Update mcr.microsoft.com/k8s/csi/smb-csi Docker tag to v1.17.0

.gitea/workflows/ci.yml

@@ -29,62 +29,3 @@ jobs:
           terraform init -backend=false
           terraform validate
         working-directory: 2-nomad-config
-
-  nomad-validate:
-    name: Nomad job spec validate
-    runs-on: ubuntu-latest
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install Nomad CLI
-        run: |
-          curl -fsSL https://apt.releases.hashicorp.com/gpg | gpg --dearmor -o /usr/share/keyrings/hashicorp.gpg
-          . /etc/os-release
-          echo "deb [signed-by=/usr/share/keyrings/hashicorp.gpg] https://apt.releases.hashicorp.com ${VERSION_CODENAME} main" | tee /etc/apt/sources.list.d/hashicorp.list
-          apt-get update && apt-get install -y nomad
-
-      - name: Validate all job specs
-        env:
-          NOMAD_ADDR: http://jaglan-beta-m20.lan:4646
-        run: |
-          find 2-nomad-config -name '*.nomad.hcl' | while read f; do
-            echo "==> $f"
-            nomad job validate "$f"
-          done
-
-  image-pull:
-    name: Docker image pull validation
-    runs-on: ubuntu-latest
-    # Only run on PRs that touch nomad job specs
-    if: github.event_name == 'pull_request'
-
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Pull changed images
-        run: |
-          git fetch origin ${{ github.base_ref }}
-          IMAGES=$(git diff origin/${{ github.base_ref }}...HEAD -- '*.nomad.hcl' \
-            | grep '^+\s*image\s*=' \
-            | grep -oP '"[^"]+:[^"]+"' \
-            | tr -d '"' \
-            | sort -u || true)
-
-          if [ -z "$IMAGES" ]; then
-            echo "No image changes detected, skipping pull."
-            exit 0
-          fi
-
-          FAILED=0
-          while IFS= read -r image; do
-            echo "==> Pulling $image"
-            if ! docker pull "$image"; then
-              echo "ERROR: Failed to pull $image"
-              FAILED=1
-            fi
-          done <<< "$IMAGES"
-
-          exit $FAILED

1-nixos-node/.terraform.lock.hcl

@@ -2,34 +2,22 @@
 # Manual edits may be lost in future updates.
 
 provider "registry.terraform.io/hashicorp/null" {
-  version     = "3.3.1"
+  version     = "3.2.1"
-  constraints = "3.3.1"
+  constraints = "3.2.1"
   hashes = [
-    "h1:4pjRixNj9/nijyC0jrCr8tYOpZ8afFwZ2M86y81PMa0=",
+    "h1:FbGfc+muBsC17Ohy5g806iuI1hQc4SIexpYCrQHQd8w=",
-    "h1:6H++HbVhT9h31TNdGvlkW+2rjeWzgdjy98zqWpEJbgk=",
+    "zh:58ed64389620cc7b82f01332e27723856422820cfd302e304b5f6c3436fb9840",
-    "h1:8fi/ACgBQzyw1gloPdzewHbGNeNCX1roaKHRYA1oJIM=",
+    "zh:62a5cc82c3b2ddef7ef3a6f2fedb7b9b3deff4ab7b414938b08e51d6e8be87cb",
-    "h1:EVks/Xyl9ffLEDraAp8RSsynzoVbTHOsof5n2niAsa0=",
+    "zh:63cff4de03af983175a7e37e52d4bd89d990be256b16b5c7f919aff5ad485aa5",
-    "h1:GYp3g8OhJCT2nc0Nv5s8HPh9nsMydHbjyUh6P4sE+8w=",
+    "zh:74cb22c6700e48486b7cabefa10b33b801dfcab56f1a6ac9b6624531f3d36ea3",
-    "h1:KWpBuTftQiLorSdw8QDMivKf6IhvVV0RzrdWSN53Qzs=",
-    "h1:TuxJq10DVnRP7c5HBZPyyvQGcckNVfijyU1eXEu5e4M=",
-    "h1:VMDxsLCSHpRC04bNeQw0JTvm5HhShID64QCSPvi9DRc=",
-    "h1:c7EI8Sso93CiiAmD7P/53OOjAm5A7Q2+Z30aUTUFaEs=",
-    "h1:m5FqidbIgh+E9OigiZh8/xbkvpUQFSj3hZo/jqNLCLQ=",
-    "h1:mV9WSUbshqmqPnhbOg198pgnjJQNnYixjXlovJBbl54=",
-    "h1:oTK+zJCvllZur0nfzBZFGbflcZbvxnESJxepZprFRik=",
-    "zh:08c59776542ea16e5a8545752787b17ff412922182b4cfabe16139197be8ac44",
-    "zh:123109cc7e5ed6d515787fbc212f2a3fd5e75647bb24ab7c801ccd4d4ed42451",
-    "zh:14b3fa4372754b54844b41d5dbd4671a292d8d6828b90169061feb4d7b15dd05",
-    "zh:56a4daaa3212f57b764bf3d1f333141c6610c5f21abb240e0111221f7c7fa4d4",
     "zh:78d5eefdd9e494defcb3c68d282b8f96630502cac21d1ea161f53cfe9bb483b3",
-    "zh:7e888a026dbacd2474a42264227ae35f639780f0f0c613529d10a95cd61988b3",
+    "zh:79e553aff77f1cfa9012a2218b8238dd672ea5e1b2924775ac9ac24d2a75c238",
-    "zh:85a53646267e87d600df7124e4767ffde9bba3b6356d45d961618bdd68131cc7",
+    "zh:a1e06ddda0b5ac48f7e7c7d59e1ab5a4073bbcf876c73c0299e4610ed53859dc",
-    "zh:8ffa0e9c7c39b2ab0905b472465d6e35ef0b776b3f6273bb34c150340b61bff1",
+    "zh:c37a97090f1a82222925d45d84483b2aa702ef7ab66532af6cbcfb567818b970",
-    "zh:9846510a1841530d4403f4818e233f91e3b3bade7441047599fbf800742f65be",
+    "zh:e4453fbebf90c53ca3323a92e7ca0f9961427d2f0ce0d2b65523cc04d5d999c2",
-    "zh:afa98d44860875f037c6def0a7e6ff208e042712ba771f620482b143cd336891",
+    "zh:e80a746921946d8b6761e77305b752ad188da60688cfd2059322875d363be5f5",
-    "zh:bdca130d9ef27488ae0b13bc8fd8019e8bbdd4f2ceff29da066bd333165d68c5",
+    "zh:fbdb892d9822ed0e4cb60f2fedbdbb556e4da0d88d3b942ae963ed6ff091e48f",
-    "zh:cb3b94cbca88210dd0d1f11e2b8a89333f48c3857faf8f70f589072ce7c28610",
+    "zh:fca01a623d90d0cad0843102f9b8b9fe0d3ff8244593bd817f126582b52dd694",
-    "zh:f0c0ba87925fe32f84b80f7513b1efb1b0866f51f899ba825e95ad59ff09b018",
   ]
 }
 

