birbit stack

* Remove invalid dashboard and panel ids from alert rules

* Pin grafana and prometheus versions

* Configure custom grafana server URL

.gitea/workflows/test-k8s-deploy.yml

@@ -1,23 +1,16 @@
 name: K8s Deploy Test
 
 on:
-  pull_request:
-    branches: '*'
   push:
-    branches:
-      - main
-      - ci-test
-    paths-ignore:
-      - '.gitea/workflows/triggers/*'
-
-# Needed until we can incorporate docker startup into the executor container
-env:
-  DOCKER_HOST: unix:///var/run/dind.sock
+    branches: '*'
+    paths:
+      - '!**'
+      - '.gitea/workflows/triggers/fixturenet-laconicd-test'
 
 jobs:
   test:
-    name: "Run deploy test suite"
-    runs-on: ubuntu-latest
+    name: "Run deploy test suite on kind/k8s"
+    runs-on: ubuntu-22.04-with-syn-ethdb
     steps:
       - name: "Clone project repository"
         uses: actions/checkout@v3
@@ -41,15 +34,9 @@ jobs:
         run: ./scripts/create_build_tag_file.sh
       - name: "Build local shiv package"
         run: ./scripts/build_shiv_package.sh
-      - name: Start dockerd # Also needed until we can incorporate into the executor
-        run: |
-          dockerd -H $DOCKER_HOST --userland-proxy=false &
-          sleep 5
-      - name: "Install Go"
-        uses: actions/setup-go@v4
-        with:
-          go-version: '1.21'
-      - name: "Install Kind"
-        run: go install sigs.k8s.io/kind@v0.20.0
-      - name: "Debug Kind"
-        run: kind create cluster --retain && docker logs kind-control-plane
+      - name: "Install kind"
+        run: ./tests/scripts/install-kind.sh
+      - name: "Install Kubectl"
+        run: ./tests/scripts/install-kubectl.sh
+      - name: "Run k8s deployment test"
+        run: ./tests/k8s-deploy/run-deploy-test.sh

.gitea/workflows/test-webapp.yml

@@ -41,6 +41,8 @@ jobs:
         run: ./scripts/create_build_tag_file.sh
       - name: "Build local shiv package"
         run: ./scripts/build_shiv_package.sh
+      - name: "Install wget" # 20240109 - Only needed until the executors are updated.
+        run: apt update && apt install -y wget
       - name: Start dockerd # Also needed until we can incorporate into the executor
         run: |
           dockerd -H $DOCKER_HOST --userland-proxy=false &

.gitea/workflows/triggers/test-k8s-deploy

@@ -0,0 +1 @@
+Change this file to trigger running the test-k8s-deploy CI job

stack_orchestrator/data/compose/docker-compose-fixturenet-laconicd.yml

@@ -2,7 +2,7 @@ services:
   laconicd:
     restart: unless-stopped
     image: cerc/laconicd:local
-    command: ["sh", "/docker-entrypoint-scripts.d/create-fixturenet.sh"]
+    entrypoint: ["sh", "/docker-entrypoint-scripts.d/create-fixturenet.sh"]
     volumes:
       # The cosmos-sdk node's database directory:
       - laconicd-data:/root/.laconicd
@@ -15,12 +15,12 @@ services:
       - "6060"
       - "26657"
       - "26656"
-      - "9473"
+      - "9473:9473"
       - "8545"
       - "8546"
       - "9090"
       - "9091"
-      - "1317"
+      - "1317:1317"
   cli:
     image: cerc/laconic-registry-cli:local
     volumes:

stack_orchestrator/data/compose/docker-compose-geojson.yml

@@ -0,0 +1,8 @@
+version: "3.2"
+
+services:
+  geojson:
+    image: cerc/geojson:local
+    restart: always
+    ports:
+      - 0.0.0.0:8080:8080

stack_orchestrator/data/compose/docker-compose-grafana.yml

@@ -0,0 +1,23 @@
+version: "3.7"
+
+services:
+  grafana:
+    image: grafana/grafana:10.2.2
+    restart: always
+    environment:
+      GF_SERVER_ROOT_URL: ${GF_SERVER_ROOT_URL}
+    volumes:
+      - ../config/monitoring/grafana/provisioning:/etc/grafana/provisioning
+      - ../config/monitoring/grafana/dashboards:/etc/grafana/dashboards
+      - grafana_storage:/var/lib/grafana
+    ports:
+      - "3000"
+    healthcheck:
+      test: ["CMD", "nc", "-vz", "localhost", "3000"]
+      interval: 30s
+      timeout: 5s
+      retries: 10
+      start_period: 3s
+
+volumes:
+  grafana_storage:

stack_orchestrator/data/compose/docker-compose-node-exporter.yml

@@ -0,0 +1,15 @@
+version: '3.8'
+
+services:
+  node-exporter:
+    image: prom/node-exporter:latest
+    restart: unless-stopped
+    command:
+      - '--web.listen-address=:9100'
+      - '--path.rootfs=/host'
+      - '--collector.systemd'
+      - '--collector.processes'
+    network_mode: host
+    pid: host
+    volumes:
+      - '/:/host:ro,rslave'

stack_orchestrator/data/compose/docker-compose-osmosis-front-end-urbit.yml

@@ -0,0 +1,22 @@
+version: "3.2"
+
+services:
+  osmosis-front-end:
+    image: cerc/osmosis-front-end-urbit:local
+    restart: on-failure
+    environment:
+      - NEXT_PUBLIC_WEB_API_BASE_URL=${CERC_WEB_API_BASE_URL}
+      - ASSET_LIST_COMMIT_HASH=a326bcefc51372b4912be5a2a2fa84a5d142a438
+      - NEXT_PUBLIC_BASEPATH=/apps/osmosis
+      - NEXT_PUBLIC_URBIT_DEPLOYMENT=true
+    working_dir: /app/packages/web
+    command: ["./build-app-for-urbit.sh"]
+    volumes:
+      - ../config/osmosis/build-app-for-urbit.sh:/app/packages/web/build-app-for-urbit.sh
+      - ../config/osmosis/.env.production:/app/packages/web/.env.production
+      - urbit_app_builds:/app-builds
+      - ../config/osmosis/urbit-files/mar:/app/packages/web/mar
+      - ../config/osmosis/urbit-files/desk.docket-0:/app/packages/web/desk.docket-0
+
+volumes:
+  urbit_app_builds:

stack_orchestrator/data/compose/docker-compose-osmosis-front-end.yml

@@ -6,10 +6,12 @@ services:
     restart: on-failure
     environment:
       - NEXT_PUBLIC_WEB_API_BASE_URL=${CERC_WEB_API_BASE_URL}
+      - ASSET_LIST_COMMIT_HASH=a326bcefc51372b4912be5a2a2fa84a5d142a438
     working_dir: /app/packages/web
     command: ["./build-app.sh"]
     volumes:
       - ../config/osmosis/build-app.sh:/app/packages/web/build-app.sh
+      - ../config/osmosis/.env.production:/app/packages/web/.env.production
       - app_builds:/app-builds
 
   nginx:

stack_orchestrator/data/compose/docker-compose-prom-server.yml

@@ -0,0 +1,57 @@
+version: "3.7"
+
+services:
+  prometheus:
+    image: prom/prometheus:v2.49.1
+    restart: always
+    volumes:
+      - ../config/monitoring/prometheus:/etc/prometheus
+      - prometheus_data:/prometheus
+    ports:
+      - "9090"
+    healthcheck:
+      test: ["CMD", "nc", "-vz", "localhost", "9090"]
+      interval: 30s
+      timeout: 5s
+      retries: 10
+      start_period: 3s
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+
+  blackbox:
+    image: prom/blackbox-exporter:latest
+    restart: always
+    volumes:
+      - ../config/monitoring/blackbox.yml:/etc/blackbox_exporter/config.yml
+    ports:
+      - '9115'
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+
+  chain-head-exporter:
+    image: cerc/watcher-ts:local
+    restart: always
+    working_dir: /app/packages/cli
+    environment:
+      ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT}
+      FIL_RPC_ENDPOINT: ${CERC_FIL_RPC_ENDPOINT}
+      ETH_RPC_API_KEY: ${CERC_INFURA_KEY}
+      PORT: ${CERC_METRICS_PORT}
+    command: ["sh", "-c", "yarn export-metrics:chain-heads"]
+    ports:
+      - '5000'
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+
+  postgres-exporter:
+    image: quay.io/prometheuscommunity/postgres-exporter
+    restart: always
+    volumes:
+      - ../config/monitoring/postgres-exporter.yml:/postgres_exporter.yml
+    ports:
+      - '9187'
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+
+volumes:
+  prometheus_data:

stack_orchestrator/data/compose/docker-compose-watcher-merkl-sushiswap-v3.yml

@@ -35,7 +35,7 @@ services:
       - ../config/watcher-merkl-sushiswap-v3/watcher-config-template.toml:/app/environments/watcher-config-template.toml
       - ../config/watcher-merkl-sushiswap-v3/start-job-runner.sh:/app/start-job-runner.sh
     ports:
-      - "9000"
+      - "9002:9000"
     healthcheck:
       test: ["CMD", "nc", "-v", "localhost", "9000"]
       interval: 20s
@@ -62,7 +62,7 @@ services:
       - ../config/watcher-merkl-sushiswap-v3/start-server.sh:/app/start-server.sh
     ports:
       - "127.0.0.1:3007:3008"
-      - "9001"
+      - "9003:9001"
     healthcheck:
       test: ["CMD", "nc", "-v", "localhost", "3008"]
       interval: 20s

stack_orchestrator/data/compose/docker-compose-watcher-sushiswap-v3.yml

@@ -35,7 +35,7 @@ services:
       - ../config/watcher-sushiswap-v3/watcher-config-template.toml:/app/environments/watcher-config-template.toml
       - ../config/watcher-sushiswap-v3/start-job-runner.sh:/app/start-job-runner.sh
     ports:
-      - "9000"
+      - "9000:9000"
     healthcheck:
       test: ["CMD", "nc", "-v", "localhost", "9000"]
       interval: 20s
@@ -62,7 +62,7 @@ services:
       - ../config/watcher-sushiswap-v3/start-server.sh:/app/start-server.sh
     ports:
       - "127.0.0.1:3008:3008"
-      - "9001"
+      - "9001:9001"
     healthcheck:
       test: ["CMD", "nc", "-v", "localhost", "3008"]
       interval: 20s

stack_orchestrator/data/config/monitoring/blackbox.yml

@@ -0,0 +1,7 @@
+modules:
+  http_2xx:
+    prober: http
+    timeout: 5s
+    http:
+      valid_status_codes: [] #default to 2xx
+      method: GET

stack_orchestrator/data/config/monitoring/grafana/dashboards/nodejs-app-dashboard.json

