wip:milestone 0 fixes

templates/all-in-one.yaml

@@ -0,0 +1,132 @@
+id: all-in-one
+name: All-in-One Development Node
+description: Complete MadBase stack on a single server for development/testing
+version: 1.0
+
+min_hetzner_plan: CX41
+estimated_monthly_cost: 25.60
+
+services:
+  - id: postgresql
+    name: PostgreSQL
+    image: registry.gitlab.com/postgres-ai/postgresql-autobase/patroni:3.0.2
+    ports: ["5432:5432", "8008:8008"]
+    resource_profile: balanced
+
+  - id: etcd
+    name: etcd
+    image: quay.io/coreos/etcd:v3.5.9
+    ports: ["2379:2379", "2380:2380"]
+    resource_profile: minimal
+
+  - id: haproxy
+    name: HAProxy
+    image: haproxy:2.8-alpine
+    ports: ["5433:5433"]
+    resource_profile: minimal
+
+  - id: redis
+    name: Redis
+    image: redis:7-alpine
+    ports: ["6379:6379"]
+    resource_profile: minimal
+
+  - id: minio
+    name: MinIO
+    image: quay.io/minio/minio:latest
+    ports: ["9000:9000", "9001:9001"]
+    command: ["server", "/data", "--console-address", ":9001"]
+    environment:
+      MINIO_ROOT_USER: ${MINIO_ROOT_USER:-minioadmin}
+      MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:-minioadmin}
+    volumes:
+      - minio_data:/data
+    resource_profile: balanced
+    optional: true
+    condition: USE_SELF_HOSTED_STORAGE == true
+
+  - id: worker
+    name: MadBase Worker
+    image: madbase/worker:latest
+    ports: ["8002:8002"]
+    replicas: 2
+    resource_profile: cpu_intensive
+
+  - id: proxy
+    name: Gateway Proxy
+    image: madbase/proxy:latest
+    ports: ["8080:8080"]
+    resource_profile: balanced
+
+  - id: control
+    name: Control Plane API
+    image: madbase/control:latest
+    ports: ["8001:8001"]
+    resource_profile: balanced
+
+  - id: victoria
+    name: VictoriaMetrics
+    image: victoriametrics/victoria-metrics:latest
+    ports: ["8428:8428"]
+    volumes:
+      - vm_data:/victoria-metrics-data
+    resource_profile: balanced
+
+  - id: loki
+    name: Loki
+    image: grafana/loki:latest
+    ports: ["3100:3100"]
+    volumes:
+      - loki_data:/loki
+    resource_profile: balanced
+
+  - id: vmagent
+    name: VictoriaMetrics Agent
+    image: victoriametrics/vmagent:latest
+    ports: ["8429:8429"]
+    resource_profile: minimal
+
+  - id: promtail
+    name: Promtail
+    image: grafana/promtail:latest
+    volumes:
+      - /var/log:/var/log:ro
+      - ./config/promtail.yml:/etc/promtail/config.yml:ro
+    resource_profile: minimal
+
+  - id: grafana
+    name: Grafana
+    image: grafana/grafana:latest
+    ports: ["3030:3030"]
+    environment:
+      GF_SECURITY_ADMIN_USER: ${GRAFANA_USER:-admin}
+      GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_PASSWORD}
+      GF_SERVER_ROOT_URL: http://localhost:3030
+      GF_INSTALL_PLUGINS: grafana-piechart-panel
+    volumes:
+      - grafana_data:/var/lib/grafana
+    resource_profile: balanced
+
+requirements:
+  min_nodes: 1
+  max_nodes: 1
+  supports_ha: false
+  recommended_deployment: "Single server for development, testing, or production MVP"
+
+notes: |
+  This template runs ALL services on one machine.
+  Not recommended for production with significant traffic.
+  Upgrade to dedicated templates when:
+  - CPU usage > 70% sustained
+  - Memory usage > 80%
+  - Need true HA for database
+
+networks:
+  frontend:
+    ports: [8080, 3030]
+  backend:
+    ports: [8001, 8002, 5433, 6379]
+  monitoring:
+    ports: [8428, 3100, 8429]
+  storage:
+    ports: [9000, 9001]

templates/control-plane-node.yaml

@@ -0,0 +1,31 @@
+id: control-plane-node
+name: Control Plane Node
+description: Management APIs and Studio UI
+version: 1.0
+min_hetzner_plan: CX11
+estimated_monthly_cost: 3.69
+services:
+  - id: proxy
+    name: Gateway Proxy
+    image: madbase/proxy:latest
+    ports: ["8080:8080"]
+  - id: control
+    name: Control Plane API
+    image: madbase/control:latest
+    ports: ["8001:8001"]
+  - id: grafana
+    name: Grafana
+    image: grafana/grafana:latest
+    ports: ["3030:3030"]
+    optional: true
+  - id: keepalived
+    name: Keepalived
+    image: osixia/keepalived:latest
+    network_mode: host
+    optional: true
+    condition: HA_MODE == true
+requirements:
+  min_nodes: 1
+  max_nodes: 2
+  supports_ha: true
+  floating_ip_required: true

