Compare commits

..

1 Commits

Author SHA1 Message Date
Codex
783720cc58 feat(fc-devicemgmt): add Kubernetes deployment manifests 2026-05-17 21:55:33 -05:00
17 changed files with 82 additions and 3099 deletions

View File

@@ -118,7 +118,6 @@ That test project sweeps `bluejay-infra/apps/**` plus the canonical sibling `Flo
## References
- OpenVox noc1 durability runbook: `docs/runbooks/openvoxserver-quadlet-durability.md`
- Cert-manager recovery playbook: `FlowerCore.Notes/memory/project_cert_manager_recovery_2026_04_22.md`
- Why pfSense DNS is required: `FlowerCore.Notes/memory/feedback_pfsense_dns_required_for_acme.md`
- Public DNS operator host: `https://dns.iamworkin.lan`

View File

@@ -30,41 +30,3 @@ spec:
port: 80
tls:
secretName: chat-web-tls
---
# Public host profile marker. The app treats this header as authoritative for
# the public twin, while the internal chat.iamworkin.lan route does not attach
# it and keeps the operator-oriented UI.
apiVersion: traefik.io/v1alpha1
kind: Middleware
metadata:
name: chat-public-profile-header
namespace: fc-chat
spec:
headers:
customRequestHeaders:
X-FC-Chat-Host-Profile: "public"
---
# Public Cloudflare-fronted twin for the anonymous chat surface. Operator
# paths are intentionally absent from the allowlist below, so /admin,
# /operator, /console, /ops, /api/operator, and /operatorhub miss this route
# and return Traefik 404 before reaching the pod. Operator action still needed:
# create/verify Cloudflare DNS chat.flowercore.io -> public Traefik endpoint
# and mirror the cf-origin-flowercore-io TLS secret into namespace fc-chat.
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: chat-web-public
namespace: fc-chat
spec:
entryPoints:
- websecure
routes:
- match: Host(`chat.flowercore.io`) && (Path(`/`) || Path(`/chat`) || PathPrefix(`/_blazor`) || PathPrefix(`/_framework`) || PathPrefix(`/_content`) || PathPrefix(`/avatars`) || PathPrefix(`/css`) || PathPrefix(`/js`) || PathPrefix(`/favicon`) || PathPrefix(`/chathub`)) && (Method(`GET`) || Method(`HEAD`) || Method(`POST`) || Method(`OPTIONS`))
kind: Rule
middlewares:
- name: chat-public-profile-header
services:
- name: chat-web
port: 80
tls:
secretName: cf-origin-flowercore-io

View File

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

View File

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

View File

@@ -47,7 +47,7 @@ spec:
fsGroupChangePolicy: OnRootMismatch
containers:
- name: operator
image: localhost/fc-devicemgmt-operator:v20260519-sp34cl3-fix
image: localhost/fc-devicemgmt-operator:v20260512-cx5
imagePullPolicy: Never
ports:
- name: metrics

View File

@@ -4,22 +4,6 @@
# Sprint 9+ lane. This manifest is static-valid without requiring the image to
# exist yet; import localhost/fc-devicemgmt-web:<tag> to all schedulable RKE2
# nodes before letting ArgoCD sync a live rollout.
#
# SCALED TO 0 — 2026-05-19 morning-routine cleanup.
# The Web pod cannot start until TWO upstream gaps close:
# 1. MySQL DB instance `flowercore_devicemgmt` (user `fc_devicemgmt`) is
# provisioned via fc-mysql Manager. The cluster currently has ZERO
# MySqlInstanceCrds and no `mysql.fc-mysql.svc:3306` Service, so the
# deployment-web container env `FlowerCore__Database__Host=mysql.fc-mysql.svc`
# points at nothing. Provision via the fc-mysql Manager UI/REST/MCP.
# 2. 1Password vault item `IAmWorkin/FlowerCore DeviceManagement Runtime`
# with 5 fields (DB-Password, mtls-ca.pem, mtls-client.crt, mtls-client.key,
# mtls-chain.pem) — see apps/fc-devicemgmt/1password-item.yaml. Mint mTLS
# from step-ca-agent ClusterIssuer per ADR-126; DB-Password must match the
# password configured for the MySQL user.
# Re-enable: change replicas back to 2 after both gaps close. The image tag
# in this file (v20260512-cx5) MAY also need a refresh — it predates the
# Sprint 34 Cl-3 operator fix; Web may have an analogous bug.
apiVersion: apps/v1
kind: Deployment
metadata:
@@ -36,7 +20,7 @@ metadata:
annotations:
flowercore.io/traceability-standard: k8s-pod-ownership-and-traceability-standard
spec:
replicas: 0
replicas: 2
revisionHistoryLimit: 3
selector:
matchLabels:

View File

@@ -532,7 +532,7 @@ spec:
fsGroupChangePolicy: OnRootMismatch
containers:
- name: web
image: localhost/fc-ttsreader-web:v20260518-sprint36-demo-finish-b132cbf
image: localhost/fc-ttsreader-web:v20260506-phase6
imagePullPolicy: Never
ports:
- containerPort: 5217
@@ -555,13 +555,9 @@ spec:
- name: TtsReader__Jobs__Root
value: "/data/jobs"
- name: TtsReader__Piper__Host
value: "10.0.57.17"
value: "ttsreader-piper.fc-ttsreader.svc.cluster.local."
- name: TtsReader__Piper__Port
value: "8500"
- name: TtsReader__Piper__Transport
value: "http"
- name: TtsReader__Piper__HttpPath
value: "/tts"
value: "10200"
- name: TtsReader__Kokoro__Enabled
value: "true"
- name: TtsReader__Kokoro__BaseUrl

