Compare commits

..

1 Commits

Author SHA1 Message Date
Andrew Stoltz
6382582090 fc-desktop: add remotedesktop warm pool intent 2026-05-19 12:27:47 -05:00
14 changed files with 355 additions and 1352 deletions

View File

@@ -1,448 +0,0 @@
# Authentik OIDC backend
# ArgoCD-managed. BlueJay Lab.
#
# Stack:
# - PostgreSQL 16 StatefulSet (single replica, Longhorn RWO 5Gi)
# - Redis 7 Deployment (no persistence — session/cache only)
# - Authentik server + worker Deployments (image ghcr.io/goauthentik/server:2024.12.3)
# - Media PVC shared between server + worker (Longhorn RWO 2Gi)
# - Certificate via step-ca-acme ClusterIssuer
# - Traefik IngressRoute at id.iamworkin.lan
#
# Secrets come from 1Password item "authentik-credentials" (IAmWorkin vault, id y6i74ch22q5wvm7znquq4nhhcu)
# via the OnePasswordItem CRD, materialized into k8s Secret authentik/authentik-credentials.
#
# Why the discovery URL is /application/o/pimanager/ : Authentik issues per-application OIDC providers.
# The pimanager OIDC application/provider is created after the cluster pods are healthy (manual or
# via API once the bootstrap token is available — see Notes substrate).
---
apiVersion: v1
kind: Namespace
metadata:
name: authentik
labels:
app.kubernetes.io/part-of: bluejay-infra
---
# 1Password operator pulls the authentik-credentials item into a k8s Secret of the same name.
# Field labels in 1P become Secret keys: AUTHENTIK_SECRET_KEY, POSTGRES_PASSWORD, REDIS_PASSWORD,
# BOOTSTRAP_ADMIN_PASSWORD, BOOTSTRAP_ADMIN_TOKEN, BOOTSTRAP_ADMIN_EMAIL.
apiVersion: onepassword.com/v1
kind: OnePasswordItem
metadata:
name: authentik-credentials
namespace: authentik
spec:
itemPath: "vaults/IAmWorkin/items/authentik-credentials"
---
# Shared media volume for server + worker pods.
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: authentik-media
namespace: authentik
spec:
storageClassName: longhorn
accessModes: [ReadWriteOnce]
resources:
requests:
storage: 2Gi
---
# PostgreSQL 16 StatefulSet — Authentik's primary store.
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: authentik-postgres
namespace: authentik
labels:
app: authentik-postgres
argocd.argoproj.io/instance: infra-authentik
spec:
persistentVolumeClaimRetentionPolicy:
whenDeleted: Retain
whenScaled: Retain
podManagementPolicy: OrderedReady
serviceName: authentik-postgres
replicas: 1
revisionHistoryLimit: 10
selector:
matchLabels:
app: authentik-postgres
template:
metadata:
labels:
app: authentik-postgres
spec:
containers:
- name: postgres
image: postgres:16-alpine
ports:
- containerPort: 5432
name: postgres
env:
- name: POSTGRES_USER
value: authentik
- name: POSTGRES_PASSWORD
valueFrom:
secretKeyRef:
name: authentik-credentials
key: POSTGRES_PASSWORD
- name: POSTGRES_DB
value: authentik
- name: POSTGRES_INITDB_ARGS
value: "--encoding=UTF-8 --lc-collate=C --lc-ctype=C"
- name: PGDATA
value: /var/lib/postgresql/data/pgdata
readinessProbe:
exec:
command: ["pg_isready", "-U", "authentik"]
initialDelaySeconds: 5
periodSeconds: 5
livenessProbe:
exec:
command: ["pg_isready", "-U", "authentik"]
initialDelaySeconds: 30
periodSeconds: 30
resources:
requests: { cpu: 100m, memory: 256Mi }
limits: { cpu: 1000m, memory: 1Gi }
volumeMounts:
- name: pgdata
mountPath: /var/lib/postgresql/data
volumeClaimTemplates:
- metadata:
name: pgdata
spec:
storageClassName: longhorn
accessModes: [ReadWriteOnce]
volumeMode: Filesystem
resources:
requests:
storage: 5Gi
---
apiVersion: v1
kind: Service
metadata:
name: authentik-postgres
namespace: authentik
spec:
clusterIP: None
selector:
app: authentik-postgres
ports:
- name: postgres
port: 5432
targetPort: 5432
---
# Redis 7 — session storage + Celery broker. No persistence needed (cache).
apiVersion: apps/v1
kind: Deployment
metadata:
name: authentik-redis
namespace: authentik
labels:
app: authentik-redis
argocd.argoproj.io/instance: infra-authentik
spec:
replicas: 1
strategy:
type: Recreate
selector:
matchLabels:
app: authentik-redis
template:
metadata:
labels:
app: authentik-redis
spec:
containers:
- name: redis
image: redis:7-alpine
args:
- "--save"
- ""
- "--appendonly"
- "no"
- "--requirepass"
- "$(REDIS_PASSWORD)"
env:
- name: REDIS_PASSWORD
valueFrom:
secretKeyRef:
name: authentik-credentials
key: REDIS_PASSWORD
ports:
- containerPort: 6379
name: redis
readinessProbe:
tcpSocket: { port: 6379 }
initialDelaySeconds: 5
periodSeconds: 5
livenessProbe:
tcpSocket: { port: 6379 }
initialDelaySeconds: 30
periodSeconds: 30
resources:
requests: { cpu: 50m, memory: 64Mi }
limits: { cpu: 500m, memory: 256Mi }
---
apiVersion: v1
kind: Service
metadata:
name: authentik-redis
namespace: authentik
spec:
selector:
app: authentik-redis
ports:
- name: redis
port: 6379
targetPort: 6379
---
# Authentik server Deployment — HTTP frontend on :9000.
apiVersion: apps/v1
kind: Deployment
metadata:
name: authentik-server
namespace: authentik
labels:
app: authentik-server
argocd.argoproj.io/instance: infra-authentik
spec:
replicas: 1
strategy:
type: Recreate # shares /media RWO PVC with worker
