Compare commits

...

10 Commits

Author SHA1 Message Date
Andrew Stoltz
13d8ca8c1a infra: export appset and mirror alert polish 2026-06-10 16:36:18 -05:00
Andrew Stoltz
b0a3ef7448 monitoring: delay PiManagerDown duplicate pages 2026-06-10 16:23:49 -05:00
Andrew Stoltz
81ac1f3e4f authentik: align volumeClaimTemplates TypeMeta with SSA-created live object
StatefulSet/authentik-postgres has been eternally OutOfSync since ~Sprint 65
even though 'kubectl diff --server-side --field-manager=argocd-controller'
shows zero real change. The STS was created via ServerSideApply, so the live
object carries apiVersion/kind inside volumeClaimTemplates[]; git omitting
them makes ArgoCD's normalized diff disagree forever. Declare them in git.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-06-10 15:18:29 -05:00
b842738a0e Merge pull request 'Sprint 63 Cx-10: align hardening probe paths with live routes' (#44) from codex/s63-cx10 into main
Sprint 63 Cx-10 live-proof fix after Traefik curls found three stale probe-path annotations. Local lint 100/100; git diff --check clean; no Gitea statuses attached.
2026-06-05 03:02:14 +00:00
Andrew Stoltz
f0cb7a5e81 fix(hardening): align probe-path annotations with live health routes 2026-06-04 22:01:04 -05:00
ac0f665323 Merge pull request 'Draft: Sprint 62 Cx-10 broader exposure hardening' (#43) from codex/s62-cx10 into main
Sprint 63 Cx-10 reconcile-first merge after local lint proof: 100/100 passed, no Gitea statuses attached, CRLF diff check clean.
2026-06-05 02:51:37 +00:00
Andrew Stoltz
c4b08f41ab feat(infra): prestage broader app exposure hardening 2026-06-04 18:14:22 -05:00
Andrew Stoltz
417d3830ae test(lint): reconcile baseline infra assertions 2026-06-04 18:02:32 -05:00
cb4ea13e7a monitoring: mirror Sprint 60 probe coverage
Merged on local lint plus live noc1 Prometheus /api/v1/rules proof.
2026-06-04 18:19:47 +00:00
Andrew Stoltz
a3cd67d6bb monitoring: mirror Sprint 60 probe coverage 2026-06-04 13:15:18 -05:00
27 changed files with 1251 additions and 485 deletions

View File

@@ -2,6 +2,22 @@
Infrastructure manifests for ArgoCD. An `ApplicationSet` in `argocd` namespace watches the `apps/*` directories in this repo and creates one `Application` per subdir (prefixed `infra-<name>`). Infrastructure manifests for ArgoCD. An `ApplicationSet` in `argocd` namespace watches the `apps/*` directories in this repo and creates one `Application` per subdir (prefixed `infra-<name>`).
## Root GitOps ApplicationSet
`argocd/applicationset-bluejay-infra.yaml` is the root of this GitOps tree, but
it is **NOT self-managed** by ArgoCD. Apply it manually when the root generator
or sync policy changes:
```bash
kubectl -n argocd apply -f argocd/applicationset-bluejay-infra.yaml
```
Keep the per-StatefulSet `ignoreDifferences` entries in that file synced with
the live ApplicationSet. They intentionally cover `zabbix-postgres`,
`guac-mysql`, `matrix-postgres`, and `authentik-postgres` so ArgoCD does not
loop forever on server-side-apply `volumeClaimTemplates` status drift. Every new
StatefulSet with `volumeClaimTemplates` needs its own entry appended.
## Adding a new service to the cluster ## Adding a new service to the cluster
Follow these steps in order. **Step 1 must run before step 3** — if you skip it, cert-manager HTTP-01 will silently fail for ~2h per cert (exponential backoff) until someone diagnoses the DNS. Follow these steps in order. **Step 1 must run before step 3** — if you skip it, cert-manager HTTP-01 will silently fail for ~2h per cert (exponential backoff) until someone diagnoses the DNS.

View File

@@ -113,7 +113,12 @@ spec:
- name: pgdata - name: pgdata
mountPath: /var/lib/postgresql/data mountPath: /var/lib/postgresql/data
volumeClaimTemplates: volumeClaimTemplates:
- metadata: # apiVersion/kind included deliberately: this STS was created via ArgoCD ServerSideApply,
# so the live object carries PVC TypeMeta inside volumeClaimTemplates; omitting it here
# leaves the app eternally OutOfSync even though kubectl SSA dry-run shows no change.
- apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: pgdata name: pgdata
spec: spec:
storageClassName: longhorn storageClassName: longhorn

View File

@@ -46,6 +46,8 @@ spec:
template: template:
metadata: metadata:
annotations: annotations:
fc.flowercore.io/healthz-anon: "true"
fc.flowercore.io/probe-path: "/healthz"
prometheus.io/path: /metrics/prometheus prometheus.io/path: /metrics/prometheus
prometheus.io/port: "5000" prometheus.io/port: "5000"
prometheus.io/scrape: "true" prometheus.io/scrape: "true"
@@ -54,6 +56,7 @@ spec:
app.kubernetes.io/part-of: flowercore app.kubernetes.io/part-of: flowercore
spec: spec:
containers: containers:
# fc-safe-to-expose: X-Forwarded-Proto handled by AddFlowerCoreWebAuth (ADR-178) before any future public/OIDC flip.
- envFrom: - envFrom:
- configMapRef: - configMapRef:
name: aistation-web-config name: aistation-web-config
@@ -167,3 +170,26 @@ spec:
port: 80 port: 80
tls: tls:
secretName: aistation-web-tls secretName: aistation-web-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose aistation-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: aistation-web-public
# namespace: fc-aistation
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`aistation.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: aistation-web-public-profile-header # injects entitlement profile
# services:
# - name: aistation-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -112,6 +112,8 @@ spec:
app.kubernetes.io/name: chat-web app.kubernetes.io/name: chat-web
app.kubernetes.io/part-of: flowercore app.kubernetes.io/part-of: flowercore
annotations: annotations:
fc.flowercore.io/healthz-anon: "true"
fc.flowercore.io/probe-path: "/healthz"
prometheus.io/scrape: "true" prometheus.io/scrape: "true"
prometheus.io/port: "8080" prometheus.io/port: "8080"
prometheus.io/path: "/metrics/prometheus" prometheus.io/path: "/metrics/prometheus"
@@ -128,6 +130,7 @@ spec:
ports: ports:
- name: http - name: http
containerPort: 8080 containerPort: 8080
# fc-safe-to-expose: X-Forwarded-Proto handled by AddFlowerCoreWebAuth (ADR-178) before any future public/OIDC flip.
envFrom: envFrom:
- configMapRef: - configMapRef:
name: chat-web-config name: chat-web-config