View File

@@ -15,18 +15,9 @@ All repo-scoped Linux runners use:
Actions tool cache
`github-runner` for `FlowerCore.Common` is single-replica because it retains the
original Longhorn ReadWriteOnce NuGet PVC. Every other repo-scoped runner uses
two replicas with per-pod `emptyDir` caches. That is the safe backlog-drain
strategy: no two pods share one RWO PVC.
Sprint 32 final long-tail wave adds 16 two-replica Deployments:
`FlowerCore.Knowledge`, `FlowerCore.LlmBridge`, `FlowerCore.Media`,
`FlowerCore.Presentations`, `FlowerCore.RemoteDesktop`, `FlowerCore.DNS`,
`FlowerCore.Distribution`, `FlowerCore.Scoreboard`,
`FlowerCore.SegmentDisplay`, `FlowerCore.Signage.Contracts`,
`FlowerCore.SignalControl`, `FlowerCore.Intranet.Web`,
`FlowerCore.Provisioning`, `FlowerCore.Redis`, `FlowerCore.MessageBoard`, and
`FlowerCore.MenuBoard`.
original Longhorn ReadWriteOnce NuGet PVC. `github-runner-sharedpos` and the top
Linux-cost repo runners use two replicas with per-pod `emptyDir` caches. That is
the safe backlog-drain strategy: no two pods share one RWO PVC.
## Post-Merge Proof
@@ -41,13 +32,7 @@ Verify GitHub registration for the repo-scoped runners:
```bash
for repo in FlowerCore.Common FlowerCore.Shared.Pos FlowerCore.Puppet FlowerCore.Signage \
FlowerCore.DMS FlowerCore.Telephony FlowerCore.Print.Web FlowerCore.Chat \
FlowerCore.MySQL FlowerCore.Kiosk.Linux FlowerCore.Marquee FlowerCore.TtsReader \
FlowerCore.Knowledge FlowerCore.LlmBridge FlowerCore.Media \
FlowerCore.Presentations FlowerCore.RemoteDesktop FlowerCore.DNS \
FlowerCore.Distribution FlowerCore.Scoreboard FlowerCore.SegmentDisplay \
FlowerCore.Signage.Contracts FlowerCore.SignalControl FlowerCore.Intranet.Web \
FlowerCore.Provisioning FlowerCore.Redis FlowerCore.MessageBoard \
FlowerCore.MenuBoard; do
FlowerCore.MySQL FlowerCore.Kiosk.Linux; do
echo "=== $repo ==="
gh api "/repos/astoltz/$repo/actions/runners" \
--jq '.runners[] | select(.labels[].name == "fc-build-linux") | {name,status,busy,labels:[.labels[].name]}'

File diff suppressed because it is too large Load Diff

View File

@@ -966,52 +966,6 @@ data:
annotations:
summary: "Disk usage high on {{ $labels.instance }} ({{ $value | printf \"%.1f\" }}%)"
# Puppet agent + service alerts.
# Mirror of FlowerCore.Notes/scripts/monitoring/alerts.yml `puppet` group
# so a future migration to in-cluster Prometheus inherits the ruleset.
# Source-of-truth for the live Podman Prometheus on noc1 is the Notes file.
# See feedback_monitoring_k8s_target_vs_live_podman.
- name: puppet
rules:
- alert: PuppetAgentReportStale
expr: puppet_last_run_age_seconds > 7200
for: 30m
labels:
severity: warning
alert_channel: irc
annotations:
summary: "Puppet agent {{ $labels.instance }} hasn't reported in over 2h"
description: "Last run age: {{ $value | humanizeDuration }}. The puppet agent on {{ $labels.instance }} may be stopped, the node may be powered off, or noc1 may be unreachable from this node."
runbook: "1. SSH to node (via noc1 jumpbox if needed) 2. sudo systemctl status puppet 3. sudo puppet agent -t --noop to force a run 4. Check r10k: ssh fcadmin@10.0.56.10 'sudo podman logs openvoxserver --tail 50' 5. Verify noc1 reachability: ping puppet.iamworkin.lan"
- alert: PuppetAgentReportCritical
expr: puppet_last_run_age_seconds > 86400
for: 1h
labels:
severity: critical
alert_channel: irc
annotations:
summary: "Puppet agent {{ $labels.instance }} silent for over 24h — node is unmanaged"
description: "Last run age: {{ $value | humanizeDuration }}. Node {{ $labels.instance }} has not submitted a Puppet report in over 24 hours. Config drift is accumulating — investigate immediately. If intentional (maintenance), add to the exclusion filter or silence in Grafana."
runbook: "URGENT: 1. Check node power state 2. SSH via noc1 jumpbox: ssh fcadmin@10.0.56.10 then ssh <node> 3. sudo systemctl status puppet 4. sudo systemctl start puppet + sudo puppet agent -t 5. Check for network partitions (VLAN connectivity to 10.0.56.10) 6. If node was recently reimaged: sudo puppet agent -t to re-register with new SSL cert"
# Sprint 33 Cx-7 Phase B (2026-05-25 postmortem follow-up):
# Detects puppet.service in failed state — distinct from PuppetAgentReportStale
# which catches "agent hasn't run." This catches "systemd gave up restarting it"
# (CA-verify loop or other fatal exit). Requires node-exporter systemd collector
# enabled with --collector.systemd. If `node_systemd_unit_state` has no series
# for a node, the collector is disabled there — flag in postmortem follow-up.
- alert: PuppetServiceFailed
expr: node_systemd_unit_state{name="puppet.service",state="failed"} == 1
for: 5m
labels:
severity: warning
alert_channel: irc
annotations:
summary: "Puppet service failed on {{ $labels.instance }}"
description: "puppet.service on {{ $labels.instance }} has been in failed state for 5+ minutes. systemd has stopped auto-restarting (CA-verify-loop or other exit). Manual `systemctl status puppet` confirms. Run `sudo systemctl start puppet` to recover; investigate journal for root cause."
runbook_url: "https://github.com/astoltz/FlowerCore.Notes/blob/master/memory/feedback_puppet_service_dead_after_ca_loop_alert_misreads.md"
# K8s pod-state alerts. Require kube-state-metrics scrape (added
# 2026-04-26 — see scrape_configs above). Would have surfaced the
# agent-zero ollama-proxy 172x crash-loop instead of letting it
@@ -1273,55 +1227,24 @@ metadata:
data:
notify.py: |
#!/usr/bin/env python3
"""HTTP->IRC alert relay with thermal-printer DIGEST forwarding.
Listens on :9119, posts to #alerts on UnrealIRCd, forwards to Print.Web
/api/print/alert. Thermal printing is BATCHED into hourly digests by
default so the printer no longer spam-fires per Grafana webhook.
Routing (per Grafana webhook alert):
- IRC: always per-event (operator likes the stream)
- Thermal printer:
* severity in {critical,disaster,page} OR
label alert_channel=thermal_print_immediate -> print NOW
* label alert_channel=thermal_print -> enqueue into hourly digest
* everything else -> IRC only
- RESOLVED webhooks remove the alert from the digest buffer
Env vars (defaults preserve old behavior on first deploy):
THERMAL_PRINT_ENABLED default "true" - master kill switch
BATCH_INTERVAL_MIN default "60" - minutes between digest prints
BATCH_MAX_PENDING default "50" - force-flush threshold
HTTP surface:
POST / - Grafana webhook entry
POST /flush - manual digest flush (idempotent)
GET / - status + config + buffer depth + stats
"""HTTP->IRC alert relay with thermal printer forwarding for Grafana webhooks.
Listens on :9119, posts to #alerts on UnrealIRCd via raw IRC protocol.
Alerts tagged alert_channel=thermal_print also POST to Print.Web /api/print/alert.
"""
import json, os, socket, sys, threading, time
from collections import defaultdict
from datetime import datetime, timezone
import json, socket, sys, time
from http.server import HTTPServer, BaseHTTPRequestHandler
from urllib.request import Request, urlopen
from urllib.error import URLError
THERMAL_PRINT_ENABLED = os.environ.get("THERMAL_PRINT_ENABLED", "true").lower() == "true"
BATCH_INTERVAL_MIN = int(os.environ.get("BATCH_INTERVAL_MIN", "60"))
BATCH_MAX_PENDING = int(os.environ.get("BATCH_MAX_PENDING", "50"))
IRC_HOST = os.environ.get("IRC_HOST", "unrealircd.irc.svc")
IRC_PORT = int(os.environ.get("IRC_PORT", "6667"))
IRC_NICK = os.environ.get("IRC_NICK", "grafana-bot")
IRC_CHANNEL = os.environ.get("IRC_CHANNEL", "#alerts")
PRINT_WEB_URL = os.environ.get("PRINT_WEB_URL", "http://10.0.57.16:5200/api/print/alert")
_buffer_lock = threading.Lock()
_buffer = {} # fingerprint -> {"alert": dict, "first_seen": float, "last_seen": float}
_last_flush_time = time.time()
_stats = {"webhooks_received": 0, "irc_sent": 0, "print_immediate": 0,
"digest_flushed": 0, "buffer_dedup": 0, "buffer_added": 0,
"buffer_resolved": 0, "started_at": time.time()}
IRC_HOST = "unrealircd.irc.svc" # short name: CoreDNS ndots:5 + iamworkin.lan template hijacks full .cluster.local (see memory)
IRC_PORT = 6667
IRC_NICK = "grafana-bot"
IRC_CHANNEL = "#alerts"
PRINT_WEB_URL = "http://10.0.57.16:5200/api/print/alert"
PRINT_ENABLED = True
def send_irc(message):
"""Connect, handle PING, join, send, quit."""
try:
sock = socket.create_connection((IRC_HOST, IRC_PORT), timeout=15)
sock.sendall(f"NICK {IRC_NICK}\r\n".encode())
@@ -1354,137 +1277,52 @@ data:
time.sleep(0.5)
sock.sendall(b"QUIT :alert delivered\r\n")
sock.close()
_stats["irc_sent"] += 1
return True
except Exception as e:
print(f"[irc-notify] IRC send failed: {e}", file=sys.stderr)
return False
def post_thermal(payload, kind):
if not THERMAL_PRINT_ENABLED:
print(f"[irc-notify] thermal disabled; skip {kind} ({payload.get('title','?')[:40]})", file=sys.stderr)
return False
def send_thermal_print(alert):
if not PRINT_ENABLED: return
labels = alert.get("labels", {})
annotations = alert.get("annotations", {})
status = alert.get("status", "firing").upper()
summary = annotations.get("summary", "")
description = annotations.get("description", "")
runbook = annotations.get("runbook", "")
# Build a useful message: summary + description + runbook steps
parts = []
if summary: parts.append(summary)
if description and description != summary: parts.append(description)
if runbook: parts.append("STEPS: " + runbook)