@@ -0,0 +1,943 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "datasource",
+          "uid": "grafana"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "description": "node.js prometheus client basic metrics",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "gnetId": 11159,
+  "graphTooltip": 0,
+  "id": 15,
+  "links": [],
+  "liveNow": false,
+  "panels": [
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "PBFA97CFB590B2093"
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 7,
+        "w": 10,
+        "x": 0,
+        "y": 0
+      },
+      "hiddenSeries": false,
+      "id": 6,
+      "legend": {
+        "alignAsTable": true,
+        "avg": true,
+        "current": true,
+        "max": true,
+        "min": true,
+        "show": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 1,
+      "links": [],
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "paceLength": 10,
+      "percentage": false,
+      "pluginVersion": "10.2.2",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "expr": "irate(process_cpu_user_seconds_total{instance=~\"$instance\"}[2m]) * 100",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "legendFormat": "User CPU - {{instance}}",
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "expr": "irate(process_cpu_system_seconds_total{instance=~\"$instance\"}[2m]) * 100",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "legendFormat": "Sys CPU - {{instance}}",
+          "refId": "B"
+        }
+      ],
+      "thresholds": [],
+      "timeRegions": [],
+      "title": "Process CPU Usage",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "mode": "time",
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "format": "percent",
+          "logBase": 1,
+          "show": true
+        },
+        {
+          "format": "short",
+          "logBase": 1,
+          "show": true
+        }
+      ],
+      "yaxis": {
+        "align": false
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "PBFA97CFB590B2093"
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 7,
+        "w": 9,
+        "x": 10,
+        "y": 0
+      },
+      "hiddenSeries": false,
+      "id": 8,
+      "legend": {
+        "alignAsTable": true,
+        "avg": true,
+        "current": true,
+        "max": true,
+        "min": true,
+        "show": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 1,
+      "links": [],
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "paceLength": 10,
+      "percentage": false,
+      "pluginVersion": "10.2.2",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "expr": "nodejs_eventloop_lag_seconds{instance=~\"$instance\"}",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "legendFormat": "{{instance}}",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeRegions": [],
+      "title": "Event Loop Lag",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "mode": "time",
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "format": "s",
+          "logBase": 1,
+          "show": true
+        },
+        {
+          "format": "short",
+          "logBase": 1,
+          "show": true
+        }
+      ],
+      "yaxis": {
+        "align": false
+      }
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "PBFA97CFB590B2093"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "fixedColor": "text",
+            "mode": "fixed"
+          },
+          "mappings": [
+            {
+              "options": {
+                "match": "null",
+                "result": {
+                  "text": "N/A"
+                }
+              },
+              "type": "special"
+            }
+          ],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              }
+            ]
+          },
+          "unit": "none"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 3,
+        "w": 5,
+        "x": 19,
+        "y": 0
+      },
+      "id": 2,
+      "interval": "",
+      "links": [],
+      "maxDataPoints": 100,
+      "options": {
+        "colorMode": "none",
+        "graphMode": "none",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "mean"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "name",
+        "wideLayout": true
+      },
+      "pluginVersion": "10.2.2",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "expr": "sum(nodejs_version_info{instance=~\"$instance\"}) by (version)",
+          "format": "time_series",
+          "instant": false,
+          "interval": "",
+          "intervalFactor": 1,
+          "legendFormat": "{{version}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Node.js Version",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "PBFA97CFB590B2093"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "fixedColor": "#F2495C",
+            "mode": "fixed"
+          },
+          "mappings": [
+            {
+              "options": {
+                "match": "null",
+                "result": {
+                  "text": "N/A"
+                }
+              },
+              "type": "special"
+            }
+          ],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "none"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 5,
+        "x": 19,
+        "y": 3
+      },
+      "id": 4,
+      "links": [],
+      "maxDataPoints": 100,
+      "options": {
+        "colorMode": "none",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "horizontal",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "pluginVersion": "10.2.2",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "expr": "sum(changes(process_start_time_seconds{instance=~\"$instance\"}[1m]))",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "legendFormat": "{{instance}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Process Restart Times",
+      "type": "stat"
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "PBFA97CFB590B2093"
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 7,
+        "w": 16,
+        "x": 0,
+        "y": 7
+      },
+      "hiddenSeries": false,
+      "id": 7,
+      "legend": {
+        "alignAsTable": true,
+        "avg": true,
+        "current": true,
+        "max": true,
+        "min": true,
+        "rightSide": true,
+        "show": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 1,
+      "links": [],
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "paceLength": 10,
+      "percentage": false,
+      "pluginVersion": "10.2.2",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "expr": "process_resident_memory_bytes{instance=~\"$instance\"}",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "legendFormat": "Process Memory - {{instance}}",
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "expr": "nodejs_heap_size_total_bytes{instance=~\"$instance\"}",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "legendFormat": "Heap Total - {{instance}}",
+          "refId": "B"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "expr": "nodejs_heap_size_used_bytes{instance=~\"$instance\"}",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "legendFormat": "Heap Used - {{instance}}",
+          "refId": "C"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "expr": "nodejs_external_memory_bytes{instance=~\"$instance\"}",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "legendFormat": "External Memory - {{instance}}",
+          "refId": "D"
+        }
+      ],
+      "thresholds": [],
+      "timeRegions": [],
+      "title": "Process Memory Usage",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "mode": "time",
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "format": "bytes",
+          "logBase": 1,
+          "show": true
+        },
+        {
+          "format": "short",
+          "logBase": 1,
+          "show": true
+        }
+      ],
+      "yaxis": {
+        "align": false
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "PBFA97CFB590B2093"
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 7,
+        "w": 8,
+        "x": 16,
+        "y": 7
+      },
+      "hiddenSeries": false,
+      "id": 9,
+      "legend": {
+        "alignAsTable": true,
+        "avg": true,
+        "current": true,
+        "max": true,
+        "min": true,
+        "show": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 1,
+      "links": [],
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "paceLength": 10,
+      "percentage": false,
+      "pluginVersion": "10.2.2",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "expr": "nodejs_active_handles_total{instance=~\"$instance\"}",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "legendFormat": "Active Handler - {{instance}}",
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "expr": "nodejs_active_requests_total{instance=~\"$instance\"}",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "legendFormat": "Active Request - {{instance}}",
+          "refId": "B"
+        }
+      ],
+      "thresholds": [],
+      "timeRegions": [],
+      "title": "Active Handlers/Requests Total",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "mode": "time",
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "format": "short",
+          "logBase": 1,
+          "show": true
+        },
+        {
+          "format": "short",
+          "logBase": 1,
+          "show": true
+        }
+      ],
+      "yaxis": {
+        "align": false
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "PBFA97CFB590B2093"
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 0,
+        "y": 14
+      },
+      "hiddenSeries": false,
+      "id": 10,
+      "legend": {
+        "alignAsTable": true,
+        "avg": true,
+        "current": true,
+        "max": true,
+        "min": true,
+        "rightSide": false,
+        "show": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 1,
+      "links": [],
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "paceLength": 10,
+      "percentage": false,
+      "pluginVersion": "10.2.2",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "expr": "nodejs_heap_space_size_total_bytes{instance=~\"$instance\"}",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "legendFormat": "Heap Total - {{instance}} - {{space}}",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeRegions": [],
+      "title": "Heap Total Detail",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "mode": "time",
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "format": "bytes",
+          "logBase": 1,
+          "show": true
+        },
+        {
+          "format": "short",
+          "logBase": 1,
+          "show": true
+        }
+      ],
+      "yaxis": {
+        "align": false
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "PBFA97CFB590B2093"
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 8,
+        "y": 14
+      },
+      "hiddenSeries": false,
+      "id": 11,
+      "legend": {
+        "alignAsTable": true,
+        "avg": true,
+        "current": true,
+        "max": true,
+        "min": true,
+        "rightSide": false,
+        "show": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 1,
+      "links": [],
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "paceLength": 10,
+      "percentage": false,
+      "pluginVersion": "10.2.2",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "expr": "nodejs_heap_space_size_used_bytes{instance=~\"$instance\"}",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "legendFormat": "Heap Used - {{instance}} - {{space}}",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeRegions": [],
+      "title": "Heap Used Detail",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "mode": "time",
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "format": "bytes",
+          "logBase": 1,
+          "show": true
+        },
+        {
+          "format": "short",
+          "logBase": 1,
+          "show": true
+        }
+      ],
+      "yaxis": {
+        "align": false
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "PBFA97CFB590B2093"
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 16,
+        "y": 14
+      },
+      "hiddenSeries": false,
+      "id": 12,
+      "legend": {
+        "alignAsTable": true,
+        "avg": true,
+        "current": true,
+        "max": true,
+        "min": true,
+        "rightSide": false,
+        "show": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 1,
+      "links": [],
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "paceLength": 10,
+      "percentage": false,
+      "pluginVersion": "10.2.2",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "expr": "nodejs_heap_space_size_available_bytes{instance=~\"$instance\"}",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "legendFormat": "Heap Used - {{instance}} - {{space}}",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeRegions": [],
+      "title": "Heap Available Detail",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "mode": "time",
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "format": "bytes",
+          "logBase": 1,
+          "show": true
+        },
+        {
+          "format": "short",
+          "logBase": 1,
+          "show": true
+        }
+      ],
+      "yaxis": {
+        "align": false
+      }
+    }
+  ],
+  "refresh": "10s",
+  "schemaVersion": 38,
+  "tags": [
+    "nodejs"
+  ],
+  "templating": {
+    "list": [
+      {
+        "current": {
+          "selected": true,
+          "text": [
+            "All"
+          ],
+          "value": [
+            "$__all"
+          ]
+        },
+        "datasource": {
+          "type": "prometheus",
+          "uid": "PBFA97CFB590B2093"
+        },
+        "definition": "label_values(nodejs_version_info, instance)",
+        "hide": 0,
+        "includeAll": true,
+        "label": "instance",
+        "multi": true,
+        "name": "instance",
+        "options": [],
+        "query": "label_values(nodejs_version_info, instance)",
+        "refresh": 1,
+        "regex": "",
+        "skipUrlSync": false,
+        "sort": 1,
+        "tagValuesQuery": "",
+        "tagsQuery": "",
+        "type": "query",
+        "useTags": false
+      }
+    ]
+  },
+  "time": {
+    "from": "now-15m",
+    "to": "now"
+  },
+  "timepicker": {
+    "refresh_intervals": [
+      "5s",
+      "10s",
+      "30s",
+      "1m",
+      "5m",
+      "15m",
+      "30m",
+      "1h",
+      "2h",
+      "1d"
+    ],
+    "time_options": [
+      "5m",
+      "15m",
+      "1h",
+      "6h",
+      "12h",
+      "24h",
+      "2d",
+      "7d",
+      "30d"
+    ]
+  },
+  "timezone": "",
+  "title": "NodeJS Application Dashboard",
+  "uid": "PTSqcpJWk",
+  "version": 3,
+  "weekStart": ""
+}

stack_orchestrator/data/config/monitoring/grafana/provisioning/alerting/contactpoints.yml

@@ -0,0 +1,14 @@
+# https://www.clever-cloud.com/blog/features/2021/12/03/slack-alerts-for-grafana/
+
+apiVersion: 1
+
+contactPoints:
+  - orgId: 1
+    name: SlackNotifier
+    receivers:
+      - uid: a71b06e3-58b6-41fe-af65-fbbb29653951
+        type: slack
+        settings:
+          # Slack hook URL (see https://api.slack.com/messaging/webhooks)
+          url: <YOUR_SLACK_HOOK_URL>
+        disableResolveMessage: false

stack_orchestrator/data/config/monitoring/grafana/provisioning/alerting/policies.yml

@@ -0,0 +1,15 @@
+# https://grafana.com/docs/grafana/latest/alerting/alerting-rules/create-notification-policy/
+
+apiVersion: 1
+
+policies:
+  - orgId: 1
+    receiver: grafana-default-email
+    group_by:
+      - grafana_folder
+      - alertname
+    routes:
+      - receiver: SlackNotifier
+        object_matchers:
+          # Add matchers below
+          # - ['grafana_folder', '=', 'MyAlerts']

stack_orchestrator/data/config/monitoring/grafana/provisioning/dashboards/dashboards.yml

@@ -0,0 +1,10 @@
+apiVersion: 1
+
+providers:
+  - name: dashboards
+    type: file
+    updateIntervalSeconds: 10
+    allowUiUpdates: true
+    options:
+      path: /etc/grafana/dashboards
+      foldersFromFilesStructure: true

stack_orchestrator/data/config/monitoring/grafana/provisioning/datasources/prometheus.yml

@@ -0,0 +1,16 @@
+apiVersion: 1
+
+datasources:
+  - id: 1
+    orgId: 1
+    name: Prometheus
+    type: prometheus
+    typeName: Prometheus
+    typeLogoUrl: public/app/plugins/datasource/prometheus/img/prometheus_logo.svg
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true
+    jsonData:
+      httpMethod: POST
+    version: 1
+    editable: true

stack_orchestrator/data/config/monitoring/postgres-exporter.yml

@@ -0,0 +1,8 @@
+auth_modules:
+  foo:
+    type: userpass
+    userpass:
+      username: username
+      password: password
+    options:
+      sslmode: disable

stack_orchestrator/data/config/monitoring/prometheus/prometheus.yml

@@ -0,0 +1,67 @@
+global:
+  scrape_interval:     10s
+  evaluation_interval: 15s
+
+rule_files:
+  # - "first.rules"
+  # - "second.rules"
+
+scrape_configs:
+  - job_name: prometheus
+    static_configs:
+      - targets: ['localhost:9090']
+
+  - job_name: node
+    static_configs:
+      # Add node-exporter targets to be monitored below
+      # - targets: ['example-host:9100']
+      #   labels:
+      #     instance: 'my-host'
+
+  - job_name: 'blackbox'
+    scrape_interval: 10s
+    metrics_path: /probe
+    params:
+      module: [http_2xx]
+    static_configs:
+      # Add URLs to be monitored below
+      - targets:
+        # - https://github.com
+    relabel_configs:
+      - source_labels: [__address__]
+        regex: (.*)(:80)?
+        target_label: __param_target
+      - source_labels: [__param_target]
+        regex: (.*)
+        target_label: instance
+        replacement: ${1}
+      - source_labels: []
+        regex: .*
+        target_label: __address__
+        replacement: blackbox:9115
+
+  - job_name: chain_heads
+    scrape_interval: 10s
+    metrics_path: /metrics
+    scheme: http
+    static_configs:
+      - targets: ['chain-head-exporter:5000']
+
+  - job_name: 'postgres'
+    scrape_interval: 30s
+    scrape_timeout: 30s
+    static_configs:
+      # Add DB targets below
+      # - targets: [example-server:5432]
+        # labels:
+          # instance: 'example-label'
+    metrics_path: /probe
+    params:
+      auth_module: [foo]
+    relabel_configs:
+      - source_labels: [__address__]
+        target_label: __param_target
+      - source_labels: [__param_target]
+        target_label: instance
+      - target_label: __address__
+        replacement: postgres-exporter:9187

stack_orchestrator/data/config/monitoring/watcher-alert-rules.yml

@@ -0,0 +1,933 @@
+# https://grafana.com/docs/grafana/latest/alerting/alerting-rules/create-grafana-managed-rule/
+
+apiVersion: 1
+
+groups:
+  - orgId: 1
+    name: watcher
+    folder: WatcherAlerts
+    interval: 30s
+    rules:
+      # Azimuth
+      - uid: azimuth_diff_external
+        title: azimuth_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="azimuth", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="azimuth", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
+        isPaused: false
+      - uid: censures_diff_external
+        title: censures_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="censures", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="censures", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
+        isPaused: false
+      - uid: claims_diff_external
+        title: claims_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="claims", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="claims", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
+        isPaused: false
+      - uid: conditional_star_release_diff_external
+        title: conditional_star_release_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="conditional_star_release", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="conditional_star_release", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
+        isPaused: false
+      - uid: delegated_sending_diff_external
+        title: delegated_sending_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="delegated_sending", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="delegated_sending", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
+        isPaused: false
+      - uid: ecliptic_diff_external
+        title: ecliptic_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="ecliptic", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="ecliptic", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
+        isPaused: false
+      - uid: linear_star_release_diff_external
+        title: linear_star_release_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="linear_star_release", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="azimuth", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
+        isPaused: false
+      - uid: polls_diff_external
+        title: polls_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="polls", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="polls", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
+        isPaused: false
+
+      # Sushi
+      - uid: sushiswap_diff_external
+        title: sushiswap_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="sushi", instance="sushiswap", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="filecoin"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="sushi", instance="sushiswap", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
+        isPaused: false
+      - uid: merkl_sushiswap_diff_external
+        title: merkl_sushiswap_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="sushi", instance="merkl_sushiswap", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="filecoin"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="sushi", instance="merkl_sushiswap", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
+        isPaused: false

stack_orchestrator/data/config/osmosis/.env.production

@@ -0,0 +1,3 @@
+NEXT_PUBLIC_COINGECKO_URL=https://api.coingecko.com
+
+NEXT_PUBLIC_ENABLE_FEATURES=true

stack_orchestrator/data/config/osmosis/build-app-for-urbit.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+
+set -e
+if [ -n "$CERC_SCRIPT_DEBUG" ]; then
+  set -x
+fi
+
+# Check and exit if a deployment already exists (on restarts)
+if [ -d /app-builds/osmosis/build ]; then
+  echo "Build already exists, remove volume to rebuild"
+  exit 0
+fi
+
+yarn build:static
+./build-urbit.sh
+
+# Move build to app-builds
+mkdir -p /app-builds/osmosis
+cp -r ./out /app-builds/osmosis/build
+
+cp -r mar /app-builds/osmosis/
+cp desk.docket-0 /app-builds/osmosis/

stack_orchestrator/data/config/osmosis/build-app.sh

@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 
 set -e
 if [ -n "$CERC_SCRIPT_DEBUG" ]; then

stack_orchestrator/data/config/osmosis/urbit-files/desk.docket-0

@@ -0,0 +1,10 @@
+:~  title+'Osmosis'
+    info+'Osmosis DEX Frontend, built and maintained by Laconic'
+    color+0xcd.75df
+    image+'https://altcoinsbox.com/wp-content/uploads/2023/03/osmosis-logo.png'
+    base+'osmosis'
+    glob-http+['REPLACE_WITH_GLOB_URL' REPLACE_WITH_GLOB_HASH]
+    version+[0 0 2]
+    website+'https://osmosis.zone/'
+    license+'MIT'
+==

stack_orchestrator/data/config/osmosis/urbit-files/mar/ico.hoon

@@ -0,0 +1,12 @@
+|_  dat=@
+++  grow
+  |%
+  ++  mime  [/image/x-icon (as-octs:mimes:html dat)]
+  --
+++  grab
+  |%
+  ++  mime  |=([p=mite q=octs] q.q)
+  ++  noun  @
+  --
+++  grad  %mime
+--

stack_orchestrator/data/config/osmosis/urbit-files/mar/jpg.hoon

@@ -0,0 +1,12 @@
+|_  dat=@
+++  grow
+  |%
+  ++  mime  [/image/jpeg (as-octs:mimes:html dat)]
+  --
+++  grab
+  |%
+  ++  mime  |=([p=mite q=octs] q.q)
+  ++  noun  @
+  --
+++  grad  %mime
+--

stack_orchestrator/data/config/osmosis/urbit-files/mar/map.hoon

@@ -0,0 +1,18 @@
+::
+::::  /hoon/map/mar
+  ::  Mark for js source maps
+/?    310
+::
+=,  eyre
+|_  mud=@
+++  grow
+  |%
+  ++  mime  [/application/octet-stream (as-octs:mimes:html (@t mud))]
+  --
+++  grab
+  |%                                                    ::  convert from
+  ++  mime  |=([p=mite q=octs] (@t q.q))
+  ++  noun  cord                                        ::  clam from %noun
+  --
+++  grad  %mime
+--

stack_orchestrator/data/config/osmosis/urbit-files/mar/webp.hoon

@@ -0,0 +1,12 @@
+|_  dat=@
+++  grow
+  |%
+  ++  mime  [/image/webp (as-octs:mimes:html dat)]
+  --
+++  grab
+  |%
+  ++  mime  |=([p=mite q=octs] q.q)
+  ++  noun  @
+  --
+++  grad  %mime
+--

stack_orchestrator/data/config/watcher-merkl-sushiswap-v3/watcher-config-template.toml

