Compare commits

..

40 Commits

Author SHA1 Message Date
Andrew Stoltz
0ed9b989fa monitoring: mirror Sprint 57 coverage rules 2026-06-03 22:46:33 -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
Andrew Stoltz
67d67ab73d fix(monitoring): repoint pirelay scrape to signalcontrol 2026-06-03 20:20:36 -05:00
Andrew Stoltz
f7d41cdc60 revert: drop fc-library manifest — Library.Web already deployed live (41h)
Library.Web is already running + serving at library.iamworkin.lan (root=200,
healthz=200), deployed manually 41h ago (image fc-library-web:v20260602-...,
PVC library-web-data holding the live SQLite DB). My from-scratch manifest used
a different PVC name (library-data) which ArgoCD would attach as a fresh empty
volume, orphaning the live DB. Adopting the live deploy into GitOps is a
separate careful task. Not disturbing a working deployment.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-03 19:30:23 -05:00
Andrew Stoltz
2c0afc28e4 deploy(fc-library): add Library.Web internal-host deployment
From-scratch .Web deploy at library.iamworkin.lan (operator-authorized 2026-06-03).
Cloned from the worldbuilder pattern: Deployment + Service + Longhorn RWO PVC +
step-ca cert + Traefik IngressRoute. SQLite at /data/library.db, no OIDC, both
/health + /healthz probes. Image localhost/fc-library:v202606031925 imported to
both RKE2 nodes. DNS library.iamworkin.lan -> 10.0.56.200 already in pfSense.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-03 19:28:22 -05:00
Robot
ba5f5dd0fb deploy(knowledge): roll audit backfill fix 2026-06-03 18:24:22 -05:00
Robot
dc699da7b3 fix(knowledge): persist federation database on PVC 2026-06-03 18:17:31 -05:00
Robot
1e8bf54c6e deploy: roll Chat and Knowledge OIDC images 2026-06-03 18:13:09 -05:00
Andrew Stoltz
e2e93d482c Deploy TtsReader schema repair image
Co-Authored-By: Codex <codex@openai.com>
2026-06-02 22:00:15 -05:00
4319cc2b51 Merge PR #32: divoom pi deploy artifact manifests
Lands Divoom-as-DM-device and Divoom-TV Pi HDMI deploy artifacts for Cx-6.
2026-06-03 02:47:36 +00:00
Andrew Stoltz
2bf339ce51 Deploy TtsReader PR29 live proof image
Co-Authored-By: Codex <codex@openai.com>
2026-06-02 21:47:04 -05:00
Andrew Stoltz
5bdedfc5ae divoom: add pi deploy artifact manifests
Add source-controlled Puppet/Hiera contracts for edge2 Divoom-as-DM-device without replacing the live flowercore-divoom systemd deployment.

Add Divoom TV Pi HDMI systemd/Puppet deployment artifacts, LF shell-script guardrails, and focused lint coverage for the additive non-K8s deploy shape.

Co-Authored-By: Codex <codex@openai.com>
2026-06-02 21:45:27 -05:00
Andrew Stoltz
0307ae16ae monitoring(probe): signage/mysql/php blackbox probe / -> /healthz (K8s-target mirror)
Mirrors the live noc1 podman fix + Notes scripts/monitoring/prometheus.yml.
These services enforce OIDC bearer auth (FlowerCore__Auth__Enabled=true), so an
anonymous probe of / returns 401 -> false TraefikServiceDown. All three expose
anonymous /healthz=200. This noc-monitoring.yaml is the forward K8s-migration
target (not live); brings it in sync with the live config.
2026-06-02 01:09:57 -05:00
Andrew Stoltz
6c18f69cf2 mail: remove cert-manager Certificate (manage mail-tls via step-ca JWK + noc1 renew timer)
step-ca-acme only has an HTTP-01 (Traefik) solver, but mail.iamworkin.lan must resolve
to the dedicated MetalLB IP 10.0.56.202 (SMTP/IMAP), so HTTP-01 cannot validate (order
stuck pending since 2026-05-06; cert expired 2026-05-24). mail-tls is now issued from
step-ca's JWK 'admin' provisioner and auto-renewed by a systemd timer on noc1 that writes
the mail-tls secret directly. The secret + Deployment mount + webmail IngressRoute are
unchanged. Re-add a Certificate only if a DNS-01 solver is deployed for step-ca-acme.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-01 15:55:38 -05:00
Andrew Stoltz
47e2256556 Deploy TtsReader correction bridge images 2026-05-31 12:35:45 -05:00
Andrew Stoltz
9d77f8ba0e fc-updater: disable loki audit sink 2026-05-31 11:34:12 -05:00
Andrew Stoltz
2f4be19c85 fc-updater: bump signing diagnostics image 2026-05-31 00:32:48 -05:00
Andrew Stoltz
2a62c40990 fc-updater: bump image to MSI installer surface 2026-05-30 23:31:48 -05:00
Andrew Stoltz
7be98e5efc Bump UpdateCenter image to hosted-service fix 2026-05-30 20:22:13 -05:00
Andrew Stoltz
a65b356c9d deploy(fc-updater): roll UC to v202605301823-a6c3354 (Phase 3 SQLite fixes)
Durable image bump for FlowerCore.Updater main a6c3354 (PRs #63-#66): hosted-service
+ request-path SQLite DateTimeOffset fixes, StopHost restored + per-tick resilience,
Shared.Settings 1.0.1. Image built + imported to rke2-server. Un-degrades the Phase-9
provenance verifier + settings poll (were stopped under the removed global Ignore mask).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-30 18:27:45 -05:00
Andrew Stoltz
08c17ef1b4 fc-updater: bump to v202605301703-296f350-fix2 (BackgroundServiceExceptionBehavior=Ignore so a hosted-service SQLite query crash can't stop the host)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-30 17:04:54 -05:00
Andrew Stoltz
06f2f002b7 fc-updater: bump image to v202605301657-296f350-fix1 (Shared.Settings SQLite poll fix)
The v202605301642-296f350-rework image crash-looped: FlowerCore.Shared.Settings SettingsDbPollHostedService
ran a DateTimeOffset Where/OrderBy on SettingsRecordChanges that SQLite can't
translate, and as a BackgroundService it stopped the host. Shared.Settings 1.0.1
materializes the change-log then filters/orders in memory; Updater Web bumped to 1.0.1.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-30 16:59:37 -05:00
Andrew Stoltz
7ac4a8b4b7 fc-updater: bump image to v202605301642-296f350-rework (ADR-179 rework live)
Deploy the current FlowerCore.Updater main (PRs #52-#61) to prod: MSI-first
packaging, beta gating + per-install tokens, interactive+bearer Authentik OIDC,
native installer apply, and the .fcsetup.exe retirement (DropReleaseInstallers
migration runs on the now-empty DB). Image pre-imported to rke2-server + agent1.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-30 16:47:28 -05:00
Andrew Stoltz
90f2a86819 ops: trim load for degraded 2-node cluster (agent2 PSU dead)
Scale all github-runner deployments to 1 replica and halt the ci1
KubeVirt VM. With agent2 down (failed PSU) the cluster runs on two
passively-cooled NUCs; the ci1 8-vCPU VM drove agent1 to ~100C. Keep
total load trimmed until replacement hardware is in place.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-28 13:47:13 -05:00
Andrew Stoltz
cbdefb2b23 Revert "ci1: expose WinRM/RDP/SSH ports on masquerade interface for Phase 2 bootstrap"
The port additions caused the new VMI to stick at phase=Scheduled with
reason=GuestNotRunning. The guest-console-log sidecar exited 1 and
qemu never started. Reverting to the working 9-day-stable shape until
the port-add path is verified in a non-production VM.

Phase 2 (Windows runner install + registration) needs an operator-
interactive virtctl-vnc session against the rebuilt VM, OR a separate
investigation of why this port-add tipped over the VM.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 11:35:10 -05:00
Andrew Stoltz
1c36fe3a0a ci1: expose WinRM/RDP/SSH ports on masquerade interface for Phase 2 bootstrap
The Phase 1 VM has been Running for 9 days but Phase 2 (Puppet bootstrap +
runner registration) was deferred because the operator-interactive
virtctl-vnc path was the only way in. The masquerade interface listed
no exposed ports, so virtctl ssh and kubectl port-forward both hit
'no route to host' — qemu user-mode NAT does not forward inbound by
default.

Adding 5985 (WinRM HTTP) lets a kubectl port-forward + PowerShell
remoting path drive runner registration entirely from outside the VM.
3389 + 22 are reserved for desktop access via Guacamole or virtctl ssh
once OpenSSH Server is installed.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 11:24:34 -05:00
Andrew Stoltz
2b420ce8a4 runners: fleet-wide right-size CPU requests from 500m to 100m
All 33 runner Deployments now request 100m CPU instead of 500m,
freeing roughly 50 idle pods × 400m = ~20 cores back to the cluster.
Observed CPU usage on idle runners is ~1m via kubectl top; the 500m
request was a 500× over-provision that was eating allocatable CPU
and blocking new workload scheduling — WorldBuilder runner could not
be scheduled even at the new 100m request because the pre-existing
fleet held the cluster at 99% requested.

Burst headroom preserved by limits.cpu: 2000m unchanged. TtsReader
keeps its 8Gi memory limit from the 2026-05-25 OOMKill fix; only
the CPU request line moves.

Recreate strategy on each deployment means a brief offline window
per runner during rollout; in-flight CI jobs complete on the
existing container before the new spec takes effect.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 10:09:24 -05:00
Andrew Stoltz
5cbc1a06b1 runners: scale DM/AiStation.Linux/WorldBuilder down to 1 replica until cluster relieved
After cutting requests to 100m, 4 of 6 new pods scheduled and 2 stayed
Pending — cluster CPU REQUEST utilization is 49.6 of 48 allocatable cores
because the existing fleet of ~50 idle runners reserves 25.6 cores
(500m × ~50) for ~50m actual use. Single-replica per new repo gets the
service online without competing with in-flight CI from the rest of the
fleet.

When the broader fleet-wide request right-sizing pass lands
(500m → 100m on all idle runners would free ~20 cores), these can be
bumped back to 2 replicas if PR-CI backlog warrants it.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 10:03:30 -05:00
Andrew Stoltz
9e7ee39b3a runners: drop CPU request 500m→100m on DM/AiStation.Linux/WorldBuilder
All 3 fleet nodes were at 99% CPU REQUEST allocation; the 6 new pods
from the previous commit (3 deployments × 2 replicas × 500m) couldn't
schedule. Idle runners actually use ~1m CPU per `kubectl top pods`;
the 500m request was significantly over-provisioned. Burst headroom
preserved by limits.cpu: 2000m unchanged.

Follow-up: similar request right-sizing pass across the rest of the
runner fleet is queued for a future morning-routine sweep — 25 cores
reserved for ~50m actual use is a large slack we can reclaim cluster-
wide.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 10:00:23 -05:00
Andrew Stoltz
ae030a5f33 runners: add github-runner Deployments for DeviceManagement + AiStation.Linux + WorldBuilder
Morning-routine 2026-05-26 — these three repos had ZERO online Linux PR-CI
capacity, blocking the Sprint 37 Cx-1 Linux-CI-migration PRs (DM #20/#21/
#22, AiStation.Linux #13, WorldBuilder #3/#4). Chicken-and-egg: the
migration PRs need Linux runners that the migration creates.

