Merge pull request：由 monitoring 提供 Prometheus Operator CRD

首期使用静态 Account 凭据；SPIRE Auth Callout 后续见 #56。YAML 与 collection tests 已通过，Ansible lint 卡在无关的 Galaxy 依赖下载。

.gitea/workflows/kind-on-kata-smoke.yml

@@ -1,63 +0,0 @@
----
-name: kind-on-kata-smoke
-
-on:
-  push:
-    branches:
-      - poc/kind-on-kata
-    paths:
-      - .gitea/workflows/kind-on-kata-smoke.yml
-  workflow_dispatch:
-
-jobs:
-  smoke:
-    runs-on: kata-poc
-    steps:
-      - name: Create nested kind cluster
-        shell: sh
-        env:
-          KIND_VERSION: v0.27.0
-          KIND_NODE_IMAGE: kindest/node:v1.32.2@sha256:f226345927d7e348497136874b6d207e0b32cc52154ad8323129352923a3142f
-        run: |
-          set -eu
-          apk add --no-cache ca-certificates curl docker-cli
-          curl --retry 5 --retry-all-errors --connect-timeout 15 -fsSLo /tmp/kind \
-            "https://kind.sigs.k8s.io/dl/${KIND_VERSION}/kind-linux-amd64"
-          curl --retry 5 --retry-all-errors --connect-timeout 15 -fsSLo /tmp/kind.sha256sum \
-            "https://kind.sigs.k8s.io/dl/${KIND_VERSION}/kind-linux-amd64.sha256sum"
-          expected="$(awk '{print $1}' /tmp/kind.sha256sum)"
-          printf '%s  %s\n' "$expected" /tmp/kind | sha256sum -c -
-          install -m 0755 /tmp/kind /usr/local/bin/kind
-          docker info --format 'kernel={{.KernelVersion}} driver={{.Driver}}'
-          test "$(docker info --format '{{.Driver}}')" = overlay2
-
-          cleanup() {
-            kind delete cluster --name nested >/dev/null 2>&1 || true
-          }
-          trap cleanup EXIT
-
-          cat >/tmp/kind-config.yaml <<'EOF'
-          kind: Cluster
-          apiVersion: kind.x-k8s.io/v1alpha4
-          name: nested
-          nodes:
-            - role: control-plane
-              extraMounts:
-                - hostPath: /dev/kmsg
-                  containerPath: /dev/kmsg
-          EOF
-          kind create cluster -v 9 --retain --config /tmp/kind-config.yaml --image "$KIND_NODE_IMAGE" --wait 5m
-          docker exec nested-control-plane kubectl \
-            --kubeconfig=/etc/kubernetes/admin.conf wait \
-            --for=condition=Ready node/nested-control-plane --timeout=2m
-          docker exec nested-control-plane kubectl \
-            --kubeconfig=/etc/kubernetes/admin.conf run smoke \
-            --image=docker.io/library/busybox:1.37 --restart=Never \
-            --command -- sh -c 'echo kind-on-kata-ok'
-          docker exec nested-control-plane kubectl \
-            --kubeconfig=/etc/kubernetes/admin.conf wait \
-            --for=jsonpath='{.status.phase}'=Succeeded pod/smoke --timeout=2m
-          test "$(docker exec nested-control-plane kubectl \
-            --kubeconfig=/etc/kubernetes/admin.conf logs smoke)" = kind-on-kata-ok
-          kind delete cluster --name nested
-          trap - EXIT

clusters/homelab/apps/nats.yaml

@@ -0,0 +1,18 @@
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: nats
+  namespace: flux-system
+spec:
+  dependsOn:
+    - name: cert-manager
+    - name: external-secrets
+    - name: openebs
+  interval: 10m
+  path: ./platform/nats
+  prune: false
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+  timeout: 10m
+  wait: true

