infra: full IaC state after hf-pdocker-01 rebuild (2026-03-08)

Replaces initial Nomad/Consul/Terraform skeleton with current Docker-based infrastructure across all three nodes (hf-pdocker-01, hf-pdocker-02, bart). Key changes: - CLAUDE.md: updated service distribution reflecting hf-pdocker-01 restored - docs/plans/2026-03-08-hf-pdocker-01-rebuild.md: new rebuild plan doc - compose/bart/: ai-agents, guacamole, matrix, media, openvas, smarthome, watchtower - compose/hf-pdocker-02/: traefik, monitoring, adguard, gitea, semaphore, wikijs, unifi, vaultwarden, actual-budget, mcpo, netclaw, trivy, watchtower, n8n - compose/hf-pdocker-01/: frigate, frigate-notify, farm-agent - stacks/: all Swarm stack definitions (monitoring, traefik, smarthome, matrix, guacamole, media, ai-agents, frigate, gitea, semaphore, wikijs, unifi, etc.) - .gitignore: exclude .env credential files and acme.json certs - .env.example: placeholder credential files for all services - .claude/agents/: gitea-backup and other infrastructure agent configs - scripts/: frigate media cleanup and NAS sync scripts Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-08 18:51:25 -05:00
parent b1d111a011
commit de1d9e1d93
102 changed files with 12634 additions and 3 deletions
@@ -0,0 +1,127 @@
+services:
+  synapse:
+    image: matrixdotorg/synapse:latest
+    restart: unless-stopped
+    environment:
+      - SYNAPSE_SERVER_NAME=mess.hobbs.farm
+      - SYNAPSE_REPORT_STATS=no
+    volumes:
+      - /mnt/docker-data/configs/matrix/data:/data
+    ports:
+      - "8008:8008"
+    networks:
+      - traefik-public
+      - matrix-internal
+    healthcheck:
+      test: ["CMD-SHELL", "curl -fSs http://localhost:8008/health || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
+    deploy:
+      mode: replicated
+      replicas: 1
+      placement:
+        constraints:
+          - node.hostname == hf-pdocker-01
+      labels:
+        - "traefik.enable=true"
+        - "traefik.docker.network=traefik-public"
+        - "traefik.http.services.mess.loadbalancer.server.scheme=http"
+        - "traefik.http.services.mess.loadbalancer.server.port=8008"
+        - "traefik.http.routers.mess.rule=Host(`mess.hobbs.farm`)"
+        - "traefik.http.routers.mess.entrypoints=websecure"
+        - "traefik.http.routers.mess.tls=true"
+        - "traefik.http.routers.mess.tls.certresolver=letsencrypt"
+        - "traefik.http.routers.mess.service=mess"
+        - "traefik.http.routers.mess-federation.rule=Host(`mess.hobbs.farm`) && PathPrefix(`/_matrix/federation`)"
+        - "traefik.http.routers.mess-federation.entrypoints=websecure"
+        - "traefik.http.routers.mess-federation.tls=true"
+        - "traefik.http.routers.mess-federation.tls.certresolver=letsencrypt"
+        - "traefik.http.routers.mess-federation.service=mess"
+      resources:
+        limits:
+          memory: 1G
+
+  wellknown:
+    image: nginx:alpine
+    restart: unless-stopped
+    volumes:
+      - /mnt/docker-data/configs/matrix/wellknown:/usr/share/nginx/html/.well-known/matrix:ro
+    networks:
+      - traefik-public
+    healthcheck:
+      test: ["CMD-SHELL", "wget -q --spider http://localhost:80/ || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 15s
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
+    deploy:
+      mode: replicated
+      replicas: 1
+      placement:
+        constraints:
+          - node.hostname == hf-pdocker-01
+      labels:
+        - "traefik.enable=true"
+        - "traefik.http.services.wellknown.loadbalancer.server.port=80"
+        - "traefik.http.routers.wellknown.rule=Host(`hobbs.farm`) && PathPrefix(`/.well-known/matrix`)"
+        - "traefik.http.routers.wellknown.entrypoints=websecure"
+        - "traefik.http.routers.wellknown.tls=true"
+        - "traefik.http.routers.wellknown.tls.certresolver=letsencrypt"
+        - "traefik.http.routers.wellknown.service=wellknown"
+      resources:
+        limits:
+          memory: 64M
+
+  synapse-db:
+    image: postgres:15-alpine
+    user: "1024:100"
+    restart: unless-stopped
+    environment:
+      - POSTGRES_USER=synapse
+      - POSTGRES_PASSWORD=${MATRIX_DB_PASSWORD}
+      - POSTGRES_DB=synapse
+      - POSTGRES_INITDB_ARGS=--encoding=UTF-8 --lc-collate=C --lc-ctype=C
+    volumes:
+      - /mnt/docker-data/databases/matrix-db:/var/lib/postgresql/data
+    networks:
+      - matrix-internal
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U synapse -d synapse"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
+    deploy:
+      mode: replicated
+      replicas: 1
+      placement:
+        constraints:
+          - node.hostname == hf-pdocker-01
+      labels:
+        - "com.centurylinklabs.watchtower.enable=false"
+      resources:
+        limits:
+          memory: 256M
+
+networks:
+  traefik-public:
+    external: true
+  matrix-internal:
+    driver: overlay