Each Deployment uses the same canonical emptyDir-only pattern as the
fresh-2026-05-26 updater deployment that lives just above:
  - replicas: 2 (room for parallel PR-CI without head-of-line blocking)
  - per-pod emptyDir caches (no RWO PVC contention)
  - shared github-runner-token secret (existing ACCESS_TOKEN PAT has
    org-wide read access)
  - LABELS: self-hosted,linux,fc-build-linux
  - DOTNET_INSTALL_DIR pinned per ADR-170 family

For AiStation.Linux specifically: Linux job will now pick up; the
Windows job in #13 remains queued indefinitely until the Windows runner
host substrate lands per Sprint 36 v2 Cl-2 / ADR-174 — that's a separate
arc, not this PR.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 09:55:31 -05:00
bc8c35896f tests: add bluejay-ws runner-exclusion lint + fix 3 stale runner-fleet assertions (#30)
BLUEJAY-WS must never be a fleet GHA runner (operator directive 2026-05-26). Build-side analog of Sprint 9 safe-account exclusion. Also fixes 3 stale runner-fleet assertions broken by initContainer addition + replica tuning.
2026-05-26 03:42:01 +00:00
Andrew Stoltz
2cc91b6df0 runners: bump tts-reader memory limit 4Gi -> 8Gi
The github-runner-tts-reader pod was being OOMKilled (exit 137)
mid-`dotnet test` on the TtsReader 1000+ test suite. PR #21 CI
(the Windows -> Linux runner migration) flapped twice with the
"self-hosted runner lost communication" annotation before the
K8s-side symptoms surfaced via kubectl describe pod.

Requests bumped 1Gi -> 2Gi, limits 4Gi -> 8Gi. Comment added
inline so future fleet runs don't trip the same wall.

Unblocks PR #21 + the 9 other open TtsReader PRs that all rebase
through it.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 22:31:48 -05:00
0d2090fe81 runners: add github-runner-updater Deployment (#29)
Close runner-fleet gap for FlowerCore.Updater. Matches Sprint 32 long-tail pattern; registers entry in fleet-lint required-set.
2026-05-26 03:24:13 +00:00
Andrew Stoltz
bc3548e715 runners: add github-runner-pimanager Deployment
FlowerCore.PiManager build run 26417714843 sat queued 5h with zero
self-hosted runners registered to the repo. PiManager was missed in
the Sprint 32 long-tail sweep — every other FC repo got a dedicated
repo-scoped Deployment with its own ACCESS_TOKEN registration, but
PiManager fell through the cracks.

Adds a 2-replica ephemeral runner Deployment matching the Signage /
DMS / Print.Web pattern (per-pod emptyDir caches, no shared PVC,
labels `self-hosted,linux,fc-build-linux`, shared github-runner-token
PAT). Once ArgoCD syncs, the queued job will pick up automatically.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 20:33:44 -05:00
74333cc26b selenium: right-size hub + chrome + edge memory limits (#28) 2026-05-26 01:12:15 +00:00
Andrew Stoltz
7310fb88c2 selenium: right-size hub + chrome + edge memory limits
Edge node has been OOMKilled 51 times in 5 days (~1 every 2.4h) on a
1Gi memory limit. Chrome runs maxSessions=2 on the same 1Gi cap and
was idling at 684Mi — first concurrent session pushing the node to
~900Mi+ would be the next OOM. Hub was running at 766Mi against a 1Gi
limit (75%); no recent restarts but no headroom either.

Firefox node has been running at 2Gi memory limit for 9 days with
zero restarts — that is the right size for a Selenium 4.27 browser
node under our session profile (screen recording sidecar + 1080p
rendering + page captures). Match it.

Changes:
- Hub:    limit 1Gi -> 1.5Gi, request 512Mi -> 1Gi
- Chrome: limit 1Gi -> 2Gi,   request 512Mi -> 1Gi
- Edge:   limit 1Gi -> 2Gi,   request 512Mi -> 1Gi

CPU left alone on all three — observed utilization is well under the
existing limits (hub 54m / 500m, chrome 185m / 1, edge 11m / 1).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 20:11:41 -05:00
148bc87b9a runners: bake step-ca root CA into image (v20260525-stepca) (#27) 2026-05-26 01:04:14 +00:00
Andrew Stoltz
2a1e842100 runners: bake step-ca root CA into image (v20260525-stepca)
Without the IAmWorkin step-ca root CA in the runner image's system
trust store, .NET HttpClient calls from CI tests against
`*.iamworkin.lan` (e.g. `https://selenium.iamworkin.lan/session`) fail
with `The remote certificate is invalid because of errors in the
certificate chain: PartialChain`. FlowerCore.Print.Web's
`WebScreenshotService` unit tests hit this on every build.

Drop the step-ca root PEM into `/usr/local/share/ca-certificates/`,
run `update-ca-certificates` once during apt install, and let OpenSSL +
.NET-on-Linux read the regenerated `/etc/ssl/certs/ca-certificates.crt`
automatically — no `SSL_CERT_FILE` env var, no per-Deployment volume
mount.

Image rebuilt + saved + imported on all 3 schedulable RKE2 nodes
(rke2-server, rke2-agent1, rke2-agent2) before this PR — verified with
`ctr images list -q | grep stepca` on each node.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 19:55:38 -05:00
bc28430d24 selenium: allow github-runner namespace ingress on 4444 (#26) 2026-05-26 00:44:23 +00:00
35 changed files with 2731 additions and 152 deletions

4
.gitattributes vendored Normal file
View File

@@ -0,0 +1,4 @@
/.gitattributes text eol=lf
*.yaml text eol=lf
*.yml text eol=lf
*.sh text eol=lf

View File

@@ -116,6 +116,16 @@ dotnet test tests/bluejay-infra-lint/BluejayInfraLint.Tests.csproj -c Release
That test project sweeps `bluejay-infra/apps/**` plus the canonical sibling `FlowerCore.*\\k8s` manifests that share the same workspace. Matching `conftest.dev` policy files live under `tests/bluejay-infra-lint/conftest.dev/` for environments that also have `conftest` or `opa`. That test project sweeps `bluejay-infra/apps/**` plus the canonical sibling `FlowerCore.*\\k8s` manifests that share the same workspace. Matching `conftest.dev` policy files live under `tests/bluejay-infra-lint/conftest.dev/` for environments that also have `conftest` or `opa`.
## Non-K8s Pi Artifacts
Some `apps/*` directories are deployment artifact bundles consumed by Puppet
instead of Kubernetes workloads. `apps/fc-signage-pi-player/` carries the
Chromium signage Pi player, `apps/fc-divoom-dm-pi-device/` carries the additive
edge2 Divoom-as-DeviceManagement-device profile/Hiera contract, and
`apps/fc-divoom-tv-pi/` carries the Divoom TV Pi HDMI systemd/Puppet shape.
These bundles intentionally avoid Deployment, IngressRoute, Certificate, and
OnePasswordItem resources.
## References ## References
- OpenVox noc1 durability runbook: `docs/runbooks/openvoxserver-quadlet-durability.md` - OpenVox noc1 durability runbook: `docs/runbooks/openvoxserver-quadlet-durability.md`

