# Exclude github-runner: ephemeral runner deployments flap 0/1 between jobs by design.
expr: kube_deployment_spec_replicas{namespace!="github-runner"} != kube_deployment_status_replicas_available{namespace!="github-runner"}
for: 15m
labels:
@@ -3664,6 +3652,38 @@ data:
relativeTimeRange: {from: 120, to: 0}
datasourceUid: __expr__
model: {type: threshold, expression: B, conditions: [{evaluator: {params: [600], type: gt}}], refId: C}
- orgId: 1
name: SNMP Devices
folder: Infrastructure Alerts
interval: 1m
rules:
- uid: epson-printer-down-stale-window
title: EpsonPrinterDown
condition: C
for: 30m
noDataState: OK
execErrState: OK
annotations:
summary: Epson ET-3750 SNMP unreachable
description: The Epson ET-3750 snmp-printer target has reported only failed scrapes for at least 35 minutes.
runbook: "1. Check if printer is intentionally powered off 2. If printing needed: press power button on printer 3. Ping 10.0.58.107 after wake-up 4. Check WiFi on printer LCD if still unreachable"
labels:
severity: info
service: printer
alert_channel: irc
data:
- refId: A
relativeTimeRange: {from: 2100, to: 0}
datasourceUid: prometheus
model: {expr: '(max_over_time(up{job="snmp-printer"}[35m]) == bool 0) == 1 and (hour() >= 13 or hour() < 1)', instant: true, refId: A}
- refId: B
relativeTimeRange: {from: 2100, to: 0}
datasourceUid: __expr__
model: {type: reduce, expression: A, reducer: last, refId: B}
- refId: C
relativeTimeRange: {from: 2100, to: 0}
datasourceUid: __expr__
model: {type: threshold, expression: B, conditions: [{evaluator: {params: [0], type: gt}}], refId: C}
- orgId: 1
name: CI Runners
folder: CI Alerts

View File

@@ -15,6 +15,7 @@ public sealed class FleetManifestLintTests
{
"brochure.flowercore.io",
"dist.flowercore.io",
"dns.iamworkin.lan",
};
// Public hosts that allow a tightly bounded write surface in addition to
@@ -423,82 +424,6 @@ public sealed class FleetManifestLintTests
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_MustKeepHealthzAnonymousContractVisibleInManifest()
{
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("true");
ProbeHttpGetPath(container, "readinessProbe").Should().Be("/healthz");
PodAnnotation(distribution, "flowercore.io/healthz-auth-policy").Should().Be("allow-anonymous");
}
[Fact]
public void StatefulSets_WithVolumeClaimTemplates_MustDeclareFilesystemDefaults()
{
@@ -781,146 +706,6 @@ public sealed class FleetManifestLintTests
application.Scalar("spec", "destination", "namespace").Should().Be("fc-devicemgmt");
}
[Fact]
public void OidcFlipServices_AreGitOpsManagedWithHealthzProbes()
{
var deployments = new[]
{
(App: "fc-dns", Name: "dns-web", Slug: "dns", Secret: "dns-oidc-client"),
(App: "fc-media", Name: "fc-media-web", Slug: "media", Secret: "media-oidc-client"),
(App: "fc-distribution", Name: "fc-distribution", Slug: "distribution", Secret: "distribution-oidc-client"),
};
foreach (var expected in deployments)
{
var deployment = AppDocuments(expected.App)
.Single(document => document.Kind == "Deployment" && document.Name == expected.Name);
var container = deployment.MainContainerMappings().Should().ContainSingle().Subject;
EnvValue(container, "FlowerCore__Auth__Enabled").Should().Be("true");
EnvValue(container, "FlowerCore__Auth__Oidc__Enabled").Should().Be("true");
(EnvValue(container, "FlowerCore__Auth__Oidc__Audience") ?? EnvValue(container, "FlowerCore__Auth__Oidc__ClientId"))
.Should()
.Be(expected.Slug);
EnvSecretName(container, "FlowerCore__Auth__Oidc__ClientSecret").Should().Be(expected.Secret);
EnvSecretOptional(container, "FlowerCore__Auth__Oidc__ClientSecret").Should().Be("true");
ProbePath(container, "readinessProbe").Should().Be("/healthz");
if (ProbePath(container, "startupProbe") is { } startupProbePath)
{
startupProbePath.Should().Be("/healthz");
}
if (ProbePath(container, "livenessProbe") is { } livenessProbePath)
{
livenessProbePath.Should().Be("/healthz");
}
}
}
[Fact]
public void OidcFlipServices_UseOnePasswordItemClientSecrets()
{
var expectedItems = new Dictionary<string, (string Name, string ItemPath)>(StringComparer.Ordinal)
{
["fc-dns"] = ("dns-oidc-client", "vaults/IAmWorkin/items/dns-oidc-client"),
["fc-media"] = ("media-oidc-client", "vaults/IAmWorkin/items/media-oidc-client"),
["fc-distribution"] = ("distribution-oidc-client", "vaults/IAmWorkin/items/distribution-oidc-client"),
};
foreach (var expected in expectedItems)
{