message = " | ".join(parts) if parts else labels.get("alertname", "Unknown alert")
payload = {
"title": labels.get("alertname", "Unknown"),
"severity": labels.get("severity", "warning").capitalize(),
"host": labels.get("instance", labels.get("host", "unknown")),
"message": message,
"eventId": alert.get("fingerprint", ""),
"source": "Grafana",
"status": "RESOLVED" if status == "RESOLVED" else "PROBLEM",
"acknowledged": False
}
try:
req = Request(PRINT_WEB_URL, data=json.dumps(payload).encode("utf-8"),
headers={"Content-Type": "application/json"}, method="POST")
resp = urlopen(req, timeout=10)
if kind == "immediate": _stats["print_immediate"] += 1
print(f"[irc-notify] thermal {kind} sent: {payload.get('title','?')[:50]}", file=sys.stderr)
return True
print(f"[irc-notify] Thermal print sent: {resp.read().decode()}", file=sys.stderr)
except Exception as e:
print(f"[irc-notify] thermal {kind} failed: {e}", file=sys.stderr)
return False
print(f"[irc-notify] Thermal print failed: {e}", file=sys.stderr)
def fingerprint_of(alert):
fp = alert.get("fingerprint", "")
if fp: return fp
def should_print(alert):
labels = alert.get("labels", {})
target = labels.get("pod") or labels.get("instance") or labels.get("deployment") or labels.get("statefulset") or labels.get("namespace") or ""
return f"{labels.get('alertname','?')}/{labels.get('namespace','')}/{target}"
def is_critical(alert):
return alert.get("labels", {}).get("severity", "").lower() in ("critical", "disaster", "page")
def is_immediate_label(alert):
return alert.get("labels", {}).get("alert_channel") == "thermal_print_immediate"
def is_batched_label(alert):
return alert.get("labels", {}).get("alert_channel") == "thermal_print"
def add_to_digest(alert):
"""Add an alert to the digest buffer. Returns True if the buffer GREW
(new fingerprint), False if it was a dedup, resolution, or no-op.
"""
if not THERMAL_PRINT_ENABLED: return False
fp = fingerprint_of(alert)
status = alert.get("status", "firing").lower()
with _buffer_lock:
if status == "resolved":
if fp in _buffer:
del _buffer[fp]
_stats["buffer_resolved"] += 1
return False
if fp in _buffer:
_buffer[fp]["last_seen"] = time.time()
_buffer[fp]["alert"] = alert
_stats["buffer_dedup"] += 1
return False
_buffer[fp] = {"alert": alert, "first_seen": time.time(), "last_seen": time.time()}
_stats["buffer_added"] += 1
return True
def build_digest_payload():
with _buffer_lock:
items = list(_buffer.values())
if not items: return None
by_name = defaultdict(list)
for item in items:
labels = item["alert"].get("labels", {})
by_name[labels.get("alertname", "Unknown")].append(item)
lines = []
for name, group in sorted(by_name.items()):
targets = []
for it in group[:5]:
labels = it["alert"].get("labels", {})
t = (labels.get("pod") or labels.get("instance") or labels.get("deployment")
or labels.get("statefulset") or labels.get("namespace") or "?")
targets.append(t)
more = f" (+{len(group)-5})" if len(group) > 5 else ""
sevs = sorted({it["alert"].get("labels", {}).get("severity", "warning") for it in group})
lines.append(f"[{'/'.join(sevs)}] {name} x{len(group)}: {', '.join(targets)}{more}")
now = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M UTC")
title = f"Alert digest: {len(items)} firing"
body = "\n".join([
f"=== {title} ===",
f"as of {now}",
"",
*lines,
"",
"Stream: #alerts (IRC) | Triage: grafana-noc1.iamworkin.lan",
"Force-flush: POST irc-notify.monitoring.svc:9119/flush",
])
return {"title": title, "severity": "Warning", "host": "monitoring",
"message": body, "eventId": f"digest-{int(time.time())}",
"source": "Grafana digest", "status": "PROBLEM", "acknowledged": False}
def flush_digest():
payload = build_digest_payload()
if payload is None:
print("[irc-notify] flush: buffer empty, no digest sent", file=sys.stderr)
return False
sent = post_thermal(payload, "digest")
with _buffer_lock:
_buffer.clear()
if sent: _stats["digest_flushed"] += 1
return sent
def digest_loop():
global _last_flush_time
while True:
try:
now = time.time()
elapsed = now - _last_flush_time
if elapsed >= BATCH_INTERVAL_MIN * 60:
print(f"[irc-notify] digest tick: interval reached ({BATCH_INTERVAL_MIN}m); buffer={len(_buffer)}", file=sys.stderr)
flush_digest()
_last_flush_time = now
elif len(_buffer) >= BATCH_MAX_PENDING:
print(f"[irc-notify] digest tick: buffer full ({len(_buffer)}); force flush", file=sys.stderr)
flush_digest()
_last_flush_time = now
time.sleep(15)
except Exception as e:
print(f"[irc-notify] digest loop error: {e}", file=sys.stderr)
time.sleep(60)
if labels.get("alert_channel") == "thermal_print": return True
if labels.get("severity", "").lower() in ("critical", "disaster"): return True