selector:
matchLabels:
app: authentik-server
template:
metadata:
labels:
app: authentik-server
spec:
securityContext:
# Authentik image runs as uid 1000 "authentik" but the Longhorn PVC mounts
# root:root by default. fsGroup recursively chgrp + chmod g+rwx so the
# non-root container can mkdir /media/public during the tenant_files migration.
fsGroup: 1000
containers:
- name: server
image: ghcr.io/goauthentik/server:2024.12.3
args: ["server"]
ports:
- containerPort: 9000
name: http
- containerPort: 9443
name: https
env:
- name: AUTHENTIK_SECRET_KEY
valueFrom:
secretKeyRef:
name: authentik-credentials
key: AUTHENTIK_SECRET_KEY
- name: AUTHENTIK_REDIS__HOST
value: authentik-redis
- name: AUTHENTIK_REDIS__PASSWORD
valueFrom:
secretKeyRef:
name: authentik-credentials
key: REDIS_PASSWORD
- name: AUTHENTIK_POSTGRESQL__HOST
value: authentik-postgres
- name: AUTHENTIK_POSTGRESQL__NAME
value: authentik
- name: AUTHENTIK_POSTGRESQL__USER
value: authentik
- name: AUTHENTIK_POSTGRESQL__PASSWORD
valueFrom:
secretKeyRef:
name: authentik-credentials
key: POSTGRES_PASSWORD
- name: AUTHENTIK_BOOTSTRAP_PASSWORD
valueFrom:
secretKeyRef:
name: authentik-credentials
key: BOOTSTRAP_ADMIN_PASSWORD
- name: AUTHENTIK_BOOTSTRAP_TOKEN
valueFrom:
secretKeyRef:
name: authentik-credentials
key: BOOTSTRAP_ADMIN_TOKEN
- name: AUTHENTIK_BOOTSTRAP_EMAIL
valueFrom:
secretKeyRef:
name: authentik-credentials
key: BOOTSTRAP_ADMIN_EMAIL
- name: AUTHENTIK_DISABLE_UPDATE_CHECK
value: "true"
- name: AUTHENTIK_ERROR_REPORTING__ENABLED
value: "false"
- name: AUTHENTIK_LOG_LEVEL
value: info
# First-boot Authentik can take 3+ min on the migration phase
# (waiting on DB lock while worker also runs migrations). Initial
# delays are generous so kubelet doesn't kill the pod mid-migration;
# periodSeconds keeps post-startup probing responsive.
readinessProbe:
httpGet:
path: /-/health/ready/
port: 9000
initialDelaySeconds: 60
periodSeconds: 10
timeoutSeconds: 5
failureThreshold: 12
livenessProbe:
httpGet:
path: /-/health/live/
port: 9000
initialDelaySeconds: 300
periodSeconds: 30
timeoutSeconds: 10
failureThreshold: 3
startupProbe:
httpGet:
path: /-/health/live/
port: 9000
initialDelaySeconds: 30
periodSeconds: 15
timeoutSeconds: 10
failureThreshold: 40 # 30s + 40*15s = 10.5 min budget
resources:
requests: { cpu: 150m, memory: 512Mi }
limits: { cpu: 1500m, memory: 1Gi }
volumeMounts:
- name: media
mountPath: /media
volumes:
- name: media
persistentVolumeClaim:
claimName: authentik-media
---
# Authentik worker Deployment — runs Celery background tasks.
apiVersion: apps/v1
kind: Deployment
metadata:
name: authentik-worker
namespace: authentik
labels:
app: authentik-worker
argocd.argoproj.io/instance: infra-authentik
spec:
replicas: 1
strategy:
type: Recreate # shares /media RWO PVC with server
selector:
matchLabels:
app: authentik-worker
template:
metadata:
labels:
app: authentik-worker
spec:
securityContext:
# Same as server pod — non-root uid 1000 needs PVC group write.
fsGroup: 1000
containers:
- name: worker
image: ghcr.io/goauthentik/server:2024.12.3
args: ["worker"]
env:
- name: AUTHENTIK_SECRET_KEY
valueFrom:
secretKeyRef:
name: authentik-credentials
key: AUTHENTIK_SECRET_KEY
- name: AUTHENTIK_REDIS__HOST
value: authentik-redis
- name: AUTHENTIK_REDIS__PASSWORD
valueFrom:
secretKeyRef:
name: authentik-credentials
key: REDIS_PASSWORD
- name: AUTHENTIK_POSTGRESQL__HOST
value: authentik-postgres
- name: AUTHENTIK_POSTGRESQL__NAME
value: authentik
- name: AUTHENTIK_POSTGRESQL__USER
value: authentik
- name: AUTHENTIK_POSTGRESQL__PASSWORD
valueFrom:
secretKeyRef:
name: authentik-credentials
key: POSTGRES_PASSWORD
- name: AUTHENTIK_DISABLE_UPDATE_CHECK
value: "true"
- name: AUTHENTIK_ERROR_REPORTING__ENABLED
value: "false"
- name: AUTHENTIK_LOG_LEVEL
value: info
resources:
requests: { cpu: 100m, memory: 256Mi }
limits: { cpu: 1000m, memory: 768Mi }
volumeMounts:
- name: media
mountPath: /media
volumes:
- name: media
persistentVolumeClaim:
claimName: authentik-media
---
apiVersion: v1
kind: Service
metadata:
name: authentik-server
namespace: authentik
spec:
selector:
app: authentik-server
ports:
- name: http
port: 9000
targetPort: 9000
- name: https
port: 9443
targetPort: 9443
---
# step-ca leaf certificate for id.iamworkin.lan.
# step-ca container resolver uses pfSense Unbound, so the public A record for id.iamworkin.lan
# MUST exist before this Certificate is applied (cert-manager HTTP-01 will silently 2h-backoff
# otherwise). Added 2026-05-25 via scripts/pfsense-add-id-host.py.
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: authentik-tls
namespace: authentik
spec:
secretName: authentik-tls
dnsNames:
- id.iamworkin.lan
issuerRef:
name: step-ca-acme
kind: ClusterIssuer
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: authentik
namespace: authentik
spec:
entryPoints: [websecure]
routes:
- match: Host(`id.iamworkin.lan`)
kind: Rule
services:
- name: authentik-server
port: 9000
tls:
secretName: authentik-tls