1-nixos-node/node.tf

@@ -2,7 +2,7 @@ terraform {
   required_providers {
     null = {
       source  = "hashicorp/null"
-      version = "3.3.1"
+      version = "3.2.1"
     }
     template = {
       source  = "hashicorp/template"

2-nomad-config/1-data/csi-smb.nomad.hcl

@@ -6,7 +6,7 @@ job "csi-smb" {
       driver = "docker"
 
       config {
-        image = "mcr.microsoft.com/k8s/csi/smb-csi:v1.7.0"
+        image = "mcr.microsoft.com/k8s/csi/smb-csi:v1.17.0"
         args = [
           "--v=5",
           "--nodeid=${attr.unique.hostname}",

2-nomad-config/1-data/pgadmin.nomad.hcl

@@ -58,10 +58,8 @@ job "pgadmin" {
         ]
 
         check {
-          name     = "alive"
           type     = "http"
           path     = "/"
-          port     = "http"
           interval = "10s"
           timeout  = "2s"
         }

2-nomad-config/1-data/postgres.nomad.hcl

@@ -7,10 +7,6 @@ job "postgres" {
       connect {
         sidecar_service {}
       }
-
-      # Note: TCP checks are not valid for Connect-enabled services (runs through
-      # Envoy sidecar). Postgres is a single-writer DB that we never canary, so
-      # observable health via Consul is lower priority than other services.
     }
 
     task "postgres" {

2-nomad-config/2-ingress/authelia.nomad.hcl

@@ -33,10 +33,8 @@ job "authelia" {
       }
 
       check {
-        name     = "alive"
         type     = "http"
         path     = "/health"
-        port     = "http"
         interval = "10s"
         timeout  = "2s"
       }

2-nomad-config/2-ingress/traefik.nomad.hcl

@@ -35,8 +35,7 @@ job "traefik" {
 
       check {
         name     = "alive"
-        type     = "http"
+        type     = "tcp"
-        path     = "/ping"
         port     = "api"
         interval = "10s"
         timeout  = "2s"
@@ -86,9 +85,6 @@ api:
   dashboard: true
   insecure: true
 
-ping:
-  entryPoint: traefik
-
 providers:
   file:
     directory: "/etc/traefik/configs/"