if alert.get("status", "").upper() == "RESOLVED": return False
return False
class Handler(BaseHTTPRequestHandler):
def do_POST(self):
if self.path == "/flush":
ok = flush_digest()
self.send_response(200); self.send_header("Content-Type", "application/json"); self.end_headers()
self.wfile.write(json.dumps({"flushed": ok, "buffer_after": len(_buffer)}).encode())
return
_stats["webhooks_received"] += 1
length = int(self.headers.get("Content-Length", 0))
body = json.loads(self.rfile.read(length)) if length else {}
for alert in body.get("alerts", []):
@@ -1499,56 +1337,22 @@ data:
msg = f"{icon}{sev_tag} {name}: {summary}"
if desc: msg += f"\n {desc}"
send_irc(msg)
# Thermal routing — EVERYTHING (including criticals) goes into
# the hourly digest. Only the explicit `alert_channel=thermal_print_immediate`
# label bypasses, and even that flushes-the-current-digest rather
# than printing a standalone job, so the same fingerprint can't
# spam the printer per webhook cycle.
if status == "RESOLVED":
add_to_digest(alert) # removes from buffer
continue
if is_immediate_label(alert):
# Explicit opt-in for "paper this NOW" — first arrival of a
# new fingerprint triggers an immediate digest flush; repeat
# webhooks for the same fingerprint dedupe in the buffer
# until the next interval or until the alert resolves.
new_in_buffer = add_to_digest(alert)
if new_in_buffer:
global _last_flush_time
flush_digest()
_last_flush_time = time.time()
elif is_critical(alert) or is_batched_label(alert):
add_to_digest(alert)
# else: IRC-only (warnings without thermal_print label)
self.send_response(200); self.send_header("Content-Type", "application/json"); self.end_headers()
if should_print(alert): send_thermal_print(alert)
self.send_response(200)
self.send_header("Content-Type", "application/json")
self.end_headers()
self.wfile.write(b'{"status":"ok"}')
def do_GET(self):
self.send_response(200); self.send_header("Content-Type", "application/json"); self.end_headers()
with _buffer_lock:
alertnames = sorted({it["alert"].get("labels", {}).get("alertname", "?") for it in _buffer.values()})
depth = len(_buffer)
info = {
"service": "irc-notify",
"config": {"thermal_print_enabled": THERMAL_PRINT_ENABLED,
"batch_interval_min": BATCH_INTERVAL_MIN,
"batch_max_pending": BATCH_MAX_PENDING,
"irc_target": f"{IRC_HOST}:{IRC_PORT} {IRC_CHANNEL}",
"print_web_url": PRINT_WEB_URL},
"buffer": {"depth": depth, "alertnames": alertnames,
"seconds_since_last_flush": int(time.time() - _last_flush_time),
"seconds_until_next_flush": max(0, int(BATCH_INTERVAL_MIN*60 - (time.time() - _last_flush_time)))},
"stats": _stats,
}
self.wfile.write(json.dumps(info, indent=2).encode())
self.send_response(200)
self.send_header("Content-Type", "application/json")
self.end_headers()
self.wfile.write(json.dumps({"service":"irc-notify","thermal_print":PRINT_ENABLED}).encode())
def log_message(self, format, *args):
print(f"[irc-notify] {args[0]}", file=sys.stderr)
if __name__ == "__main__":
threading.Thread(target=digest_loop, daemon=True).start()
server = HTTPServer(("0.0.0.0", 9119), Handler)
print(f"[irc-notify] :9119 -> IRC {IRC_HOST}:{IRC_PORT} {IRC_CHANNEL} | thermal={'ON' if THERMAL_PRINT_ENABLED else 'OFF'} | digest={BATCH_INTERVAL_MIN}m max={BATCH_MAX_PENDING}", file=sys.stderr)
print(f"IRC alert relay :9119 -> {IRC_HOST}:{IRC_PORT} {IRC_CHANNEL} (thermal: {PRINT_ENABLED})")
server.serve_forever()
# =============================================================================

View File

@@ -28,12 +28,9 @@ Source: `D:\git\FlowerCore\FlowerCore.WorldBuilder` (master)
Memory: `feedback_rke2_image_import_per_node_scp`.
3. **Bump image tag** in `worldbuilder.yaml` and git push.
ArgoCD ApplicationSet picks up within ~3 minutes.
4. **First production render** — open
`https://worldbuilder.iamworkin.lan/studio/c32e0000-0000-4000-8000-000000000004`
and confirm the Cyberpunk Blue Jay demo prompt loads with five seeded fake
generated images. This Sprint 32 visitor-safe profile uses
`ClientMode=fake`; switch the image-generation env vars back to ComfyUI only
for an operator-owned GPU render lane.
4. **First production render** — open `https://worldbuilder.iamworkin.lan`,
create World → Character → Storyboard → ExportJob, confirm artifact
downloads. ComfyUI lives on BLUEJAY-WS at `http://10.0.56.20:8188`.
## Health probes
@@ -56,13 +53,8 @@ Source: `D:\git\FlowerCore\FlowerCore.WorldBuilder` (master)
## Image generation backend
Sprint 32 pins the Kubernetes profile to
`FlowerCore:WorldBuilder:ImageGeneration:ClientMode=fake` with
`BaseUrl=http://127.0.0.1:1`. That keeps the public/internal visitor demo
deterministic, avoids GPU exposure, and still exercises the studio/gallery