View File

@@ -1,10 +1,13 @@
# FlowerCore Remote Desktop — TLS + Ingress # FlowerCore Remote Desktop — TLS + Ingress
# #
# Source-of-truth split: # Source-of-truth split:
# - bluejay-infra OWNS: Certificate, IngressRoute, all NetworkPolicies # - bluejay-infra OWNS: Certificate, IngressRoute, all NetworkPolicies,
# and the explicit RemoteDesktopPoolCrd warm-pool intent in
# remotedesktop-pools.yaml.
# (see network-policies.yaml in this directory). # (see network-policies.yaml in this directory).
# - FlowerCore.RemoteDesktop scripts/deploy-web.sh OWNS: Deployment + # - FlowerCore.RemoteDesktop OWNS: CRD definition/operator Deployment and
# Service. Reason: image refs like `localhost/fc-desktop:linux-xfce` # scripts/deploy-web.sh Deployment + Service. Reason: image refs like
# `localhost/fc-desktop:linux-xfce`
# only exist on each node's containerd after a manual import, so a # only exist on each node's containerd after a manual import, so a
# Deployment manifest in bluejay-infra would race the image-import # Deployment manifest in bluejay-infra would race the image-import
# step and crash-loop. # step and crash-loop.

View File

@@ -0,0 +1,101 @@
# FlowerCore RemoteDesktop warm-pool intent.
#
# These CRDs are deliberately explicit. The RemoteDesktop warmup loop no
# longer scans template defaults to decide what to warm; every enabled pool
# here represents operator/GitOps intent and prevents a repeat of the
# orphan-pool leak from 2026-05-08.
---
apiVersion: flowercore.io/v1
kind: RemoteDesktopPoolCrd
metadata:
name: browser-lab-pool
namespace: fc-desktop
labels:
app.kubernetes.io/name: remotedesktop-pool
app.kubernetes.io/part-of: flowercore-remotedesktop
app.kubernetes.io/managed-by: bluejay-infra
spec:
templateSlug: browser-only
desiredSize: 1
enabled: true
reconcileNow: true
---
apiVersion: flowercore.io/v1
kind: RemoteDesktopPoolCrd
metadata:
name: opensuse-xfce-pool
namespace: fc-desktop
labels:
app.kubernetes.io/name: remotedesktop-pool
app.kubernetes.io/part-of: flowercore-remotedesktop
app.kubernetes.io/managed-by: bluejay-infra
spec:
templateSlug: opensuse-xfce
desiredSize: 1
enabled: true
userVolumeMode: LateAttach
reconcileNow: true
---
apiVersion: flowercore.io/v1
kind: RemoteDesktopPoolCrd
metadata:
name: dev-workstation-pool
namespace: fc-desktop
labels:
app.kubernetes.io/name: remotedesktop-pool
app.kubernetes.io/part-of: flowercore-remotedesktop
app.kubernetes.io/managed-by: bluejay-infra
spec:
templateSlug: dev-workstation
desiredSize: 1
enabled: true
userVolumeMode: LateAttach
reconcileNow: true
---
apiVersion: flowercore.io/v1
kind: RemoteDesktopPoolCrd
metadata:
name: ai-station-pool
namespace: fc-desktop
labels:
app.kubernetes.io/name: remotedesktop-pool
app.kubernetes.io/part-of: flowercore-remotedesktop
app.kubernetes.io/managed-by: bluejay-infra
spec:
templateSlug: ai-station
desiredSize: 1
enabled: true
userVolumeMode: LateAttach
reconcileNow: true
---
apiVersion: flowercore.io/v1
kind: RemoteDesktopPoolCrd
metadata:
name: linux-xfce-pool
namespace: fc-desktop
labels:
app.kubernetes.io/name: remotedesktop-pool
app.kubernetes.io/part-of: flowercore-remotedesktop
app.kubernetes.io/managed-by: bluejay-infra
spec:
templateSlug: linux-xfce
desiredSize: 1
enabled: true
userVolumeMode: LateAttach
reconcileNow: true
---
apiVersion: flowercore.io/v1
kind: RemoteDesktopPoolCrd
metadata:
name: linux-xfce-rdp-pool
namespace: fc-desktop
labels:
app.kubernetes.io/name: remotedesktop-pool
app.kubernetes.io/part-of: flowercore-remotedesktop
app.kubernetes.io/managed-by: bluejay-infra
spec:
templateSlug: linux-xfce-rdp
desiredSize: 1
enabled: true
userVolumeMode: LateAttach
reconcileNow: true