View File

@@ -51,3 +51,26 @@ spec:
port: 8080 port: 8080
tls: tls:
secretName: remotedesktop-web-tls secretName: remotedesktop-web-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose remotedesktop-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: remotedesktop-web-public
# namespace: fc-desktop
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`desktop.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: remotedesktop-web-public-profile-header # injects entitlement profile
# services:
# - name: remotedesktop-web
# port: 8080
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -52,6 +52,8 @@ spec:
flowercore.io/tenant-id: system flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra flowercore.io/created-by: bluejay-infra
annotations: annotations:
fc.flowercore.io/healthz-anon: "true"
fc.flowercore.io/probe-path: "/healthz"
prometheus.io/scrape: "true" prometheus.io/scrape: "true"
prometheus.io/port: "8080" prometheus.io/port: "8080"
prometheus.io/path: "/metrics" prometheus.io/path: "/metrics"
@@ -67,6 +69,7 @@ spec:
ports: ports:
- name: http - name: http
containerPort: 8080 containerPort: 8080
# fc-safe-to-expose: X-Forwarded-Proto handled by AddFlowerCoreWebAuth (ADR-178) before any future public/OIDC flip.
env: env:
- name: ASPNETCORE_URLS - name: ASPNETCORE_URLS
value: "http://+:8080" value: "http://+:8080"