@@ -41,7 +41,7 @@
     timeTravelMaxAge = 86400 # 1 day
 
 [metrics]
-  host = "127.0.0.1"
+  host = "0.0.0.0"
   port = 9000
   [metrics.gql]
     port = 9001
@@ -84,8 +84,6 @@
   subgraphEventsOrder = true
   # Filecoin block time: https://docs.filecoin.io/basics/the-blockchain/blocks-and-tipsets#blocktime
   blockDelayInMilliSecs = 30000
-  prefetchBlocksInMem = false
-  prefetchBlockCount = 10
 
   # Boolean to switch between modes of processing events when starting the server.
   # Setting to true will fetch filtered events and required blocks in a range of blocks and then process them.

stack_orchestrator/data/config/watcher-sushiswap-v3/watcher-config-template.toml

@@ -41,7 +41,7 @@
     timeTravelMaxAge = 86400 # 1 day
 
 [metrics]
-  host = "127.0.0.1"
+  host = "0.0.0.0"
   port = 9000
   [metrics.gql]
     port = 9001
@@ -84,8 +84,6 @@
   subgraphEventsOrder = true
   # Filecoin block time: https://docs.filecoin.io/basics/the-blockchain/blocks-and-tipsets#blocktime
   blockDelayInMilliSecs = 30000
-  prefetchBlocksInMem = false
-  prefetchBlockCount = 10
 
   # Boolean to switch between modes of processing events when starting the server.
   # Setting to true will fetch filtered events and required blocks in a range of blocks and then process them.

stack_orchestrator/data/container-build/cerc-act-runner-task-executor/build.sh

@@ -2,4 +2,6 @@
 # Build a local version of the task executor for act-runner
 source ${CERC_CONTAINER_BASE_DIR}/build-base.sh
 SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
-docker build -t cerc/act-runner-task-executor:local -f ${CERC_REPO_BASE_DIR}/hosting/act-runner/Dockerfile.task-executor ${build_command_args} ${SCRIPT_DIR}
+
+cd ${CERC_REPO_BASE_DIR}/hosting/act-runner
+docker build -t cerc/act-runner-task-executor:local -f Dockerfile.task-executor ${build_command_args} .

stack_orchestrator/data/container-build/cerc-birbit/build.sh

@@ -0,0 +1,4 @@
+#!/usr/bin/env bash
+# Build the birbit image
+source ${CERC_CONTAINER_BASE_DIR}/build-base.sh
+docker build -t cerc/birbit:local -f ${CERC_REPO_BASE_DIR}/birbit/Dockerfile ${build_command_args} ${CERC_REPO_BASE_DIR}/birbit

stack_orchestrator/data/container-build/cerc-geojson/Dockerfile

@@ -0,0 +1,11 @@
+FROM node:14
+
+WORKDIR /app
+
+COPY . .
+
+RUN npm install && npm run build
+
+EXPOSE 8080
+
+CMD ["npm", "run", "serve"]

stack_orchestrator/data/container-build/cerc-geojson/build.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+# Build the geojson image
+source ${CERC_CONTAINER_BASE_DIR}/build-base.sh
+docker build -t cerc/geojson:local -f ${CERC_CONTAINER_BASE_DIR}/cerc-geojson/Dockerfile ${build_command_args} ${CERC_REPO_BASE_DIR}/geojson.io
+#docker build -t cerc/geojson:local -f ${CERC_REPO_BASE_DIR}/geojson.io/Dockerfile ${build_command_args} ${CERC_REPO_BASE_DIR}/geojson.io

stack_orchestrator/data/container-build/cerc-laconic-registry-cli/demo-records/demo-record-10.yml

@@ -0,0 +1,14 @@
+record:
+  type: ApplicationDeploymentRecord
+  version: 1.2.3
+  name: name
+  description: description
+  application: application
+  url: url
+  dns: dns
+  request: request
+  meta:
+    foo: bar
+  tags:
+    - a
+    - b 

stack_orchestrator/data/container-build/cerc-laconic-registry-cli/demo-records/demo-record-11.yml

@@ -0,0 +1,12 @@
+record:
+  type: GeneralRecord
+  version: 1.2.3
+  name: name
+  description: description
+  category: category
+  value: value
+  meta:
+    foo: bar
+  tags:
+    - a
+    - b 

stack_orchestrator/data/container-build/cerc-laconic-registry-cli/demo-records/demo-record-12.yml

@@ -0,0 +1,17 @@
+record:
+  type: ApplicationArtifact
+  version: 1.2.3
+  name: name
+  description: description
+  application: appidgoeshere
+  content_type: content_type
+  os: os
+  cpu: cpu
+  uri:
+    - uri://a
+    - uri://b
+  meta:
+    foo: bar
+  tags:
+    - a
+    - b

stack_orchestrator/data/container-build/cerc-laconic-registry-cli/demo-records/demo-record-7.yml

@@ -0,0 +1,11 @@
+record:
+  type: DnsRecord
+  version: 0.0.1
+  name: "foo"
+  resource_type: "A"
+  value: "bar"
+  meta:
+    foo: bar
+  tags:
+    - a
+    - b

stack_orchestrator/data/container-build/cerc-laconic-registry-cli/demo-records/demo-record-8.yml

@@ -0,0 +1,18 @@
+record:
+  type: ApplicationRecord
+  version: 0.0.1
+  name: my-demo-app
+  description: "Description of my app"
+  homepage: http://my.demo.app
+  license: license
+  author: author
+  repository:
+    - "https://my.demo.repo"
+  repository_ref: "v0.1.0"
+  app_version: "0.1.0"
+  app_type: "webapp"
+  meta:
+    foo: bar
+  tags:
+    - a
+    - b

stack_orchestrator/data/container-build/cerc-laconic-registry-cli/demo-records/demo-record-9.yml

@@ -0,0 +1,17 @@
+record:
+  type: ApplicationDeploymentRequest
+  version: 1.2.3
+  application: application
+  dns: dns
+  config:
+    env:
+      ENV_VAR_A: A
+      ENV_VAR_B: B
+  crn:
+    - crn://foo.bar
+    - crn://bar.baz
+  meta:
+    foo: bar
+  tags:
+    - a
+    - b

stack_orchestrator/data/container-build/cerc-nextjs-base/Dockerfile

@@ -1,6 +1,6 @@
 # Originally from: https://github.com/devcontainers/images/blob/main/src/javascript-node/.devcontainer/Dockerfile
 # [Choice] Node.js version (use -bullseye variants on local arm64/Apple Silicon): 18, 16, 14, 18-bullseye, 16-bullseye, 14-bullseye, 18-buster, 16-buster, 14-buster
-ARG VARIANT=20-bullseye
+ARG VARIANT=20-bullseye-slim
 FROM node:${VARIANT}
 
 ARG USERNAME=node
@@ -30,7 +30,7 @@ RUN \
 
 # [Optional] Uncomment this section to install additional OS packages.
 RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
-    && apt-get -y install --no-install-recommends jq gettext-base moreutils
+    && apt-get -y install --no-install-recommends jq gettext-base
 
 # [Optional] Uncomment if you want to install more global node modules
 # RUN su node -c "npm install -g <your-package-list-here>"

stack_orchestrator/data/container-build/cerc-nextjs-base/scripts/build-app.sh

@@ -21,6 +21,11 @@ WORK_DIR="${1:-/app}"
 
 cd "${WORK_DIR}" || exit 1
 
+# If this file doesn't exist at all, we'll get errors below.
+if [ ! -f "next.config.js" ]; then
+  touch next.config.js
+fi
+
 if [ ! -f "next.config.dist" ]; then
   cp next.config.js next.config.dist
 fi
@@ -104,7 +109,8 @@ CUR_NEXT_VERSION="`jq -r '.dependencies.next' package.json`"
 
 if [ "$CERC_NEXT_VERSION" != "keep" ] && [ "$CUR_NEXT_VERSION" != "$CERC_NEXT_VERSION" ]; then
   echo "Changing 'next' version specifier from '$CUR_NEXT_VERSION' to '$CERC_NEXT_VERSION' (set with '--extra-build-args \"--build-arg CERC_NEXT_VERSION=$CERC_NEXT_VERSION\"')"
-  cat package.json | jq ".dependencies.next = \"$CERC_NEXT_VERSION\"" | sponge package.json
+  cat package.json | jq ".dependencies.next = \"$CERC_NEXT_VERSION\"" > package.json.$$
+  mv package.json.$$ package.json
 fi
 
 $CERC_BUILD_TOOL install || exit 1
@@ -128,7 +134,8 @@ to use for the build with:
 ###############################################################################
 
 EOF
-  cat package.json | jq ".dependencies.next = \"^$CERC_MIN_NEXTVER\"" | sponge package.json
+  cat package.json | jq ".dependencies.next = \"^$CERC_MIN_NEXTVER\"" > package.json.$$
+  mv package.json.$$ package.json
   $CERC_BUILD_TOOL install || exit 1
 fi
 

stack_orchestrator/data/container-build/cerc-nextjs-base/scripts/start-serving-app.sh

@@ -42,7 +42,7 @@ if [ "$CERC_NEXTJS_SKIP_GENERATE" != "true" ]; then
     while [ $count -lt $CERC_MAX_GENERATE_TIME ] && [ "$generate_done" == "false" ]; do
       sleep 1
       count=$((count + 1))
-      grep 'rendered as static HTML' gen.out > /dev/null
+      grep 'rendered as static' gen.out > /dev/null
       if [ $? -eq 0 ]; then
         generate_done="true"
       fi

stack_orchestrator/data/container-build/cerc-osmosis-front-end-urbit/build.sh

@@ -0,0 +1,4 @@
+#!/usr/bin/env bash
+# Build the osmosis front end image
+source ${CERC_CONTAINER_BASE_DIR}/build-base.sh
+docker build -t cerc/osmosis-front-end-urbit:local -f ${CERC_REPO_BASE_DIR}/osmosis-frontend/docker/Dockerfile.static ${build_command_args} ${CERC_REPO_BASE_DIR}/osmosis-frontend

stack_orchestrator/data/container-build/cerc-urbit-globs-host/Dockerfile

@@ -1,7 +0,0 @@
-FROM python:3.13.0a2-alpine3.18
-
-RUN apk --update --no-cache add alpine-sdk jq bash curl wget
-
-WORKDIR /app
-
-ENTRYPOINT [ "bash" ]

stack_orchestrator/data/container-build/cerc-urbit-globs-host/build.sh

@@ -1,9 +0,0 @@
-#!/usr/bin/env bash
-# Build the urbit-globs-host image
-
-source ${CERC_CONTAINER_BASE_DIR}/build-base.sh
-
-# See: https://stackoverflow.com/a/246128/1701505
-SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
-
-docker build -t cerc/urbit-globs-host:local -f ${SCRIPT_DIR}/Dockerfile ${build_command_args} ${SCRIPT_DIR}

stack_orchestrator/data/stacks/act-runner/stack.yml

@@ -3,7 +3,7 @@ name: act-runner
 description: "Local act-runner"
 repos:
   - git.vdb.to/cerc-io/hosting
-  - gitea.com/gitea/act_runner
+  - gitea.com/telackey/act_runner@telackey/entrypoint
 containers:
   - cerc/act-runner
   - cerc/act-runner-task-executor

stack_orchestrator/data/stacks/azimuth/README.md

@@ -40,20 +40,36 @@ network:
   ports:
     watcher-db:
      - 0.0.0.0:15432:5432
+    azimuth-watcher-job-runner:
+     - 0.0.0.0:9000:9000
     azimuth-watcher-server:
      - 0.0.0.0:3001:3001
+    censures-watcher-job-runner:
+     - 0.0.0.0:9002:9002
     censures-watcher-server:
      - 0.0.0.0:3002:3002
+    claims-watcher-job-runner:
+     - 0.0.0.0:9004:9004
     claims-watcher-server:
      - 0.0.0.0:3003:3003
+    conditional-star-release-watcher-job-runner:
+     - 0.0.0.0:9006:9006
     conditional-star-release-watcher-server:
      - 0.0.0.0:3004:3004
+    delegated-sending-watcher-job-runner:
+     - 0.0.0.0:9008:9008
     delegated-sending-watcher-server:
      - 0.0.0.0:3005:3005
+    ecliptic-watcher-job-runner:
+     - 0.0.0.0:9010:9010
     ecliptic-watcher-server:
      - 0.0.0.0:3006:3006
+    linear-star-release-watcher-job-runner:
+     - 0.0.0.0:9012:9012
     linear-star-release-watcher-server:
      - 0.0.0.0:3007:3007
+    polls-watcher-job-runner:
+     - 0.0.0.0:9014:9014
     polls-watcher-server:
      - 0.0.0.0:3008:3008
     gateway-server:

stack_orchestrator/data/stacks/azimuth/stack.yml

@@ -1,7 +1,7 @@
 version: "1.0"
 name: azimuth
 repos:
-  - github.com/cerc-io/azimuth-watcher-ts@v0.1.2
+  - github.com/cerc-io/azimuth-watcher-ts@v0.1.3
 containers:
   - cerc/watcher-azimuth
 pods:

stack_orchestrator/data/stacks/birbit/README.md

@@ -0,0 +1,3 @@
+# birbit
+
+takes geo-tagged images, publishes the metadata on chain, then generates a geojson front end of that geo data

stack_orchestrator/data/stacks/birbit/stack.yml

@@ -0,0 +1,19 @@
+version: "0.1"
+name: birbit
+repos:
+  #- github.com/zramsay/birbit
+  - github.com/mapbox/geojson.io
+containers:
+  #- cerc/birbit
+  - cerc/geojson
+pods:
+    # configurable process that reads from chain and generates a view for the front end
+    # for MVP is basically does nothing, b/c FE view is  reading all records
+    # imagine a 'watcher' for a specific view
+    #- birbit
+    # front end, gets its file from kubo;
+    # https://github.com/mapbox/geojson.io/blob/main/API.md#datadatatextx-url
+    # deployed via kubernetes
+  - geojson
+    # hosts all the dot geojson files that are required to generated views
+  - kubo

stack_orchestrator/data/stacks/merkl-sushiswap-v3/stack.yml

@@ -2,7 +2,7 @@ version: "1.0"
 name: merkl-sushiswap-v3
 description: "SushiSwap v3 watcher stack"
 repos:
-  - github.com/cerc-io/merkl-sushiswap-v3-watcher-ts@v0.1.4
+  - github.com/cerc-io/merkl-sushiswap-v3-watcher-ts@v0.1.6
 containers:
   - cerc/watcher-merkl-sushiswap-v3
 pods:

stack_orchestrator/data/stacks/monitoring/README.md

@@ -0,0 +1,180 @@
+# monitoring
+
+* Instructions to setup and run a Prometheus server and Grafana dashboard
+* Comes with the following built-in exporters / dashboards:
+  * Chain Head Exporter - for tracking chain heads given external ETH RPC endpoints
+  * Watchers dashboard
+  * [Prometheus Blackbox](https://grafana.com/grafana/dashboards/7587-prometheus-blackbox-exporter/) - for tracking HTTP endpoints
+  * [NodeJS Application Dashboard](https://grafana.com/grafana/dashboards/11159-nodejs-application-dashboard/) - for default NodeJS metrics
+  * [PostgreSQL Database](https://grafana.com/grafana/dashboards/9628-postgresql-database/) - for monitoring Postgres dbs
+  * [Node Exporter Full](https://grafana.com/grafana/dashboards/1860-node-exporter-full/) - for monitoring system metrics
+* See [monitoring-watchers.md](./monitoring-watchers.md) for an example usage of the stack with pre-configured dashboards for watchers
+
+## Setup
+
+Clone required repositories:
+
+```bash
+laconic-so --stack monitoring setup-repositories --git-ssh --pull
+```
+
+Build the container images:
+
+```bash
+laconic-so --stack monitoring build-containers
+```
+
+## Create a deployment
+
+First, create a spec file for the deployment, which will map the stack's ports and volumes to the host:
+
+```bash
+laconic-so --stack monitoring deploy init --output monitoring-spec.yml
+```
+
+### Ports
+
+Edit `network` in spec file to map container ports to same ports in host:
+
+```
+...
+network:
+  ports:
+    prometheus:
+      - '9090:9090'
+    grafana:
+      - '3000:3000'
+...
+```
+
+### Data volumes
+
+Container data volumes are bind-mounted to specified paths in the host filesystem.
+The default setup (generated by `laconic-so deploy init`) places the volumes in the `./data` subdirectory of the deployment directory. The default mappings can be customized by editing the "spec" file generated by `laconic-so deploy init`.
+
+---
+
+Once you've made any needed changes to the spec file, create a deployment from it:
+
+```bash
+laconic-so --stack monitoring deploy create --spec-file monitoring-spec.yml --deployment-dir monitoring-deployment
+```
+
+## Configure
+
+### Prometheus Config
+
+* Add desired scrape configs to prometheus config file (`monitoring-deployment/config/monitoring/prometheus/prometheus.yml`) in the deployment folder; for example:
+
+  ```yml
+  ...
+  - job_name: <JOB_NAME>
+    metrics_path: /metrics/path
+    scheme: http
+    static_configs:
+      - targets: ['<METRICS_ENDPOINT_HOST>:<METRICS_ENDPOINT_PORT>']
+  ```
+
+* Node exporter: update the `node` job to add any node-exporter targets to be monitored:
+
+  ```yml
+  ...
+  - job_name: 'node'
+    ...
+    static_configs:
+      # Add node-exporter targets to be monitored below
+      - targets: [example-host:9100]
+        labels:
+          instance: 'my-host'
+  ```
+
+* Blackbox (in-stack exporter): update the `blackbox` job to add any endpoints to be monitored on the Blackbox dashboard:
+
+  ```yml
+  ...
+  - job_name: 'blackbox'
+    ...
+    static_configs:
+      # Add URLs to be monitored below
+      - targets:
+        - <HTTP_ENDPOINT_1>
+        - <HTTP_ENDPOINT_2>
+  ```
+
+* Postgres (in-stack exporter):
+  * Update the `postgres` job to add Postgres db targets to be monitored:
+
+    ```yml
+    ...
+    - job_name: 'postgres'
+      ...
+      static_configs:
+        # Add DB targets below
+        - targets: [example-server:5432]
+          labels:
+            instance: 'example-db'
+    ```
+  * Add database credentials to be used in `auth_modules` in the postgres-exporter config file (`monitoring-deployment/config/monitoring/postgres-exporter.yml`)
+
+Note: Use `host.docker.internal` as host to access ports on the host machine
+
+### Grafana Config
+
+Place the dashboard json files in grafana dashboards config directory (`monitoring-deployment/config/monitoring/grafana/dashboards`) in the deployment folder
+
+### Env
+
+Set the following env variables in the deployment env config file (`monitoring-deployment/config.env`):
+
+  ```bash
+  # For chain-head exporter
+
+  # External ETH RPC endpoint (ethereum)
+  # (Optional, default: https://mainnet.infura.io/v3)
+  CERC_ETH_RPC_ENDPOINT=
+
+  # Infura key to be used
+  # (Optional, used with ETH_RPC_ENDPOINT if provided)
+  CERC_INFURA_KEY=
+
+  # External ETH RPC endpoint (filecoin)
+  # (Optional, default: https://api.node.glif.io/rpc/v1)
+  CERC_FIL_RPC_ENDPOINT=
+
+  # Grafana server host URL (used in various links in alerts, etc.)
+  # (Optional, default: http://localhost:3000)
+  GF_SERVER_ROOT_URL=
+  ```
+
+## Start the stack
+
+Start the deployment:
+
+```bash
+laconic-so deployment --dir monitoring-deployment start
+```
+
+* List and check the health status of all the containers using `docker ps` and wait for them to be `healthy`
+
+* Grafana should now be visible at http://localhost:3000 with configured dashboards
+
+## Clean up
+
+To stop monitoring services running in the background, while preserving data:
+
+```bash
+# Only stop the docker containers
+laconic-so deployment --dir monitoring-deployment stop
+
+# Run 'start' to restart the deployment
+```
+
+To stop monitoring services and also delete data:
+
+```bash
+# Stop the docker containers
+laconic-so deployment --dir monitoring-deployment stop --delete-volumes
+
+# Remove deployment directory (deployment will have to be recreated for a re-run)
+rm -rf monitoring-deployment
+```

stack_orchestrator/data/stacks/monitoring/monitoring-watchers.md

@@ -0,0 +1,170 @@
+# Monitoring Watchers
+
+Instructions to setup and run monitoring stack with configured Watchers dashboard
+
+## Create a deployment
+
+After completing [setup](./README.md#setup), create a spec file for the deployment, which will map the stack's ports and volumes to the host:
+
+```bash
+laconic-so --stack monitoring deploy init --output monitoring-watchers-spec.yml
+```
+
+### Ports
+
+Edit `network` in spec file to map container ports to same ports in host:
+
+```
+...
+network:
+  ports:
+    prometheus:
+      - '9090:9090'
+    grafana:
+      - '3000:3000'
+...
+```
+
+---
+
+Once you've made any needed changes to the spec file, create a deployment from it:
+
+```bash
+laconic-so --stack monitoring deploy create --spec-file monitoring-watchers-spec.yml --deployment-dir monitoring-watchers-deployment
+```
+
+## Configure
+
+### Prometheus scrape config
+
+Add the following scrape configs to prometheus config file (`monitoring-watchers-deployment/config/monitoring/prometheus/prometheus.yml`) in the deployment folder:
+
+  ```yml
+  ...
+  - job_name: 'blackbox'
+    ...
+    static_configs:
+      - targets:
+        - <AZIMUTH_GATEWAY_GQL_ENDPOINT>
+  ...
+  - job_name: azimuth
+    scrape_interval: 10s
+    metrics_path: /metrics
+    scheme: http
+    static_configs:
+      - targets: ['AZIMUTH_WATCHER_HOST:AZIMUTH_WATCHER_PORT']
+        labels:
+          instance: 'azimuth'
+          chain: 'ethereum'
+      - targets: ['CENSURES_WATCHER_HOST:CENSURES_WATCHER_PORT']
+        labels:
+          instance: 'censures'
+          chain: 'ethereum'
+      - targets: ['CLAIMS_WATCHER_HOST:CLAIMS_WATCHER_PORT']
+        labels:
+          instance: 'claims'
+          chain: 'ethereum'
+      - targets: ['CONDITIONAL_STAR_RELEASE_WATCHER_HOST:CONDITIONAL_STAR_RELEASE_WATCHER_PORT']
+        labels:
+          instance: 'conditional_star_release'
+          chain: 'ethereum'
+      - targets: ['DELEGATED_SENDING_WATCHER_HOST:DELEGATED_SENDING_WATCHER_PORT']
+        labels:
+          instance: 'delegated_sending'
+          chain: 'ethereum'
+      - targets: ['ECLIPTIC_WATCHER_HOST:ECLIPTIC_WATCHER_PORT']
+        labels:
+          instance: 'ecliptic'
+          chain: 'ethereum'
+      - targets: ['LINEAR_STAR_WATCHER_HOST:LINEAR_STAR_WATCHER_PORT']
+        labels:
+          instance: 'linear_star_release'
+          chain: 'ethereum'
+      - targets: ['POLLS_WATCHER_HOST:POLLS_WATCHER_PORT']
+        labels:
+          instance: 'polls'
+          chain: 'ethereum'
+
+  - job_name: sushi
+    scrape_interval: 20s
+    metrics_path: /metrics
+    scheme: http
+    static_configs:
+      - targets: ['SUSHISWAP_WATCHER_HOST:SUSHISWAP_WATCHER_PORT']
+        labels:
+          instance: 'sushiswap'
+          chain: 'filecoin'
+      - targets: ['MERKLE_SUSHISWAP_WATCHER_HOST:MERKLE_SUSHISWAP_WATCHER_PORT']
+        labels:
+          instance: 'merkl_sushiswap'
+          chain: 'filecoin'
+  ```
+
+Add scrape config as done above for any additional watcher to add it to the Watchers dashboard.
+
+### Grafana alerts config
+
+Place the pre-configured watcher alerts rules in Grafana provisioning directory:
+
+  ```bash
+  cp monitoring-watchers-deployment/config/monitoring/watcher-alert-rules.yml monitoring-watchers-deployment/config/monitoring/grafana/provisioning/alerting/
+  ```
+
+Update the alerting contact points config (`monitoring-watchers-deployment/config/monitoring/grafana/provisioning/alerting/contactpoints.yml`) with desired contact points
+
+Add corresponding routes to the notification policies config (`monitoring-watchers-deployment/monitoring/grafana/provisioning/alerting/policies.yaml`) with appropriate object-matchers:
+
+  ```yml
+  ...
+    routes:
+      - receiver: SlackNotifier
+      object_matchers:
+        # Add matchers below
+        - ['grafana_folder', '=', 'WatcherAlerts']
+  ```
+
+### Env
+
+Set the following env variables in the deployment env config file (`monitoring-watchers-deployment/config.env`):
+
+  ```bash
+  # Infura key to be used
+  CERC_INFURA_KEY=
+
+  # Grafana server host URL to be used
+  # (Optional, default: http://localhost:3000)
+  GF_SERVER_ROOT_URL=
+  ```
+
+## Start the stack
+
+Start the deployment:
+
+```bash
+laconic-so deployment --dir monitoring-watchers-deployment start
+```
+
+* List and check the health status of all the containers using `docker ps` and wait for them to be `healthy`
+
+* Grafana should now be visible at http://localhost:3000 with configured dashboards
+
+## Clean up
+
+To stop monitoring services running in the background, while preserving data:
+
+```bash
+# Only stop the docker containers
+laconic-so deployment --dir monitoring-watchers-deployment stop
+
+# Run 'start' to restart the deployment
+```
+
+To stop monitoring services and also delete data:
+
+```bash
+# Stop the docker containers
+laconic-so deployment --dir monitoring-watchers-deployment stop --delete-volumes
+
+# Remove deployment directory (deployment will have to be recreated for a re-run)
+rm -rf monitoring-watchers-deployment
+```

stack_orchestrator/data/stacks/monitoring/stack.yml

@@ -0,0 +1,9 @@
+version: "0.1"
+name: monitoring
+repos:
+  - github.com/cerc-io/watcher-ts@v0.2.79
+containers:
+  - cerc/watcher-ts
+pods:
+  - prom-server
+  - grafana

stack_orchestrator/data/stacks/node-exporter/README.md

@@ -0,0 +1,17 @@
+# node-exporter
+
+## Start the stack
+
+```bash
+laconic-so --stack node-exporter deploy up
+```
+
+* The host node's metrics can be accessed at `http://localhost:9100/metrics`
+
+## Clean up
+
+Stop the node-exporter running in background:
+
+```bash
+laconic-so --stack node-exporter deploy down
+```

stack_orchestrator/data/stacks/node-exporter/stack.yml

@@ -0,0 +1,6 @@
+version: "0.1"
+name: node-exporter
+repos:
+containers:
+pods:
+  - node-exporter