var item = AppDocuments(expected.Key)
.Single(document => document.Kind == "OnePasswordItem" && document.Name == expected.Value.Name);
item.Scalar("spec", "itemPath").Should().Be(expected.Value.ItemPath);
}
}
[Fact]
public void DnsAndMediaGitOpsAdoption_PreservesLiveStorageAndImageShape()
{
var dnsDeployment = AppDocuments("fc-dns")
.Single(document => document.Kind == "Deployment" && document.Name == "dns-web");
var dnsContainer = dnsDeployment.MainContainerMappings().Should().ContainSingle().Subject;
var dnsPvc = AppDocuments("fc-dns")
.Single(document => document.Kind == "PersistentVolumeClaim" && document.Name == "dns-web-data");
ManifestNodeExtensions.Scalar(dnsContainer, "image").Should().Be("localhost/fc-dns-web:v20260604-oidc-proper");
dnsPvc.Scalar("spec", "storageClassName").Should().Be("longhorn");
dnsPvc.Scalar("spec", "resources", "requests", "storage").Should().Be("1Gi");
var mediaDeployment = AppDocuments("fc-media")
.Single(document => document.Kind == "Deployment" && document.Name == "fc-media-web");
var mediaContainer = mediaDeployment.MainContainerMappings().Should().ContainSingle().Subject;
var mediaPvc = AppDocuments("fc-media")
.Single(document => document.Kind == "PersistentVolumeClaim" && document.Name == "fc-media-data");
ManifestNodeExtensions.Scalar(mediaContainer, "image").Should().Be("localhost/fc-media-web:v20260604-oidc-proper");
mediaPvc.Scalar("spec", "storageClassName").Should().Be("longhorn");
mediaPvc.Scalar("spec", "resources", "requests", "storage").Should().Be("20Gi");
mediaDeployment.AllScalars().Should().Contain(new[]
{
"/volume1/kubernetes/fc-media-transcodes",
"/volume1/kubernetes/fc-media-inbox",
"/volume1/video",
});
var distributionDeployment = AppDocuments("fc-distribution")
.Single(document => document.Kind == "Deployment" && document.Name == "fc-distribution");
var distributionContainer = distributionDeployment.MainContainerMappings().Should().ContainSingle().Subject;
ManifestNodeExtensions.Scalar(distributionContainer, "image").Should().Be("localhost/fc-distribution:v20260604-oidc-root-anon");
}
[Fact]
public void MonitoringProbes_UseHealthzForOidcGatedHosts()
{
var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
monitoring.Should().Contain("\"https://dns.iamworkin.lan/healthz\"");
monitoring.Should().Contain("\"https://dist.iamworkin.lan/healthz\"");
monitoring.Should().Contain("\"https://media.iamworkin.lan/healthz\"");
monitoring.Should().NotContain("\"https://dns.iamworkin.lan/\"");
monitoring.Should().NotContain("\"https://dist.iamworkin.lan/\"");
monitoring.Should().NotContain("\"https://media.iamworkin.lan/\"");
}
[Fact]
public void DistributionPublicIngress_KeepsGetHeadMethodAllowlist()
{
var publicIngress = AppDocuments("fc-distribution")
.Single(document => document.Kind == "IngressRoute" && document.Name == "fc-distribution-public");
var route = publicIngress.MappingSequence("spec", "routes").Should().ContainSingle().Subject;
var match = ManifestNodeExtensions.Scalar(route, "match");
match.Should().Contain("Host(`dist.flowercore.io`)");
match.Should().Contain("Method(`GET`)");
match.Should().Contain("Method(`HEAD`)");
match.Should().NotContain("Method(`POST`)");
}
[Fact]
public void DnsAndMediaIngressRoutes_MatchLiveInternalHosts()
{
var dnsRoute = AppDocuments("fc-dns")
.Single(document => document.Kind == "IngressRoute" && document.Name == "dns-web")
.MappingSequence("spec", "routes")
.Should()
.ContainSingle()
.Subject;
var mediaRoute = AppDocuments("fc-media")
.Single(document => document.Kind == "IngressRoute" && document.Name == "fc-media-web")
.MappingSequence("spec", "routes")
.Should()
.ContainSingle()
.Subject;
ManifestNodeExtensions.Scalar(dnsRoute, "match").Should().Be("Host(`dns.iamworkin.lan`)");
ManifestNodeExtensions.Scalar(mediaRoute, "match").Should().Be("Host(`media.iamworkin.lan`)");
}
private static IEnumerable<string> ProbeViolations(
ManifestDocument document,
YamlMappingNode container,
@@ -977,44 +762,12 @@ public sealed class FleetManifestLintTests
: null;
}
private static string? EnvSecretOptional(YamlMappingNode container, string name)
{
return EnvMapping(container, name) is { } env
? ManifestNodeExtensions.Scalar(env, "valueFrom", "secretKeyRef", "optional")
: null;
}
private static string? ProbePath(YamlMappingNode container, string probeKey)
{
return ManifestNodeExtensions.Scalar(container, probeKey, "httpGet", "path");
}