View File

@@ -30,3 +30,26 @@ spec:
port: 80 port: 80
tls: tls:
secretName: dms-web-tls secretName: dms-web-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose dms-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: dms-web-public
# namespace: fc-dms
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`dms.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: dms-web-public-profile-header # injects entitlement profile
# services:
# - name: dms-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -46,6 +46,8 @@ spec:
template: template:
metadata: metadata:
annotations: annotations:
fc.flowercore.io/healthz-anon: "true"
fc.flowercore.io/probe-path: "/health"
prometheus.io/path: /metrics/prometheus prometheus.io/path: /metrics/prometheus
prometheus.io/port: "5000" prometheus.io/port: "5000"
prometheus.io/scrape: "true" prometheus.io/scrape: "true"
@@ -54,6 +56,7 @@ spec:
app.kubernetes.io/part-of: flowercore app.kubernetes.io/part-of: flowercore
spec: spec:
containers: containers:
# fc-safe-to-expose: X-Forwarded-Proto handled by AddFlowerCoreWebAuth (ADR-178) before any future public/OIDC flip.
- envFrom: - envFrom:
- configMapRef: - configMapRef:
name: library-web-config name: library-web-config
@@ -167,3 +170,26 @@ spec:
port: 80 port: 80
tls: tls:
secretName: library-web-tls secretName: library-web-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose library-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: library-web-public
# namespace: fc-library
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`library.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: library-web-public-profile-header # injects entitlement profile
# services:
# - name: library-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -83,6 +83,8 @@ spec:
app.kubernetes.io/name: fc-llm-bridge app.kubernetes.io/name: fc-llm-bridge
app.kubernetes.io/part-of: flowercore app.kubernetes.io/part-of: flowercore
annotations: annotations:
fc.flowercore.io/healthz-anon: "true"
fc.flowercore.io/probe-path: "/healthz"
prometheus.io/scrape: "true" prometheus.io/scrape: "true"
prometheus.io/port: "8080" prometheus.io/port: "8080"
prometheus.io/path: "/metrics" prometheus.io/path: "/metrics"
@@ -116,6 +118,7 @@ spec:
ports: ports:
- containerPort: 8080 - containerPort: 8080
name: http name: http
# fc-safe-to-expose: X-Forwarded-Proto handled by AddFlowerCoreWebAuth (ADR-178) before any future public/OIDC flip.
env: env:
- name: ASPNETCORE_URLS - name: ASPNETCORE_URLS
value: "http://+:8080" value: "http://+:8080"
@@ -281,3 +284,26 @@ spec:
port: 8080 port: 8080
tls: tls:
secretName: fc-llm-bridge-tls secretName: fc-llm-bridge-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose fc-llm-bridge publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: fc-llm-bridge-public
# namespace: fc-llm-bridge
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`llm-bridge.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: fc-llm-bridge-public-profile-header # injects entitlement profile
# services:
# - name: fc-llm-bridge
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -30,3 +30,26 @@ spec:
port: 80 port: 80
tls: tls:
secretName: menuboard-web-tls secretName: menuboard-web-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose menuboard-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: menuboard-web-public
# namespace: fc-menuboard
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`menuboard.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: menuboard-web-public-profile-header # injects entitlement profile
# services:
# - name: menuboard-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -41,6 +41,8 @@ spec:
labels: labels:
app: messageboard-web app: messageboard-web
annotations: annotations:
fc.flowercore.io/healthz-anon: "true"
fc.flowercore.io/probe-path: "/health"
prometheus.io/scrape: "true" prometheus.io/scrape: "true"
prometheus.io/port: "8080" prometheus.io/port: "8080"
prometheus.io/path: "/metrics/prometheus" prometheus.io/path: "/metrics/prometheus"
@@ -52,6 +54,7 @@ spec:
ports: ports:
- containerPort: 8080 - containerPort: 8080
name: http name: http
# fc-safe-to-expose: X-Forwarded-Proto handled by AddFlowerCoreWebAuth (ADR-178) before any future public/OIDC flip.
envFrom: envFrom:
- configMapRef: - configMapRef:
name: messageboard-web-config name: messageboard-web-config
@@ -141,3 +144,26 @@ spec:
port: 80 port: 80
tls: tls:
secretName: messageboard-web-tls secretName: messageboard-web-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose messageboard-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: messageboard-web-public
# namespace: fc-messageboard
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`messageboard.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: messageboard-web-public-profile-header # injects entitlement profile
# services:
# - name: messageboard-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -30,3 +30,26 @@ spec:
port: 5300 port: 5300
tls: tls:
secretName: mysql-web-tls secretName: mysql-web-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose mysql-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: mysql-web-public
# namespace: fc-mysql
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`mysql.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: mysql-web-public-profile-header # injects entitlement profile
# services:
# - name: mysql-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -30,3 +30,26 @@ spec:
port: 5400 port: 5400
tls: tls:
secretName: php-web-tls secretName: php-web-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose php-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: php-web-public
# namespace: fc-php
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`php.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: php-web-public-profile-header # injects entitlement profile
# services:
# - name: php-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -30,3 +30,26 @@ spec:
port: 80 port: 80
tls: tls:
secretName: presentations-web-tls secretName: presentations-web-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose presentations-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: presentations-web-public
# namespace: fc-presentations
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`presentations.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: presentations-web-public-profile-header # injects entitlement profile
# services:
# - name: presentations-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -46,6 +46,8 @@ spec:
template: template:
metadata: metadata:
annotations: annotations:
fc.flowercore.io/healthz-anon: "true"
fc.flowercore.io/probe-path: "/healthz"
kubectl.kubernetes.io/restartedAt: "2026-06-02T01:34:08-05:00" kubectl.kubernetes.io/restartedAt: "2026-06-02T01:34:08-05:00"
prometheus.io/path: /metrics/prometheus prometheus.io/path: /metrics/prometheus
prometheus.io/port: "5000" prometheus.io/port: "5000"
@@ -55,6 +57,7 @@ spec:
app.kubernetes.io/part-of: flowercore app.kubernetes.io/part-of: flowercore
spec: spec:
containers: containers:
# fc-safe-to-expose: X-Forwarded-Proto handled by AddFlowerCoreWebAuth (ADR-178) before any future public/OIDC flip.
- envFrom: - envFrom:
- configMapRef: - configMapRef:
name: retail-web-config name: retail-web-config
@@ -168,3 +171,26 @@ spec:
port: 80 port: 80
tls: tls:
secretName: retail-web-tls secretName: retail-web-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose retail-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: retail-web-public
# namespace: fc-retail
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`retail.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: retail-web-public-profile-header # injects entitlement profile
# services:
# - name: retail-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -30,3 +30,26 @@ spec:
port: 80 port: 80
tls: tls:
secretName: scoreboard-web-tls secretName: scoreboard-web-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose scoreboard-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: scoreboard-web-public
# namespace: fc-scoreboard
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`scoreboard.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: scoreboard-web-public-profile-header # injects entitlement profile
# services:
# - name: scoreboard-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -37,3 +37,26 @@ spec:
port: 80 port: 80
tls: tls:
secretName: segmentdisplay-web-tls secretName: segmentdisplay-web-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose segmentdisplay-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: segmentdisplay-web-public
# namespace: fc-segmentdisplay
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`segmentdisplay.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: segmentdisplay-web-public-profile-header # injects entitlement profile
# services:
# - name: segmentdisplay-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -46,3 +46,26 @@ spec:
services: services:
- name: signage-web - name: signage-web
port: 5190 port: 5190
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose signage-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: signage-web-public
# namespace: fc-signage
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`signage.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: signage-web-public-profile-header # injects entitlement profile
# services:
# - name: signage-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -97,6 +97,7 @@ spec:
containers: containers:
- name: piper - name: piper
image: rhasspy/wyoming-piper:latest image: rhasspy/wyoming-piper:latest
# fc-safe-to-expose: X-Forwarded-Proto handled by AddFlowerCoreWebAuth (ADR-178) before any future public/OIDC flip.
env: env:
- name: PYTHONHTTPSVERIFY - name: PYTHONHTTPSVERIFY
value: "0" value: "0"
@@ -523,6 +524,8 @@ spec:
app.kubernetes.io/name: ttsreader-web app.kubernetes.io/name: ttsreader-web
app.kubernetes.io/part-of: flowercore app.kubernetes.io/part-of: flowercore
annotations: annotations:
fc.flowercore.io/healthz-anon: "true"
fc.flowercore.io/probe-path: "/health"
prometheus.io/scrape: "true" prometheus.io/scrape: "true"
prometheus.io/port: "5217" prometheus.io/port: "5217"
prometheus.io/path: "/metrics" prometheus.io/path: "/metrics"
@@ -762,3 +765,26 @@ spec:
port: 5217 port: 5217
tls: tls:
secretName: ttsreader-tls secretName: ttsreader-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose ttsreader-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: ttsreader-web-public
# namespace: fc-ttsreader
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`ttsreader.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: ttsreader-web-public-profile-header # injects entitlement profile
# services:
# - name: ttsreader-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -52,6 +52,9 @@ spec:
app: updatecenter-web app: updatecenter-web
template: template:
metadata: metadata:
annotations:
fc.flowercore.io/healthz-anon: "true"
fc.flowercore.io/probe-path: "/"
labels: labels:
app: updatecenter-web app: updatecenter-web
spec: spec:
@@ -63,6 +66,7 @@ spec:
ports: ports:
- containerPort: 8080 - containerPort: 8080
name: http name: http
# fc-safe-to-expose: X-Forwarded-Proto handled by AddFlowerCoreWebAuth (ADR-178) before any future public/OIDC flip.
env: env:
- name: ASPNETCORE_URLS - name: ASPNETCORE_URLS
value: http://+:8080 value: http://+:8080