2-nomad-config/act-runner.nomad.hcl

@@ -28,7 +28,8 @@ job "act-runner" {
       }
 
       env = {
-        GITEA_INSTANCE_URL = "https://gitea-1ef0bea6b75a4fd3e9393a9f7f7e4b02.othrayte.one"
+        GITEA_INSTANCE_URL = "http://localhost:3000"
+        CONFIG_FILE        = "/secrets/runner-config.yml"
       }
 
       # Required SOPS key:
@@ -42,6 +43,19 @@ EOF
         env         = true
       }
 
+      # Limit which images/labels the runner will accept so it doesn't pick up
+      # unrelated workloads if more runners are added later.
+      template {
+        data        = <<EOF
+runner:
+  labels:
+    - "ubuntu-latest:docker://node:20-bookworm"
+    - "ubuntu-22.04:docker://node:20-bookworm"
+    - "ubuntu-24.04:docker://node:20-bookworm"
+EOF
+        destination = "secrets/runner-config.yml"
+      }
+
       resources {
         cpu        = 200
         memory     = 256

2-nomad-config/deluge.nomad.hcl

@@ -54,10 +54,8 @@ EOH
       ]
 
       check {
-        name     = "alive"
         type     = "http"
         path     = "/"
-        port     = "http"
         interval = "10s"
         timeout  = "2s"
       }
@@ -80,10 +78,8 @@ EOH
       }
 
       check {
-        name     = "alive"
         type     = "http"
         path     = "/"
-        port     = "http"
         interval = "10s"
         timeout  = "2s"
       }

2-nomad-config/gitea.nomad.hcl

@@ -27,15 +27,11 @@ job "gitea" {
       tags = [
         "traefik.enable=true",
         "traefik.http.routers.gitea.middlewares=auth@file",
-        # Token subdomain — no auth middleware — used by act_runner step containers for git checkout
-        "traefik.http.routers.gitea-token.rule=Host(`gitea-1ef0bea6b75a4fd3e9393a9f7f7e4b02.othrayte.one`)",
       ]
 
       check {
-        name     = "alive"
         type     = "http"
-        path     = "/api/healthz"
+        path     = "/"
-        port     = "http"
         interval = "10s"
         timeout  = "2s"
       }

2-nomad-config/glance.nomad.hcl

@@ -12,7 +12,7 @@ job "glance" {
       driver = "docker"
 
       config {
-        image = "glanceapp/glance:v0.7.8"
+        image = "glanceapp/glance:latest"
         ports = ["http"]
         volumes = [
           "local/glance.yml:/app/config/glance.yml",
@@ -30,8 +30,7 @@ job "glance" {
 
         check {
           name     = "alive"
-          type     = "http"
+          type     = "tcp"
-          path     = "/"
           port     = "http"
           interval = "10s"
           timeout  = "2s"

2-nomad-config/jellyfin.nomad.hcl

@@ -28,11 +28,10 @@ job "jellyfin" {
 
         check {
           name     = "alive"
-          type     = "http"
+          type     = "tcp"
-          path     = "/health"
           port     = "http"
           interval = "10s"
-          timeout  = "5s"
+          timeout  = "2s"
         }
       }
 

2-nomad-config/ntfy.nomad.hcl

@@ -33,10 +33,8 @@ job "ntfy" {
       ]
 
       check {
-        name     = "alive"
         type     = "http"
         path     = "/healthz"
-        port     = "http"
         interval = "10s"
         timeout  = "2s"
       }

2-nomad-config/openreader.nomad.hcl

@@ -31,10 +31,8 @@ job "openreader" {
       ]
 
       check {
-        name     = "alive"
         type     = "http"
         path     = "/"
-        port     = "http"
         interval = "10s"
         timeout  = "2s"
       }
@@ -50,10 +48,8 @@ job "openreader" {
       }
 
       check {
-        name     = "alive"
         type     = "http"
         path     = "/"
-        port     = "http"
         interval = "10s"
         timeout  = "2s"
       }

2-nomad-config/prowlarr.nomad.hcl

@@ -34,9 +34,8 @@ job "prowlarr" {
       ]
 
       check {
-        name     = "alive"
         type     = "http"
-        path     = "/ping"
+        path     = "/"
         interval = "10s"
         timeout  = "2s"
       }
@@ -52,9 +51,8 @@ job "prowlarr" {
       }
 
       check {
-        name     = "alive"
         type     = "http"
-        path     = "/ping"
+        path     = "/"
         interval = "10s"
         timeout  = "2s"
       }

2-nomad-config/sonarr.nomad.hcl

@@ -37,9 +37,8 @@ job "sonarr" {
       ]
 
       check {
-        name     = "alive"
         type     = "http"
-        path     = "/ping"
+        path     = "/"
         interval = "10s"
         timeout  = "2s"
       }
@@ -55,9 +54,8 @@ job "sonarr" {
       }
 
       check {
-        name     = "alive"
         type     = "http"
-        path     = "/ping"
+        path     = "/"
         interval = "10s"
         timeout  = "2s"
       }