private static IReadOnlyList<ManifestDocument> AppDocuments(string app)
{
return Inventory.Documents
.Where(document => document.RelativePath.StartsWith($"{app}/", StringComparison.Ordinal))
.ToList();
}
private static YamlMappingNode? EnvMapping(YamlMappingNode container, string name)
{
return ManifestNodeExtensions.MappingSequence(container, "env")
.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()
{
return Inventory.Documents

View File

@@ -0,0 +1,124 @@
using FluentAssertions;
using System.Text.RegularExpressions;
using Xunit;
namespace BluejayInfraLint.Tests;
[Trait("Category", "Unit")]
public sealed class MonitoringCoverageLintTests
{
private static readonly ManifestInventory Inventory = ManifestInventory.Load();
private static readonly string[] Sprint57ProbeTargets =
{
"https://dns.iamworkin.lan/",
"https://flowercore.iamworkin.lan/healthz",
"https://replay.iamworkin.lan/healthz",
"https://signalcontrol.iamworkin.lan/health",
"https://updatecenter-internal.iamworkin.lan/api/v1/manifests/_schema",
"https://updates.iamworkin.lan/api/v1/manifests/_schema",
"https://worldbuilder.iamworkin.lan/healthz",
};
[Fact]
public void PrometheusScrape_MustNotTargetDeadPiManagerPort()
{
var monitoring = ReadMonitoringMirror();
monitoring.Should().NotContain("10.0.58.113:5100");
monitoring.Should().Contain("10.0.58.113:5200");
}
[Fact]
public void ProbeJobs_MustKeepEnvironmentSpecificBlackboxRelabels()
{
var monitoring = ReadMonitoringMirror();
var probeJobs = FindProbeJobs(monitoring);
probeJobs.Should().NotBeEmpty();
probeJobs.Should().OnlyContain(
job => job.Contains("replacement: blackbox-exporter.monitoring.svc:9115", StringComparison.Ordinal),
"the bluejay-infra mirror runs Prometheus in-cluster and should use the blackbox service DNS");
var livePodmanPrometheus = TryReadNotesMonitoringFile("prometheus.yml");
if (livePodmanPrometheus is not null)
{
FindProbeJobs(livePodmanPrometheus).Should().OnlyContain(
job => job.Contains("replacement: localhost:9115", StringComparison.Ordinal),
"live Podman monitoring uses host networking, so blackbox probes must relabel to localhost:9115");
}
}
[Fact]
public void TraefikServiceProbes_MustCoverSprint57LiveFlowerCoreHosts()
{
var monitoring = ReadMonitoringMirror();
foreach (var target in Sprint57ProbeTargets)
{
monitoring.Should().Contain(target);
}
}
[Fact]
public void EpsonPrinterDown_MustUseRangeWindowForStaleScrapeCoverage()
{
var alerts = ReadMonitoringMirror();
alerts.Should().Contain("- alert: EpsonPrinterDown");
alerts.Should().Contain("max_over_time(up{job=\"snmp-printer\"}[35m]) == bool 0");
alerts.Should().NotContain("expr: up{job=\"snmp-printer\"} == 0");
}
[Fact]
public void MonitoringMirror_MustCarryRunnerExclusionsAndEpsonGrafanaDelivery()
{
var mirror = ReadMonitoringMirror();
GetAlertBlock(mirror, "KubeContainerRestartingFrequently")
.Should()
.Contain("kube_pod_container_status_restarts_total{namespace!=\"github-runner\"}[1h]");
GetAlertBlock(mirror, "KubeContainerCrashLooping")
.Should()
.Contain("kube_pod_container_status_restarts_total{namespace!=\"github-runner\"}[15m]");
GetAlertBlock(mirror, "KubeDeploymentReplicasMismatch")
.Should()
.Contain("kube_deployment_spec_replicas{namespace!=\"github-runner\"} != kube_deployment_status_replicas_available{namespace!=\"github-runner\"}");
mirror.Should().Contain("uid: epson-printer-down-stale-window");
mirror.Should().Contain("title: EpsonPrinterDown");
mirror.Should().Contain("alert_channel: irc");
}
private static string ReadMonitoringMirror() =>
File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
private static string? TryReadNotesMonitoringFile(string fileName)
{
var overrideRoot = Environment.GetEnvironmentVariable("FLOWERCORE_NOTES_ROOT");
if (string.IsNullOrWhiteSpace(overrideRoot))
{
return null;
}
var path = Path.Combine(overrideRoot, "scripts", "monitoring", fileName);
return File.ReadAllText(path);
}
private static IReadOnlyList<string> FindProbeJobs(string yaml) =>
Regex.Matches(
yaml,
"(?ms)^\\s+- job_name: \"probe-[^\"]+\".*?(?=^\\s+- job_name:|\\z)")
.Cast<Match>()
.Select(match => match.Value)
.ToList();
private static string GetAlertBlock(string yaml, string alertName)
{
var match = Regex.Match(
yaml,
$"(?ms)^\\s+- alert: {Regex.Escape(alertName)}\\s*$.*?(?=^\\s+- alert:|\\z)");
match.Success.Should().BeTrue($"alert {alertName} should be present in noc-monitoring.yaml");
return match.Value;
}
}