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

@@ -1,5 +1,206 @@
# FlowerCore Chat — TLS + Ingress # FlowerCore Chat
# Deployment and Service managed by deploy script (not ArgoCD) #
# ArgoCD-managed workload plus TLS/Ingress. The chat-web-secret remains an
# out-of-band Secret until the values are moved into a 1Password-backed item;
# the Deployment references it as optional so GitOps can own the workload
# without storing secret material in this repo.
---
apiVersion: v1
kind: Namespace
metadata:
name: fc-chat
labels:
app.kubernetes.io/part-of: flowercore
---
apiVersion: v1
kind: ConfigMap
metadata:
name: chat-web-config
namespace: fc-chat
labels:
app.kubernetes.io/name: chat-web
app.kubernetes.io/part-of: flowercore
data:
ASPNETCORE_ENVIRONMENT: Production
ASPNETCORE_URLS: "http://+:8080"
ASPNETCORE_FORWARDEDHEADERS_ENABLED: "true"
FlowerCore__Auth__Enabled: "false"
FlowerCore__Auth__Oidc__Enabled: "true"
FlowerCore__Auth__Oidc__Authority: "https://id.iamworkin.lan/application/o/chat/"
FlowerCore__Auth__Oidc__Audience: "chat"
FlowerCore__Auth__Oidc__ClientId: "chat"
FlowerCore__Database__ConnectionStrings__Sqlite: "Data Source=/data/chat.db"
# Ollama target. Switched 2026-04-25 from edge1 Pi5 (10.0.57.17) to BLUEJAY-WS
# workstation (10.0.56.20, RX 9070 XT 16GB, OLLAMA_HOST=0.0.0.0:11434, Vulkan
# backend per feedback_rdna4_vulkan_broken). The Pi5 was timing out every team-
# round speaker at the 300s per-turn cap (live-proven 2026-04-25 03:53 UTC,
# see feedback_chat_team_round_edge1_too_slow). Workstation has gemma3:4b for
# the Cheap tier, plus gemma3:27b/phi4:14b/qwen3:14b for Default/Balanced/Deep.
# Piper TTS stays on edge1 below (different service, Pi handles TTS fine).
FlowerCore__AI__OllamaBaseUrl: "http://10.0.56.20:11434"
FlowerCore__AI__DefaultModelName: "phi4:14b"
ChatOptions__BehaviorRuleEngine__OllamaBaseUrl: "http://10.0.56.20:11434"
ChatOptions__BehaviorRuleEngine__FallbackOllamaBaseUrl: "http://10.0.57.17:11434"
ChatOptions__BehaviorRuleEngine__ModelName: "gemma3:12b"
FlowerCore__AI__Memory__UseSharedIndexingAdapter: "true"
FlowerCore__AI__Memory__UseOllamaEmbeddings: "true"
FlowerCore__AI__Memory__EmbeddingModel: "nomic-embed-text"
FlowerCore__AI__Memory__EnableSharedIndexingBackfill: "true"
FlowerCore__AI__Memory__SharedIndexingDatabasePath: "/data/chat-memory-index.db"
FlowerCore__AI__Skills__Library__LibraryApiUrl: "http://library-web.fc-library.svc.cluster.local"
FlowerCore__AI__Skills__Retail__RetailApiUrl: "http://retail-web.fc-retail.svc.cluster.local"
FlowerCore__AI__Skills__Intranet__IntranetBaseUrl: "http://intranet-web.intranet.svc.cluster.local"
FlowerCore__AI__Skills__Print__PrintMcpBaseUrl: "http://10.0.57.16:5200"
FlowerCore__AI__IrcBridge__Enabled: "true"
FlowerCore__AI__IrcBridge__DefaultProfileSlug: "it-helpdesk"
FlowerCore__AI__IrcBridge__MentionProfileSlug: "it-helpdesk"
FlowerCore__AI__IrcBridge__MentionReactiveMode: "mentions-only"
FlowerCore__AI__IrcBridge__AllowActionExecution: "false"
FlowerCore__AI__Voice__Piper__Host: "10.0.57.17"
FlowerCore__AI__Voice__Piper__Port: "10400"
FlowerCore__AI__Voice__OutputRoot: "/data/audio"
FlowerCore__AI__Voice__RetentionDays: "30"
# LLM provider abstraction (ADR-088). Anthropic stays disabled here -- when
# an operator wants to enable Claude, they flip Enabled=true and mount
# FlowerCore__Anthropic__ApiKey from the onepassword-synced Secret (see
# docs/ai-agents/anthropic-integration.md).
FlowerCore__Anthropic__Enabled: "false"
FlowerCore__Anthropic__BaseUrl: "https://api.anthropic.com"
FlowerCore__Anthropic__DefaultModel: "claude-sonnet-4-6"
FlowerCore__Anthropic__CheapModel: "claude-haiku-4-5-20251001"
FlowerCore__Anthropic__DeepModel: "claude-opus-4-7"
FlowerCore__Budget__ResponseCacheEnabled: "true"
OTEL_SERVICE_NAME: FlowerCore.Chat
OTEL_EXPORTER_OTLP_ENDPOINT: "http://otel-collector.monitoring.svc.cluster.local:4317"
OTEL_EXPORTER_OTLP_PROTOCOL: grpc
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: chat-web-data
namespace: fc-chat
labels:
app.kubernetes.io/name: chat-web
app.kubernetes.io/part-of: flowercore
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
volumeMode: Filesystem
resources:
requests:
storage: 1Gi
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: chat-web
namespace: fc-chat
labels:
app.kubernetes.io/name: chat-web
app.kubernetes.io/part-of: flowercore
spec:
replicas: 1
strategy:
type: Recreate
selector:
matchLabels:
app.kubernetes.io/name: chat-web
template:
metadata:
labels:
app.kubernetes.io/name: chat-web
app.kubernetes.io/part-of: flowercore
annotations:
prometheus.io/scrape: "true"
prometheus.io/port: "8080"
prometheus.io/path: "/metrics/prometheus"
spec:
nodeSelector:
kubernetes.io/hostname: rke2-server
securityContext:
fsGroup: 1654
fsGroupChangePolicy: OnRootMismatch
containers:
- name: chat-web
image: localhost/fc-chat-web:v20260603-oidc-authentik
imagePullPolicy: Never
ports:
- name: http
containerPort: 8080
envFrom:
- configMapRef:
name: chat-web-config
- secretRef:
name: chat-web-secret
optional: true
env:
- name: FlowerCore__Auth__Oidc__Authority
valueFrom:
secretKeyRef:
name: chat-oidc-client
key: issuer_url
optional: true
- name: FlowerCore__Auth__Oidc__ClientId
valueFrom:
secretKeyRef:
name: chat-oidc-client
key: client_id
optional: true
- name: FlowerCore__Auth__Oidc__ClientSecret
valueFrom:
secretKeyRef:
name: chat-oidc-client
key: client_secret
optional: true
volumeMounts:
- name: data
mountPath: /data
resources:
requests:
memory: "128Mi"
cpu: "100m"
limits:
memory: "512Mi"
cpu: "500m"
readinessProbe:
httpGet:
path: /healthz
port: 8080
initialDelaySeconds: 10
periodSeconds: 10
timeoutSeconds: 5
failureThreshold: 6
livenessProbe:
httpGet:
path: /healthz
port: 8080
initialDelaySeconds: 30
periodSeconds: 30
timeoutSeconds: 5
failureThreshold: 3
volumes:
- name: data
persistentVolumeClaim:
claimName: chat-web-data
---
apiVersion: v1
kind: Service
metadata:
name: chat-web
namespace: fc-chat
labels:
app.kubernetes.io/name: chat-web
app.kubernetes.io/part-of: flowercore
spec:
type: ClusterIP
selector:
app.kubernetes.io/name: chat-web
ports:
- name: http
port: 80
targetPort: 8080
protocol: TCP
--- ---
apiVersion: cert-manager.io/v1 apiVersion: cert-manager.io/v1
kind: Certificate kind: Certificate

View File

@@ -0,0 +1,45 @@
# FlowerCore Divoom DM Pi Device
Source-controlled Puppet/Hiera deployment contract for registering the edge2
Divoom MiniToo panel as a FlowerCore DeviceManagement-managed Pi device.
This is not a Kubernetes application. The live panel remains the existing
edge2 `flowercore-divoom.service` managed by `FlowerCore.Puppet`
`profile::pi::service::divoom`, with the .NET payload deployed out of band
and `/opt/flowercore/divoom/data` plus the Bluetooth shell wrappers preserved.
Because edge2 is already Hiera-driven through `profile::pi::service::apps`,
the deploy home is additive `profile::pi::service` data/profile source, not
`profile::edge::service::apps` and not an ArgoCD/K8s app.
## Scope
- Stage DeviceManagement registration metadata for the edge2 Divoom MiniToo.
- Stage a separate, disabled-by-default DM Agent executor unit for privileged
Bluetooth operations once the DM-RPC lane lands.
- Keep `flowercore-divoom.service` and `flowercore-divoom-bt.service`
untouched: no service replacement, no restart subscription, no K8s surface.
- Preserve the current wrapper contract:
`/opt/flowercore/divoom/bt-link.sh`,
`/opt/flowercore/divoom/bt-reset.sh`, and
`/opt/flowercore/divoom/audio-link.sh`.
- Keep FM radio disabled and require visible render proof; device-info echo is
not render proof.
## Artifact Map
| Path | Use |
| --- | --- |
| `hiera/edge2-divoom-dm-device.overlay.yaml` | Additive Hiera overlay for edge2. Merge into the existing node YAML without removing `fc-pimanager` or `fc-divoom`. |
| `puppet/profile/pi/service/divoom_dm_device.pp` | Puppet profile shape to vendor into `FlowerCore.Puppet` after the DM-RPC executor binary exists. |
| `puppet/templates/divoom-device-registration.json.epp` | DM device registration metadata rendered on edge2. |
| `puppet/templates/flowercore-divoom-dm-agent.service.epp` | Separate DM Agent systemd unit. Defaults are stopped and disabled until a later cutover. |
## Rollout Notes
1. Land these artifacts in bluejay-infra as the deploy contract.
2. Vendor the Puppet profile and EPP templates into `FlowerCore.Puppet`.
3. Merge the Hiera overlay into `data/nodes/edge2.iamworkin.lan.yaml`.
4. Run Puppet in noop first, preferably with a node-local validation directory
under `~/.fcv` rather than `/tmp`.
5. Only enable the DM Agent service after the DeviceManagement BT executor has
landed and passed operator-eyeball render proof.

View File

@@ -0,0 +1,32 @@
---
# Merge into FlowerCore.Puppet data/nodes/edge2.iamworkin.lan.yaml.
# Additive overlay only: keep the existing fc-pimanager version/tarball entry,
# keep fc-divoom enabled, and do not move Divoom into Kubernetes.
profile::pi::service::apps:
fc-pimanager:
binary: 'FlowerCore.PiManager.Web'
install_dir: '/opt/fc-pimanager'
port: 5000
environment: 'edge2'
version: '2026.05.28.1646'
tarball_source: 'puppet:///modules/profile/pi/builds/fc-pimanager.tar.gz'
fc-divoom:
enabled: true
profile::pi::service::divoom_dm_device::ensure: 'present'
profile::pi::service::divoom_dm_device::service_enabled: false
profile::pi::service::divoom_dm_device::service_ensure: 'stopped'
profile::pi::service::divoom_dm_device::device_id: 'edge2-divoom-minitoo'
profile::pi::service::divoom_dm_device::display_name: 'edge2 Divoom MiniToo'
profile::pi::service::divoom_dm_device::host_fqdn: 'edge2.iamworkin.lan'
profile::pi::service::divoom_dm_device::dm_web_url: 'https://devicemgmt.iamworkin.lan'
profile::pi::service::divoom_dm_device::divoom_install_dir: '/opt/flowercore/divoom'
profile::pi::service::divoom_dm_device::agent_install_dir: '/opt/flowercore/devicemanagement-agent'
profile::pi::service::divoom_dm_device::bt_candidate_channels:
- '1'
- '10'
profile::pi::service::divoom_dm_device::default_bt_channel: '1'
profile::pi::service::divoom_dm_device::a2dp_default_state: 'off'
profile::pi::service::divoom_dm_device::fm_radio_enabled: false
profile::pi::service::divoom_dm_device::visible_render_proof_required: true

View File

@@ -0,0 +1,140 @@
# Drop into FlowerCore.Puppet site-modules/profile/manifests/pi/service/divoom_dm_device.pp.
# This profile is additive to profile::pi::service::divoom. It must not manage,
# restart, replace, or subscribe the existing flowercore-divoom.service.
class profile::pi::service::divoom_dm_device (
Enum['present', 'absent'] $ensure = 'present',
Boolean $service_enabled = false,
Enum['running', 'stopped'] $service_ensure = 'stopped',
String $service_name = 'flowercore-divoom-dm-agent',
String $device_id = 'edge2-divoom-minitoo',
String $display_name = 'edge2 Divoom MiniToo',
String $host_fqdn = 'edge2.iamworkin.lan',
String $dm_web_url = 'https://devicemgmt.iamworkin.lan',
String $divoom_install_dir = '/opt/flowercore/divoom',
String $agent_install_dir = '/opt/flowercore/devicemanagement-agent',
String $agent_binary = 'FlowerCore.DeviceManagement.Agent',
Array[String] $bt_candidate_channels = ['1', '10'],
String $default_bt_channel = '1',
Enum['on', 'off'] $a2dp_default_state = 'off',
Boolean $fm_radio_enabled = false,
Boolean $visible_render_proof_required = true,
) {
include profile::workstation::safe_account_exclusion
$safe_account = $profile::workstation::safe_account_exclusion::safe_account
$config_dir = '/etc/flowercore/device-management/devices'
$state_dir = '/var/lib/flowercore/divoom-dm-agent'
$log_dir = '/var/log/flowercore/divoom-dm-agent'
$registration_path = "${config_dir}/${device_id}.json"
$agent_binary_path = "${agent_install_dir}/${agent_binary}"
$bt_channels_json = inline_template('[<%= @bt_candidate_channels.map { |c| "\"#{c}\"" }.join(", ") %>]')
if $safe_account {
notify { 'fc-divoom-dm-device safe-account exclusion':
message => 'SAFE-ACCOUNT-EXCLUSION: Divoom DM Pi device profile refused to apply on operator workstation',
}
if $facts['os']['family'] != 'windows' {
ensure_resource('file', '/var/log/flowercore-audit', {
'ensure' => 'directory',
'owner' => 'root',
'group' => 'root',
'mode' => '0755',
})
file { '/var/log/flowercore-audit/safe-account-noop-fc-divoom-dm-device.log':
ensure => file,
owner => 'root',
group => 'root',
mode => '0644',
content => "noop: divoom dm pi device profile refused to apply on safe-account host\n",
require => File['/var/log/flowercore-audit'],
}
}
} elsif $ensure == 'absent' {
service { $service_name:
ensure => stopped,
enable => false,
}
file { [
"/etc/systemd/system/${service_name}.service",
$registration_path,
]:
ensure => absent,
}
exec { 'fc-divoom-dm-agent-systemd-reload':
command => '/usr/bin/systemctl daemon-reload',
refreshonly => true,
path => ['/usr/bin', '/bin'],
}
} else {
case $facts['os']['family'] {
'Debian': {}
default: { fail("profile::pi::service::divoom_dm_device only supports Debian-family OS, got ${facts['os']['family']}") }
}
file { [$config_dir, $state_dir, $log_dir]:
ensure => directory,
owner => 'root',
group => 'root',
mode => '0755',
}
file { $registration_path:
ensure => file,
owner => 'root',
group => 'root',
mode => '0644',
content => epp('profile/pi/fc_divoom_dm/divoom-device-registration.json.epp', {
'device_id' => $device_id,
'display_name' => $display_name,
'host_fqdn' => $host_fqdn,
'divoom_install_dir' => $divoom_install_dir,
'bt_channels_json' => $bt_channels_json,
'default_bt_channel' => $default_bt_channel,
'a2dp_default_state' => $a2dp_default_state,
'fm_radio_enabled' => $fm_radio_enabled,
'visible_render_proof_required' => $visible_render_proof_required,
}),
require => File[$config_dir],
}
file { "/etc/systemd/system/${service_name}.service":
ensure => file,
owner => 'root',
group => 'root',
mode => '0644',
content => epp('profile/pi/fc_divoom_dm/flowercore-divoom-dm-agent.service.epp', {
'service_name' => $service_name,
'device_id' => $device_id,
'dm_web_url' => $dm_web_url,
'registration_path' => $registration_path,
'divoom_install_dir' => $divoom_install_dir,
'agent_install_dir' => $agent_install_dir,
'agent_binary_path' => $agent_binary_path,
'state_dir' => $state_dir,
'log_dir' => $log_dir,
}),
notify => Exec['fc-divoom-dm-agent-systemd-reload'],
require => File[$registration_path],
}
exec { 'fc-divoom-dm-agent-systemd-reload':
command => '/usr/bin/systemctl daemon-reload',
refreshonly => true,
path => ['/usr/bin', '/bin'],
}
service { $service_name:
ensure => $service_ensure,
enable => $service_enabled,
require => [
File["/etc/systemd/system/${service_name}.service"],
File[$registration_path],
Exec['fc-divoom-dm-agent-systemd-reload'],
],
}
}
}