stack_orchestrator/data/stacks/osmosis-urbit-app/README.md

@@ -0,0 +1,158 @@
+# Self-hosted Osmosis Front End On Urbit
+
+Instructions to build and deploy:
+- Urbit
+- An ipfs node
+- The osmosis front end
+
+## Setup
+
+Clone required repositories:
+
+```bash
+laconic-so --stack osmosis-urbit-app setup-repositories --pull
+
+# If this throws an error as a result of being already checked out to a branch/tag in a repo, remove the repositories and re-run the command
+```
+
+Build the container images:
+
+```bash
+laconic-so --stack osmosis-urbit-app build-containers
+```
+
+## Create a deployment
+
+First, create a spec file for the deployment, which will map the stack's ports and volumes to the host:
+
+```bash
+laconic-so --stack osmosis-urbit-app deploy init --output osmosis-urbit-app-spec.yml
+```
+
+### Ports
+
+Edit `network` in spec file to map container ports to same ports in host:
+
+```yml
+...
+network:
+  ports:
+    urbit-fake-ship:
+      - '8080:80'
+    proxy-server:
+      - '4000:4000'
+    ipfs:
+      - '8081:8080'
+      - '5001:5001'
+```
+
+Note: Skip the `ipfs` ports if need to use an externally running IPFS node
+
+### Data volumes
+
+Container data volumes are bind-mounted to specified paths in the host filesystem.
+The default setup (generated by `laconic-so deploy init`) places the volumes in the `./data` subdirectory of the deployment directory. The default mappings can be customized by editing the "spec" file generated by `laconic-so deploy init`.
+
+---
+
+Once you've made any needed changes to the spec file, create a deployment from it:
+
+```bash
+laconic-so --stack osmosis-urbit-app deploy create --spec-file osmosis-urbit-app-spec.yml --deployment-dir osmosis-urbit-app-deployment
+```
+
+## Set env variables
+
+Inside the deployment directory, open the file `config.env` and set the following env variables:
+
+(Note: Use the following config as is if running the stack locally)
+
+  ```bash
+  # App to be installed (Do not change)
+  CERC_URBIT_APP=osmosis
+
+  # Osmosis API base URL
+  # Set this to proxy server endpoint for osmosis app
+  # (Eg. http://localhost:4000 - in case stack is being run locally with proxy enabled)
+  # (Eg. https://abc.xyz.com - in case https://abc.xyz.com is pointed to the proxy endpoint)
+  CERC_WEB_API_BASE_URL=http://localhost:4000
+
+  # Optional
+
+  # Whether to enable app installation on Urbit
+  # (just builds and uploads the glob file if disabled) (Default: true)
+  CERC_ENABLE_APP_INSTALL=
+
+  # Whether to run the proxy server
+  # (Disable only if proxy not required to be run) (Default: true)
+  CERC_ENABLE_PROXY=
+
+  # Proxy server configuration
+  # Used only if proxy is enabled
+
+  # Upstream API URL
+  CERC_PROXY_UPSTREAM=https://app.osmosis.zone
+
+  # IPFS configuration
+
+  # IFPS endpoint to host the glob file on
+  # (Default: http://ipfs:5001 pointing to in-stack IPFS node)
+  CERC_IPFS_GLOB_HOST_ENDPOINT=
+
+  # IFPS endpoint to fetch the glob file from
+  # (Default: http://ipfs:8080 pointing to in-stack IPFS node)
+  CERC_IPFS_SERVER_ENDPOINT=
+  ```
+
+## Start the stack
+
+Start the deployment:
+
+```bash
+laconic-so deployment --dir osmosis-urbit-app-deployment start
+```
+
+* List and check the health status of all the containers using `docker ps` and wait for them to be `healthy`
+
+* Run the following to get login password for Urbit web interface:
+
+  ```bash
+  laconic-so deployment --dir osmosis-urbit-app-deployment exec urbit-fake-ship "curl -s --data '{\"source\":{\"dojo\":\"+code\"},\"sink\":{\"stdout\":null}}' http://localhost:12321"
+
+  # Expected output: "<PASSWORD>\n"%
+  ```
+
+* Open the Urbit web UI at http://localhost:8080 and use the `PASSWORD` from previous step to login
+
+* The osmosis app is not available when starting stack for the first time. Check `urbit-fake-ship` logs to see that app has installed:
+
+  ```bash
+  laconic-so deployment --dir osmosis-urbit-app-deployment logs -f
+
+  # Expected output:
+  # laconic-3ccf7ee79bdae874-urbit-fake-ship-1    | docket: fetching %http glob for %osmosis desk
+  # laconic-3ccf7ee79bdae874-urbit-fake-ship-1    | ">="">="osmosis app installed
+  ```
+
+* The osmosis app will be now visible at http://localhost:8080
+
+## Clean up
+
+To stop all osmosis-urbit-app services running in the background, while preserving data:
+
+```bash
+# Only stop the docker containers
+laconic-so deployment --dir osmosis-urbit-app-deployment stop
+
+# Run 'start' to restart the deployment
+```
+
+To stop all osmosis-urbit-app services and also delete data:
+
+```bash
+# Stop the docker containers
+laconic-so deployment --dir osmosis-urbit-app-deployment stop --delete-volumes
+
+# Remove deployment directory (deployment will have to be recreated for a re-run)
+rm -r osmosis-urbit-app-deployment
+```

stack_orchestrator/data/stacks/osmosis-urbit-app/stack.yml

@@ -0,0 +1,13 @@
+version: "0.1"
+name: osmosis-urbit-app
+repos:
+  - github.com/cerc-io/osmosis-frontend@laconic
+  - github.com/cerc-io/watcher-ts@v0.2.78
+containers:
+  - cerc/osmosis-front-end-urbit
+  - cerc/watcher-ts
+pods:
+  - osmosis-front-end-urbit
+  - proxy-server
+  - fixturenet-urbit
+  - kubo

stack_orchestrator/data/stacks/osmosis/README.md

@@ -1,26 +1,26 @@
 # self-hosted osmosis
 
 Instructions to build and deploy:
-- self-hosted gitea
-- an ipfs node
-- the osmosis front end
-- a laconicd chain
+- Self-hosted gitea
+- An ipfs node
+- The osmosis front end
+- A laconicd chain
 
 ## Setup
 
 Clone required repositories:
 
 ```bash
-laconic-so --stack osmosis setup-repositories
+laconic-so --stack osmosis setup-repositories --pull
 
 # If this throws an error as a result of being already checked out to a branch/tag in a repo, remove the repositories and re-run the command
 ```
 
 Build the container images:
 
-```
-# support image for the gitea package registry
-laconic-so --stack build-support build-containers
+```bash
+# TODO: support image for the gitea package registry
+# laconic-so --stack build-support build-containers
 
 laconic-so --stack osmosis build-containers
 ```
@@ -62,9 +62,11 @@ laconic-so --stack osmosis deploy create --spec-file osmosis-spec.yml --deployme
 
 Inside the deployment directory, open the file `config.env` and set the following env variables:
 
+  (Note: Following config can be used as is if the stack is being run locally)
+
   ```bash
   # Osmosis API base URL
-  # Set this to proxy server endpoint for uniswap app
+  # Set this to proxy server endpoint for osmosis app
   # (Eg. http://localhost:4000 - in case stack is being run locally with proxy enabled)
   # (Eg. https://abc.xyz.com - in case https://abc.xyz.com is pointed to the proxy endpoint)
   CERC_WEB_API_BASE_URL=http://localhost:4000
@@ -85,10 +87,17 @@ Inside the deployment directory, open the file `config.env` and set the followin
 ## Start the stack
 
 Start the deployment:
+
 ```bash
 laconic-so deployment --dir osmosis-deployment start
 ```
 
+* The `osmosis-front-end` container will take some time to run to completion as it builds the front-end app with given configuration; same can be tracked in the logs:
+
+  ```bash
+  laconic-so deployment --dir osmosis-deployment logs -f osmosis-front-end
+  ```
+
 * List and check the health status of all the containers using `docker ps` and wait for them to be `healthy`
 
 * The web app can be accessed at http://localhost:3000
@@ -96,7 +105,8 @@ laconic-so deployment --dir osmosis-deployment start
 ## Laconic registry
 
 Setup a test chain:
-```
+
+```bash
 export CERC_NPM_REGISTRY_URL=https://git.vdb.to/api/packages/cerc-io/npm/
 
 laconic-so --stack fixturenet-laconic-loaded setup-repositories --include git.vdb.to/cerc-io/laconicd,git.vdb.to/cerc-io/laconic-sdk,git.vdb.to/cerc-io/laconic-registry-cli,git.vdb.to/cerc-io/laconic-console

stack_orchestrator/data/stacks/osmosis/stack.yml

@@ -6,14 +6,14 @@ repos:
   # - gitea.com/gitea/act_runner
   # For osmosis frontend
   - github.com/cerc-io/watcher-ts@v0.2.78
-  - github.com/cerc-io/osmosis-frontend@laconic
+  - github.com/cerc-io/osmosis-frontend@laconic # TODO: Use release
 containers:
   # - cerc/act-runner
   # - cerc/act-runner-task-executor
   - cerc/watcher-ts
   - cerc/osmosis-front-end
 pods:
-  - kubo
+  # - kubo
   - proxy-server
   - osmosis-front-end
   # TODO: Fix pod config for deployment command

stack_orchestrator/data/stacks/package-registry/stack.yml

@@ -3,7 +3,7 @@ name: package-registry
 description: "Local Package Registry"
 repos:
   - git.vdb.to/cerc-io/hosting
-  - gitea.com/gitea/act_runner
+  - gitea.com/telackey/act_runner@telackey/entrypoint
 containers:
   - cerc/act-runner
   - cerc/act-runner-task-executor

stack_orchestrator/data/stacks/sushiswap-v3/stack.yml

@@ -2,7 +2,7 @@ version: "1.0"
 name: sushiswap-v3
 description: "SushiSwap v3 watcher stack"
 repos:
-  - github.com/cerc-io/sushiswap-v3-watcher-ts@v0.1.4
+  - github.com/cerc-io/sushiswap-v3-watcher-ts@v0.1.6
 containers:
   - cerc/watcher-sushiswap-v3
 pods:

stack_orchestrator/data/stacks/uniswap-urbit-app/README.md

@@ -14,7 +14,7 @@ Clone required repositories:
 ```bash
 laconic-so --stack uniswap-urbit-app setup-repositories --pull
 
-# If this throws an error as a result of being already checked out to a branch/tag in a repo, remove the repositories mentioned below and re-run the command
+# If this throws an error as a result of being already checked out to a branch/tag in a repo, remove the repositories and re-run the command
 ```
 
 Build the container images:
@@ -35,7 +35,7 @@ laconic-so --stack uniswap-urbit-app deploy init --output uniswap-urbit-app-spec
 
 Edit `network` in spec file to map container ports to same ports in host:
 
-```
+```yml
 ...
 network:
   ports:
@@ -134,13 +134,14 @@ laconic-so deployment --dir uniswap-urbit-app-deployment start
 
 * Open the Urbit web UI at http://localhost:8080 and use the `PASSWORD` from previous step to login
 
-* The uniswap app is not available when starting stack for the first time. Check `urbit-fake-ship` logs to see that app has installed
-  ```
+* The uniswap app is not available when starting stack for the first time. Check `urbit-fake-ship` logs to see that app has installed:
+
+  ```bash
   laconic-so deployment --dir uniswap-urbit-app-deployment logs -f
 