View File

@@ -24,6 +24,12 @@ original Longhorn ReadWriteOnce NuGet PVC. Every other repo-scoped runner uses
two replicas with per-pod `emptyDir` caches. That is the safe backlog-drain two replicas with per-pod `emptyDir` caches. That is the safe backlog-drain
strategy: no two pods share one RWO PVC. strategy: no two pods share one RWO PVC.
Ephemeral runner pods are expected to register, run one job, deregister, and
exit so the Deployment starts a fresh pod for the next registration token. A
small amount of exit-1/restart churn from token-expiry or no-work windows is
accepted operational noise as long as jobs are not stuck queued and the
repo-scoped runner-offline alerts stay quiet.
Sprint 32 final long-tail wave adds 16 two-replica Deployments: Sprint 32 final long-tail wave adds 16 two-replica Deployments:
`FlowerCore.Knowledge`, `FlowerCore.LlmBridge`, `FlowerCore.Media`, `FlowerCore.Knowledge`, `FlowerCore.LlmBridge`, `FlowerCore.Media`,
`FlowerCore.Presentations`, `FlowerCore.RemoteDesktop`, `FlowerCore.DNS`, `FlowerCore.Presentations`, `FlowerCore.RemoteDesktop`, `FlowerCore.DNS`,

View File

@@ -90,6 +90,8 @@ spec:
app.kubernetes.io/name: knowledge-web app.kubernetes.io/name: knowledge-web
app.kubernetes.io/part-of: bluejay-infra app.kubernetes.io/part-of: bluejay-infra
annotations: annotations:
fc.flowercore.io/healthz-anon: "true"
fc.flowercore.io/probe-path: "/healthz"
prometheus.io/scrape: "true" prometheus.io/scrape: "true"
prometheus.io/port: "8080" prometheus.io/port: "8080"
prometheus.io/path: "/metrics" prometheus.io/path: "/metrics"
@@ -117,6 +119,7 @@ spec:
ports: ports:
- containerPort: 8080 - containerPort: 8080
name: http name: http
# fc-safe-to-expose: X-Forwarded-Proto handled by AddFlowerCoreWebAuth (ADR-178) before any future public/OIDC flip.
env: env:
- name: ASPNETCORE_URLS - name: ASPNETCORE_URLS
value: "http://+:8080" value: "http://+:8080"
@@ -286,3 +289,26 @@ spec:
port: 80 port: 80
tls: tls:
secretName: knowledge-tls secretName: knowledge-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose knowledge-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: knowledge-web-public
# namespace: knowledge
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`knowledge.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: knowledge-web-public-profile-header # injects entitlement profile
# services:
# - name: knowledge-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -216,19 +216,24 @@ data:
- job_name: "pimanager-app" - job_name: "pimanager-app"
scrape_interval: 15s scrape_interval: 15s
metrics_path: /metrics metrics_path: /metrics
scheme: https
tls_config:
insecure_skip_verify: true
static_configs: static_configs:
- targets: ["10.0.58.25:5000"] - targets: ["piez.iamworkin.lan"]
labels: labels:
instance: "piez" instance: "piez"
service: "pimanager" service: "signalcontrol"
vlan: "home" vlan: "home"
device: "pi4-ezconnect" device: "pi4-ezconnect"
- targets: ["10.0.58.113:5200"] rig: "signal-b"
- targets: ["pirelay.iamworkin.lan"]
labels: labels:
instance: "pirelay" instance: "pirelay"
service: "pimanager" service: "signalcontrol"
vlan: "home" vlan: "home"
device: "pi3-ks0212" device: "pi3-ks0212"
rig: "signal-a"
# Epson ET-3750 EcoTank Printer SNMP # Epson ET-3750 EcoTank Printer SNMP
- job_name: "snmp-printer" - job_name: "snmp-printer"
@@ -488,6 +493,12 @@ data:
- "https://desktop.iamworkin.lan/" - "https://desktop.iamworkin.lan/"
- "https://print.iamworkin.lan/healthz" # root 401 behind API key auth; /healthz anonymous 200 - "https://print.iamworkin.lan/healthz" # root 401 behind API key auth; /healthz anonymous 200
- "https://dns.iamworkin.lan/healthz" # root auth-gated by OIDC; /healthz anonymous 200 - "https://dns.iamworkin.lan/healthz" # root auth-gated by OIDC; /healthz anonymous 200
- "https://signalcontrol.iamworkin.lan/health" # FlowerCore.SignalControl Pi control plane
- "https://flowercore.iamworkin.lan/healthz" # FlowerCore landing
- "https://replay.iamworkin.lan/healthz" # FlowerCore.Signage replay surface
- "https://worldbuilder.iamworkin.lan/healthz" # FlowerCore.WorldBuilder
- "https://updates.iamworkin.lan/api/v1/manifests/_schema" # UpdateCenter plural LAN alias
- "https://updatecenter-internal.iamworkin.lan/api/v1/manifests/_schema" # internal UC schema route
- "https://chat.iamworkin.lan/healthz" # OIDC staged; keep blackbox off root before enforcement flips - "https://chat.iamworkin.lan/healthz" # OIDC staged; keep blackbox off root before enforcement flips
- "https://dist.iamworkin.lan/healthz" # root/admin auth-gated by OIDC; /healthz anonymous 200 - "https://dist.iamworkin.lan/healthz" # root/admin auth-gated by OIDC; /healthz anonymous 200
- "https://dms.iamworkin.lan/healthz" # future OIDC posture; health route is already anonymous/live - "https://dms.iamworkin.lan/healthz" # future OIDC posture; health route is already anonymous/live
@@ -832,7 +843,9 @@ data:
rules: rules:
- alert: PiManagerDown - alert: PiManagerDown
expr: up{job="pimanager-app"} == 0 expr: up{job="pimanager-app"} == 0
for: 3m # Sprint 67: delayed behind NodeDown's critical page so a powered-off
# Pi does not create the first duplicate page for the same host.
for: 8m
labels: labels:
severity: warning severity: warning
annotations: annotations:
@@ -911,12 +924,13 @@ data:
# 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.
- 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: info
alert_channel: irc
annotations: annotations:
summary: "Epson ET-3750 SNMP unreachable for >30m (likely actual fault, not sleep)" summary: "Epson ET-3750 SNMP unreachable during waking hours (30m)"
- alert: SynologyDiskLow - alert: SynologyDiskLow
expr: hrStorageUsed{job="snmp-nas"} / hrStorageSize{job="snmp-nas"} * 100 > 85 expr: hrStorageUsed{job="snmp-nas"} / hrStorageSize{job="snmp-nas"} * 100 > 85
@@ -1230,6 +1244,58 @@ data:
summary: "Marquee animation duration drifting > 10% on {{ $labels.renderer }} ({{ $labels.phase }})" summary: "Marquee animation duration drifting > 10% on {{ $labels.renderer }} ({{ $labels.phase }})"
description: "Median observed cycle duration deviates from target DurationMs by >10%. Could indicate browser tab throttling, GPU pressure, or phase-advancement bug." description: "Median observed cycle duration deviates from target DurationMs by >10%. Could indicate browser tab throttling, GPU pressure, or phase-advancement bug."
# ============================================================
# Update Center public-edge probes
# Live-mirrored from FlowerCore.Notes/scripts/monitoring/alerts.yml.
# This K8s ConfigMap is the future migration target; live Prometheus
# still reads the canonical Notes file from noc1 Podman.
# ============================================================
- name: update_center
rules:
# Critical only when the edge is genuinely unreachable. A Cloudflare
# HTTP 429 means the prober hit a rate-limit, not that real clients
# are down, so the warning rule below owns that signal.
- alert: UpdateCenterPublicEdgeDown
expr: |
(probe_success{job="probe-update-center-public-edge"} == 0)
unless on(instance)
(probe_http_status_code{job="probe-update-center-public-edge"} == 429)
for: 10m
labels:
severity: critical
service: update-center
alert_channel: irc
annotations:
summary: "Update Center public edge probe failed for {{ $labels.instance }}"
description: >-
The external probe for {{ $labels.instance }} failed for 10 minutes with a
non-2xx status that is not a rate-limit. Public Update Center clients may be
unable to fetch manifest schema metadata through Cloudflare.
runbook: >-
1. curl -sk https://{{ $labels.instance }}/api/v1/manifests/_schema
2. Verify Cloudflare DNS record is proxied and targets the current public edge IP
3. kubectl -n fc-updater get ingressroute updatecenter-web-public secret cf-origin-flowercore-io
4. Check Traefik logs for Method() or TLS secret errors
- alert: UpdateCenterPublicEdgeRateLimited
expr: probe_http_status_code{job="probe-update-center-public-edge"} == 429
for: 15m
labels:
severity: warning
service: update-center
alert_channel: irc
annotations:
summary: "Cloudflare is rate-limiting (HTTP 429) the public-edge probe for {{ $labels.instance }}"
description: >-
The blackbox prober receives HTTP 429 from Cloudflare for {{ $labels.instance }}
while the origin is healthy. This is a Cloudflare rate-limit / WAF condition on
the public hostname, not an outage.
runbook: >-
1. curl -sk https://{{ $labels.instance }}/api/v1/manifests/_schema (expect 200 from a normal client)
2. Review Cloudflare rate-limit / WAF rules for the hostname; the 5m-cadence prober is tripping a 429
3. Add a Cloudflare rate-limit exception for the prober source IP or the /api/v1/manifests/_schema path
4. Confirm whether the singular host update.flowercore.io is still required, or only updates.flowercore.io
# ============================================================================= # =============================================================================
# ConfigMap: Blackbox Exporter Configuration # ConfigMap: Blackbox Exporter Configuration
# ============================================================================= # =============================================================================