View File

@@ -0,0 +1,33 @@
# Explicit ArgoCD Application shape for bootstrap/review.
#
# The live bluejay-infra ApplicationSet already discovers apps/* directories
# and creates this same Application name (`infra-fc-devicemgmt`) automatically.
# Keep repoURL on the internal Gitea ClusterIP URL; ArgoCD does not trust the
# external step-ca HTTPS endpoint.
apiVersion: argoproj.io/v1alpha1
kind: Application
metadata:
name: infra-fc-devicemgmt
namespace: argocd
labels:
app.kubernetes.io/name: fc-devicemgmt
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
project: default
source:
repoURL: http://gitea-clusterip.gitea.svc.cluster.local:3000/bluejay/bluejay-infra.git
targetRevision: main
path: apps/fc-devicemgmt
destination:
server: https://kubernetes.default.svc
namespace: fc-devicemgmt
syncPolicy:
automated:
prune: true
selfHeal: true
syncOptions:
- CreateNamespace=true
- ServerSideApply=true

View File

@@ -1,2 +0,0 @@
*.sh text eol=lf
Dockerfile text eol=lf

View File

@@ -1,54 +0,0 @@
FROM myoung34/github-runner:latest
ARG RUBY_VERSION=3.3.11
ARG RUBY_MINOR=3.3
ARG RUBY_BUILD_VERSION=v20260326
ARG RUNNER_UID=1001
ARG RUNNER_GID=1001
ENV RUNNER_TOOL_CACHE=/home/runner/_tool
ENV RUNNER_RUBY_TOOLCACHE=/opt/runner-toolcache
ENV PATH="/home/runner/_tool/Ruby/${RUBY_MINOR}/x64/bin:/opt/runner-toolcache/Ruby/${RUBY_MINOR}/x64/bin:${PATH}"
USER root
# Bake the IAmWorkin step-ca root CA into the system trust store. Without
# this, .NET HttpClient calls from CI tests against *.iamworkin.lan
# (e.g. https://selenium.iamworkin.lan/session) fail with `PartialChain`
# because the runner image's default Ubuntu trust bundle doesn't include
# our internal Root CA. update-ca-certificates regenerates
# /etc/ssl/certs/ca-certificates.crt, which OpenSSL + .NET on Linux read
# automatically — no SSL_CERT_FILE env var needed.
COPY step-ca-root.crt /usr/local/share/ca-certificates/iamworkin-step-ca-root.crt
RUN apt-get update \
&& DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
autoconf \
bison \
build-essential \
ca-certificates \
curl \
libdb-dev \
libffi-dev \
libgdbm-dev \
libgmp-dev \
libncurses-dev \
libreadline-dev \
libssl-dev \
libyaml-dev \
patch \
pkg-config \
uuid-dev \
zlib1g-dev \
&& update-ca-certificates \
&& curl -fsSL "https://github.com/rbenv/ruby-build/archive/refs/tags/${RUBY_BUILD_VERSION}.tar.gz" -o /tmp/ruby-build.tar.gz \
&& mkdir -p /tmp/ruby-build \
&& tar -xzf /tmp/ruby-build.tar.gz --strip-components=1 -C /tmp/ruby-build \
&& /tmp/ruby-build/install.sh \
&& rm -rf /tmp/ruby-build /tmp/ruby-build.tar.gz /var/lib/apt/lists/*
COPY install-ruby-toolcache.sh /usr/local/bin/install-ruby-toolcache.sh
RUN chmod +x /usr/local/bin/install-ruby-toolcache.sh \
&& RUBY_VERSION="${RUBY_VERSION}" RUBY_MINOR="${RUBY_MINOR}" TOOLCACHE_ROOT="${RUNNER_RUBY_TOOLCACHE}" RUNNER_UID="${RUNNER_UID}" RUNNER_GID="${RUNNER_GID}" /usr/local/bin/install-ruby-toolcache.sh \
&& ruby -v