   # Expected output:
   # laconic-3ccf7ee79bdae874-urbit-fake-ship-1    | docket: fetching %http glob for %uniswap desk
-  # laconic-3ccf7ee79bdae874-urbit-fake-ship-1    | ">="">="Uniswap app installed
+  # laconic-3ccf7ee79bdae874-urbit-fake-ship-1    | ">="">="uniswap app installed
   ```
 
 * The uniswap app will be now visible at http://localhost:8080

stack_orchestrator/data/stacks/uniswap-urbit-app/stack.yml

@@ -6,7 +6,6 @@ repos:
 containers:
   - cerc/uniswap-interface
   - cerc/watcher-ts
-  - cerc/urbit-globs-host
 pods:
   - uniswap-interface
   - proxy-server

stack_orchestrator/deploy/compose/deploy_docker.py

@@ -40,6 +40,12 @@ class DockerDeployer(Deployer):
         except DockerException as e:
             raise DeployerException(e)
 
+    def update(self):
+        try:
+            return self.docker.compose.restart()
+        except DockerException as e:
+            raise DeployerException(e)
+
     def status(self):
         try:
             for p in self.docker.compose.ps():

stack_orchestrator/deploy/deploy.py

@@ -120,6 +120,14 @@ def status_operation(ctx):
         ctx.obj.deployer.status()
 
 
+def update_operation(ctx):
+    global_context = ctx.parent.parent.obj
+    if not global_context.dry_run:
+        if global_context.verbose:
+            print("Running compose update")
+        ctx.obj.deployer.update()
+
+
 def ps_operation(ctx):
     global_context = ctx.parent.parent.obj
     if not global_context.dry_run:

stack_orchestrator/deploy/deployer.py

@@ -27,6 +27,10 @@ class Deployer(ABC):
     def down(self, timeout, volumes):
         pass
 
+    @abstractmethod
+    def update(self):
+        pass
+
     @abstractmethod
     def ps(self):
         pass

stack_orchestrator/deploy/deployment.py

@@ -19,7 +19,7 @@ import sys
 from stack_orchestrator import constants
 from stack_orchestrator.deploy.images import push_images_operation
 from stack_orchestrator.deploy.deploy import up_operation, down_operation, ps_operation, port_operation, status_operation
-from stack_orchestrator.deploy.deploy import exec_operation, logs_operation, create_deploy_context
+from stack_orchestrator.deploy.deploy import exec_operation, logs_operation, create_deploy_context, update_operation
 from stack_orchestrator.deploy.deploy_types import DeployCommandContext
 from stack_orchestrator.deploy.deployment_context import DeploymentContext
 
@@ -149,3 +149,10 @@ def logs(ctx, tail, follow, extra_args):
 def status(ctx):
     ctx.obj = make_deploy_context(ctx)
     status_operation(ctx)
+
+
+@command.command()
+@click.pass_context
+def update(ctx):
+    ctx.obj = make_deploy_context(ctx)
+    update_operation(ctx)

stack_orchestrator/deploy/deployment_create.py

@@ -444,7 +444,7 @@ def create_operation(deployment_command_context, spec_file, deployment_dir, netw
     deployer_config_generator = getDeployerConfigGenerator(deployment_type)
     # TODO: make deployment_dir_path a Path above
     deployer_config_generator.generate(deployment_dir_path)
-    call_stack_deploy_create(deployment_context, [network_dir, initial_peers])
+    call_stack_deploy_create(deployment_context, [network_dir, initial_peers, deployment_command_context])
 
 
 # TODO: this code should be in the stack .py files but

stack_orchestrator/deploy/k8s/cluster_info.py

@@ -168,8 +168,8 @@ class ClusterInfo:
             result.append(pv)
         return result
 
-    # to suit the deployment, and also annotate the container specs to point at said volumes
-    def get_deployment(self):
+    # TODO: put things like image pull policy into an object-scope struct
+    def get_deployment(self, image_pull_policy: str = None):
         containers = []
         for pod_name in self.parsed_pod_yaml_map:
             pod = self.parsed_pod_yaml_map[pod_name]
@@ -189,6 +189,7 @@ class ClusterInfo:
                 container = client.V1Container(
                     name=container_name,
                     image=image_to_use,
+                    image_pull_policy=image_pull_policy,
                     env=envs_from_environment_variables_map(self.environment_variables.map),
                     ports=[client.V1ContainerPort(container_port=port)],
                     volume_mounts=volume_mounts,
@@ -199,9 +200,10 @@ class ClusterInfo:
                 )
                 containers.append(container)
         volumes = volumes_for_pod_files(self.parsed_pod_yaml_map)
+        image_pull_secrets = [client.V1LocalObjectReference(name="laconic-registry")]
         template = client.V1PodTemplateSpec(
             metadata=client.V1ObjectMeta(labels={"app": self.app_name}),
-            spec=client.V1PodSpec(containers=containers, volumes=volumes),
+            spec=client.V1PodSpec(containers=containers, image_pull_secrets=image_pull_secrets, volumes=volumes),
         )
         spec = client.V1DeploymentSpec(
             replicas=1, template=template, selector={

stack_orchestrator/deploy/k8s/deploy_k8s.py

@@ -13,6 +13,8 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http:#www.gnu.org/licenses/>.
 
+from datetime import datetime, timezone
+
 from pathlib import Path
 from kubernetes import client, config
 
@@ -109,7 +111,7 @@ class K8sDeployer(Deployer):
                 print("PVCs created:")
                 print(f"{pvc_resp}")
         # Process compose files into a Deployment
-        deployment = self.cluster_info.get_deployment()
+        deployment = self.cluster_info.get_deployment(image_pull_policy=None if self.is_kind() else "Always")
         # Create the k8s objects
         if opts.o.debug:
             print(f"Sending this deployment: {deployment}")
@@ -130,18 +132,18 @@ class K8sDeployer(Deployer):
             print("Service created:")
             print(f"{service_resp}")
 
-        # TODO: disable ingress for kind
-        ingress: client.V1Ingress = self.cluster_info.get_ingress()
+        if not self.is_kind():
+            ingress: client.V1Ingress = self.cluster_info.get_ingress()
 
-        if opts.o.debug:
-            print(f"Sending this ingress: {ingress}")
-        ingress_resp = self.networking_api.create_namespaced_ingress(
-            namespace=self.k8s_namespace,
-            body=ingress
-        )
-        if opts.o.debug:
-            print("Ingress created:")
-            print(f"{ingress_resp}")
+            if opts.o.debug:
+                print(f"Sending this ingress: {ingress}")
+            ingress_resp = self.networking_api.create_namespaced_ingress(
+                namespace=self.k8s_namespace,
+                body=ingress
+            )
+            if opts.o.debug:
+                print("Ingress created:")
+                print(f"{ingress_resp}")
 
     def down(self, timeout, volumes):
         self.connect_api()
@@ -194,16 +196,16 @@ class K8sDeployer(Deployer):
         except client.exceptions.ApiException as e:
             _check_delete_exception(e)
 
-        # TODO: disable ingress for kind
-        ingress: client.V1Ingress = self.cluster_info.get_ingress()
-        if opts.o.debug:
-            print(f"Deleting this ingress: {ingress}")
-        try:
-            self.networking_api.delete_namespaced_ingress(
-                name=ingress.metadata.name, namespace=self.k8s_namespace
-            )
-        except client.exceptions.ApiException as e:
-            _check_delete_exception(e)
+        if not self.is_kind():
+            ingress: client.V1Ingress = self.cluster_info.get_ingress()
+            if opts.o.debug:
+                print(f"Deleting this ingress: {ingress}")
+            try:
+                self.networking_api.delete_namespaced_ingress(
+                    name=ingress.metadata.name, namespace=self.k8s_namespace
+                )
+            except client.exceptions.ApiException as e:
+                _check_delete_exception(e)
 
         if self.is_kind():
             # Destroy the kind cluster
@@ -217,7 +219,7 @@ class K8sDeployer(Deployer):
 
         if all_pods.items:
             for p in all_pods.items:
-                if self.cluster_info.app_name in p.metadata.name:
+                if f"{self.cluster_info.app_name}-deployment" in p.metadata.name:
                     pods.append(p)
 
         if not pods:
@@ -264,7 +266,7 @@ class K8sDeployer(Deployer):
         ret = []
 
         for p in pods.items:
-            if self.cluster_info.app_name in p.metadata.name:
+            if f"{self.cluster_info.app_name}-deployment" in p.metadata.name:
                 pod_ip = p.status.pod_ip
                 ports = AttrDict()
                 for c in p.spec.containers:
@@ -297,13 +299,49 @@ class K8sDeployer(Deployer):
 
     def logs(self, services, tail, follow, stream):
         self.connect_api()
-        pods = pods_in_deployment(self.core_api, "test-deployment")
+        pods = pods_in_deployment(self.core_api, self.cluster_info.app_name)
         if len(pods) > 1:
             print("Warning: more than one pod in the deployment")
-        k8s_pod_name = pods[0]
-        log_data = self.core_api.read_namespaced_pod_log(k8s_pod_name, namespace="default", container="test")
+        if len(pods) == 0:
+            log_data = "******* Pods not running ********\n"
+        else:
+            k8s_pod_name = pods[0]
+            # If the pod is not yet started, the logs request below will throw an exception
+            try:
+                log_data = self.core_api.read_namespaced_pod_log(k8s_pod_name, namespace="default", container="test")
+            except client.exceptions.ApiException as e:
+                if opts.o.debug:
+                    print(f"Error from read_namespaced_pod_log: {e}")
+                log_data = "******* No logs available ********\n"
         return log_stream_from_string(log_data)
 
+    def update(self):
+        self.connect_api()
+        ref_deployment = self.cluster_info.get_deployment()
+
+        deployment = self.apps_api.read_namespaced_deployment(
+            name=ref_deployment.metadata.name,
+            namespace=self.k8s_namespace
+        )
+
+        new_env = ref_deployment.spec.template.spec.containers[0].env
+        for container in deployment.spec.template.spec.containers:
+            old_env = container.env
+            if old_env != new_env:
+                container.env = new_env
+
+        deployment.spec.template.metadata.annotations = {
+            "kubectl.kubernetes.io/restartedAt": datetime.utcnow()
+            .replace(tzinfo=timezone.utc)
+            .isoformat()
+        }
+
+        self.apps_api.patch_namespaced_deployment(
+            name=ref_deployment.metadata.name,
+            namespace=self.k8s_namespace,
+            body=deployment
+        )
+
     def run(self, image: str, command=None, user=None, volumes=None, entrypoint=None, env={}, ports=[], detach=False):
         # We need to figure out how to do this -- check why we're being called first
         pass

stack_orchestrator/deploy/k8s/helpers.py

@@ -21,6 +21,7 @@ from typing import Set, Mapping, List
 
 from stack_orchestrator.opts import opts
 from stack_orchestrator.deploy.deploy_util import parsed_pod_files_map_from_file_names
+from stack_orchestrator.deploy.deployer import DeployerException
 
 
 def _run_command(command: str):
@@ -29,10 +30,13 @@ def _run_command(command: str):
     result = subprocess.run(command, shell=True)
     if opts.o.debug:
         print(f"Result: {result}")
+    return result
 
 
 def create_cluster(name: str, config_file: str):
-    _run_command(f"kind create cluster --name {name} --config {config_file}")
+    result = _run_command(f"kind create cluster --name {name} --config {config_file}")
+    if result.returncode != 0:
+        raise DeployerException(f"kind create cluster failed: {result}")
 
 
 def destroy_cluster(name: str):
@@ -41,12 +45,14 @@ def destroy_cluster(name: str):
 
 def load_images_into_kind(kind_cluster_name: str, image_set: Set[str]):
     for image in image_set:
-        _run_command(f"kind load docker-image {image} --name {kind_cluster_name}")
+        result = _run_command(f"kind load docker-image {image} --name {kind_cluster_name}")
+        if result.returncode != 0:
+            raise DeployerException(f"kind create cluster failed: {result}")
 
 
 def pods_in_deployment(core_api: client.CoreV1Api, deployment_name: str):
     pods = []
-    pod_response = core_api.list_namespaced_pod(namespace="default", label_selector="app=test-app")
+    pod_response = core_api.list_namespaced_pod(namespace="default", label_selector=f"app={deployment_name}")
     if opts.o.debug:
         print(f"pod_response: {pod_response}")
     for pod_info in pod_response.items:

stack_orchestrator/deploy/webapp/deploy_webapp.py

@@ -54,26 +54,7 @@ def _fixup_url_spec(spec_file_name: str, url: str):
         wfile.write(contents)
 
 
-@click.group()
-@click.pass_context
-def command(ctx):
-    '''manage a webapp deployment'''
-
-    # Check that --stack wasn't supplied
-    if ctx.parent.obj.stack:
-        error_exit("--stack can't be supplied with the deploy-webapp command")
-
-
-@command.command()
-@click.option("--kube-config", help="Provide a config file for a k8s deployment")
-@click.option("--image-registry", help="Provide a container image registry url for this k8s cluster")
-@click.option("--deployment-dir", help="Create deployment files in this directory", required=True)
-@click.option("--image", help="image to deploy", required=True)
-@click.option("--url", help="url to serve", required=True)
-@click.option("--env-file", help="environment file for webapp")
-@click.pass_context
-def create(ctx, deployment_dir, image, url, kube_config, image_registry, env_file):
-    '''create a deployment for the specified webapp container'''
+def create_deployment(ctx, deployment_dir, image, url, kube_config, image_registry, env_file):
     # Do the equivalent of:
     # 1. laconic-so --stack webapp-template deploy --deploy-to k8s init --output webapp-spec.yml
     #   --config (eqivalent of the contents of my-config.env)
@@ -92,7 +73,7 @@ def create(ctx, deployment_dir, image, url, kube_config, image_registry, env_fil
     # TODO: support env file
     deploy_command_context: DeployCommandContext = create_deploy_context(
         global_options2(ctx), None, stack, None, None, None, env_file, "k8s"
-        )
+    )
     init_operation(
         deploy_command_context,
         stack,
@@ -116,3 +97,27 @@ def create(ctx, deployment_dir, image, url, kube_config, image_registry, env_fil
     # Fix up the container tag inside the deployment compose file
     _fixup_container_tag(deployment_dir, image)
     os.remove(spec_file_name)
+
+
+@click.group()
+@click.pass_context
+def command(ctx):
+    '''manage a webapp deployment'''
+
+    # Check that --stack wasn't supplied
+    if ctx.parent.obj.stack:
+        error_exit("--stack can't be supplied with the deploy-webapp command")
+
+
+@command.command()
+@click.option("--kube-config", help="Provide a config file for a k8s deployment")
+@click.option("--image-registry", help="Provide a container image registry url for this k8s cluster")
+@click.option("--deployment-dir", help="Create deployment files in this directory", required=True)
+@click.option("--image", help="image to deploy", required=True)
+@click.option("--url", help="url to serve", required=True)
+@click.option("--env-file", help="environment file for webapp")
+@click.pass_context
+def create(ctx, deployment_dir, image, url, kube_config, image_registry, env_file):
+    '''create a deployment for the specified webapp container'''
+
+    return create_deployment(ctx, deployment_dir, image, url, kube_config, image_registry, env_file)

stack_orchestrator/deploy/webapp/deploy_webapp_from_registry.py

@@ -0,0 +1,272 @@
+# Copyright ©2023 Vulcanize
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http:#www.gnu.org/licenses/>.
+
+import hashlib
+import json
+import os
+import shlex
+import shutil
+import sys
+import tempfile
+
+import click
+
+from stack_orchestrator.deploy.webapp import deploy_webapp
+from stack_orchestrator.deploy.webapp.util import (LaconicRegistryClient,
+                                                   build_container_image, push_container_image,
+                                                   file_hash, deploy_to_k8s, publish_deployment,
+                                                   hostname_for_deployment_request, generate_hostname_for_app,
+                                                   match_owner)
+
+
+def process_app_deployment_request(
+    ctx,