clusters/homelab/kustomization.yaml

@@ -10,6 +10,7 @@ resources:
   - apps/gitea-actions.yaml
   - apps/http-echo.yaml
   - apps/openebs.yaml
+  - apps/nats.yaml
   - apps/spire.yaml
   - apps/observability.yaml
   - apps/zot.yaml

infrastructure/dns/records.yml

@@ -12,6 +12,7 @@ homelab_dns:
       - { zone: ad.ddupan.top, name: pve3, type: A, values: [192.168.10.9] }
       - { zone: ad.ddupan.top, name: retrolab, type: A, values: [10.60.0.10] }
       - { zone: ad.ddupan.top, name: netbox, type: A, values: [192.168.10.127] }
+      - { zone: ad.ddupan.top, name: nats, type: A, values: [192.168.10.127] }
       - { zone: ad.ddupan.top, name: s3, type: A, values: [192.168.10.127] }
       - { zone: ad.ddupan.top, name: spire-oidc, type: A, values: [192.168.10.127] }
       - { zone: ad.ddupan.top, name: zot, type: A, values: [192.168.10.127] }

platform/cert-manager/README.md

@@ -119,6 +119,10 @@ issuerRef:
   kind: ClusterIssuer
 ```
 
+`values.yaml` 必须保持 `config.gatewayAPI.enabled: true`。`bao-acme` 的 HTTP-01
+solver 通过共享 Gateway 创建临时 HTTPRoute；关闭该项不会让 ClusterIssuer 变为
+NotReady，而是会让每个 Challenge 卡在 `gateway api is not enabled`。
+
 Issuance is capped by `default_directory_policy = role:bao-server`
 (`../../infrastructure/openbao/terraform/pki.tf`), which permits `ad.ddupan.top` subdomains only. Clients
 need the internal CA in their trust store — already true for the PVE nodes, the DC and

platform/cert-manager/values.yaml

@@ -44,6 +44,13 @@ cainjector:
     limits:
       memory: 256Mi
 
+# bao-acme solves HTTP-01 through the shared Gateway. The ClusterIssuer can be
+# accepted while this is disabled, but every Challenge then stays pending with
+# "gateway api is not enabled". Gateway API CRDs are installed by Envoy Gateway.
+config:
+  gatewayAPI:
+    enabled: true
+
 # ⚠ DNS-01 self-check: cert-manager polls authoritative NS for the _acme-challenge
 # TXT record before telling the CA to validate. By default it asks the cluster's
 # resolver, which for ad.ddupan.top is CoreDNS -> the Samba AD DC (k3s/coredns-custom.yaml).

platform/nats/README.md

@@ -0,0 +1,43 @@
+# NATS
+
+共享的轻量消息基础设施。首期为 Gitea microVM runner 提供 JetStream work queue，
+但 Account、subject 与部署位置均不与 CI controller 绑定，其他服务可按独立 Account
+复用。
+
+## 当前拓扑
+
+- 单节点 NATS；当前 homelab 没有资源运行有意义的三副本 JetStream quorum。
+- JetStream file store 使用 `localpv-zfs-ceph`，PVC 2 GiB。
+- 服务通过 k3s ServiceLB 在 `nats.ad.ddupan.top:4222` 暴露给内网；集群内客户端
+  使用 `nats.nats.svc.cluster.local:4222`。访问控制由 TLS、Account 与用户权限负责，
+  不额外维护易漂移的源 IP 白名单。
+- TLS 证书由 `bao-acme` 签发。PVE 节点已信任内部 CA。
+- `SYS` Account 用于管理；`CI` Account 启用 JetStream，存储上限 1 GiB。
+
+首期使用静态用户，密码只存在 OpenBao `kv/k8s/nats`：
+
+```text
+sys_password
+ci_producer_password
+ci_worker_password
+```
+
+`ci-producer` 只能发布 `ci.runner.>` 并调用必要的 JetStream API；`ci-worker`
+只能调用 JetStream pull/ACK API。二者都不能读取另一个 Account 的 subject。
+
+后续 SPIRE/Auth Callout 动态认证见 homelab-infra issue #56。该迁移只替换连接
+凭据，不改变 Account、stream、subject 或 consumer。
+
+## CI stream 约定
+
+controller 首次启动时幂等创建 `CI_RUNNER` stream：`ci.runner.*`、
+`WorkQueuePolicy`、file storage、24h/10000 条/256 MiB 上限。每类 runner 使用独立
+subject 和 durable pull consumer；同类型的多个 worker 共享 durable consumer。