View File

@@ -114,6 +114,9 @@ spec:
app: telephony-web app: telephony-web
template: template:
metadata: metadata:
annotations:
fc.flowercore.io/healthz-anon: "true"
fc.flowercore.io/probe-path: "/health"
labels: labels:
app: telephony-web app: telephony-web
spec: spec:
@@ -161,6 +164,7 @@ spec:
ports: ports:
- containerPort: 5100 - containerPort: 5100
name: http name: http
# fc-safe-to-expose: X-Forwarded-Proto handled by AddFlowerCoreWebAuth (ADR-178) before any future public/OIDC flip.
env: env:
- name: Telephony__Twilio__AccountSid - name: Telephony__Twilio__AccountSid
valueFrom: valueFrom:
@@ -387,4 +391,3 @@ spec:

View File

@@ -77,6 +77,8 @@ spec:
flowercore.io/tenant-id: system flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra flowercore.io/created-by: bluejay-infra
annotations: annotations:
fc.flowercore.io/healthz-anon: "true"
fc.flowercore.io/probe-path: "/healthz"
prometheus.io/scrape: "true" prometheus.io/scrape: "true"
prometheus.io/port: "8080" prometheus.io/port: "8080"
prometheus.io/path: "/metrics/prometheus" prometheus.io/path: "/metrics/prometheus"
@@ -93,6 +95,7 @@ spec:
ports: ports:
- containerPort: 8080 - containerPort: 8080
name: http name: http
# fc-safe-to-expose: X-Forwarded-Proto handled by AddFlowerCoreWebAuth (ADR-178) before any future public/OIDC flip.
env: env:
- name: ASPNETCORE_URLS - name: ASPNETCORE_URLS
value: "http://+:8080" value: "http://+:8080"
@@ -254,3 +257,26 @@ spec:
port: 80 port: 80
tls: tls:
secretName: worldbuilder-web-tls secretName: worldbuilder-web-tls
# ---- PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only) ----
# When the operator decides to expose worldbuilder-web publicly, uncomment + update the host,
# then verify the five safe-to-expose gates (authentik-safe-to-expose-readiness-2026-06-07.md section 2).
#
# --- IngressRoute ---
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: worldbuilder-web-public
# namespace: worldbuilder
# spec:
# entryPoints: [websecure]
# routes:
# - match: Host(`worldbuilder.flowercore.io`) && (Method(`GET`) || Method(`HEAD`))
# kind: Rule
# middlewares:
# - name: worldbuilder-web-public-profile-header # injects entitlement profile
# services:
# - name: worldbuilder-web
# port: 80
# tls: {}
# # POST/PUT/PATCH/DELETE miss every route -> Traefik 404 -> no admin writes on the public surface.
# # Reference pattern: dist.flowercore.io (already live + method-gated; do not edit that one).