View File

@@ -0,0 +1,34 @@
{
"deviceId": "<%= $device_id %>",
"displayName": "<%= $display_name %>",
"hostFqdn": "<%= $host_fqdn %>",
"kind": "DivoomMiniToo",
"managedBy": "FlowerCore.DeviceManagement",
"executionMode": "Pi",
"transport": {
"kind": "BluetoothSerial",
"candidateChannels": <%= $bt_channels_json %>,
"defaultChannel": "<%= $default_bt_channel %>",
"deviceInfoIsRenderProof": false,
"visibleRenderProofRequired": <%= $visible_render_proof_required %>
},
"paths": {
"divoomInstallDir": "<%= $divoom_install_dir %>",
"btLink": "<%= $divoom_install_dir %>/bt-link.sh",
"btReset": "<%= $divoom_install_dir %>/bt-reset.sh",
"audioLink": "<%= $divoom_install_dir %>/audio-link.sh"
},
"capabilities": {
"supportsBluetoothSerial": true,
"supportsBtChannelRedetect": true,
"supportsBtHardReset": true,
"supportsBtAudioProfileSwitch": true,
"a2dpDefaultState": "<%= $a2dp_default_state %>",
"fmRadioEnabled": <%= $fm_radio_enabled %>
},
"safety": {
"preserveExistingService": "flowercore-divoom.service",
"preserveDataDirectory": "<%= $divoom_install_dir %>/data",
"doNotEnableFmRadio": true
}
}

View File

@@ -0,0 +1,36 @@
[Unit]
Description=FlowerCore Divoom DM Agent Bluetooth executor
Documentation=https://github.com/astoltz/FlowerCore.Notes/blob/master/docs/standards/divoom-tv-hdmi-multitarget-render-substrate.md
Wants=network-online.target
After=network-online.target bluetooth.service
Requires=bluetooth.service
ConditionPathExists=<%= $agent_binary_path %>
ConditionPathExists=<%= $registration_path %>
ConditionPathExists=<%= $divoom_install_dir %>/bt-link.sh
ConditionPathExists=<%= $divoom_install_dir %>/bt-reset.sh
ConditionPathExists=<%= $divoom_install_dir %>/audio-link.sh
[Service]
Type=simple
User=stoltz
Group=stoltz
WorkingDirectory=<%= $agent_install_dir %>
Environment=DOTNET_CLI_TELEMETRY_OPTOUT=1
Environment=FLOWERCORE_DM_DEVICE_REGISTRATION=<%= $registration_path %>
Environment=Divoom__Bluetooth__DeviceInfoIsRenderProof=false
Environment=Divoom__Bluetooth__VisibleRenderProofRequired=true
Environment=Divoom__Bluetooth__A2dpDefaultState=off
ExecStart=<%= $agent_binary_path %> --mode=Pi --device-id=<%= $device_id %> --dm-web-url=<%= $dm_web_url %> --registration=<%= $registration_path %>
Restart=on-failure
RestartSec=10s
StartLimitBurst=3
StartLimitIntervalSec=300s
SupplementaryGroups=bluetooth audio dialout
NoNewPrivileges=true
PrivateTmp=true
ProtectSystem=strict
ProtectHome=true
ReadWritePaths=<%= $state_dir %> <%= $log_dir %>
[Install]
WantedBy=multi-user.target

View File

@@ -0,0 +1,44 @@
# FlowerCore Divoom TV Pi HDMI
Source-controlled deploy shape for the native `FlowerCore.Divoom.Tv`
Avalonia HDMI renderer on a Raspberry Pi connected to a TV.
This is a Puppet/systemd appliance bundle, not a Kubernetes application. It
mirrors the existing `fc-signage-pi-player` pattern: bluejay-infra carries the
systemd units, scripts, Hiera shape, and Puppet profile source that
`FlowerCore.Puppet` vendors and installs.
## Scope
- Launch the future `FlowerCore.Divoom.Tv` linux-arm64 self-contained payload
from `/opt/flowercore/divoom-tv/FlowerCore.Divoom.Tv`.
- Prefer `cage` as the Wayland fullscreen compositor, with direct app launch as
a fallback for development images.
- Restart the app after HDMI hotplug with a 2 second DRM settle delay.
- Keep all runtime state local: `/var/lib/fc-divoom-tv` and
`/var/log/fc-divoom-tv`.
- Avoid CDN/runtime fetches; the app renders the in-house Divoom scene catalog
locally.
## Artifact Map
| Path | Use |
| --- | --- |
| `systemd/flowercore-divoom-tv.service` | Fullscreen Avalonia HDMI app service. |
| `systemd/flowercore-divoom-tv-hdmi.service` | HDMI hotplug responder service. |
| `systemd/99-flowercore-divoom-tv-hdmi.rules` | DRM udev hotplug rule. |
| `scripts/flowercore-divoom-tv-prelaunch.sh` | Preflight checks and local directory creation. |
| `scripts/flowercore-divoom-tv-launch.sh` | Cage-first fullscreen launcher. |
| `scripts/flowercore-divoom-tv-hdmi-respond.sh` | Hotplug settle and restart script. |
| `puppet/profile/pi/service/divoom_tv.pp` | Puppet profile shape to vendor into `FlowerCore.Puppet`. |
| `hiera/example-divoom-tv-pi.iamworkin.lan.yaml` | Example node Hiera for a Divoom TV Pi. |
## Rollout Notes
1. Build `FlowerCore.Divoom.Tv` with `dotnet.exe publish -c Release -r linux-arm64 --self-contained`.
2. Stage the payload to `/opt/flowercore/divoom-tv/` through the standard noc1
jump path and avoid `/tmp` for unprivileged Pi scratch.
3. Vendor the profile and static files into `FlowerCore.Puppet`.
4. Run Puppet noop, then apply on the target Pi.
5. Prove deployment with `systemctl is-active flowercore-divoom-tv.service`,
journal lines showing frames presented, and a visible HDMI display check.

View File

@@ -0,0 +1,19 @@
---
# Example node data for a dedicated Pi -> HDMI -> TV Divoom renderer.
# Copy into FlowerCore.Puppet data/nodes/<hostname>.iamworkin.lan.yaml only
# after the Pi has a static DHCP/DNS entry and the linux-arm64 payload exists.
facts:
role: pi_prototype
profile::motd::role: 'Divoom TV HDMI Renderer'
profile::pi::service::divoom_tv::ensure: 'present'
profile::pi::service::divoom_tv::service_enabled: true
profile::pi::service::divoom_tv::service_ensure: 'running'
profile::pi::service::divoom_tv::install_dir: '/opt/flowercore/divoom-tv'
profile::pi::service::divoom_tv::state_dir: '/var/lib/fc-divoom-tv'
profile::pi::service::divoom_tv::log_dir: '/var/log/fc-divoom-tv'
profile::pi::service::divoom_tv::presentation_mode: 'PillarboxSquare'
profile::pi::service::divoom_tv::startup_scene: 'bluejay-clock'
profile::pi::service::divoom_tv::reduced_motion: false