+ACK 后消息立即删除，不保存 CI 历史。
+
+## 验证
+
+```bash
+kubectl -n nats get helmrelease,pod,pvc,certificate,externalsecret
+kubectl -n nats logs statefulset/nats -c nats
+```

platform/nats/certificate.yaml

@@ -0,0 +1,20 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: nats-ad-ddupan-top
+  namespace: nats
+spec:
+  secretName: nats-server-tls
+  issuerRef:
+    name: bao-acme
+    kind: ClusterIssuer
+    group: cert-manager.io
+  commonName: nats.ad.ddupan.top
+  dnsNames:
+    - nats.ad.ddupan.top
+  duration: 720h
+  renewBefore: 168h
+  privateKey:
+    algorithm: ECDSA
+    size: 256
+    rotationPolicy: Always

platform/nats/external-secret.yaml

@@ -0,0 +1,16 @@
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: nats-auth
+  namespace: nats
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    kind: ClusterSecretStore
+    name: openbao
+  target:
+    creationPolicy: Owner
+    name: nats-auth
+  dataFrom:
+    - extract:
+        key: k8s/nats

platform/nats/helmrelease.yaml

@@ -0,0 +1,31 @@
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: nats
+  namespace: nats
+spec:
+  chart:
+    spec:
+      chart: nats
+      interval: 1h
+      sourceRef:
+        kind: HelmRepository
+        name: nats
+      version: 2.14.2
+  driftDetection:
+    mode: enabled
+  install:
+    strategy:
+      name: RetryOnFailure
+      retryInterval: 5m
+  interval: 30m
+  releaseName: nats
+  targetNamespace: nats
+  timeout: 10m
+  upgrade:
+    strategy:
+      name: RetryOnFailure
+      retryInterval: 5m
+  valuesFrom:
+    - kind: ConfigMap
+      name: nats-values

platform/nats/helmrepository.yaml

@@ -0,0 +1,8 @@
+apiVersion: source.toolkit.fluxcd.io/v1
+kind: HelmRepository
+metadata:
+  name: nats
+  namespace: nats
+spec:
+  interval: 1h
+  url: https://nats-io.github.io/k8s/helm/charts/

platform/nats/kustomization.yaml

@@ -0,0 +1,17 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+generatorOptions:
+  disableNameSuffixHash: true
+  labels:
+    reconcile.fluxcd.io/watch: Enabled
+configMapGenerator:
+  - name: nats-values
+    namespace: nats
+    files:
+      - values.yaml=values.yaml
+resources:
+  - namespace.yaml
+  - helmrepository.yaml
+  - external-secret.yaml
+  - certificate.yaml
+  - helmrelease.yaml

platform/nats/namespace.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: nats

platform/nats/values.yaml

@@ -0,0 +1,74 @@
+config:
+  jetstream:
+    enabled: true
+    fileStore:
+      enabled: true
+      maxSize: 2Gi
+      pvc:
+        enabled: true
+        size: 2Gi
+        storageClassName: localpv-zfs-ceph
+    memoryStore:
+      enabled: true
+      maxSize: 64Mi
+  nats:
+    tls:
+      enabled: true
+      secretName: nats-server-tls
+  merge:
+    system_account: SYS
+    accounts:
+      SYS:
+        users:
+          - user: sys
+            password: "<< $NATS_SYS_PASSWORD >>"
+      CI:
+        jetstream:
+          max_memory: 32Mi
+          max_file: 1Gi
+          max_streams: 16
+          max_consumers: 64
+          max_bytes_required: true
+        users:
+          - user: ci-producer
+            password: "<< $NATS_CI_PRODUCER_PASSWORD >>"