View File

@@ -0,0 +1,74 @@
apiVersion: argoproj.io/v1alpha1
kind: ApplicationSet
metadata:
annotations:
argocd.argoproj.io/refresh: "true"
name: bluejay-infra
namespace: argocd
spec:
generators:
- git:
directories:
- path: apps/*
repoURL: http://gitea-clusterip.gitea.svc:3000/bluejay/bluejay-infra.git
revision: main
template:
metadata: {}
spec:
destination: {}
project: ""
goTemplate: true
goTemplateOptions:
- missingkey=error
template:
metadata:
name: infra-{{.path.basename}}
spec:
destination:
server: https://kubernetes.default.svc
ignoreDifferences:
- group: apps
jqPathExpressions:
- .spec.volumeClaimTemplates[]?.status
jsonPointers:
- /spec/volumeClaimTemplates
kind: StatefulSet
name: zabbix-postgres
namespace: zabbix
- group: apps
jqPathExpressions:
- .spec.volumeClaimTemplates[]?.status
jsonPointers:
- /spec/volumeClaimTemplates
kind: StatefulSet
name: guac-mysql
namespace: guacamole
- group: apps
jqPathExpressions:
- .spec.volumeClaimTemplates[]?.status
jsonPointers:
- /spec/volumeClaimTemplates
kind: StatefulSet
name: matrix-postgres
namespace: matrix
- group: apps
jqPathExpressions:
- .spec.volumeClaimTemplates[]?.status
jsonPointers:
- /spec/volumeClaimTemplates
kind: StatefulSet
name: authentik-postgres
namespace: authentik
project: default
source:
path: '{{.path.path}}'
repoURL: http://gitea-clusterip.gitea.svc:3000/bluejay/bluejay-infra.git
targetRevision: main
syncPolicy:
automated:
prune: true
selfHeal: true
syncOptions:
- CreateNamespace=true
- ServerSideApply=true
- RespectIgnoreDifferences=true