View File

@@ -0,0 +1,149 @@
# Drop into FlowerCore.Puppet site-modules/profile/manifests/pi/service/divoom_tv.pp.
# Static files come from profile/pi/fc_divoom_tv/ after this bluejay-infra
# bundle is vendored into the Puppet control repo.
class profile::pi::service::divoom_tv (
Enum['present', 'absent'] $ensure = 'present',
Boolean $service_enabled = false,
Enum['running', 'stopped'] $service_ensure = 'stopped',
String $service_name = 'flowercore-divoom-tv',
String $user = 'fc-divoom-tv',
String $group = 'fc-divoom-tv',
String $install_dir = '/opt/flowercore/divoom-tv',
String $state_dir = '/var/lib/fc-divoom-tv',
String $log_dir = '/var/log/fc-divoom-tv',
String $presentation_mode = 'PillarboxSquare',
String $startup_scene = 'bluejay-clock',
Boolean $reduced_motion = false,
) {
include profile::workstation::safe_account_exclusion
$safe_account = $profile::workstation::safe_account_exclusion::safe_account
if $safe_account {
notify { 'fc-divoom-tv safe-account exclusion':
message => 'SAFE-ACCOUNT-EXCLUSION: Divoom TV Pi profile refused to apply on operator workstation',
}
} elsif $ensure == 'absent' {
service { $service_name:
ensure => stopped,
enable => false,
}
file { [
"/etc/systemd/system/${service_name}.service",
"/etc/systemd/system/${service_name}-hdmi.service",
'/etc/udev/rules.d/99-flowercore-divoom-tv-hdmi.rules',
'/usr/local/bin/flowercore-divoom-tv-prelaunch.sh',
'/usr/local/bin/flowercore-divoom-tv-launch.sh',
'/usr/local/bin/flowercore-divoom-tv-hdmi-respond.sh',
'/etc/flowercore/divoom-tv.env',
]:
ensure => absent,
}
} else {
case $facts['os']['family'] {
'Debian': {}
default: { fail("profile::pi::service::divoom_tv only supports Debian-family OS, got ${facts['os']['family']}") }
}
package { ['cage', 'libgbm1', 'libdrm2', 'libxkbcommon0', 'fonts-dejavu-core']:
ensure => installed,
}
group { $group:
ensure => present,
system => true,
}
user { $user:
ensure => present,
system => true,
gid => $group,
home => $state_dir,
managehome => false,
shell => '/usr/sbin/nologin',
require => Group[$group],
}
file { [$install_dir, $state_dir, $log_dir, '/etc/flowercore']:
ensure => directory,
owner => $user,
group => $group,
mode => '0755',
}
file { '/etc/flowercore/divoom-tv.env':
ensure => file,
owner => 'root',
group => 'root',
mode => '0644',
content => "FC_DIVOOM_TV_PRESENTATION_MODE=${presentation_mode}\nFC_DIVOOM_TV_START_SCENE=${startup_scene}\nFC_DIVOOM_TV_REDUCED_MOTION=${reduced_motion}\n",
require => File['/etc/flowercore'],
}
$script_map = {
'/usr/local/bin/flowercore-divoom-tv-prelaunch.sh' => 'profile/pi/fc_divoom_tv/flowercore-divoom-tv-prelaunch.sh',
'/usr/local/bin/flowercore-divoom-tv-launch.sh' => 'profile/pi/fc_divoom_tv/flowercore-divoom-tv-launch.sh',
'/usr/local/bin/flowercore-divoom-tv-hdmi-respond.sh' => 'profile/pi/fc_divoom_tv/flowercore-divoom-tv-hdmi-respond.sh',
}
$script_map.each |$dest, $src| {
file { $dest:
ensure => file,
owner => 'root',
group => 'root',
mode => '0755',
source => "puppet:///modules/${src}",
}
}
$unit_map = {
"/etc/systemd/system/${service_name}.service" => 'profile/pi/fc_divoom_tv/flowercore-divoom-tv.service',
"/etc/systemd/system/${service_name}-hdmi.service" => 'profile/pi/fc_divoom_tv/flowercore-divoom-tv-hdmi.service',
}
$unit_map.each |$dest, $src| {
file { $dest:
ensure => file,
owner => 'root',
group => 'root',
mode => '0644',
source => "puppet:///modules/${src}",
notify => Exec['fc-divoom-tv-systemd-reload'],
}
}
file { '/etc/udev/rules.d/99-flowercore-divoom-tv-hdmi.rules':
ensure => file,
owner => 'root',
group => 'root',
mode => '0644',
source => 'puppet:///modules/profile/pi/fc_divoom_tv/99-flowercore-divoom-tv-hdmi.rules',
notify => Exec['fc-divoom-tv-udev-reload'],
}
exec { 'fc-divoom-tv-systemd-reload':
command => '/usr/bin/systemctl daemon-reload',
refreshonly => true,
path => ['/usr/bin', '/bin'],
}
exec { 'fc-divoom-tv-udev-reload':
command => '/usr/bin/udevadm control --reload-rules',
refreshonly => true,
path => ['/usr/bin', '/bin'],
}
service { $service_name:
ensure => $service_ensure,
enable => $service_enabled,
require => [
File["/etc/systemd/system/${service_name}.service"],
File['/etc/flowercore/divoom-tv.env'],
File['/usr/local/bin/flowercore-divoom-tv-prelaunch.sh'],
File['/usr/local/bin/flowercore-divoom-tv-launch.sh'],
Exec['fc-divoom-tv-systemd-reload'],
],
}
}
}

View File

@@ -0,0 +1,5 @@
#!/usr/bin/env bash
set -euo pipefail
sleep 2
systemctl restart flowercore-divoom-tv.service

View File

@@ -0,0 +1,25 @@
#!/usr/bin/env bash
set -euo pipefail
APP_BIN="${FC_DIVOOM_TV_BIN:-/opt/flowercore/divoom-tv/FlowerCore.Divoom.Tv}"
STATE_DIR="${FC_DIVOOM_TV_STATE_DIR:-/var/lib/fc-divoom-tv}"
LOG_DIR="${FC_DIVOOM_TV_LOG_DIR:-/var/log/fc-divoom-tv}"
PRESENTATION_MODE="${FC_DIVOOM_TV_PRESENTATION_MODE:-PillarboxSquare}"
START_SCENE="${FC_DIVOOM_TV_START_SCENE:-bluejay-clock}"
REDUCED_MOTION="${FC_DIVOOM_TV_REDUCED_MOTION:-false}"
COMMON_ARGS=(
"--target=hdmi"
"--presentation-mode=${PRESENTATION_MODE}"
"--startup-scene=${START_SCENE}"
"--reduced-motion=${REDUCED_MOTION}"
"--state-dir=${STATE_DIR}"
"--log-dir=${LOG_DIR}"
)
if command -v cage >/dev/null 2>&1; then
exec cage -- "${APP_BIN}" "${COMMON_ARGS[@]}" "$@"
fi
echo "[$(date -Is)] cage not found; launching FlowerCore.Divoom.Tv directly" >&2
exec "${APP_BIN}" "${COMMON_ARGS[@]}" "$@"

View File

@@ -0,0 +1,23 @@
#!/usr/bin/env bash
set -euo pipefail
APP_BIN="${FC_DIVOOM_TV_BIN:-/opt/flowercore/divoom-tv/FlowerCore.Divoom.Tv}"
STATE_DIR="${FC_DIVOOM_TV_STATE_DIR:-/var/lib/fc-divoom-tv}"
LOG_DIR="${FC_DIVOOM_TV_LOG_DIR:-/var/log/fc-divoom-tv}"
mkdir -p "${STATE_DIR}" "${LOG_DIR}"
if [[ ! -x "${APP_BIN}" ]]; then
echo "[$(date -Is)] missing executable ${APP_BIN}" >&2
exit 1
fi
if [[ -d /sys/class/drm ]] && ! find /sys/class/drm -maxdepth 1 -name 'card*-HDMI-A-*' -print -quit | grep -q .; then
echo "[$(date -Is)] no HDMI connector visible yet; continuing so the app can wait for display" >&2
fi
if command -v cage >/dev/null 2>&1; then
echo "[$(date -Is)] cage available for fullscreen Wayland launch"
else
echo "[$(date -Is)] cage not installed; direct launch fallback will be used" >&2
fi

View File

@@ -0,0 +1,2 @@
# Settle DRM for 2s before restarting the fullscreen Avalonia renderer.
SUBSYSTEM=="drm", KERNEL=="card?-HDMI-A-?", ACTION=="change", RUN+="/usr/bin/systemctl start flowercore-divoom-tv-hdmi.service"

View File

@@ -0,0 +1,7 @@
[Unit]
Description=FlowerCore Divoom TV HDMI hotplug responder
DefaultDependencies=no
[Service]
Type=oneshot
ExecStart=/usr/local/bin/flowercore-divoom-tv-hdmi-respond.sh

View File

@@ -0,0 +1,40 @@
[Unit]
Description=FlowerCore Divoom TV HDMI Renderer (Avalonia fullscreen)
Documentation=https://github.com/astoltz/FlowerCore.Notes/blob/master/docs/standards/divoom-tv-hdmi-multitarget-render-substrate.md
Wants=network-online.target
After=network-online.target systemd-user-sessions.service
ConditionPathExists=/opt/flowercore/divoom-tv/FlowerCore.Divoom.Tv
[Service]
Type=simple
User=fc-divoom-tv
Group=fc-divoom-tv
WorkingDirectory=/opt/flowercore/divoom-tv
EnvironmentFile=-/etc/flowercore/divoom-tv.env
Environment=DOTNET_CLI_TELEMETRY_OPTOUT=1
Environment=XDG_RUNTIME_DIR=/run/fc-divoom-tv
RuntimeDirectory=fc-divoom-tv
RuntimeDirectoryMode=0700
ExecStartPre=/usr/local/bin/flowercore-divoom-tv-prelaunch.sh
ExecStart=/usr/local/bin/flowercore-divoom-tv-launch.sh
Restart=always
RestartSec=10s
StartLimitBurst=5
StartLimitIntervalSec=300s
MemoryMax=2G
MemoryHigh=1500M
PrivateTmp=true
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
ReadWritePaths=/var/lib/fc-divoom-tv /var/log/fc-divoom-tv /run/fc-divoom-tv
TTYPath=/dev/tty1
StandardInput=tty
StandardOutput=journal
StandardError=journal
TTYReset=yes
TTYVHangup=yes
TTYVTDisallocate=yes
[Install]
WantedBy=graphical.target

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

@@ -532,7 +532,7 @@ spec:
fsGroupChangePolicy: OnRootMismatch fsGroupChangePolicy: OnRootMismatch
containers: containers:
- name: web - name: web
image: localhost/fc-ttsreader-web:v20260518-sprint36-demo-finish-b132cbf image: localhost/fc-ttsreader-web:v20260603-s54cx14-pr29-schema
imagePullPolicy: Never imagePullPolicy: Never
ports: ports:
- containerPort: 5217 - containerPort: 5217
@@ -554,6 +554,8 @@ spec:
value: "/data/chapter-context.db" value: "/data/chapter-context.db"
- name: TtsReader__Jobs__Root - name: TtsReader__Jobs__Root
value: "/data/jobs" value: "/data/jobs"
- name: TtsReader__Export__LocalCasRoot
value: "/data/bundles/cas"
- name: TtsReader__Piper__Host - name: TtsReader__Piper__Host
value: "10.0.57.17" value: "10.0.57.17"
- name: TtsReader__Piper__Port - name: TtsReader__Piper__Port

View File

@@ -58,7 +58,7 @@ spec:
nodeName: rke2-server nodeName: rke2-server
containers: containers:
- name: web - name: web
image: localhost/fc-updater-web:v20260509-4162dca-authgate image: localhost/fc-updater-web:v202605310029-7974fc4
imagePullPolicy: Never imagePullPolicy: Never
ports: ports:
- containerPort: 8080 - containerPort: 8080
@@ -88,6 +88,8 @@ spec:
value: Faith AI Mike Edition value: Faith AI Mike Edition
- name: FlowerCore__Updater__PublicShares__Links__0__Description - name: FlowerCore__Updater__PublicShares__Links__0__Description
value: Private release link for Mike's Faith AI bundle. value: Private release link for Mike's Faith AI bundle.
- name: FlowerCore__Audit__Sinks__Loki__Enabled
value: "false"
- name: FlowerCore__Updater__Auth__Bootstrap__Enabled - name: FlowerCore__Updater__Auth__Bootstrap__Enabled
value: "true" value: "true"
- name: FlowerCore__Updater__Auth__Bootstrap__Username - name: FlowerCore__Updater__Auth__Bootstrap__Username