surface with persisted generated-image metadata.
The previous ComfyUI backend target was `http://10.0.56.20:8188` on
BLUEJAY-WS (R9700 / gfx1201 / ROCm 7.2.1). Re-enable it only in an
operator-owned follow-up that also verifies workstation reachability and image
import freshness.
`FlowerCore:WorldBuilder:ImageGeneration:BaseUrl=http://10.0.56.20:8188` —
ComfyUI runs on BLUEJAY-WS Windows (R9700 / gfx1201 / ROCm 7.2.1). Pod reaches
the workstation directly across the 10.0.56.0/24 VLAN (no Podman-style host-
filter issues — K8s pods route via Calico, which is L3-routed across the
VLAN).

View File

@@ -16,11 +16,7 @@ kind: Namespace
metadata:
name: fc-worldbuilder
labels:
app.kubernetes.io/name: fc-worldbuilder
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
---
# SQLite DB + generated image gallery + PDF/PNG exports.
# Longhorn RWO — single replica with `Recreate` rollout strategy keeps it safe.
@@ -29,13 +25,6 @@ kind: PersistentVolumeClaim
metadata:
name: worldbuilder-data
namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-data
app.kubernetes.io/component: storage
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
accessModes:
- ReadWriteOnce
@@ -51,13 +40,7 @@ metadata:
namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
flowercore.io/traceability-standard: k8s-pod-ownership-and-traceability-standard
spec:
replicas: 1
revisionHistoryLimit: 3
@@ -71,16 +54,11 @@ spec:
metadata:
labels:
app.kubernetes.io/name: worldbuilder-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
prometheus.io/scrape: "true"
prometheus.io/port: "8080"
prometheus.io/path: "/metrics/prometheus"
flowercore.io/audit-trace-id: "worldbuilder-runtime-demo"
spec:
securityContext:
fsGroup: 1654
@@ -114,14 +92,11 @@ spec:
value: "/data/gallery"
- name: FlowerCore__WorldBuilder__Export__RootPath
value: "/data/exports"
# Visitor-safe Sprint 32 profile: fake backend keeps public demo
# rendering deterministic and avoids exposing BLUEJAY-WS GPU.
# ComfyUI on BLUEJAY-WS (R9700 / gfx1201 / ROCm 7.2.1).
- name: FlowerCore__WorldBuilder__ImageGeneration__BaseUrl
value: "http://127.0.0.1:1"
value: "http://10.0.56.20:8188"
- name: FlowerCore__WorldBuilder__ImageGeneration__ClientMode
value: "fake"
- name: FlowerCore__WorldBuilder__ImageGeneration__BackendId
value: "fake"
value: "comfyui"
resources:
# Cluster CPU-request budget runs hot (99% on all 3 nodes at deploy
# time) while actual CPU usage is well below capacity. Idle Blazor
@@ -190,11 +165,7 @@ metadata:
namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
type: ClusterIP
selector:
@@ -209,13 +180,6 @@ kind: Certificate
metadata:
name: worldbuilder-web-tls
namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-web-tls
app.kubernetes.io/component: ingress
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
secretName: worldbuilder-web-tls
issuerRef:
@@ -236,13 +200,6 @@ kind: IngressRoute
metadata:
name: worldbuilder-web
namespace: fc-worldbuilder
labels:
app.kubernetes.io/name: worldbuilder-web
app.kubernetes.io/component: ingress
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
entryPoints:
- websecure

View File

@@ -1,84 +0,0 @@
# openvoxserver Quadlet Durability
This runbook documents the noc1 `openvoxserver` durability fix for the Puppet control-repo deploy path. The service is a noc1 host artifact, not an ArgoCD application, so discovery always starts on noc1 rather than in `apps/*`.
## Current State
As of the Sprint 32 Cx-12 apply on 2026-05-17:
- `/etc/containers/systemd/openvoxserver.container` has a `GIT_SSH_COMMAND` environment entry that points at the persisted serverdata deploy key.
- `/etc/systemd/system/openvoxserver-safeconfig.service` is enabled and active, and reapplies `git config --global --add safe.directory *` inside the running container.
- `/opt/puppet/r10k-deploy.sh` self-heals before each fetch by setting `safe.directory`, the repo-local `core.sshCommand`, and the persisted `known_hosts` file when needed.
- `puppet-deploy.service` exits `0/SUCCESS` after the apply and the control repo reports `HEAD == origin/master`.
- `systemctl cat openvoxserver` does not currently resolve to a generated unit on noc1. The container is running through Podman with `restart=always`, so destructive recreate smoke must not run until the generated unit is present.
## Discovery
Run every command through noc1 as `fcadmin`; do not assume BLUEJAY-WS can reach container-local surfaces directly.
```bash
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "hostname && sudo -n true"
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo find /etc/containers/systemd /usr/share/containers/systemd /etc/systemd/system -name 'openvoxserver*' 2>/dev/null"