View File

@@ -7,17 +7,12 @@ Deployments with `kubectl`; update this manifest and let ArgoCD reconcile.
All repo-scoped Linux runners use: All repo-scoped Linux runners use:
- `localhost/fc-github-runner:v20260525-ruby3.3.11-stepca`, derived from
`myoung34/github-runner:latest`
- `ACCESS_TOKEN` from the `github-runner-token` Secret - `ACCESS_TOKEN` from the `github-runner-token` Secret
- `RUN_AS_ROOT=false` - `RUN_AS_ROOT=false`
- `EPHEMERAL=true` - `EPHEMERAL=true`
- `LABELS=self-hosted,linux,fc-build-linux` - `LABELS=self-hosted,linux,fc-build-linux`
- writable non-root paths under `/home/runner` for .NET, NuGet, XDG cache, and - writable non-root paths under `/home/runner` for .NET, NuGet, XDG cache, and
Actions tool cache Actions tool cache
- Ruby 3.3.11 seeded into `/home/runner/_tool/Ruby/3.3/x64` from the baked
`/opt/runner-toolcache` copy so `ruby/setup-ruby@v1` can discover it on
self-hosted `ubuntu-20.04-x64` runners
`github-runner` for `FlowerCore.Common` is single-replica because it retains the `github-runner` for `FlowerCore.Common` is single-replica because it retains the
original Longhorn ReadWriteOnce NuGet PVC. Every other repo-scoped runner uses original Longhorn ReadWriteOnce NuGet PVC. Every other repo-scoped runner uses
@@ -33,46 +28,6 @@ Sprint 32 final long-tail wave adds 16 two-replica Deployments:
`FlowerCore.Provisioning`, `FlowerCore.Redis`, `FlowerCore.MessageBoard`, and `FlowerCore.Provisioning`, `FlowerCore.Redis`, `FlowerCore.MessageBoard`, and
`FlowerCore.MenuBoard`. `FlowerCore.MenuBoard`.
## Image Build
Ruby is baked with a pinned `ruby-build` release and Ruby patch version. The pod
still mounts an `emptyDir` over `/home/runner`, so the `setup-runner-home` init
container copies the baked toolcache from `/opt/runner-toolcache/Ruby` into
`/home/runner/_tool/Ruby` before the runner container starts.
The IAmWorkin step-ca root CA is also baked into the system trust store
(`/usr/local/share/ca-certificates/iamworkin-step-ca-root.crt`, registered by
`update-ca-certificates`). Without it, .NET HttpClient calls from CI tests
against `*.iamworkin.lan` (e.g. `https://selenium.iamworkin.lan/session`)
fail with `PartialChain`. To refresh the bundled cert when the root rotates,
re-extract from the cluster and overwrite `step-ca-root.crt`:
```bash
kubectl get secret -n cert-manager step-ca-root \
-o jsonpath='{.data.ca\.crt}' | base64 -d > step-ca-root.crt
```
```bash
cd apps/github-runner
podman build -t localhost/fc-github-runner:v20260525-ruby3.3.11-stepca .
podman run --rm localhost/fc-github-runner:v20260525-ruby3.3.11-stepca ruby -v
podman run --rm localhost/fc-github-runner:v20260525-ruby3.3.11-stepca \
test -f /opt/runner-toolcache/Ruby/3.3/x64.complete
podman save localhost/fc-github-runner:v20260525-ruby3.3.11-stepca \
-o fc-github-runner-v20260525-ruby3.3.11-stepca.tar
```
Import the saved image on every schedulable RKE2 node before ArgoCD rolls the
Deployments:
```bash
for node in rke2-server rke2-agent1 rke2-agent2; do
scp fc-github-runner-v20260525-ruby3.3.11-stepca.tar "$node:/tmp/"
ssh "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images rm localhost/fc-github-runner:v20260525-ruby3.3.11-stepca || true'
ssh "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images import /tmp/fc-github-runner-v20260525-ruby3.3.11-stepca.tar'
done
```
## Post-Merge Proof ## Post-Merge Proof
After the PR is merged and ArgoCD syncs, verify the runner fleet: After the PR is merged and ArgoCD syncs, verify the runner fleet:
@@ -81,14 +36,6 @@ After the PR is merged and ArgoCD syncs, verify the runner fleet:
kubectl -n github-runner get deploy,pods,pvc kubectl -n github-runner get deploy,pods,pvc
``` ```
Verify the Ruby toolcache in a fresh pod:
```bash
kubectl -n github-runner exec deploy/github-runner-puppet -c runner -- ruby -v
kubectl -n github-runner exec deploy/github-runner-puppet -c runner -- sh -c \
'echo "$RUNNER_TOOL_CACHE" && test -f "$RUNNER_TOOL_CACHE/Ruby/3.3/x64.complete"'
```
Verify GitHub registration for the repo-scoped runners: Verify GitHub registration for the repo-scoped runners:
```bash ```bash
@@ -122,10 +69,6 @@ from GitHub Actions and verify it lands on an `rke2-linux-*` runner.
- `actions/setup-dotnet` permission error at `/usr/share/dotnet`: check that - `actions/setup-dotnet` permission error at `/usr/share/dotnet`: check that
`DOTNET_INSTALL_DIR=/home/runner/.dotnet` and related cache env vars are `DOTNET_INSTALL_DIR=/home/runner/.dotnet` and related cache env vars are
present on the runner pod. present on the runner pod.
- `ruby/setup-ruby@v1` says self-hosted runners must install Ruby in
`$RUNNER_TOOL_CACHE`: check that the init container copied
`/opt/runner-toolcache/Ruby` into `/home/runner/_tool/Ruby` and that
`/home/runner/_tool/Ruby/3.3/x64.complete` exists.
- `404` during runner registration: the fine-grained PAT is valid but missing - `404` during runner registration: the fine-grained PAT is valid but missing
repository access for that repo. Add the repo to the PAT access list; the PAT repository access for that repo. Add the repo to the PAT access list; the PAT
value does not change. value does not change.