View File

@@ -12,6 +12,15 @@ ENV PATH="/home/runner/_tool/Ruby/${RUBY_MINOR}/x64/bin:/opt/runner-toolcache/Ru
USER root USER root
# Bake the IAmWorkin step-ca root CA into the system trust store. Without
# this, .NET HttpClient calls from CI tests against *.iamworkin.lan
# (e.g. https://selenium.iamworkin.lan/session) fail with `PartialChain`
# because the runner image's default Ubuntu trust bundle doesn't include
# our internal Root CA. update-ca-certificates regenerates
# /etc/ssl/certs/ca-certificates.crt, which OpenSSL + .NET on Linux read
# automatically — no SSL_CERT_FILE env var needed.
COPY step-ca-root.crt /usr/local/share/ca-certificates/iamworkin-step-ca-root.crt
RUN apt-get update \ RUN apt-get update \
&& DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \ && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
autoconf \ autoconf \
@@ -31,6 +40,7 @@ RUN apt-get update \
pkg-config \ pkg-config \
uuid-dev \ uuid-dev \
zlib1g-dev \ zlib1g-dev \
&& update-ca-certificates \
&& curl -fsSL "https://github.com/rbenv/ruby-build/archive/refs/tags/${RUBY_BUILD_VERSION}.tar.gz" -o /tmp/ruby-build.tar.gz \ && 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 \ && mkdir -p /tmp/ruby-build \
&& tar -xzf /tmp/ruby-build.tar.gz --strip-components=1 -C /tmp/ruby-build \ && tar -xzf /tmp/ruby-build.tar.gz --strip-components=1 -C /tmp/ruby-build \