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo sed -n '1,220p' /etc/containers/systemd/openvoxserver.container"
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo systemctl cat puppet-deploy.service"
```
If a future noc1 profile manages these files, update the Puppet control repo and let `puppet-deploy.service` apply the change. On 2026-05-17, host `puppet` was not installed, so Cx-12 used a direct noc1 host edit.
## Durable Fix Shape
The Quadlet keeps the deploy key as a path reference only:
```ini
Environment=GIT_SSH_COMMAND=ssh -i /opt/puppetlabs/server/data/puppetserver/.puppet-deploy-key -o StrictHostKeyChecking=yes -o IdentitiesOnly=yes -o UserKnownHostsFile=/opt/puppetlabs/server/data/puppetserver/.known_hosts
```
The safeconfig service is intentionally independent of `openvoxserver.service` until the generated unit exists. It waits for the `openvoxserver` container name and then runs:
```bash
/usr/bin/podman exec openvoxserver git config --global --add safe.directory *
```
The deploy script self-heals inside the container before it fetches the control repo:
```bash
git config --global --add safe.directory "*" 2>/dev/null || true
DEPLOY_KEY="/opt/puppetlabs/server/data/puppetserver/.puppet-deploy-key"
KNOWN_HOSTS="/opt/puppetlabs/server/data/puppetserver/.known_hosts"
REPO="/etc/puppetlabs/code/environments/production"
export GIT_SSH_COMMAND="ssh -i $DEPLOY_KEY -o StrictHostKeyChecking=yes -o IdentitiesOnly=yes -o UserKnownHostsFile=$KNOWN_HOSTS"
git -C "$REPO" config core.sshCommand "$GIT_SSH_COMMAND" 2>/dev/null || true
```
## Validation
Non-destructive validation:
```bash
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo grep -n 'GIT_SSH_COMMAND' /etc/containers/systemd/openvoxserver.container"
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo systemctl status openvoxserver-safeconfig.service --no-pager -l"
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo systemctl start puppet-deploy.service && sudo systemctl status puppet-deploy.service --no-pager -l"
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "sudo podman exec openvoxserver git -C /etc/puppetlabs/code/environments/production config --get core.sshCommand"
```
Destructive recreate smoke is opt-in only:
```bash
scp scripts/monitoring/openvox-recreate-smoke.sh fcadmin@10.0.56.10:/tmp/openvox-recreate-smoke.sh
ssh -i ~/.ssh/fcadmin_ed25519 fcadmin@10.0.56.10 "chmod +x /tmp/openvox-recreate-smoke.sh && sudo OPENVOX_RECREATE_SMOKE=1 /tmp/openvox-recreate-smoke.sh"
```
Do not run the smoke during normal sprint work. It stops and removes the production container before starting it again through systemd, and it now refuses to continue unless `systemctl cat openvoxserver` succeeds.
## Credential Rotation Note
When rotating the Puppet deploy key, update the persisted serverdata copy on noc1:
```bash
sudo install -m 0600 -o root -g root <new-deploy-key> /opt/puppet/serverdata/.puppet-deploy-key
sudo podman exec openvoxserver sh -c "ssh-keyscan github.com > /opt/puppetlabs/server/data/puppetserver/.known_hosts"
sudo systemctl start openvoxserver-safeconfig.service
sudo systemctl start puppet-deploy.service
```
Never commit the deploy key or print it in logs.

View File

@@ -1,48 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
if [ "${OPENVOX_RECREATE_SMOKE:-}" != "1" ]; then
echo "SKIP: set OPENVOX_RECREATE_SMOKE=1 to run the destructive openvoxserver recreate smoke." >&2
exit 64
fi
SUDO="${SUDO:-sudo}"
REPO="/etc/puppetlabs/code/environments/production"
CORE_SSH_COMMAND_FRAGMENT=".puppet-deploy-key"
if ! $SUDO systemctl cat openvoxserver >/dev/null 2>&1; then
echo "SKIP: systemctl cat openvoxserver failed; refusing to remove a container without a verified systemd recreate path." >&2
exit 65
fi
before="$($SUDO podman exec openvoxserver git -C "$REPO" rev-parse --short HEAD)"
echo "Before recreate: $before"
$SUDO systemctl stop openvoxserver
$SUDO podman rm openvoxserver 2>/dev/null || true
$SUDO systemctl start openvoxserver
sleep 50
$SUDO systemctl start puppet-deploy.service
sleep 5
$SUDO systemctl status puppet-deploy.service --no-pager -l
after="$($SUDO podman exec openvoxserver git -C "$REPO" rev-parse --short origin/master)"
echo "After recreate origin/master: $after"
$SUDO test -d /opt/puppet/code/environments/production/site-modules/profile/manifests
core_ssh="$($SUDO podman exec openvoxserver git -C "$REPO" config --get core.sshCommand)"
case "$core_ssh" in
*"$CORE_SSH_COMMAND_FRAGMENT"*) ;;
*)
echo "FAIL: core.sshCommand does not reference the persisted deploy key." >&2
exit 1
;;
esac