File diff suppressed because it is too large Load Diff

View File

@@ -1,19 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
RUBY_VERSION="${RUBY_VERSION:-3.3.11}"
RUBY_MINOR="${RUBY_MINOR:-3.3}"
TOOLCACHE_ROOT="${TOOLCACHE_ROOT:-/opt/runner-toolcache}"
RUNNER_UID="${RUNNER_UID:-1001}"
RUNNER_GID="${RUNNER_GID:-1001}"
RUBY_PREFIX="${TOOLCACHE_ROOT}/Ruby/${RUBY_VERSION}/x64"
mkdir -p "${TOOLCACHE_ROOT}/Ruby"
RUBY_CONFIGURE_OPTS="${RUBY_CONFIGURE_OPTS:---disable-install-doc --disable-yjit}" ruby-build "${RUBY_VERSION}" "${RUBY_PREFIX}"
touch "${TOOLCACHE_ROOT}/Ruby/${RUBY_VERSION}/x64.complete"
ln -sfn "${RUBY_VERSION}" "${TOOLCACHE_ROOT}/Ruby/${RUBY_MINOR}"
"${RUBY_PREFIX}/bin/ruby" -v
chown -R "${RUNNER_UID}:${RUNNER_GID}" "${TOOLCACHE_ROOT}"
chmod -R a+rX "${TOOLCACHE_ROOT}"

View File

@@ -1,12 +0,0 @@
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----

View File

@@ -280,14 +280,13 @@ data:
printer_model: "NuPrint 210" printer_model: "NuPrint 210"
# Print.Web health (Blazor app on edge2:5200) # Print.Web health (Blazor app on edge2:5200)
# Target `/health` (anonymous) — root path requires API key auth and returns 401.
- job_name: "probe-printweb" - job_name: "probe-printweb"
metrics_path: /probe metrics_path: /probe
params: params:
module: [http_2xx] module: [http_2xx]
scrape_interval: 30s scrape_interval: 30s
static_configs: static_configs:
- targets: ["http://10.0.57.16:5200/health"] - targets: ["http://10.0.57.16:5200/"]
labels: labels:
instance: "print-web" instance: "print-web"
service: "print-web" service: "print-web"

View File

@@ -24,16 +24,7 @@
# (10.0.57.16:5200), public internet 80/443 (excluding RFC1918), and # (10.0.57.16:5200), public internet 80/443 (excluding RFC1918), and
# fc-signage:5190 for the signage AAT lane. # fc-signage:5190 for the signage AAT lane.
# - Ingress: Traefik (4444 + 8089 ACME-solver-style), intra-pod, # - Ingress: Traefik (4444 + 8089 ACME-solver-style), intra-pod,
# telephony / gitea / fc-system / fc-signage / github-runner namespaces # telephony / gitea / fc-system / fc-signage namespaces on 4444.
# on 4444.
#
# 2026-05-25: added github-runner ingress on 4444 so CI jobs running in
# self-hosted runner pods (e.g. FlowerCore.Print.Web `help-screenshots`)
# can reach the grid. Without this allow, the session POST to
# `selenium-hub.selenium.svc.cluster.local:4444` was DNAT'd to the hub
# pod IP and then dropped at the Calico ingress hook — Selenium UI showed
# 0/4 sessions while the .NET HTTP client timed out at 60s. Same family
# as `feedback_netpol_dnat_backend_port`, wrong-source-namespace flavor.
apiVersion: networking.k8s.io/v1 apiVersion: networking.k8s.io/v1
kind: NetworkPolicy kind: NetworkPolicy
metadata: metadata:
@@ -212,13 +203,6 @@ spec:
ports: ports:
- port: 4444 - port: 4444
protocol: TCP protocol: TCP
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: github-runner
ports:
- port: 4444
protocol: TCP
podSelector: {} podSelector: {}
policyTypes: policyTypes:
- Ingress - Ingress