View File

@@ -7,7 +7,7 @@ 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:v20260520-ruby3.3.11`, derived from - `localhost/fc-github-runner:v20260525-ruby3.3.11-stepca`, derived from
`myoung34/github-runner:latest` `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`
@@ -40,14 +40,26 @@ still mounts an `emptyDir` over `/home/runner`, so the `setup-runner-home` init
container copies the baked toolcache from `/opt/runner-toolcache/Ruby` into container copies the baked toolcache from `/opt/runner-toolcache/Ruby` into
`/home/runner/_tool/Ruby` before the runner container starts. `/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 ```bash
cd apps/github-runner cd apps/github-runner
podman build -t localhost/fc-github-runner:v20260520-ruby3.3.11 . podman build -t localhost/fc-github-runner:v20260525-ruby3.3.11-stepca .
podman run --rm localhost/fc-github-runner:v20260520-ruby3.3.11 ruby -v podman run --rm localhost/fc-github-runner:v20260525-ruby3.3.11-stepca ruby -v
podman run --rm localhost/fc-github-runner:v20260520-ruby3.3.11 \ podman run --rm localhost/fc-github-runner:v20260525-ruby3.3.11-stepca \
test -f /opt/runner-toolcache/Ruby/3.3/x64.complete test -f /opt/runner-toolcache/Ruby/3.3/x64.complete
podman save localhost/fc-github-runner:v20260520-ruby3.3.11 \ podman save localhost/fc-github-runner:v20260525-ruby3.3.11-stepca \
-o fc-github-runner-v20260520-ruby3.3.11.tar -o fc-github-runner-v20260525-ruby3.3.11-stepca.tar
``` ```
Import the saved image on every schedulable RKE2 node before ArgoCD rolls the Import the saved image on every schedulable RKE2 node before ArgoCD rolls the
@@ -55,9 +67,9 @@ Deployments:
```bash ```bash
for node in rke2-server rke2-agent1 rke2-agent2; do for node in rke2-server rke2-agent1 rke2-agent2; do
scp fc-github-runner-v20260520-ruby3.3.11.tar "$node:/tmp/" scp fc-github-runner-v20260525-ruby3.3.11-stepca.tar "$node:/tmp/"
ssh "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images rm localhost/fc-github-runner:v20260520-ruby3.3.11 || true' ssh "$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 "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images import /tmp/fc-github-runner-v20260520-ruby3.3.11.tar' ssh "$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 done
``` ```

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,12 @@
-----BEGIN CERTIFICATE-----
MIIBxDCCAWqgAwIBAgIRAPY357G6ow6zMAL5+4bS2kkwCgYIKoZIzj0EAwIwQDEa
MBgGA1UEChMRSUFtV29ya2luIEFDTUUgQ0ExIjAgBgNVBAMTGUlBbVdvcmtpbiBB
Q01FIENBIFJvb3QgQ0EwHhcNMjYwMzA4MTgwNzExWhcNMzYwMzA1MTgwNzExWjBA
MRowGAYDVQQKExFJQW1Xb3JraW4gQUNNRSBDQTEiMCAGA1UEAxMZSUFtV29ya2lu
IEFDTUUgQ0EgUm9vdCBDQTBZMBMGByqGSM49AgEGCCqGSM49AwEHA0IABJ2n04X1
JZo5Zdq/i1Idv8+fqwZyAzBh7whbqj0SWsJL8UWRabCMqYCs7+dXO0xRSzqkwFDL
x+vooOai8RgRNhajRTBDMA4GA1UdDwEB/wQEAwIBBjASBgNVHRMBAf8ECDAGAQH/
AgEBMB0GA1UdDgQWBBRnuPPQR6iM/H6vOluiU3Sygayz8jAKBggqhkjOPQQDAgNI
ADBFAiEArQK9dYPGmAZsdYnjziuFVVE5NKZUcceYvGfGC+tLXUsCIAudF2zJrCRq
3mK50ZZET/fwTkJwiEF4824mjP8p1CKM
-----END CERTIFICATE-----

View File

@@ -46,7 +46,7 @@ spec:
spec: spec:
containers: containers:
- name: intranet-web - name: intranet-web
image: localhost/fc-intranet-web:v20260508-brochure-w1 image: localhost/fc-intranet-web:v20260531-ttsreader-bridge
imagePullPolicy: Never imagePullPolicy: Never
ports: ports:
- containerPort: 5300 - containerPort: 5300

View File

@@ -102,7 +102,7 @@ spec:
- name: web - name: web
# Placeholder tag — bump to the image you built + imported to ALL # Placeholder tag — bump to the image you built + imported to ALL
# RKE2 nodes via scripts/deploy-knowledge.sh before applying. # RKE2 nodes via scripts/deploy-knowledge.sh before applying.
image: localhost/fc-knowledge-web:v20260429232635 image: localhost/fc-knowledge-web:v20260603-oidc-authentik-auditfix
imagePullPolicy: Never imagePullPolicy: Never
command: command:
- /bin/sh - /bin/sh
@@ -123,6 +123,25 @@ 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
# knowledge-oidc-client Secret is provisioned and
# FlowerCore__Auth__Enabled is flipped to true.
- 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/knowledge/"
- name: FlowerCore__Auth__Oidc__Audience
value: "knowledge"
- name: FlowerCore__Auth__Oidc__ClientId
value: "knowledge"
- name: FlowerCore__Auth__Oidc__ClientSecret
valueFrom:
secretKeyRef:
name: knowledge-oidc-client
key: client_secret
optional: true
# Vector-store directory + embedding model + edition profile dir. # Vector-store directory + embedding model + edition profile dir.
# Profile JSON is baked into the image at /home/app/editions via the # Profile JSON is baked into the image at /home/app/editions via the
# csproj Content-link from FlowerCore.Common/editions/. # csproj Content-link from FlowerCore.Common/editions/.
@@ -134,6 +153,8 @@ spec:
value: "5" value: "5"
- name: Knowledge__MaxLimit - name: Knowledge__MaxLimit
value: "50" value: "50"
- name: Knowledge__Federation__DatabasePath
value: "/data/vector-stores/knowledge-federation.db"
- name: FlowerCore__Editions__ProfileDirectory - name: FlowerCore__Editions__ProfileDirectory
value: "/home/app/editions" value: "/home/app/editions"
# Embed via edge1 Pi 5 + AI HAT+ (10.0.57.17:11434). Cluster # Embed via edge1 Pi 5 + AI HAT+ (10.0.57.17:11434). Cluster

View File

@@ -25,7 +25,7 @@ metadata:
role: github-actions-runner role: github-actions-runner
flowercore.io/managed-by: bluejay-infra flowercore.io/managed-by: bluejay-infra
spec: spec:
runStrategy: Always runStrategy: Halted
template: template:
metadata: metadata:
labels: labels:

View File

@@ -207,20 +207,13 @@ spec:
- port: 993 - port: 993
targetPort: 993 targetPort: 993
name: imaps name: imaps
--- # --- mail-tls Certificate REMOVED 2026-06-01 ---
# TLS Certificate via cert-manager # mail-tls is now managed OUTSIDE cert-manager: issued from step-ca's JWK 'admin'
apiVersion: cert-manager.io/v1 # provisioner and auto-renewed by a systemd timer on noc1 (step ca renew), which
kind: Certificate # writes the mail-tls secret directly. step-ca-acme only has an HTTP-01 (Traefik)
metadata: # solver, but mail.iamworkin.lan must resolve to the dedicated MetalLB IP 10.0.56.202
name: mail-tls # (SMTP/IMAP), so HTTP-01 cannot validate. Do NOT re-add a cert-manager Certificate
namespace: mail # here unless a DNS-01 solver is deployed for step-ca-acme.
spec:
secretName: mail-tls
issuerRef:
name: step-ca-acme
kind: ClusterIssuer
dnsNames:
- mail.iamworkin.lan
--- ---
# Traefik IngressRoute - Webmail placeholder # Traefik IngressRoute - Webmail placeholder
apiVersion: traefik.io/v1alpha1 apiVersion: traefik.io/v1alpha1

View File

@@ -223,7 +223,7 @@ data:
service: "pimanager" service: "pimanager"
vlan: "home" vlan: "home"
device: "pi4-ezconnect" device: "pi4-ezconnect"
- targets: ["10.0.58.113:5100"] - targets: ["10.0.58.113:5200"]
labels: labels:
instance: "pirelay" instance: "pirelay"
service: "pimanager" service: "pimanager"
@@ -479,15 +479,17 @@ data:
- "https://gitea.iamworkin.lan/" - "https://gitea.iamworkin.lan/"
- "https://argocd.iamworkin.lan/" - "https://argocd.iamworkin.lan/"
- "https://intranet.iamworkin.lan/" - "https://intranet.iamworkin.lan/"
- "https://signage.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://kiosk.iamworkin.lan/"
- "https://media.iamworkin.lan/" - "https://media.iamworkin.lan/"
- "https://mysql.iamworkin.lan/" - "https://mysql.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200
- "https://php.iamworkin.lan/" - "https://php.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200
- "https://dns.iamworkin.lan/"
- "https://zabbix.iamworkin.lan/" - "https://zabbix.iamworkin.lan/"
- "https://flowercore.iamworkin.lan/healthz"
- "https://desktop.iamworkin.lan/" - "https://desktop.iamworkin.lan/"
- "https://print.iamworkin.lan/" - "https://print.iamworkin.lan/"
- "https://dns.iamworkin.lan/"
- "https://chat.iamworkin.lan/" - "https://chat.iamworkin.lan/"
- "https://dist.iamworkin.lan/" - "https://dist.iamworkin.lan/"
- "https://dms.iamworkin.lan/" - "https://dms.iamworkin.lan/"
@@ -496,9 +498,15 @@ data:
- "https://presentations.iamworkin.lan/" - "https://presentations.iamworkin.lan/"
- "https://retail.iamworkin.lan/" - "https://retail.iamworkin.lan/"
- "https://ttsreader.iamworkin.lan/" - "https://ttsreader.iamworkin.lan/"
- "https://updates.iamworkin.lan/api/v1/manifests/_schema"
# Explicit healthcheck paths # Explicit healthcheck paths
- "https://fc-llm-bridge.iamworkin.lan/healthz" - "https://fc-llm-bridge.iamworkin.lan/healthz"
- "https://acme.iamworkin.lan/health" - "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 # NOTE: services intentionally NOT in this probe surface
# - grafana.iamworkin.lan: every endpoint (incl. /api/health # - grafana.iamworkin.lan: every endpoint (incl. /api/health
# and /login) returns 401 behind Traefik basic-auth. # and /login) returns 401 behind Traefik basic-auth.
@@ -907,11 +915,14 @@ data:
# for: 30m absorbs sleep cycles. The EcoTank sleeps after ~5 min # for: 30m absorbs sleep cycles. The EcoTank sleeps after ~5 min
# of idle and SNMP times out, so 5m for: would page nightly. A # of idle and SNMP times out, so 5m for: would page nightly. A
# genuine printer outage (jam, disconnected) lasts well over 30m. # 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 - alert: EpsonPrinterDown
expr: up{job="snmp-printer"} == 0 expr: (max_over_time(up{job="snmp-printer"}[35m]) == bool 0) == 1 and (hour() >= 13 or hour() < 1)
for: 30m for: 30m
labels: labels:
severity: warning severity: warning
alert_channel: irc
annotations: annotations:
summary: "Epson ET-3750 SNMP unreachable for >30m (likely actual fault, not sleep)" summary: "Epson ET-3750 SNMP unreachable for >30m (likely actual fault, not sleep)"
@@ -1020,7 +1031,9 @@ 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, then restart by design.
expr: increase(kube_pod_container_status_restarts_total{namespace!="github-runner"}[1h]) > 5
for: 15m for: 15m
labels: labels:
severity: warning severity: warning
@@ -1029,7 +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." 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 # 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 for: 5m
labels: labels:
severity: critical severity: critical
@@ -1057,7 +1072,8 @@ 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 # 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 for: 15m
labels: labels:
severity: warning severity: warning
@@ -3636,6 +3652,38 @@ data:
relativeTimeRange: {from: 120, to: 0} relativeTimeRange: {from: 120, to: 0}
datasourceUid: __expr__ datasourceUid: __expr__
model: {type: threshold, expression: B, conditions: [{evaluator: {params: [600], type: gt}}], refId: C} 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 - orgId: 1
name: CI Runners name: CI Runners
folder: CI Alerts folder: CI Alerts

View File

@@ -132,13 +132,18 @@ spec:
initialDelaySeconds: 10 initialDelaySeconds: 10
periodSeconds: 5 periodSeconds: 5
timeoutSeconds: 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: resources:
limits: limits:
cpu: 500m cpu: 500m
memory: 1Gi memory: 1536Mi
requests: requests:
cpu: 250m cpu: 250m
memory: 512Mi memory: 1Gi
--- ---
apiVersion: apps/v1 apiVersion: apps/v1
kind: Deployment kind: Deployment
@@ -198,13 +203,18 @@ spec:
port: 5555 port: 5555
initialDelaySeconds: 15 initialDelaySeconds: 15
periodSeconds: 5 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: resources:
limits: limits:
cpu: '1' cpu: '1'
memory: 1Gi memory: 2Gi
requests: requests:
cpu: 500m cpu: 500m
memory: 512Mi memory: 1Gi
volumeMounts: volumeMounts:
- mountPath: /dev/shm - mountPath: /dev/shm
name: dshm name: dshm
@@ -378,13 +388,18 @@ spec:
port: 5555 port: 5555
initialDelaySeconds: 15 initialDelaySeconds: 15
periodSeconds: 5 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: resources:
limits: limits:
cpu: '1' cpu: '1'
memory: 1Gi memory: 2Gi
requests: requests:
cpu: 500m cpu: 500m
memory: 512Mi memory: 1Gi
volumeMounts: volumeMounts:
- mountPath: /dev/shm - mountPath: /dev/shm
name: dshm name: dshm

View File

@@ -0,0 +1,206 @@
using FluentAssertions;
using Xunit;
namespace BluejayInfraLint.Tests;
[Trait("Category", "Unit")]
public sealed class DivoomPiDeployArtifactTests
{
private static readonly string Root = FindRepoRoot();
private static readonly string DmRoot = Path.Combine(Root, "apps", "fc-divoom-dm-pi-device");
private static readonly string TvRoot = Path.Combine(Root, "apps", "fc-divoom-tv-pi");
public static TheoryData<string> DmRequiredArtifacts => new()
{
"README.md",
"hiera/edge2-divoom-dm-device.overlay.yaml",
"puppet/profile/pi/service/divoom_dm_device.pp",
"puppet/templates/divoom-device-registration.json.epp",
"puppet/templates/flowercore-divoom-dm-agent.service.epp",
};
public static TheoryData<string> TvRequiredArtifacts => new()
{
"README.md",
"hiera/example-divoom-tv-pi.iamworkin.lan.yaml",
"puppet/profile/pi/service/divoom_tv.pp",
"systemd/flowercore-divoom-tv.service",
"systemd/flowercore-divoom-tv-hdmi.service",
"systemd/99-flowercore-divoom-tv-hdmi.rules",
"scripts/flowercore-divoom-tv-prelaunch.sh",
"scripts/flowercore-divoom-tv-launch.sh",
"scripts/flowercore-divoom-tv-hdmi-respond.sh",
};
[Theory]
[MemberData(nameof(DmRequiredArtifacts))]
public void DmDeviceArtifacts_ArePresent(string relativePath)
{
File.Exists(Path.Combine(DmRoot, relativePath.Replace('/', Path.DirectorySeparatorChar))).Should().BeTrue(relativePath);
}
[Theory]
[MemberData(nameof(TvRequiredArtifacts))]
public void TvPiArtifacts_ArePresent(string relativePath)
{
File.Exists(Path.Combine(TvRoot, relativePath.Replace('/', Path.DirectorySeparatorChar))).Should().BeTrue(relativePath);
}
[Fact]
public void DmDeviceReadme_DeclaresPuppetSystemdNotKubernetes()
{
var readme = ReadDm("README.md");
readme.Should().Contain("not a Kubernetes application");
readme.Should().Contain("profile::pi::service::divoom");
readme.Should().Contain("no K8s surface");
}
[Fact]
public void DmHieraOverlay_PreservesExistingEdge2DivoomService()
{
var hiera = ReadDm("hiera/edge2-divoom-dm-device.overlay.yaml");
hiera.Should().Contain("fc-pimanager:");