templates/db-node.yaml

@@ -0,0 +1,28 @@
+id: db-node
+name: State Node (PostgreSQL + Redis)
+description: High-availability State Pillar with PostgreSQL and Redis for shared caching
+version: 2.0
+min_hetzner_plan: CX21
+estimated_monthly_cost: 6.94
+services:
+  - id: postgresql
+    name: PostgreSQL
+    image: registry.gitlab.com/postgres-ai/postgresql-autobase/patroni:3.0.2
+    ports: ["5432:5432", "8008:8008"]
+  - id: etcd
+    name: etcd
+    image: quay.io/coreos/etcd:v3.5.9
+    ports: ["2379:2379", "2380:2380"]
+  - id: redis
+    name: Redis
+    image: redis:7-alpine
+    ports: ["6379:6379"]
+    command: redis-server --appendonly yes --maxmemory 256mb --maxmemory-policy allkeys-lru
+  - id: haproxy
+    name: HAProxy
+    image: haproxy:2.8-alpine
+    ports: ["5433:5433", "6379:6379", "7000:7000"]
+requirements:
+  min_nodes: 3
+  max_nodes: 7
+  supports_ha: true

templates/monitoring-node.yaml

@@ -0,0 +1,24 @@
+id: monitoring-node
+name: Monitoring Node
+description: Centralized metrics and logging
+version: 1.0
+min_hetzner_plan: CX11
+estimated_monthly_cost: 3.69
+services:
+  - id: victoriametrics
+    name: VictoriaMetrics
+    image: victoriametrics/victoria-metrics:latest
+    ports: ["8428:8428"]
+  - id: loki
+    name: Loki
+    image: grafana/loki:latest
+    ports: ["3100:3100"]
+  - id: alertmanager
+    name: Alertmanager
+    image: prom/alertmanager:latest
+    ports: ["9093:9093"]
+    optional: true
+requirements:
+  min_nodes: 1
+  max_nodes: 3
+  supports_ha: true

templates/worker-db-combo.yaml

@@ -0,0 +1,101 @@
+id: worker-db-combo
+name: Worker + Database Combo
+description: Combined worker and database node for smaller deployments (2-3 servers)
+version: 1.0
+
+min_hetzner_plan: CX31
+estimated_monthly_cost: 14.21
+
+services:
+  - id: postgresql
+    name: PostgreSQL
+    image: registry.gitlab.com/postgres-ai/postgresql-autobase/patroni:3.0.2
+    ports: ["5432:5432", "8008:8008"]
+    environment:
+      POSTGRES_USER: ${DB_USER}
+      POSTGRES_PASSWORD: ${DB_PASSWORD}
+      POSTGRES_DB: madbase
+      PATRONI_SCOPE: madbase-cluster
+      PATRONI_NAME: node1
+      PATRONI_RESTAPI_LISTEN: 0.0.0.0:8008
+      PATRONI_POSTGRESQL_LISTEN: 0.0.0.0:5432
+      PATRONI_POSTGRESQL_DATA_DIR: /var/lib/postgresql/data
+      PATRONI_ETCD3_HOSTS: http://localhost:2379
+    volumes:
+      - postgres_data:/var/lib/postgresql/data
+    resource_profile: balanced
+
+  - id: etcd
+    name: etcd
+    image: quay.io/coreos/etcd:v3.5.9
+    ports: ["2379:2379", "2380:2380"]
+    environment:
+      ETCD_NAME: node1
+      ETCD_INITIAL_ADVERTISE_PEER_URLS: http://localhost:2380
+      ETCD_LISTEN_PEER_URLS: http://0.0.0.0:2380
+      ETCD_LISTEN_CLIENT_URLS: http://0.0.0.0:2379
+      ETCD_ADVERTISE_CLIENT_URLS: http://localhost:2379
+      ETCD_INITIAL_CLUSTER: node1=http://localhost:2380
+      ETCD_INITIAL_CLUSTER_STATE: new
+      ETCD_INITIAL_CLUSTER_TOKEN: madbase-etcd
+    volumes:
+      - etcd_data:/etcd-data
+    resource_profile: minimal
+
+  - id: haproxy
+    name: HAProxy
+    image: haproxy:2.8-alpine
+    ports: ["5433:5433"]
+    volumes:
+      - ./config/haproxy.cfg:/usr/local/etc/haproxy/haproxy.cfg:ro
+    resource_profile: minimal
+    depends_on:
+      - postgresql
+
+  - id: worker
+    name: MadBase Worker
+    image: madbase/worker:latest
+    ports: ["8002:8002"]
+    environment:
+      WORKER_PORT: 8002
+      DATABASE_URL: postgresql://${DB_USER}:${DB_PASSWORD}@localhost:5433/madbase
+      REDIS_URL: redis://${REDIS_HOST}:6379
+      S3_ENDPOINT: ${S3_ENDPOINT}
+      S3_ACCESS_KEY: ${S3_ACCESS_KEY}
+      S3_SECRET_KEY: ${S3_SECRET_KEY}
+      S3_BUCKET: ${S3_BUCKET}
+      S3_REGION: ${S3_REGION}
+    resource_profile: cpu_intensive
+    depends_on:
+      - postgresql
+
+  - id: vmagent
+    name: VictoriaMetrics Agent
+    image: victoriametrics/vmagent:latest
+    ports: ["8429:8429"]
+    command: ["--promscrape.config=/etc/vmagent/prometheus.yml", "--remoteWrite.url=http://victoriametrics:8428/api/v1/write"]
+    volumes:
+      - ./config/vmagent.yml:/etc/vmagent/prometheus.yml:ro
+    resource_profile: minimal
+
+requirements:
+  min_nodes: 1
+  max_nodes: 2
+  supports_ha: true
+  recommended_deployment: "2-3 servers: 1x worker-db-combo + 1x control-plane + optional monitoring node"
+
+scaling:
+  can_add_workers: true
+  can_split_database: true
+  upgrade_path: "Migrate to dedicated db-node.yaml + worker-node.yaml when load increases"
+
+resource_profiles:
+  minimal:
+    cpu_limit: "0.5"
+    memory_limit: "512Mi"
+  balanced:
+    cpu_limit: "2"
+    memory_limit: "2Gi"
+  cpu_intensive:
+    cpu_limit: "4"
+    memory_limit: "4Gi"