View File

@@ -1,427 +0,0 @@
# Selenium Grid 4 — RKE2 deployment
#
# Hub + chrome + firefox + edge browser nodes serving fleet-wide AAT runs from
# the GitHub Actions self-hosted runners. ArgoCD owns this namespace from
# 2026-05-25 (`infra-selenium` Application; previously these resources were
# orphan kubectl-applied since 2026-03-15).
#
# Endpoints:
# - Internal cluster: http://selenium-hub.selenium.svc.cluster.local:4444
# - LAN LoadBalancer (MetalLB): http://10.0.56.208:4444
# - Traefik public: https://selenium.iamworkin.lan
#
# Browser maxSessions:
# - chrome 2 (bumped from 1 on 2026-05-25 morning-routine — AAT-heavy
# Print.Web help-screenshots was the global bottleneck;
# see commit history for ops/runner-replica-rightsize)
# - firefox 1
# - edge 1
#
# Screenshots + video recording write to NFS via the chrome video sidecar.
# See: CLAUDE.md "Selenium Grid & Visual AAT Testing" + bluejay-infra ADR notes.
---
apiVersion: v1
kind: Service
metadata:
labels:
app: selenium-hub
app.kubernetes.io/name: selenium-hub
app.kubernetes.io/part-of: selenium-grid
name: selenium-hub
namespace: selenium
spec:
ports:
- name: web
port: 4444
targetPort: 4444
- name: publish
port: 4442
targetPort: 4442
- name: subscribe
port: 4443
targetPort: 4443
selector:
app: selenium-hub
type: ClusterIP
---
apiVersion: v1
kind: Service
metadata:
annotations:
metallb.io/ip-allocated-from-pool: bluejay-pool
metallb.universe.tf/loadBalancerIPs: 10.0.56.208
labels:
app: selenium-hub
component: external-access
name: selenium-hub-external
namespace: selenium
spec:
clusterIP: 10.43.90.147
clusterIPs:
- 10.43.90.147
externalTrafficPolicy: Local
healthCheckNodePort: 32213
ports:
- name: web
nodePort: 32411
port: 4444
targetPort: 4444
- name: publish
nodePort: 32068
port: 4442
targetPort: 4442
- name: subscribe
nodePort: 31000
port: 4443
targetPort: 4443
selector:
app: selenium-hub
type: LoadBalancer
---
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
app: selenium-hub
app.kubernetes.io/name: selenium-hub
app.kubernetes.io/part-of: selenium-grid
name: selenium-hub
namespace: selenium
spec:
replicas: 1
selector:
matchLabels:
app: selenium-hub
template:
metadata:
labels:
app: selenium-hub
app.kubernetes.io/name: selenium-hub
app.kubernetes.io/part-of: selenium-grid
spec:
containers:
- env:
- name: SE_NODE_SESSION_TIMEOUT
value: '300'
- name: SE_SESSION_REQUEST_TIMEOUT
value: '300'
- name: SE_SESSION_RETRY_INTERVAL
value: '5'
- name: JAVA_OPTS
value: -Xmx512m
image: selenium/hub:4.27.0
livenessProbe:
httpGet:
path: /wd/hub/status
port: 4444
initialDelaySeconds: 30
periodSeconds: 15
timeoutSeconds: 5
name: selenium-hub
ports:
- containerPort: 4444
name: web
- containerPort: 4442
name: publish
- containerPort: 4443
name: subscribe
readinessProbe:
httpGet:
path: /wd/hub/status
port: 4444
initialDelaySeconds: 10
periodSeconds: 5
timeoutSeconds: 5
# Hub baseline working set ~766Mi on 2026-05-25 (75% of prior 1Gi
# limit). Bump to 1.5Gi / 1Gi to keep ~50% headroom; matches the
# stampede-buffer pattern documented for multus
# (feedback_k8s_cni_multus_sizing). CPU left alone — observed 54m
# against a 500m limit, no contention.
resources:
limits:
cpu: 500m
memory: 1536Mi
requests:
cpu: 250m
memory: 1Gi
---
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
app: selenium-node-chrome
app.kubernetes.io/name: selenium-node-chrome
app.kubernetes.io/part-of: selenium-grid
name: selenium-node-chrome
namespace: selenium
spec:
replicas: 1
selector:
matchLabels:
app: selenium-node-chrome
template:
metadata:
labels:
app: selenium-node-chrome
app.kubernetes.io/name: selenium-node-chrome
app.kubernetes.io/part-of: selenium-grid
spec:
containers:
- env:
- name: SE_EVENT_BUS_HOST
value: selenium-hub
- name: SE_EVENT_BUS_PUBLISH_PORT
value: '4442'
- name: SE_EVENT_BUS_SUBSCRIBE_PORT
value: '4443'
- name: SE_NODE_MAX_SESSIONS
value: '2'
- name: SE_NODE_OVERRIDE_MAX_SESSIONS
value: 'false'
- name: SE_VNC_NO_PASSWORD
value: '1'
- name: SE_SCREEN_WIDTH
value: '1920'
- name: SE_SCREEN_HEIGHT
value: '1080'
- name: SE_NODE_SESSION_TIMEOUT
value: '300'
image: selenium/node-chrome:4.27.0
livenessProbe:
httpGet:
path: /status
port: 5555
initialDelaySeconds: 30
periodSeconds: 15
name: selenium-chrome
ports:
- containerPort: 5555
name: node
readinessProbe:
httpGet:
path: /status
port: 5555
initialDelaySeconds: 15
periodSeconds: 5
# Chromium-based browser node. Bumped from 1Gi -> 2Gi (req 512Mi
# -> 1Gi) on 2026-05-25 — Edge had 51 OOMKills in 5d on the
# original 1Gi cap (~1 OOM every 2.4h), and Chrome at maxSessions=2
# was running 684Mi idle on the same cap. Matches the Firefox node's
# tested-stable 2Gi limit. CPU unchanged.
resources:
limits:
cpu: '1'
memory: 2Gi
requests:
cpu: 500m
memory: 1Gi
volumeMounts:
- mountPath: /dev/shm
name: dshm
- env:
- name: DISPLAY_CONTAINER_NAME
value: localhost
- name: SE_SCREEN_WIDTH
value: '1920'
- name: SE_SCREEN_HEIGHT
value: '1080'
- name: SE_VIDEO_FILE_NAME
value: auto
- name: SE_VIDEO_UPLOAD_ENABLED
value: 'false'
image: selenium/video:ffmpeg-7.1-20250101
name: video
resources:
limits:
cpu: 500m
memory: 768Mi
requests:
cpu: 250m
memory: 384Mi
volumeMounts:
- mountPath: /videos
name: selenium-videos
volumes:
- emptyDir:
medium: Memory
sizeLimit: 2Gi
name: dshm
- emptyDir:
sizeLimit: 5Gi
name: selenium-videos
---
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
app: selenium-node-firefox
app.kubernetes.io/name: selenium-node-firefox
app.kubernetes.io/part-of: selenium-grid
name: selenium-node-firefox
namespace: selenium
spec:
replicas: 1
selector:
matchLabels:
app: selenium-node-firefox
template:
metadata:
labels:
app: selenium-node-firefox
app.kubernetes.io/name: selenium-node-firefox
app.kubernetes.io/part-of: selenium-grid
spec:
containers:
- env:
- name: SE_EVENT_BUS_HOST
value: selenium-hub
- name: SE_EVENT_BUS_PUBLISH_PORT
value: '4442'
- name: SE_EVENT_BUS_SUBSCRIBE_PORT
value: '4443'
- name: SE_NODE_MAX_SESSIONS
value: '1'
- name: SE_NODE_OVERRIDE_MAX_SESSIONS
value: 'true'
- name: SE_VNC_NO_PASSWORD
value: '1'
- name: SE_START_VNC
value: 'false'
- name: SE_SCREEN_WIDTH
value: '1920'
- name: SE_SCREEN_HEIGHT
value: '1080'
- name: SE_NODE_SESSION_TIMEOUT
value: '300'
image: selenium/node-firefox:4.27.0
livenessProbe:
failureThreshold: 5
httpGet:
path: /status
port: 5555
initialDelaySeconds: 30
periodSeconds: 15
timeoutSeconds: 5
name: selenium-firefox
ports:
- containerPort: 5555
name: node
readinessProbe:
failureThreshold: 5
httpGet:
path: /status
port: 5555
initialDelaySeconds: 15
periodSeconds: 5
timeoutSeconds: 5
resources:
limits:
cpu: '1'
memory: 2Gi
requests:
cpu: 500m
memory: 1Gi
volumeMounts:
- mountPath: /dev/shm
name: dshm
volumes:
- emptyDir:
medium: Memory
sizeLimit: 2Gi
name: dshm
---
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
app: selenium-node-edge
app.kubernetes.io/name: selenium-node-edge
app.kubernetes.io/part-of: selenium-grid
name: selenium-node-edge
namespace: selenium
spec:
replicas: 1
selector:
matchLabels:
app: selenium-node-edge
template:
metadata:
labels:
app: selenium-node-edge
app.kubernetes.io/name: selenium-node-edge
app.kubernetes.io/part-of: selenium-grid
spec:
containers:
- env:
- name: SE_EVENT_BUS_HOST
value: selenium-hub
- name: SE_EVENT_BUS_PUBLISH_PORT
value: '4442'
- name: SE_EVENT_BUS_SUBSCRIBE_PORT
value: '4443'
- name: SE_NODE_MAX_SESSIONS
value: '1'
- name: SE_NODE_OVERRIDE_MAX_SESSIONS
value: 'true'
- name: SE_VNC_NO_PASSWORD
value: '1'
- name: SE_SCREEN_WIDTH
value: '1920'
- name: SE_SCREEN_HEIGHT
value: '1080'
- name: SE_NODE_SESSION_TIMEOUT
value: '300'
image: selenium/node-edge:4.27.0
livenessProbe:
httpGet:
path: /status
port: 5555
initialDelaySeconds: 30
periodSeconds: 15
name: selenium-edge
ports:
- containerPort: 5555
name: node
readinessProbe:
httpGet:
path: /status
port: 5555
initialDelaySeconds: 15
periodSeconds: 5
# Chromium-based browser node. Bumped from 1Gi -> 2Gi (req 512Mi
# -> 1Gi) on 2026-05-25 — Edge had 51 OOMKills in 5d on the
# original 1Gi cap (~1 OOM every 2.4h), and Chrome at maxSessions=2
# was running 684Mi idle on the same cap. Matches the Firefox node's
# tested-stable 2Gi limit. CPU unchanged.
resources:
limits:
cpu: '1'
memory: 2Gi
requests:
cpu: 500m
memory: 1Gi
volumeMounts:
- mountPath: /dev/shm
name: dshm
volumes:
- emptyDir:
medium: Memory
sizeLimit: 2Gi
name: dshm
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: selenium-hub
namespace: selenium
spec:
entryPoints:
- websecure
routes:
- kind: Rule
match: Host(`selenium.iamworkin.lan`)
services:
- name: selenium-hub
port: 4444
tls:
secretName: selenium-tls