hiera.Should().Contain("fc-divoom:");
hiera.Should().Contain("enabled: true");
hiera.Should().Contain("profile::pi::service::divoom_dm_device::service_enabled: false");
hiera.Should().Contain("profile::pi::service::divoom_dm_device::service_ensure: 'stopped'");
}
[Fact]
public void DmPuppetProfile_DefaultsToStoppedDisabledService()
{
var profile = ReadDm("puppet/profile/pi/service/divoom_dm_device.pp");
profile.Should().Contain("Boolean $service_enabled = false");
profile.Should().Contain("Enum['running', 'stopped'] $service_ensure = 'stopped'");
profile.Should().Contain("service { $service_name:");
profile.Should().Contain("ensure => $service_ensure");
profile.Should().Contain("enable => $service_enabled");
}
[Fact]
public void DmPuppetProfile_DoesNotManageLiveDivoomWebUnit()
{
var profile = ReadDm("puppet/profile/pi/service/divoom_dm_device.pp");
profile.Should().NotContain("Service['flowercore-divoom.service']");
profile.Should().NotContain("service { 'flowercore-divoom.service'");
profile.Should().NotContain("notify => Service");
}
[Fact]
public void DmAgentUnit_IsSeparateAndGatedByExistingWrappers()
{
var unit = ReadDm("puppet/templates/flowercore-divoom-dm-agent.service.epp");
unit.Should().Contain("ConditionPathExists=<%= $divoom_install_dir %>/bt-link.sh");
unit.Should().Contain("ConditionPathExists=<%= $divoom_install_dir %>/bt-reset.sh");
unit.Should().Contain("ConditionPathExists=<%= $divoom_install_dir %>/audio-link.sh");
unit.Should().Contain("ExecStart=<%= $agent_binary_path %> --mode=Pi");
unit.Should().NotContain("flowercore-divoom.service");
}
[Fact]
public void DmRegistration_CarriesRenderProofAndSafetyPolicy()
{
var registration = ReadDm("puppet/templates/divoom-device-registration.json.epp");
registration.Should().Contain("\"candidateChannels\": <%= $bt_channels_json %>");
registration.Should().Contain("\"deviceInfoIsRenderProof\": false");
registration.Should().Contain("\"visibleRenderProofRequired\": <%= $visible_render_proof_required %>");
registration.Should().Contain("\"preserveExistingService\": \"flowercore-divoom.service\"");
registration.Should().Contain("\"doNotEnableFmRadio\": true");
}
[Fact]
public void TvService_UsesAvaloniaHdmiSafetyGates()
{
var unit = ReadTv("systemd/flowercore-divoom-tv.service");
unit.Should().Contain("ConditionPathExists=/opt/flowercore/divoom-tv/FlowerCore.Divoom.Tv");
unit.Should().Contain("Environment=XDG_RUNTIME_DIR=/run/fc-divoom-tv");
unit.Should().Contain("RuntimeDirectoryMode=0700");
unit.Should().Contain("ExecStartPre=/usr/local/bin/flowercore-divoom-tv-prelaunch.sh");
unit.Should().Contain("ExecStart=/usr/local/bin/flowercore-divoom-tv-launch.sh");
unit.Should().Contain("MemoryMax=2G");
unit.Should().Contain("PrivateTmp=true");
unit.Should().NotContain("/tmp");
}
[Fact]
public void TvLauncher_PrefersCageAndFallsBackToDirectLaunch()
{
var script = ReadTv("scripts/flowercore-divoom-tv-launch.sh");
script.Should().Contain("command -v cage");
script.Should().Contain("exec cage --");
script.Should().Contain("launching FlowerCore.Divoom.Tv directly");
script.Should().Contain("--target=hdmi");
script.Should().Contain("--presentation-mode=${PRESENTATION_MODE}");
}
[Fact]
public void TvHotplugRule_SettlesAndRestartsRenderer()
{
var rule = ReadTv("systemd/99-flowercore-divoom-tv-hdmi.rules");
var responder = ReadTv("scripts/flowercore-divoom-tv-hdmi-respond.sh");
rule.Should().Contain("KERNEL==\"card?-HDMI-A-?\"");
rule.Should().Contain("start flowercore-divoom-tv-hdmi.service");
responder.Should().Contain("sleep 2");
responder.Should().Contain("systemctl restart flowercore-divoom-tv.service");
}
[Fact]
public void TvPuppetProfile_InstallsCageAndStaticArtifacts()
{
var profile = ReadTv("puppet/profile/pi/service/divoom_tv.pp");
profile.Should().Contain("package { ['cage', 'libgbm1', 'libdrm2', 'libxkbcommon0', 'fonts-dejavu-core']");
profile.Should().Contain("'profile/pi/fc_divoom_tv/flowercore-divoom-tv.service'");
profile.Should().Contain("'profile/pi/fc_divoom_tv/flowercore-divoom-tv-launch.sh'");
profile.Should().Contain("profile/pi/fc_divoom_tv/99-flowercore-divoom-tv-hdmi.rules");
profile.Should().Contain("Boolean $service_enabled = false");
}
[Fact]
public void DivoomArtifacts_DoNotAddKubernetesWorkloads()
{
var allText = Directory.GetFiles(DmRoot, "*", SearchOption.AllDirectories)
.Concat(Directory.GetFiles(TvRoot, "*", SearchOption.AllDirectories))
.Select(File.ReadAllText);
foreach (var text in allText)
{
text.Should().NotContain("kind: Deployment");
text.Should().NotContain("kind: IngressRoute");
text.Should().NotContain("kind: Certificate");
text.Should().NotContain("kind: OnePasswordItem");
}
}
private static string ReadDm(string relativePath)
=> File.ReadAllText(Path.Combine(DmRoot, relativePath.Replace('/', Path.DirectorySeparatorChar)));
private static string ReadTv(string relativePath)
=> File.ReadAllText(Path.Combine(TvRoot, relativePath.Replace('/', Path.DirectorySeparatorChar)));
private static string FindRepoRoot()
{
var current = new DirectoryInfo(AppContext.BaseDirectory);
while (current is not null)
{
if (Directory.Exists(Path.Combine(current.FullName, "apps"))
&& File.Exists(Path.Combine(current.FullName, "README.md")))
{
return current.FullName;
}
current = current.Parent;
}
throw new DirectoryNotFoundException("Could not find bluejay-infra root.");
}
}

View File

@@ -67,6 +67,7 @@ public sealed class FleetManifestLintTests
["github-runner-chat"] = "https://github.com/astoltz/FlowerCore.Chat", ["github-runner-chat"] = "https://github.com/astoltz/FlowerCore.Chat",
["github-runner-mysql"] = "https://github.com/astoltz/FlowerCore.MySQL", ["github-runner-mysql"] = "https://github.com/astoltz/FlowerCore.MySQL",
["github-runner-kiosk-linux"] = "https://github.com/astoltz/FlowerCore.Kiosk.Linux", ["github-runner-kiosk-linux"] = "https://github.com/astoltz/FlowerCore.Kiosk.Linux",
["github-runner-updater"] = "https://github.com/astoltz/FlowerCore.Updater",
}; };
private static readonly HashSet<string> ScaledLinuxRunnerDeployments = new(StringComparer.Ordinal) private static readonly HashSet<string> ScaledLinuxRunnerDeployments = new(StringComparer.Ordinal)
@@ -80,6 +81,7 @@ public sealed class FleetManifestLintTests
"github-runner-chat", "github-runner-chat",
"github-runner-mysql", "github-runner-mysql",
"github-runner-kiosk-linux", "github-runner-kiosk-linux",
"github-runner-updater",
}; };
private static readonly IReadOnlyDictionary<string, string> WritableRunnerEnv = new Dictionary<string, string>(StringComparer.Ordinal) private static readonly IReadOnlyDictionary<string, string> WritableRunnerEnv = new Dictionary<string, string>(StringComparer.Ordinal)
@@ -234,7 +236,7 @@ public sealed class FleetManifestLintTests
{ {
deployments.Should().ContainKey(expectedRunner.Key); deployments.Should().ContainKey(expectedRunner.Key);
var container = deployments[expectedRunner.Key].ContainerMappings().Should().ContainSingle().Subject; var container = deployments[expectedRunner.Key].MainContainerMappings().Should().ContainSingle().Subject;
EnvValue(container, "REPO_URL").Should().Be(expectedRunner.Value); EnvValue(container, "REPO_URL").Should().Be(expectedRunner.Value);
EnvValue(container, "EPHEMERAL").Should().Be("true"); EnvValue(container, "EPHEMERAL").Should().Be("true");
EnvValue(container, "LABELS").Should().Be("self-hosted,linux,fc-build-linux"); EnvValue(container, "LABELS").Should().Be("self-hosted,linux,fc-build-linux");
@@ -250,7 +252,7 @@ public sealed class FleetManifestLintTests
{ {
foreach (var deployment in GitHubRunnerDeployments().Values) foreach (var deployment in GitHubRunnerDeployments().Values)
{ {
var container = deployment.ContainerMappings().Should().ContainSingle().Subject; var container = deployment.MainContainerMappings().Should().ContainSingle().Subject;
foreach (var expectedEnv in WritableRunnerEnv) foreach (var expectedEnv in WritableRunnerEnv)
{ {
@@ -277,7 +279,10 @@ public sealed class FleetManifestLintTests
foreach (var deploymentName in ScaledLinuxRunnerDeployments) foreach (var deploymentName in ScaledLinuxRunnerDeployments)
{ {
var deployment = deployments[deploymentName]; var deployment = deployments[deploymentName];
ReplicaCount(deployment).Should().Be(2); // Scaled runners must have >= 2 replicas (avoid single-pod bottleneck).
// Individual deployments may be tuned upward per CI activity — see
// "runners: right-size replica counts per 14d CI activity (#24)".
ReplicaCount(deployment).Should().BeGreaterOrEqualTo(2, $"{deploymentName} is in the scaled set and must run with at least 2 replicas");
var volumes = deployment.MappingSequence("spec", "template", "spec", "volumes"); var volumes = deployment.MappingSequence("spec", "template", "spec", "volumes");
var claimNames = volumes var claimNames = volumes
@@ -303,6 +308,108 @@ public sealed class FleetManifestLintTests
.Be("github-runner-nuget-cache"); .Be("github-runner-nuget-cache");
} }
[Fact]
public void Runners_MustNotPinToOperatorWorkstationHosts()
{
// CRITICAL SAFETY (operator directive 2026-05-26): BLUEJAY-WS is the
// operator's primary workstation — host of the 1Password Connect
// bearer token, fcadmin SSH keys to noc1, signing CA private keys,
// and source for every FC repo. A self-hosted GitHub Actions runner
// there would execute arbitrary PR code with that local access.
// Build-side analog of the Sprint 9 NEW safe-account exclusion gate
// (Puppet GPO/AppLocker/WDAC/audit-forwarder modules refuse to apply
// on BLUEJAY-WS). This lint asserts no GitHub-runner Deployment in
// apps/github-runner/ pins to a forbidden operator-workstation host
// via nodeName, nodeSelector, nodeAffinity, or tolerations.
// Existing legacy `bluejay-ws-sandbox-1` GitHub-registered runner is
// out of scope here (it's a runtime registration, not a K8s
// Deployment) — see CLAUDE.md "Common Mistakes" entry and
// feedback_bluejay_ws_never_public_runner.md.
var forbiddenHostPatterns = new[]
{
"bluejay-ws",
"BLUEJAY-WS",
"bluejay-ws.iamworkin.lan",
"iamworkin-ws",
};
bool ContainsForbidden(string? value) =>
!string.IsNullOrWhiteSpace(value)
&& forbiddenHostPatterns.Any(pattern => value!.Contains(pattern, StringComparison.OrdinalIgnoreCase));
var violations = GitHubRunnerDeployments().Values.SelectMany(deployment =>
{
var local = new List<string>();
var podSpec = ManifestNodeExtensions.Mapping(deployment.Root, "spec", "template", "spec");
if (podSpec is null)
{
return local;
}
// nodeName: pins the pod to a specific node by name.
var nodeName = ManifestNodeExtensions.Scalar(podSpec, "nodeName");
if (ContainsForbidden(nodeName))
{
local.Add($"{deployment.Name} sets nodeName='{nodeName}' which targets a forbidden operator-workstation host.");
}
// nodeSelector: dict of label → value pinning the pod to nodes
// carrying matching labels. Examples that would trip this:
// kubernetes.io/hostname: bluejay-ws
// flowercore.io/host: bluejay-ws.iamworkin.lan
var nodeSelector = ManifestNodeExtensions.Mapping(podSpec, "nodeSelector");
if (nodeSelector is not null)
{
foreach (var entry in nodeSelector.Children)
{
var key = entry.Key is YamlScalarNode keyScalar ? keyScalar.Value : null;
var value = entry.Value is YamlScalarNode valueScalar ? valueScalar.Value : null;
if (ContainsForbidden(value))
{
local.Add($"{deployment.Name} has nodeSelector entry '{key}: {value}' which targets a forbidden operator-workstation host.");
}
}
}
// nodeAffinity: matchExpressions over node labels.
foreach (var term in ManifestNodeExtensions.MappingSequence(podSpec, "affinity", "nodeAffinity", "requiredDuringSchedulingIgnoredDuringExecution", "nodeSelectorTerms"))
{
foreach (var expr in ManifestNodeExtensions.MappingSequence(term, "matchExpressions"))
{
var key = ManifestNodeExtensions.Scalar(expr, "key");
foreach (var valueNode in ManifestNodeExtensions.ScalarSequence(expr, "values"))
{
if (ContainsForbidden(valueNode))
{
local.Add($"{deployment.Name} has nodeAffinity matchExpression '{key}' value '{valueNode}' which targets a forbidden operator-workstation host.");
}
}
}
}
// tolerations: scheduling onto a tainted operator-workstation
// node would let the runner run there. Forbid any toleration
// value that names the workstation.
foreach (var toleration in ManifestNodeExtensions.MappingSequence(podSpec, "tolerations"))
{
var key = ManifestNodeExtensions.Scalar(toleration, "key");
var value = ManifestNodeExtensions.Scalar(toleration, "value");
if (ContainsForbidden(key))
{
local.Add($"{deployment.Name} has toleration key '{key}' which targets a forbidden operator-workstation host.");
}
if (ContainsForbidden(value))
{
local.Add($"{deployment.Name} has toleration value '{value}' which targets a forbidden operator-workstation host.");
}
}
return local;
}).ToList();
violations.Should().BeEmpty("BLUEJAY-WS / iamworkin-ws must never host a fleet GitHub Actions runner; see CLAUDE.md 'Registering BLUEJAY-WS as a fleet GitHub Actions runner' and feedback_bluejay_ws_never_public_runner.md");
}
[Fact] [Fact]
public void Monitoring_MustAlertWhenLinuxRunnerDeploymentIsUnavailable() public void Monitoring_MustAlertWhenLinuxRunnerDeploymentIsUnavailable()
{ {
@@ -890,6 +997,22 @@ internal sealed record ManifestDocument(
.ToList(); .ToList();
} }
// MainContainerMappings excludes initContainers. Use this when asserting
// properties of the primary container (env, image, volumeMounts) where an
// initContainer would be a false-positive match — e.g. the GitHub runner
// image's `setup-runner-home` initContainer should not count toward the
// single-container assertions on the runner deployments.
public IReadOnlyList<YamlMappingNode> MainContainerMappings()
{
var podSpec = PodSpec();
if (podSpec is null)
{
return Array.Empty<YamlMappingNode>();
}
return ManifestNodeExtensions.MappingSequence(podSpec, "containers").ToList();
}
public IReadOnlyList<ContainerSpec> ContainerSpecs() public IReadOnlyList<ContainerSpec> ContainerSpecs()
{ {
return ContainerMappings() return ContainerMappings()

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;
}
}