$SUDO podman exec openvoxserver git -C "$REPO" status --short --branch
echo "PASS: openvoxserver recreate smoke completed without git safety or deploy-key failure."

View File

@@ -13,7 +13,6 @@ public sealed class FleetManifestLintTests
private static readonly HashSet<string> PublicReadOnlyHosts = new(StringComparer.Ordinal)
{
"brochure.flowercore.io",
"dist.flowercore.io",
"dns.iamworkin.lan",
};
@@ -387,38 +386,6 @@ public sealed class FleetManifestLintTests
violations.Should().BeEmpty();
}
[Fact]
public void RemoteDesktopPoolCrds_MustExplicitlyOptInHookReadyTemplates()
{
var expectedModes = new Dictionary<string, string?>(StringComparer.Ordinal)
{
["browser-only"] = null,
["opensuse-xfce"] = "LateAttach",
["dev-workstation"] = "LateAttach",
["ai-station"] = "LateAttach",
["linux-xfce"] = "LateAttach",
["linux-xfce-rdp"] = "LateAttach",
};
var pools = Inventory.Documents
.Where(document => document.Kind == "RemoteDesktopPoolCrd")
.Where(document => document.RelativePath == "fc-desktop/remotedesktop-pools.yaml")
.ToDictionary(
document => document.Scalar("spec", "templateSlug") ?? string.Empty,
StringComparer.Ordinal);
pools.Keys.Should().BeEquivalentTo(expectedModes.Keys);
foreach (var expected in expectedModes)
{
var pool = pools[expected.Key];
pool.Namespace.Should().Be("fc-desktop");
pool.Scalar("spec", "desiredSize").Should().Be("1");
pool.Scalar("spec", "enabled").Should().Be("true");
pool.Scalar("spec", "reconcileNow").Should().Be("true");
pool.Scalar("spec", "userVolumeMode").Should().Be(expected.Value);
}
}
[Fact]
public void PublicEgressDeployments_MustOptOutOfIamworkinLanSearchSuffixes()
{

View File

@@ -1,99 +0,0 @@
using FluentAssertions;
using Xunit;
namespace BluejayInfraLint.Tests;
[Trait("Category", "Unit")]
public sealed class OpenVoxServerDurabilityTests
{
private static readonly string Root = FindRepoRoot();
private static readonly string RunbookPath = Path.Combine(Root, "docs", "runbooks", "openvoxserver-quadlet-durability.md");
private static readonly string SmokePath = Path.Combine(Root, "scripts", "monitoring", "openvox-recreate-smoke.sh");
[Fact]
public void Runbook_DocumentsHostArtifactAndNonArgoPath()
{
var runbook = File.ReadAllText(RunbookPath);
runbook.Should().Contain("noc1 host artifact");
runbook.Should().Contain("not an ArgoCD application");
runbook.Should().Contain("systemctl cat openvoxserver");
runbook.Should().Contain("/etc/containers/systemd/openvoxserver.container");
}
[Fact]
public void Runbook_DocumentsCx12LiveApplyState()
{
var runbook = File.ReadAllText(RunbookPath);
runbook.Should().Contain("Sprint 32 Cx-12");
runbook.Should().Contain("openvoxserver-safeconfig.service");
runbook.Should().Contain("/opt/puppet/r10k-deploy.sh");
runbook.Should().Contain("HEAD == origin/master");
}
[Fact]
public void SmokeScript_IsExplicitlyOptIn()
{
var smoke = File.ReadAllText(SmokePath);
smoke.Should().Contain("OPENVOX_RECREATE_SMOKE");
smoke.Should().Contain("exit 64");
smoke.IndexOf("OPENVOX_RECREATE_SMOKE", StringComparison.Ordinal)
.Should().BeLessThan(smoke.IndexOf("systemctl stop openvoxserver", StringComparison.Ordinal));
}
[Fact]
public void SmokeScript_RequiresGeneratedSystemdUnitBeforeRemovingContainer()
{
var smoke = File.ReadAllText(SmokePath);
smoke.Should().Contain("systemctl cat openvoxserver");
smoke.Should().Contain("refusing to remove a container without a verified systemd recreate path");
smoke.IndexOf("systemctl cat openvoxserver", StringComparison.Ordinal)
.Should().BeLessThan(smoke.IndexOf("podman rm openvoxserver", StringComparison.Ordinal));
}
[Fact]
public void Artifacts_DoNotStoreSecretsOrPaidRunnerLabels()
{
var forbidden = new[]
{
"BEGIN OPENSSH PRIVATE KEY",
"BEGIN RSA PRIVATE KEY",
"ubuntu-latest",
"windows-latest",
"macos-latest",
};
var violations = new[] { RunbookPath, SmokePath }
.SelectMany(path =>
{
var text = File.ReadAllText(path);
return forbidden
.Where(token => text.Contains(token, StringComparison.OrdinalIgnoreCase))
.Select(token => $"{Path.GetRelativePath(Root, path)} contains forbidden token {token}");
})
.ToList();
violations.Should().BeEmpty();
}
private static string FindRepoRoot()
{
var current = new DirectoryInfo(AppContext.BaseDirectory);
while (current is not null)
{
if (Directory.Exists(Path.Combine(current.FullName, "apps"))
&& Directory.Exists(Path.Combine(current.FullName, "scripts"))
&& 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

@@ -1,6 +1,6 @@
package bluejayinfra.public_method_allowlist
public_hosts := {"brochure.flowercore.io", "dist.flowercore.io", "dns.iamworkin.lan"}
public_hosts := {"dist.flowercore.io", "dns.iamworkin.lan"}
deny[msg] {
input.kind == "IngressRoute"