templates/worker-monitor-combo.yaml

@@ -0,0 +1,69 @@
+id: worker-monitor-combo
+name: Worker + Monitoring Combo
+description: Worker node with local VictoriaMetrics and Loki for smaller deployments
+version: 1.0
+
+min_hetzner_plan: CX21
+estimated_monthly_cost: 6.94
+
+services:
+  - id: worker
+    name: MadBase Worker
+    image: madbase/worker:latest
+    ports: ["8002:8002"]
+    environment:
+      WORKER_PORT: 8002
+      DATABASE_URL: ${DATABASE_URL}
+      REDIS_URL: ${REDIS_URL}
+      S3_ENDPOINT: ${S3_ENDPOINT}
+      S3_ACCESS_KEY: ${S3_ACCESS_KEY}
+      S3_SECRET_KEY: ${S3_SECRET_KEY}
+      S3_BUCKET: ${S3_BUCKET}
+      S3_REGION: ${S3_REGION}
+    resource_profile: cpu_intensive
+
+  - id: victoria
+    name: VictoriaMetrics
+    image: victoriametrics/victoria-metrics:latest
+    ports: ["8428:8428"]
+    volumes:
+      - vm_data:/victoria-metrics-data
+    resource_profile: balanced
+
+  - id: loki
+    name: Loki
+    image: grafana/loki:latest
+    ports: ["3100:3100"]
+    volumes:
+      - loki_data:/loki
+    resource_profile: balanced
+
+  - id: vmagent
+    name: VictoriaMetrics Agent
+    image: victoriametrics/vmagent:latest
+    ports: ["8429:8429"]
+    command: ["--promscrape.config=/etc/vmagent/prometheus.yml", "--remoteWrite.url=http://localhost:8428/api/v1/write"]
+    volumes:
+      - ./config/vmagent.yml:/etc/vmagent/prometheus.yml:ro
+    resource_profile: minimal
+
+  - id: promtail
+    name: Promtail
+    image: grafana/promtail:latest
+    volumes:
+      - /var/log:/var/log:ro
+      - ./config/promtail.yml:/etc/promtail/config.yml:ro
+    resource_profile: minimal
+
+requirements:
+  min_nodes: 1
+  max_nodes: 3
+  supports_ha: true
+  recommended_deployment: "For 2-3 server deployments with monitoring on worker node"
+
+notes: |
+  VictoriaMetrics and Loki run on the same node as worker.
+  Other workers can send metrics/logs to this node.
+  Upgrade to dedicated monitoring node when:
+  - Worker CPU > 60% (monitoring competes for resources)
+  - Need to scale workers horizontally

templates/worker-node.yaml

@@ -0,0 +1,26 @@
+id: worker-node
+name: Worker Node
+description: API worker nodes for horizontal scaling
+version: 1.0
+min_hetzner_plan: CX11
+estimated_monthly_cost: 3.69
+services:
+  - id: worker
+    name: MadBase Worker
+    image: madbase/worker:latest
+    replicas: 1
+    ports: ["8002-8020:8002-8020"]
+  - id: vmagent
+    name: VictoriaMetrics Agent
+    image: victoriametrics/vmagent:latest
+    ports: ["8429:8429"]
+    optional: true
+requirements:
+  min_nodes: 1
+  max_nodes: 20
+  supports_ha: true
+  auto_scale:
+    enabled: true
+    metric: cpu_usage_percent
+    scale_up_threshold: 70
+    scale_down_threshold: 20