+            permissions:
+              publish:
+                allow: [ci.runner.>, $JS.API.>]
+              subscribe:
+                allow: [_INBOX.>]
+          - user: ci-worker
+            password: "<< $NATS_CI_WORKER_PASSWORD >>"
+            permissions:
+              publish:
+                allow: [$JS.API.>, $JS.ACK.>]
+              subscribe:
+                allow: [_INBOX.>]
+
+container:
+  env:
+    NATS_SYS_PASSWORD:
+      valueFrom:
+        secretKeyRef: {name: nats-auth, key: sys_password}
+    NATS_CI_PRODUCER_PASSWORD:
+      valueFrom:
+        secretKeyRef: {name: nats-auth, key: ci_producer_password}
+    NATS_CI_WORKER_PASSWORD:
+      valueFrom:
+        secretKeyRef: {name: nats-auth, key: ci_worker_password}
+  resources:
+    requests: {cpu: 25m, memory: 64Mi}
+    limits: {memory: 192Mi}
+
+natsBox:
+  enabled: false
+
+promExporter:
+  enabled: true
+  podMonitor:
+    enabled: true
+
+service:
+  merge:
+    spec:
+      type: LoadBalancer

platform/observability/README.md

@@ -56,8 +56,10 @@ hosts and `logs/vlogs-ingress.yaml` to push their logs.
 | Manage   | **victoria-metrics-operator** | VMSingle/VMAgent/VMAlert/VMAlertmanager/VMRule **and** VLSingle as CRDs |
 | Expose   | **Tailscale ingress** (private) + **Authelia OIDC** | admin tool: private + SSO |
 
-Grafana's Prometheus-operator converter is on, so any chart shipping a
+VictoriaMetrics Operator 的 Prometheus converter 已启用；官方
-`ServiceMonitor`/`PodMonitor`/`PrometheusRule` is scraped automatically.
+`prometheus-operator-crds` chart 由 `operator/` 一并管理。因此应用 chart 可以原生
+声明 `ServiceMonitor`、`PodMonitor` 或 `PrometheusRule`，再由 converter 转换为对应
+VM 资源，不需要每个应用额外维护一份 `VM*Scrape`。
 
 ## Architecture
 

platform/observability/kustomization.yaml

@@ -3,6 +3,7 @@ kind: Kustomization
 resources:
   - namespace.yaml
   - helmrepository.yaml
+  - prometheus-helmrepository.yaml
   - grafana-helmrepository.yaml
   - operator
   - metrics

platform/observability/operator/kustomization.yaml

@@ -10,4 +10,5 @@ configMapGenerator:
     files:
       - values.yaml=values.yaml
 resources:
+  - prometheus-crds-helmrelease.yaml
   - helmrelease.yaml

platform/observability/operator/prometheus-crds-helmrelease.yaml

@@ -0,0 +1,29 @@
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: prometheus-operator-crds
+  namespace: monitoring
+spec:
+  chart:
+    spec:
+      chart: prometheus-operator-crds
+      interval: 1h
+      sourceRef:
+        kind: HelmRepository
+        name: prometheus-community
+        namespace: monitoring
+      version: 32.0.0
+  install:
+    crds: CreateReplace
+    strategy:
+      name: RetryOnFailure
+      retryInterval: 5m
+  interval: 30m
+  releaseName: prometheus-operator-crds
+  targetNamespace: monitoring
+  timeout: 10m
+  upgrade:
+    crds: CreateReplace
+    strategy:
+      name: RetryOnFailure
+      retryInterval: 5m

platform/observability/prometheus-helmrepository.yaml

@@ -0,0 +1,8 @@
+apiVersion: source.toolkit.fluxcd.io/v1
+kind: HelmRepository
+metadata:
+  name: prometheus-community
+  namespace: monitoring
+spec:
+  interval: 1h
+  url: https://prometheus-community.github.io/helm-charts