+    laconic: LaconicRegistryClient,
+    app_deployment_request,
+    deployment_record_namespace,
+    dns_record_namespace,
+    dns_suffix,
+    deployment_parent_dir,
+    kube_config,
+    image_registry
+):
+    # 1. look up application
+    app = laconic.get_record(app_deployment_request.attributes.application, require=True)
+
+    # 2. determine dns
+    requested_name = hostname_for_deployment_request(app_deployment_request, laconic)
+
+    # HACK
+    if "." in requested_name:
+        raise Exception("Only unqualified hostnames allowed at this time.")
+
+    fqdn = f"{requested_name}.{dns_suffix}"
+
+    # 3. check ownership of existing dnsrecord vs this request
+    # TODO: Support foreign DNS
+    dns_crn = f"{dns_record_namespace}/{fqdn}"
+    dns_record = laconic.get_record(dns_crn)
+    if dns_record:
+        matched_owner = match_owner(app_deployment_request, dns_record)
+        if not matched_owner and dns_record.request:
+            matched_owner = match_owner(app_deployment_request, laconic.get_record(dns_record.request, require=True))
+
+        if matched_owner:
+            print("Matched DnsRecord ownership:", matched_owner)
+        else:
+            raise Exception("Unable to confirm ownership of DnsRecord %s for request %s" %
+                            (dns_record.id, app_deployment_request.id))
+
+    # 4. get build and runtime config from request
+    env_filename = None
+    if app_deployment_request.attributes.config and "env" in app_deployment_request.attributes.config:
+        env_filename = tempfile.mktemp()
+        with open(env_filename, 'w') as file:
+            for k, v in app_deployment_request.attributes.config["env"].items():
+                file.write("%s=%s\n" % (k, shlex.quote(str(v))))
+
+    # 5. determine new or existing deployment
+    #   a. check for deployment crn
+    app_deployment_crn = f"{deployment_record_namespace}/{fqdn}"
+    if app_deployment_request.attributes.deployment:
+        app_deployment_crn = app_deployment_request.attributes.deployment
+    if not app_deployment_crn.startswith(deployment_record_namespace):
+        raise Exception("Deployment CRN %s is not in a supported namespace" % app_deployment_request.attributes.deployment)
+
+    deployment_record = laconic.get_record(app_deployment_crn)
+    deployment_dir = os.path.join(deployment_parent_dir, fqdn)
+    deployment_config_file = os.path.join(deployment_dir, "config.env")
+    deployment_container_tag = "laconic-webapp/%s:local" % hashlib.md5(deployment_dir.encode()).hexdigest()
+    #   b. check for deployment directory (create if necessary)
+    if not os.path.exists(deployment_dir):
+        if deployment_record:
+            raise Exception("Deployment record %s exists, but not deployment dir %s. Please remove name." %
+                            (app_deployment_crn, deployment_dir))
+        print("deploy_webapp", deployment_dir)
+        deploy_webapp.create_deployment(ctx, deployment_dir, deployment_container_tag,
+                                        f"https://{fqdn}", kube_config, image_registry, env_filename)
+    elif env_filename:
+        shutil.copyfile(env_filename, deployment_config_file)
+
+    needs_k8s_deploy = False
+    # 6. build container (if needed)
+    if not deployment_record or deployment_record.attributes.application != app.id:
+        build_container_image(app, deployment_container_tag)
+        push_container_image(deployment_dir)
+        needs_k8s_deploy = True
+
+    # 7. update config (if needed)
+    if not deployment_record or file_hash(deployment_config_file) != deployment_record.attributes.meta.config:
+        needs_k8s_deploy = True
+
+    # 8. update k8s deployment
+    if needs_k8s_deploy:
+        print("Deploying to k8s")
+        deploy_to_k8s(
+            deployment_record,
+            deployment_dir,
+        )
+
+    publish_deployment(
+        laconic,
+        app,
+        deployment_record,
+        app_deployment_crn,
+        dns_record,
+        dns_crn,
+        deployment_dir,
+        app_deployment_request
+    )
+
+
+def load_known_requests(filename):
+    if filename and os.path.exists(filename):
+        return json.load(open(filename, "r"))
+    return {}
+
+
+def dump_known_requests(filename, requests):
+    if not filename:
+        return
+    known_requests = load_known_requests(filename)
+    for r in requests:
+        known_requests[r.id] = r.createTime
+    json.dump(known_requests, open(filename, "w"))
+
+
+@click.command()
+@click.option("--kube-config", help="Provide a config file for a k8s deployment")
+@click.option("--laconic-config", help="Provide a config file for laconicd", required=True)
+@click.option("--image-registry", help="Provide a container image registry url for this k8s cluster")
+@click.option("--deployment-parent-dir", help="Create deployment directories beneath this directory", required=True)
+@click.option("--request-id", help="The ApplicationDeploymentRequest to process")
+@click.option("--discover", help="Discover and process all pending ApplicationDeploymentRequests", is_flag=True, default=False)
+@click.option("--state-file", help="File to store state about previously seen requests.")
+@click.option("--only-update-state", help="Only update the state file, don't process any requests anything.", is_flag=True)
+@click.option("--dns-suffix", help="DNS domain to use eg, laconic.servesthe.world")
+@click.option("--record-namespace-dns", help="eg, crn://laconic/dns")
+@click.option("--record-namespace-deployments", help="eg, crn://laconic/deployments")
+@click.option("--dry-run", help="Don't do anything, just report what would be done.", is_flag=True)
+@click.pass_context
+def command(ctx, kube_config, laconic_config, image_registry, deployment_parent_dir,
+            request_id, discover, state_file, only_update_state,
+            dns_suffix, record_namespace_dns, record_namespace_deployments, dry_run):
+    if request_id and discover:
+        print("Cannot specify both --request-id and --discover", file=sys.stderr)
+        sys.exit(2)
+
+    if not request_id and not discover:
+        print("Must specify either --request-id or --discover", file=sys.stderr)
+        sys.exit(2)
+
+    if only_update_state and not state_file:
+        print("--only-update-state requires --state-file", file=sys.stderr)
+        sys.exit(2)
+
+    if not only_update_state:
+        if not record_namespace_dns or not record_namespace_deployments or not dns_suffix:
+            print("--dns-suffix, --record-namespace-dns, and --record-namespace-deployments are all required", file=sys.stderr)
+            sys.exit(2)
+
+    laconic = LaconicRegistryClient(laconic_config)
+
+    # Find deployment requests.
+    # single request
+    if request_id:
+        requests = [laconic.get_record(request_id, require=True)]
+    # all requests
+    elif discover:
+        requests = laconic.app_deployment_requests()
+
+    if only_update_state:
+        if not dry_run:
+            dump_known_requests(state_file, requests)
+        return
+
+    previous_requests = load_known_requests(state_file)
+
+    # Collapse related requests.
+    requests.sort(key=lambda r: r.createTime)
+    requests.reverse()
+    requests_by_name = {}
+    for r in requests:
+        app = laconic.get_record(r.attributes.application)
+        if not app:
+            print("Skipping request %s, cannot locate app." % r.id)
+            continue
+
+        requested_name = r.attributes.dns
+        if not requested_name:
+            requested_name = generate_hostname_for_app(app)
+            print("Generating name %s for request %s." % (requested_name, r.id))
+
+        if requested_name not in requests_by_name:
+            print(
+                "Found request %s to run application %s on %s."
+                % (r.id, r.attributes.application, requested_name)
+            )
+            requests_by_name[requested_name] = r
+        else:
+            print(
+                "Ignoring request %s, it is superseded by %s."
+                % (r.id, requests_by_name[requested_name].id)
+            )
+
+    # Find deployments.
+    deployments = laconic.app_deployments()
+    deployments_by_request = {}
+    for d in deployments:
+        if d.attributes.request:
+            deployments_by_request[d.attributes.request] = d
+
+    # Find removal requests.
+    cancellation_requests = {}
+    removal_requests = laconic.app_deployment_removal_requests()
+    for r in removal_requests:
+        if r.attributes.request:
+            cancellation_requests[r.attributes.request] = r
+
+    requests_to_execute = []
+    for r in requests_by_name.values():
+        if r.id in cancellation_requests and match_owner(cancellation_requests[r.id], r):
+            print(f"Found deployment cancellation request for {r.id} at {cancellation_requests[r.id].id}")
+        elif r.id in deployments_by_request:
+            print(f"Found satisfied request for {r.id} at {deployments_by_request[r.id].id}")
+        else:
+            if r.id not in previous_requests:
+                print(f"Request {r.id} needs to processed.")
+                requests_to_execute.append(r)
+            else:
+                print(
+                    f"Skipping unsatisfied request {r.id} because we have seen it before."
+                )
+
+    print("Found %d unsatisfied request(s) to process." % len(requests_to_execute))
+
+    if not dry_run:
+        for r in requests_to_execute:
+            try:
+                process_app_deployment_request(
+                    ctx,
+                    laconic,
+                    r,
+                    record_namespace_deployments,
+                    record_namespace_dns,
+                    dns_suffix,
+                    os.path.abspath(deployment_parent_dir),
+                    kube_config,
+                    image_registry
+                )
+            finally:
+                dump_known_requests(state_file, [r])

stack_orchestrator/deploy/webapp/undeploy_webapp_from_registry.py

@@ -0,0 +1,189 @@
+# Copyright ©2023 Vulcanize
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http:#www.gnu.org/licenses/>.
+
+import json
+import os
+import shutil
+import subprocess
+import sys
+
+import click
+
+from stack_orchestrator.deploy.webapp.util import LaconicRegistryClient, match_owner
+
+
+def process_app_removal_request(ctx,
+                                laconic: LaconicRegistryClient,
+                                app_removal_request,
+                                deployment_parent_dir,
+                                delete_volumes,
+                                delete_names):
+    deployment_record = laconic.get_record(app_removal_request.attributes.deployment, require=True)
+    dns_record = laconic.get_record(deployment_record.attributes.dns, require=True)
+    deployment_dir = os.path.join(deployment_parent_dir, dns_record.attributes.name)
+
+    if not os.path.exists(deployment_dir):
+        raise Exception("Deployment directory %s does not exist." % deployment_dir)
+
+    # Check if the removal request is from the owner of the DnsRecord or deployment record.
+    matched_owner = match_owner(app_removal_request, deployment_record, dns_record)
+
+    # Or of the original deployment request.
+    if not matched_owner and deployment_record.request:
+        matched_owner = match_owner(app_removal_request, laconic.get_record(deployment_record.request, require=True))
+
+    if matched_owner:
+        print("Matched deployment ownership:", matched_owner)
+    else:
+        raise Exception("Unable to confirm ownership of deployment %s for removal request %s" %
+                        (deployment_record.id, app_removal_request.id))
+
+    # TODO(telackey): Call the function directly.  The easiest way to build the correct click context is to
+    # exec the process, but it would be better to refactor so we could just call down_operation with the
+    # necessary parameters
+    down_command = [sys.argv[0], "deployment", "--dir", deployment_dir, "down"]
+    if delete_volumes:
+        down_command.append("--delete-volumes")
+    result = subprocess.run(down_command)
+    result.check_returncode()
+
+    removal_record = {
+        "record": {
+            "type": "ApplicationDeploymentRemovalRecord",
+            "version": "1.0.0",
+            "request": app_removal_request.id,
+            "deployment": deployment_record.id,
+        }
+    }
+    laconic.publish(removal_record)
+
+    if delete_names:
+        if deployment_record.names:
+            for name in deployment_record.names:
+                laconic.delete_name(name)
+
+        if dns_record.names:
+            for name in dns_record.names:
+                laconic.delete_name(name)
+
+    if delete_volumes:
+        shutil.rmtree(deployment_dir)
+
+
+def load_known_requests(filename):
+    if filename and os.path.exists(filename):
+        return json.load(open(filename, "r"))
+    return {}
+
+
+def dump_known_requests(filename, requests):
+    if not filename:
+        return
+    known_requests = load_known_requests(filename)
+    for r in requests:
+        known_requests[r.id] = r.createTime
+    json.dump(known_requests, open(filename, "w"))
+
+
+@click.command()
+@click.option("--laconic-config", help="Provide a config file for laconicd", required=True)
+@click.option("--deployment-parent-dir", help="Create deployment directories beneath this directory", required=True)
+@click.option("--request-id", help="The ApplicationDeploymentRemovalRequest to process")
+@click.option("--discover", help="Discover and process all pending ApplicationDeploymentRemovalRequests",
+              is_flag=True, default=False)
+@click.option("--state-file", help="File to store state about previously seen requests.")
+@click.option("--only-update-state", help="Only update the state file, don't process any requests anything.", is_flag=True)
+@click.option("--delete-names/--preserve-names", help="Delete all names associated with removed deployments.", default=True)
+@click.option("--delete-volumes/--preserve-volumes", default=True, help="delete data volumes")
+@click.option("--dry-run", help="Don't do anything, just report what would be done.", is_flag=True)
+@click.pass_context
+def command(ctx, laconic_config, deployment_parent_dir,
+            request_id, discover, state_file, only_update_state,
+            delete_names, delete_volumes, dry_run):
+    if request_id and discover:
+        print("Cannot specify both --request-id and --discover", file=sys.stderr)
+        sys.exit(2)
+
+    if not request_id and not discover:
+        print("Must specify either --request-id or --discover", file=sys.stderr)
+        sys.exit(2)
+
+    if only_update_state and not state_file:
+        print("--only-update-state requires --state-file", file=sys.stderr)
+        sys.exit(2)
+
+    laconic = LaconicRegistryClient(laconic_config)
+
+    # Find deployment removal requests.
+    # single request
+    if request_id:
+        requests = [laconic.get_record(request_id, require=True)]
+        # TODO: assert record type
+    # all requests
+    elif discover:
+        requests = laconic.app_deployment_removal_requests()
+
+    if only_update_state:
+        if not dry_run:
+            dump_known_requests(state_file, requests)
+        return
+
+    previous_requests = load_known_requests(state_file)
+    requests.sort(key=lambda r: r.createTime)
+
+    # Find deployments.
+    deployments = {}
+    for d in laconic.app_deployments(all=True):
+        deployments[d.id] = d
+
+    # Find removal requests.
+    removals_by_deployment = {}
+    removals_by_request = {}
+    for r in laconic.app_deployment_removals():
+        if r.attributes.deployment:
+            # TODO: should we handle CRNs?
+            removals_by_deployment[r.attributes.deployment] = r
+
+    requests_to_execute = []
+    for r in requests:
+        if not r.attributes.deployment:
+            print(f"Skipping removal request {r.id} since it was a cancellation.")
+        elif r.id in removals_by_request:
+            print(f"Found satisfied request for {r.id} at {removals_by_request[r.id].id}")
+        elif r.attributes.deployment in removals_by_deployment:
+            print(
+                f"Found removal record for indicated deployment {r.attributes.deployment} at "
+                f"{removals_by_deployment[r.attributes.deployment].id}")
+        else:
+            if r.id not in previous_requests:
+                print(f"Request {r.id} needs to processed.")
+                requests_to_execute.append(r)
+            else:
+                print(f"Skipping unsatisfied request {r.id} because we have seen it before.")
+
+    print("Found %d unsatisfied request(s) to process." % len(requests_to_execute))
+
+    if not dry_run:
+        for r in requests_to_execute:
+            try:
+                process_app_removal_request(
+                    ctx,
+                    laconic,
+                    r,
+                    os.path.abspath(deployment_parent_dir),
+                    delete_volumes,
+                    delete_names
+                )
+            finally:
+                dump_known_requests(state_file, [r])

stack_orchestrator/deploy/webapp/util.py

@@ -0,0 +1,327 @@
+# Copyright © 2023 Vulcanize
+
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http:#www.gnu.org/licenses/>.
+
+import hashlib
+import json
+import os
+import random
+import subprocess
+import sys
+import tempfile
+import uuid
+
+import yaml
+
+
+class AttrDict(dict):
+    def __init__(self, *args, **kwargs):
+        super(AttrDict, self).__init__(*args, **kwargs)
+        self.__dict__ = self
+
+    def __getattribute__(self, attr):
+        __dict__ = super(AttrDict, self).__getattribute__("__dict__")
+        if attr in __dict__:
+            v = super(AttrDict, self).__getattribute__(attr)
+            if isinstance(v, dict):
+                return AttrDict(v)
+            return v
+
+
+def cmd(*vargs):
+    try:
+        result = subprocess.run(vargs, capture_output=True)
+        result.check_returncode()
+        return result.stdout.decode()
+    except Exception as err:
+        print(result.stderr.decode())
+        raise err
+
+
+def match_owner(recordA, *records):
+    for owner in recordA.owners:
+        for otherRecord in records:
+            if owner in otherRecord.owners:
+                return owner
+    return None
+
+
+class LaconicRegistryClient:
+    def __init__(self, config_file):
+        self.config_file = config_file
+        self.cache = AttrDict(
+            {
+                "name_or_id": {},
+            }
+        )
+
+    def list_records(self, criteria={}, all=False):
+        args = ["laconic", "-c", self.config_file, "cns", "record", "list"]
+
+        if all:
+            args.append("--all")
+
+        if criteria:
+            for k, v in criteria.items():
+                args.append("--%s" % k)
+                args.append(str(v))
+
+        results = [AttrDict(r) for r in json.loads(cmd(*args))]
+
+        # Most recent records first
+        results.sort(key=lambda r: r.createTime)
+        results.reverse()
+
+        return results
+
+    def is_crn(self, name_or_id: str):
+        if name_or_id:
+            return str(name_or_id).startswith("crn://")
+        return False
+
+    def is_id(self, name_or_id: str):
+        return not self.is_crn(name_or_id)
+
+    def _add_to_cache(self, records):
+        if not records:
+            return
+
+        for p in records:
+            self.cache["name_or_id"][p.id] = p
+            if p.names:
+                for crn in p.names:
+                    self.cache["name_or_id"][crn] = p
+            if p.attributes.type not in self.cache:
+                self.cache[p.attributes.type] = []
+            self.cache[p.attributes.type].append(p)
+
+    def resolve(self, name):
+        if not name:
+            return None
+
+        if name in self.cache.name_or_id:
+            return self.cache.name_or_id[name]
+
+        args = ["laconic", "-c", self.config_file, "cns", "name", "resolve", name]
+
+        parsed = [AttrDict(r) for r in json.loads(cmd(*args))]
+        if parsed:
+            self._add_to_cache(parsed)
+            return parsed[0]
+
+        return None
+
+    def get_record(self, name_or_id, require=False):
+        if not name_or_id:
+            if require:
+                raise Exception("Cannot locate record:", name_or_id)
+            return None
+
+        if name_or_id in self.cache.name_or_id:
+            return self.cache.name_or_id[name_or_id]
+
+        if self.is_crn(name_or_id):
+            return self.resolve(name_or_id)
+
+        args = [
+            "laconic",
+            "-c",
+            self.config_file,
+            "cns",
+            "record",
+            "get",
+            "--id",
+            name_or_id,
+        ]
+
+        parsed = [AttrDict(r) for r in json.loads(cmd(*args))]
+        if len(parsed):
+            self._add_to_cache(parsed)
+            return parsed[0]
+
+        if require:
+            raise Exception("Cannot locate record:", name_or_id)
+        return None
+
+    def app_deployment_requests(self, all=True):
+        return self.list_records({"type": "ApplicationDeploymentRequest"}, all)
+
+    def app_deployments(self, all=True):
+        return self.list_records({"type": "ApplicationDeploymentRecord"}, all)
+
+    def app_deployment_removal_requests(self, all=True):
+        return self.list_records({"type": "ApplicationDeploymentRemovalRequest"}, all)
+
+    def app_deployment_removals(self, all=True):
+        return self.list_records({"type": "ApplicationDeploymentRemovalRecord"}, all)
+
+    def publish(self, record, names=[]):
+        tmpdir = tempfile.mkdtemp()
+        try:
+            record_fname = os.path.join(tmpdir, "record.yml")
+            record_file = open(record_fname, 'w')
+            yaml.dump(record, record_file)
+            record_file.close()
+            print(open(record_fname, 'r').read())
+
+            new_record_id = json.loads(
+                cmd("laconic", "-c", self.config_file, "cns", "record", "publish", "--filename", record_fname)
+            )["id"]
+            for name in names:
+                self.set_name(name, new_record_id)
+            return new_record_id
+        finally:
+            cmd("rm", "-rf", tmpdir)
+
+    def set_name(self, name, record_id):
+        cmd("laconic", "-c", self.config_file, "cns", "name", "set", name, record_id)
+
+    def delete_name(self, name):
+        cmd("laconic", "-c", self.config_file, "cns", "name", "delete", name)
+
+
+def file_hash(filename):
+    return hashlib.sha1(open(filename).read().encode()).hexdigest()
+
+
+def build_container_image(app_record, tag, extra_build_args=[]):
+    tmpdir = tempfile.mkdtemp()
+
+    try:
+        record_id = app_record["id"]
+        ref = app_record.attributes.repository_ref
+        repo = random.choice(app_record.attributes.repository)
+        clone_dir = os.path.join(tmpdir, record_id)
+
+        print(f"Cloning repository {repo} to {clone_dir} ...")
+        if ref:
+            # TODO: Determing branch or hash, and use depth 1 if we can.
+            git_env = dict(os.environ.copy())
+            # Never prompt
+            git_env["GIT_TERMINAL_PROMPT"] = "0"
+            subprocess.check_call(["git", "clone", repo, clone_dir], env=git_env)
+            subprocess.check_call(["git", "checkout", ref], cwd=clone_dir, env=git_env)
+        else:
+            result = subprocess.run(["git", "clone", "--depth", "1", repo, clone_dir])
+            result.check_returncode()
+
+        print("Building webapp ...")
+        build_command = [sys.argv[0], "build-webapp", "--source-repo", clone_dir, "--tag", tag]
+        if extra_build_args:
+            build_command.append("--extra-build-args")
+            build_command.append(" ".join(extra_build_args))
+
+        result = subprocess.run(build_command)
+        result.check_returncode()
+    finally:
+        cmd("rm", "-rf", tmpdir)
+
+
+def push_container_image(deployment_dir):
+    print("Pushing image ...")
+    result = subprocess.run([sys.argv[0], "deployment", "--dir", deployment_dir, "push-images"])
+    result.check_returncode()
+
+
+def deploy_to_k8s(deploy_record, deployment_dir):
+    if not deploy_record:
+        command = "up"
+    else:
+        command = "update"
+
+    result = subprocess.run([sys.argv[0], "deployment", "--dir", deployment_dir, command])
+    result.check_returncode()
+
+
+def publish_deployment(laconic: LaconicRegistryClient,
+                       app_record,
+                       deploy_record,
+                       deployment_crn,
+                       dns_record,
+                       dns_crn,
+                       deployment_dir,
+                       app_deployment_request=None):
+    if not deploy_record:
+        deploy_ver = "0.0.1"
+    else:
+        deploy_ver = "0.0.%d" % (int(deploy_record.attributes.version.split(".")[-1]) + 1)
+
+    if not dns_record:
+        dns_ver = "0.0.1"
+    else:
+        dns_ver = "0.0.%d" % (int(dns_record.attributes.version.split(".")[-1]) + 1)
+
+    spec = yaml.full_load(open(os.path.join(deployment_dir, "spec.yml")))
+    fqdn = spec["network"]["http-proxy"][0]["host-name"]
+
+    uniq = uuid.uuid4()
+
+    new_dns_record = {
+        "record": {
+            "type": "DnsRecord",
+            "version": dns_ver,
+            "name": fqdn,
+            "resource_type": "A",
+            "meta": {
+                "so": uniq.hex
+            },
+        }
+    }
+    if app_deployment_request:
+        new_dns_record["record"]["request"] = app_deployment_request.id
+
+    dns_id = laconic.publish(new_dns_record, [dns_crn])
+
+    new_deployment_record = {
+        "record": {
+            "type": "ApplicationDeploymentRecord",
+            "version": deploy_ver,
+            "url": f"https://{fqdn}",
+            "name": app_record.attributes.name,
+            "application": app_record.id,
+            "dns": dns_id,
+            "meta": {
+                "config": file_hash(os.path.join(deployment_dir, "config.env")),
+                "so": uniq.hex
+            },
+        }
+    }
+    if app_deployment_request:
+        new_deployment_record["record"]["request"] = app_deployment_request.id
+
+    deployment_id = laconic.publish(new_deployment_record, [deployment_crn])
+    return {"dns": dns_id, "deployment": deployment_id}
+
+
+def hostname_for_deployment_request(app_deployment_request, laconic):
+    dns_name = app_deployment_request.attributes.dns
+    if not dns_name:
+        app = laconic.get_record(app_deployment_request.attributes.application, require=True)
+        dns_name = generate_hostname_for_app(app)
+    elif dns_name.startswith("crn://"):
+        record = laconic.get_record(dns_name, require=True)
+        dns_name = record.attributes.name
+    return dns_name
+
+
+def generate_hostname_for_app(app):
+    last_part = app.attributes.name.split("/")[-1]
+    m = hashlib.sha256()
+    m.update(app.attributes.name.encode())
+    m.update(b"|")
+    if isinstance(app.attributes.repository, list):
+        m.update(app.attributes.repository[0].encode())
+    else:
+        m.update(app.attributes.repository.encode())
+    return "%s-%s" % (last_part, m.hexdigest()[0:10])

stack_orchestrator/main.py

@@ -20,7 +20,10 @@ from stack_orchestrator.repos import setup_repositories
 from stack_orchestrator.build import build_containers
 from stack_orchestrator.build import build_npms
 from stack_orchestrator.build import build_webapp
-from stack_orchestrator.deploy.webapp import run_webapp, deploy_webapp
+from stack_orchestrator.deploy.webapp import (run_webapp,
+                                              deploy_webapp,
+                                              deploy_webapp_from_registry,
+                                              undeploy_webapp_from_registry)
 from stack_orchestrator.deploy import deploy
 from stack_orchestrator import version
 from stack_orchestrator.deploy import deployment
@@ -53,6 +56,8 @@ cli.add_command(build_npms.command, "build-npms")
 cli.add_command(build_webapp.command, "build-webapp")
 cli.add_command(run_webapp.command, "run-webapp")
 cli.add_command(deploy_webapp.command, "deploy-webapp")
+cli.add_command(deploy_webapp_from_registry.command, "deploy-webapp-from-registry")
+cli.add_command(undeploy_webapp_from_registry.command, "undeploy-webapp-from-registry")
 cli.add_command(deploy.command, "deploy")  # deploy is an alias for deploy-system
 cli.add_command(deploy.command, "deploy-system")
 cli.add_command(deployment.command, "deployment")

tests/k8s-deploy/run-deploy-test.sh

@@ -1,14 +1,59 @@
 #!/usr/bin/env bash
 set -e
 if [ -n "$CERC_SCRIPT_DEBUG" ]; then
-  set -x
+    set -x
+    # Dump environment variables for debugging
+    echo "Environment variables:"
+    env
 fi
+
+# Helper functions: TODO move into a separate file
+wait_for_pods_started () {
+    for i in {1..5}
+    do
+        local ps_output=$( $TEST_TARGET_SO deployment --dir $test_deployment_dir ps )
+
+        if [[ "$ps_output" == *"Running containers:"* ]]; then
+            # if ready, return
+            return
+        else
+            # if not ready, wait
+            sleep 5
+        fi
+    done
+    # Timed out, error exit
+    echo "waiting for pods to start: FAILED"
+    delete_cluster_exit
+}
+
+wait_for_log_output () {
+    for i in {1..5}
+    do
+
+        local log_output=$( $TEST_TARGET_SO deployment --dir $test_deployment_dir logs )
+
+        if [[ ! -z "$log_output" ]]; then
+            # if ready, return
+            return
+        else
+            # if not ready, wait
+            sleep 5
+        fi
+    done
+    # Timed out, error exit
+    echo "waiting for pods log content: FAILED"
+    delete_cluster_exit
+}
+
+
+delete_cluster_exit () {
+    $TEST_TARGET_SO deployment --dir $test_deployment_dir stop --delete-volumes
+    exit 1
+}
+
 # Note: eventually this test should be folded into ../deploy/
 # but keeping it separate for now for convenience
 TEST_TARGET_SO=$( ls -t1 ./package/laconic-so* | head -1 )
-# Dump environment variables for debugging
-echo "Environment variables:"
-env
 # Set a non-default repo dir
 export CERC_REPO_BASE_DIR=~/stack-orchestrator-test/repo-base-dir
 echo "Testing this package: $TEST_TARGET_SO"
@@ -18,7 +63,9 @@ echo "Version reported is: ${reported_version_string}"
 echo "Cloning repositories into: $CERC_REPO_BASE_DIR"
 rm -rf $CERC_REPO_BASE_DIR
 mkdir -p $CERC_REPO_BASE_DIR
-# Test basic stack-orchestrator deploy
+$TEST_TARGET_SO --stack test setup-repositories
+$TEST_TARGET_SO --stack test build-containers
+# Test basic stack-orchestrator deploy to k8s
 test_deployment_dir=$CERC_REPO_BASE_DIR/test-deployment-dir
 test_deployment_spec=$CERC_REPO_BASE_DIR/test-deployment-spec.yml
 $TEST_TARGET_SO --stack test deploy --deploy-to k8s-kind init --output $test_deployment_spec --config CERC_TEST_PARAM_1=PASSED
@@ -53,23 +100,36 @@ fi
 echo "deploy create output file test: passed"
 # Try to start the deployment
 $TEST_TARGET_SO deployment --dir $test_deployment_dir start
-# TODO: add a check to see if the container is up
-# Sleep because k8s not up yet
-sleep 30
+wait_for_pods_started
 # Check logs command works
+wait_for_log_output
 log_output_3=$( $TEST_TARGET_SO deployment --dir $test_deployment_dir logs )
 if [[ "$log_output_3" == *"Filesystem is fresh"* ]]; then
     echo "deployment logs test: passed"
 else
     echo "deployment logs test: FAILED"
-    exit 1
+    delete_cluster_exit
 fi
 # Check the config variable CERC_TEST_PARAM_1 was passed correctly
 if [[ "$log_output_3" == *"Test-param-1: PASSED"* ]]; then
     echo "deployment config test: passed"
 else
     echo "deployment config test: FAILED"
-    exit 1
+    delete_cluster_exit
+fi
+# Stop then start again and check the volume was preserved
+$TEST_TARGET_SO deployment --dir $test_deployment_dir stop
+# Sleep a bit just in case
+sleep 2
+$TEST_TARGET_SO deployment --dir $test_deployment_dir start
+wait_for_pods_started
+wait_for_log_output
+log_output_4=$( $TEST_TARGET_SO deployment --dir $test_deployment_dir logs )
+if [[ "$log_output_4" == *"Filesystem is old"* ]]; then
+    echo "Retain volumes test: passed"
+else
+    echo "Retain volumes test: FAILED"
+    delete_cluster_exit
 fi
 # Stop and clean up
 $TEST_TARGET_SO deployment --dir $test_deployment_dir stop --delete-volumes

tests/scripts/install-kind.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+# TODO: handle ARM
+curl --silent -Lo ./kind https://kind.sigs.k8s.io/dl/v0.20.0/kind-linux-amd64
+chmod +x ./kind
+mv ./kind /usr/local/bin

tests/scripts/install-kubectl.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+# TODO: handle ARM
+curl --silent -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl"
+chmod +x ./kubectl
+mv ./kubectl /usr/local/bin