2-nomad-config/transfer.nomad.hcl

@@ -16,10 +16,8 @@ job "transfer" {
       ]
 
       check {
-        name     = "alive"
         type     = "http"
         path     = "/"
-        port     = "http"
         interval = "10s"
         timeout  = "2s"
       }

2-nomad-config/unifi.nomad.hcl

@@ -21,26 +21,6 @@ job "unifi-network" {
         UNIFI_STDOUT       = "true"
       }
 
-      # Register in Consul so Traefik and health checks can find it.
-      # address_mode=driver uses the macvlan IP (192.168.1.50) rather than the host IP.
-      service {
-        name         = "unifi-network"
-        port         = 8443
-        address_mode = "driver"
-
-        # TCP/HTTP checks from the Consul agent can't reach the macvlan IP (host↔macvlan
-        # isolation). Use a script check instead — it runs inside the container via
-        # docker exec and connects to localhost:8443 directly.
-        check {
-          name     = "alive"
-          type     = "script"
-          command  = "/usr/bin/curl"
-          args     = ["-sk", "--max-time", "5", "-o", "/dev/null", "https://localhost:8443"]
-          interval = "30s"
-          timeout  = "10s"
-        }
-      }
-
       volume_mount {
         volume      = "unraid_appdata_unifi_network"
         destination = "/unifi" # Expected root directory (contains data, log, cert subdirs)

cicd-plan.md

@@ -188,8 +188,8 @@ Most jobs already have Consul health checks — these can use `health_check = "c
 | frigate    | ✅            | ✅ `single-node-writer` | ⚠️ same — rolling                                                                 |
 | glance     | ✅            | no                      | ✅ yes                                                                            |
 | transfer   | ✅            | ✅ `single-node-writer` | ⚠️ rolling                                                                        |
-| openreader | ✅ `/`        | ✅ `single-node-writer` | ⚠️ rolling                                                                        |
+| openreader | ❌            | ✅ `single-node-writer` | ⚠️ add check first, then rolling                                                  |
-| unifi      | ✅ script     | ✅ `single-node-writer` | ⚠️ rolling                                                                        |
+| unifi      | ❌            | ✅ `single-node-writer` | ⚠️ add check first, then rolling                                                  |
 | traefik    | (ingress)     | ✅                      | ⚠️ rolling — downtime risk, promote quickly                                       |
 | authelia   | (ingress)     | ✅                      | ✅ stateless config, canary fine                                                  |
 | renovate   | batch job     | n/a                     | n/a — no deployment model                                                         |
@@ -293,13 +293,13 @@ exit 1
 
 ## Implementation Order
 
-- [x] **Phase 1a**: Create `act-runner.nomad.hcl` + Terraform wrapper, register runner token in Gitea, get a hello-world workflow green
+- [ ] **Phase 1a**: Create `act-runner.nomad.hcl` + Terraform wrapper, register runner token in Gitea, get a hello-world workflow green
-- [x] **Phase 1b**: Add `terraform fmt` + `terraform validate -backend=false` workflow — no secrets needed
+- [ ] **Phase 1b**: Add `terraform fmt` + `terraform validate -backend=false` workflow — no secrets needed
-- [x] **Phase 1c**: Add Nomad validate step — add `NOMAD_ADDR` + read-only `NOMAD_TOKEN` to Gitea secrets
+- [ ] **Phase 1c**: Add Nomad validate step — add `NOMAD_ADDR` + read-only `NOMAD_TOKEN` to Gitea secrets
-- [x] **Phase 2**: Add image pull validation step to the workflow
+- [ ] **Phase 2**: Add image pull validation step to the workflow
 - [ ] **Phase 3a**: Add `update` stanzas to ntfy and glance (simplest, no volume conflict)
-- [ ] **Phase 3b**: Add rolling `update` stanzas to remaining service jobs (jellyfin, sonarr, prowlarr, deluge, gitea, immich, transfer, frigate, openreader, unifi, authelia, traefik)
+- [ ] **Phase 3b**: Add rolling `update` stanzas to remaining service jobs (jellyfin, sonarr, etc.)
-- [x] **Phase 3c**: Add health checks to openreader and unifi before adding update stanzas
+- [ ] **Phase 3c**: Add health checks to openreader and unifi before adding update stanzas
 - [ ] **Phase 4a**: Add on-push workflow that runs `terraform apply -auto-approve` using full credential set
 - [ ] **Phase 4b**: Add deployment promotion/revert polling script
 - [ ] **Phase 4c**: Wire ntfy notifications for promote/revert outcomes