View File

@@ -17,21 +17,17 @@ public sealed class FleetManifestLintTests
"dist.flowercore.io", "dist.flowercore.io",
}; };
// Public hosts that allow a tightly bounded write surface in addition to // Hosts that allow a tightly bounded write surface in addition to GET/HEAD.
// GET/HEAD. updatecenter.iamworkin.lan accepts POST /api/v1/checkin/{id} // updatecenter.iamworkin.lan accepts POST /api/v1/checkin/{id}
// (bootstrap-JWT) so its allowlist is GET||HEAD||POST||OPTIONS — but // (bootstrap-JWT) so its allowlist is GET||HEAD||POST||OPTIONS — but
// PUT/PATCH/DELETE must still 404 at the route. Anything wider than this // PUT/PATCH/DELETE must still 404 at the route. Public
// set should fail this lint. // update.flowercore.io remains a GET/HEAD download surface in the
// // FlowerCore.Updater sibling manifest and is covered by the general
// PUB-1 (2026-05-06): update.flowercore.io / updates.flowercore.io were // public-method allowlist lint instead of this write-surface rule.
// added for the Cloudflare-proxied public Update Center edge. They use the
// same bounded read-write allowlist as the LAN pair.
private static readonly HashSet<string> PublicReadWriteAllowlistHosts = new(StringComparer.Ordinal) private static readonly HashSet<string> PublicReadWriteAllowlistHosts = new(StringComparer.Ordinal)
{ {
"updatecenter.iamworkin.lan", "updatecenter.iamworkin.lan",
"updates.iamworkin.lan", "updates.iamworkin.lan",
"update.flowercore.io",
"updates.flowercore.io",
}; };
private static readonly HashSet<string> ApiKeyProtectedDeployments = new(StringComparer.Ordinal) private static readonly HashSet<string> ApiKeyProtectedDeployments = new(StringComparer.Ordinal)
@@ -69,7 +65,7 @@ public sealed class FleetManifestLintTests
["github-runner-updater"] = "https://github.com/astoltz/FlowerCore.Updater", ["github-runner-updater"] = "https://github.com/astoltz/FlowerCore.Updater",
}; };
private static readonly HashSet<string> ScaledLinuxRunnerDeployments = new(StringComparer.Ordinal) private static readonly HashSet<string> RepoScopedLinuxRunnerDeployments = new(StringComparer.Ordinal)
{ {
"github-runner-sharedpos", "github-runner-sharedpos",
"github-runner-puppet", "github-runner-puppet",
@@ -83,6 +79,44 @@ public sealed class FleetManifestLintTests
"github-runner-updater", "github-runner-updater",
}; };
private static readonly IReadOnlyDictionary<string, (string Deployment, string ProbePath)> BroaderHardeningDeployments =
new Dictionary<string, (string Deployment, string ProbePath)>(StringComparer.Ordinal)
{
["fc-aistation"] = ("aistation-web", "/healthz"),
["fc-chat"] = ("chat-web", "/healthz"),
["fc-devicemgmt"] = ("fc-devicemgmt-web", "/healthz"),
["fc-library"] = ("library-web", "/health"),
["fc-llm-bridge"] = ("fc-llm-bridge", "/healthz"),
["fc-messageboard"] = ("messageboard-web", "/health"),
["fc-retail"] = ("retail-web", "/healthz"),
["fc-ttsreader"] = ("ttsreader-web", "/health"),
["fc-updater"] = ("updatecenter-web", "/"),
["knowledge"] = ("knowledge-web", "/healthz"),
["telephony"] = ("telephony-web", "/health"),
["worldbuilder"] = ("worldbuilder-web", "/healthz"),
};
private static readonly HashSet<string> BroaderHardeningInternalPrestageApps = new(StringComparer.Ordinal)
{
"fc-aistation",
"fc-desktop",
"fc-dms",
"fc-library",
"fc-llm-bridge",
"fc-menuboard",
"fc-messageboard",
"fc-mysql",
"fc-php",
"fc-presentations",
"fc-retail",
"fc-scoreboard",
"fc-segmentdisplay",
"fc-signage",
"fc-ttsreader",
"knowledge",
"worldbuilder",
};
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)
{ {
["HOME"] = "/home/runner", ["HOME"] = "/home/runner",
@@ -271,17 +305,17 @@ public sealed class FleetManifestLintTests
} }
[Fact] [Fact]
public void GitHubRunnerFleet_MustAvoidRwoMultiAttachForScaledDeployments() public void GitHubRunnerFleet_MustAvoidRwoMultiAttachForRepoScopedDeployments()
{ {
var deployments = GitHubRunnerDeployments(); var deployments = GitHubRunnerDeployments();
foreach (var deploymentName in ScaledLinuxRunnerDeployments) foreach (var deploymentName in RepoScopedLinuxRunnerDeployments)
{ {
var deployment = deployments[deploymentName]; var deployment = deployments[deploymentName];
// Scaled runners must have >= 2 replicas (avoid single-pod bottleneck). // Sprint 34 ops trimmed runner load while the cluster was degraded
// Individual deployments may be tuned upward per CI activity — see // to two healthy nodes. Repo-scoped runners can be tuned back above
// "runners: right-size replica counts per 14d CI activity (#24)". // one replica, but they must stay RWO-safe before that happens.
ReplicaCount(deployment).Should().BeGreaterOrEqualTo(2, $"{deploymentName} is in the scaled set and must run with at least 2 replicas"); ReplicaCount(deployment).Should().BeGreaterOrEqualTo(1, $"{deploymentName} must keep at least one repo-scoped runner online");
var volumes = deployment.MappingSequence("spec", "template", "spec", "volumes"); var volumes = deployment.MappingSequence("spec", "template", "spec", "volumes");
var claimNames = volumes var claimNames = volumes
@@ -289,7 +323,7 @@ public sealed class FleetManifestLintTests
.Where(value => !string.IsNullOrWhiteSpace(value)) .Where(value => !string.IsNullOrWhiteSpace(value))
.ToList(); .ToList();
claimNames.Should().BeEmpty($"{deploymentName} is scaled and must not share a RWO PVC"); claimNames.Should().BeEmpty($"{deploymentName} must remain ready for safe multi-replica scaling without sharing a RWO PVC");
volumes.Should().Contain(volume => volumes.Should().Contain(volume =>
string.Equals(ManifestNodeExtensions.Scalar(volume, "name"), "nuget-cache", StringComparison.Ordinal) string.Equals(ManifestNodeExtensions.Scalar(volume, "name"), "nuget-cache", StringComparison.Ordinal)
&& ManifestNodeExtensions.Mapping(volume, "emptyDir") != null); && ManifestNodeExtensions.Mapping(volume, "emptyDir") != null);
@@ -434,6 +468,99 @@ public sealed class FleetManifestLintTests
monitoring.Should().Contain("dedicated LinuxRunnerOffline/MacMiniRunnerOffline alerts"); monitoring.Should().Contain("dedicated LinuxRunnerOffline/MacMiniRunnerOffline alerts");
} }
[Fact]
public void GithubRunnerReadme_DocumentsAcceptedEphemeralExitChurn()
{
var readme = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "github-runner", "README.md"));
readme.Should().Contain("Ephemeral runner pods");
readme.Should().Contain("exit-1/restart churn");
readme.Should().Contain("accepted operational noise");
readme.Should().Contain("repo-scoped runner-offline alerts stay quiet");
}
[Fact]
public void Monitoring_PiManagerDownDelayAndUpdateCenterRateLimit_MatchCanonicalAlerts()