View File

@@ -387,6 +387,38 @@ public sealed class FleetManifestLintTests
violations.Should().BeEmpty(); violations.Should().BeEmpty();
} }
[Fact]
public void RemoteDesktopPoolCrds_MustExplicitlyOptInHookReadyTemplates()
{
var expectedModes = new Dictionary<string, string?>(StringComparer.Ordinal)
{
["browser-only"] = null,
["opensuse-xfce"] = "LateAttach",
["dev-workstation"] = "LateAttach",
["ai-station"] = "LateAttach",
["linux-xfce"] = "LateAttach",
["linux-xfce-rdp"] = "LateAttach",
};
var pools = Inventory.Documents
.Where(document => document.Kind == "RemoteDesktopPoolCrd")
.Where(document => document.RelativePath == "fc-desktop/remotedesktop-pools.yaml")
.ToDictionary(
document => document.Scalar("spec", "templateSlug") ?? string.Empty,
StringComparer.Ordinal);
pools.Keys.Should().BeEquivalentTo(expectedModes.Keys);
foreach (var expected in expectedModes)
{
var pool = pools[expected.Key];
pool.Namespace.Should().Be("fc-desktop");
pool.Scalar("spec", "desiredSize").Should().Be("1");
pool.Scalar("spec", "enabled").Should().Be("true");
pool.Scalar("spec", "reconcileNow").Should().Be("true");
pool.Scalar("spec", "userVolumeMode").Should().Be(expected.Value);
}
}
[Fact] [Fact]
public void PublicEgressDeployments_MustOptOutOfIamworkinLanSearchSuffixes() public void PublicEgressDeployments_MustOptOutOfIamworkinLanSearchSuffixes()
{ {