{
var notesAlerts = File.ReadAllText(Path.Combine(
Inventory.WorkspaceRoot,
"FlowerCore.Notes",
"scripts",
"monitoring",
"alerts.yml"));
var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
notesAlerts.Should().Contain("# Sprint 67: keep this warning behind NodeDown's 5m critical page");
notesAlerts.Should().Contain("- alert: PiManagerDown");
notesAlerts.Should().Contain("for: 8m");
monitoring.Should().Contain("# Sprint 67: delayed behind NodeDown's critical page");
monitoring.Should().Contain("- alert: PiManagerDown");
monitoring.Should().Contain("for: 8m");
notesAlerts.Should().Contain("- alert: UpdateCenterPublicEdgeRateLimited");
notesAlerts.Should().Contain("expr: probe_http_status_code{job=\"probe-update-center-public-edge\"} == 429");
notesAlerts.Should().Contain("for: 15m");
monitoring.Should().Contain("- alert: UpdateCenterPublicEdgeRateLimited");
monitoring.Should().Contain("expr: probe_http_status_code{job=\"probe-update-center-public-edge\"} == 429");
monitoring.Should().Contain("for: 15m");
monitoring.Should().Contain("severity: warning");
}
[Fact]
public void ApplicationSetExport_MustRemainManualRootOfGitOpsTree()
{
var readme = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "README.md"));
var appsetPath = Path.Combine(Inventory.BluejayRoot, "argocd", "applicationset-bluejay-infra.yaml");
File.Exists(appsetPath).Should().BeTrue();
var appset = File.ReadAllText(appsetPath);
appset.Should().Contain("kind: ApplicationSet");
appset.Should().Contain("name: bluejay-infra");
appset.Should().NotContain("\nstatus:");
appset.Should().NotContain("managedFields:");
readme.Should().Contain("root of this GitOps tree");
readme.Should().Contain("NOT self-managed");
readme.Should().Contain("kubectl -n argocd apply -f argocd/applicationset-bluejay-infra.yaml");
}
[Fact]
public void ApplicationSetExport_MustDiscoverAppsDirectoryOnMain()
{
var appset = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "argocd", "applicationset-bluejay-infra.yaml"));
appset.Should().Contain("path: apps/*");
appset.Should().Contain("revision: main");
appset.Should().Contain("repoURL: http://gitea-clusterip.gitea.svc:3000/bluejay/bluejay-infra.git");
appset.Should().Contain("path: '{{.path.path}}'");
appset.Should().Contain("targetRevision: main");
appset.Should().Contain("ServerSideApply=true");
appset.Should().Contain("RespectIgnoreDifferences=true");
}
[Fact]
public void ApplicationSetExport_MustPreserveStatefulSetIgnoreDifferences()
{
var appset = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "argocd", "applicationset-bluejay-infra.yaml"));
appset.Should().Contain("jsonPointers:");
appset.Should().Contain("- /spec/volumeClaimTemplates");
appset.Should().Contain(".spec.volumeClaimTemplates[]?.status");
Regex.Matches(appset, "kind: StatefulSet").Should().HaveCount(4);
foreach (var (name, ns) in new[]
{
("zabbix-postgres", "zabbix"),
("guac-mysql", "guacamole"),
("matrix-postgres", "matrix"),
("authentik-postgres", "authentik"),
})
{
appset.Should().Contain($"name: {name}");
appset.Should().Contain($"namespace: {ns}");
}
}
[Fact] [Fact]
public void Monitoring_BlackboxTargetsForOidcSensitiveServices_MustUseAnonymousHealthRoutesWhenAvailable() public void Monitoring_BlackboxTargetsForOidcSensitiveServices_MustUseAnonymousHealthRoutesWhenAvailable()
{ {
@@ -612,7 +739,6 @@ public sealed class FleetManifestLintTests
var expectedFiles = new[] var expectedFiles = new[]
{ {
"1password-item.yaml", "1password-item.yaml",
"argocd-application.yaml",
"certificate-web.yaml", "certificate-web.yaml",
"clusterrole-operator.yaml", "clusterrole-operator.yaml",
"clusterrolebinding-operator.yaml", "clusterrolebinding-operator.yaml",
@@ -768,17 +894,62 @@ public sealed class FleetManifestLintTests
} }
[Fact] [Fact]
public void FcDeviceManagement_ArgocdApplicationMustMatchApplicationSetDiscoveryConventions() public void FcDeviceManagement_MustRelyOnApplicationSetDiscovery()
{ {
var application = FcDeviceManagementDocuments() var documents = FcDeviceManagementDocuments();
.Single(document => document.Kind == "Application" && document.Name == "infra-fc-devicemgmt");
application.Namespace.Should().Be("argocd"); documents.Should().NotContain(document => document.Kind == "Application");
application.Scalar("spec", "source", "repoURL")
.Should() var ns = documents.Single(document => document.Kind == "Namespace" && document.Name == "fc-devicemgmt");
.Be("http://gitea-clusterip.gitea.svc.cluster.local:3000/bluejay/bluejay-infra.git"); ns.FileText.Should().Contain("ArgoCD discovers this directory as Application `infra-fc-devicemgmt`.");
application.Scalar("spec", "source", "path").Should().Be("apps/fc-devicemgmt"); }
application.Scalar("spec", "destination", "namespace").Should().Be("fc-devicemgmt");
[Fact]
public void BroaderHardeningDeployments_MustAnnotateAnonymousHealthProbeIntent()
{
foreach (var expected in BroaderHardeningDeployments)
{
var deployment = AppDocuments(expected.Key)
.Single(document => document.Kind == "Deployment" && document.Name == expected.Value.Deployment);
PodAnnotation(deployment, "fc.flowercore.io/healthz-anon").Should().Be("true");
PodAnnotation(deployment, "fc.flowercore.io/probe-path").Should().Be(expected.Value.ProbePath);
}
}
[Fact]
public void BroaderHardeningDeployments_MustDocumentForwardedProtoAuthPosture()
{
foreach (var expected in BroaderHardeningDeployments)
{
var deployment = AppDocuments(expected.Key)
.Single(document => document.Kind == "Deployment" && document.Name == expected.Value.Deployment);
deployment.FileText.Should().Contain(
"fc-safe-to-expose: X-Forwarded-Proto handled by AddFlowerCoreWebAuth (ADR-178)");
}
}
[Fact]
public void BroaderHardeningInternalApps_MustOnlyPrestageCommentedPublicMethodAllowlist()
{
foreach (var app in BroaderHardeningInternalPrestageApps)
{
var documents = AppDocuments(app);
var text = string.Join(Environment.NewLine, documents.Select(document => document.FileText));
text.Should().Contain("PUBLIC HOST PRE-STAGING (DISABLED - Sprint 61+ exposure go-decision only)");
text.Should().Contain("# - match: Host(`");
text.Should().Contain("Method(`GET`) || Method(`HEAD`)");
documents
.Where(document => document.Kind == "IngressRoute")
.SelectMany(document => document.MappingSequence("spec", "routes"))
.Select(route => ManifestNodeExtensions.Scalar(route, "match") ?? string.Empty)
.Should()
.NotContain(match => match.Contains(".flowercore.io", StringComparison.Ordinal),
"Sprint 61 broader hardening only pre-stages commented public hosts for internal-only apps");
}
} }
[Fact] [Fact]