serverAppConfigs/dankclaw/compose.yaml

# Dankclaw stack — AI, search, development & observability services.
# Deploy: cd /home/dank/serverAppConfigs && podman-compose -f dankclaw/compose.yaml up -d
# See ../docs/Dankclaw/ and ../docs/Infrastructure/ for service documentation.

services:
  # --- SearXNG stack (gluetun + searxng + valkey) --------------------------
  # These three services are now boot-persistent Quadlet units, not compose
  # services. They live in searxng/quadlet/ and install to
  # ~/.config/containers/systemd/ on the host. searxng reuses gluetun's netns
  # (Network=gluetun.container) so its traffic exits the WireGuard tunnel.
  # Deploy with: scripts/deploy-searxng-quadlet.sh dankclaw
  # See ../docs/Dankclaw/SearXNG.md, Gluetun.md, Valkey.md.

  # --- AI image generation (ROCm GPU backend, gfx1151) ---------------------
  # Built from Containerfile.comfyui on AMD's gfx1151 torch base. The GPU is
  # reached via the /dev/kfd + /dev/dri passthrough (checked host-side; the run
  # user is already in the render group). Only the 'video' group is added:
  # rootless podman cannot map the render gid into the container namespace.
  # Models + data persist under /home/dank/comfyui-data. See ../docs/Dankclaw/ComfyUI.md.
  comfyui:
    build:
      context: .
      dockerfile: Containerfile.comfyui
    image: comfyui-rocm:gfx1151
    container_name: comfyui
    restart: unless-stopped
    command: ["python", "main.py", "--listen", "0.0.0.0", "--port", "8188"]
    ports:
      - "8188:8188"
    devices:
      - /dev/kfd:/dev/kfd
      - /dev/dri:/dev/dri
    group_add:
      - video
    volumes:
      - /home/dank/comfyui-data/models:/opt/ComfyUI/models
      - /home/dank/comfyui-data/input:/opt/ComfyUI/input
      - /home/dank/comfyui-data/output:/opt/ComfyUI/output
      - /home/dank/comfyui-data/custom_nodes:/opt/ComfyUI/custom_nodes
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8188/')"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 180s

  # --- Chat UI (open-webui) ------------------------------------------------
  # Now a boot-persistent Quadlet unit (quadlet, slirp4netns, port 3005), not
  # a compose service. See open-webui/quadlet/open-webui.container and
  # ../docs/Dankclaw/OpenWebUI.md.

  hermes:
    image: docker.io/nousresearch/hermes-agent:latest
    container_name: hermes
    restart: unless-stopped
    # The image's default s6 entrypoint runs the interactive TUI, which exits
    # without a TTY and crash-loops the container. Override it to run the
    # headless gateway (the documented Docker mode). The gateway drops to the
    # unprivileged hermes user (uid 10000), so the data dir must be writable by it.
    entrypoint: ["bash", "-c", "hermes gateway run --force -v"]
    environment:
      HERMES_DATA_DIR: /data
      # Point hermes's config/.env at the mounted data dir (persistent).
      HERMES_HOME: /data
      # Signal adapter -> the host signal-cli daemon. The slirp host alias
      # (host.containers.internal) can drop at runtime; the host LAN IP is the
      # stable container->host path. 127.0.0.1 inside the container is not the host.
      SIGNAL_HTTP_URL: "http://192.168.0.143:8080"
      SIGNAL_ACCOUNT: "${SIGNAL_ACCOUNT}"
      SIGNAL_ALLOWED_USERS: "${SIGNAL_ALLOWED_USERS}"
    ports:
      - "8090:8090"
    volumes:
      - /home/dank/hermes-data:/data
    # No healthcheck: 'hermes gateway run' starts the messaging gateway (Signal
    # SSE), not the :8090 web dashboard, so there is no HTTP endpoint to probe.
    # The container's running state + the daemon's SSE connection are the signal.

  # --- Hermes web dashboard (management UI: config, API keys, sessions) -----
  # A separate process from the Signal gateway (the gateway entrypoint does not
  # start the dashboard). Bound to the LAN with basic auth: the username + a
  # scrypt password_hash live in the git-ignored /home/dank/hermes-data config.
  # Port 9119 is published so a browser on the LAN can reach it.
  hermes-dashboard:
    image: docker.io/nousresearch/hermes-agent:latest
    container_name: hermes-dashboard
    restart: unless-stopped
    entrypoint: ["bash", "-c", "hermes dashboard --host 0.0.0.0 --port 9119 --no-open --skip-build"]
    environment:
      HERMES_DATA_DIR: /data
      HERMES_HOME: /data
    ports:
      - "9119:9119"
    volumes:
      - /home/dank/hermes-data:/data

  # --- Git hosting (Gitea) -------------------------------------------------
  # Now boot-persistent Quadlet units (private bridge network, DNS enabled),
  # not compose services. See gitea/quadlet/ and ../docs/Dankclaw/Gitea.md.

  # --- Observability -------------------------------------------------------
  prometheus:
    image: docker.io/prom/prometheus:latest
    container_name: prometheus
    restart: unless-stopped
    command:
      - --config.file=/etc/prometheus/prometheus.yml
      - --storage.tsdb.path=/prometheus
      - --storage.tsdb.retention.time=30d
      - --web.enable-lifecycle
    ports:
      - "9090:9090"
    volumes:
      - /opt/prometheus/config:/etc/prometheus
      - /opt/prometheus/data:/prometheus
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3

  grafana:
    image: docker.io/grafana/grafana:latest
    container_name: grafana
    restart: unless-stopped
    environment:
      GF_SERVER_ROOT_URL: "http://grafana.dankclaw.local"
      GF_SECURITY_ADMIN_USER: "${GRAFANA_ADMIN_USER}"
      GF_SECURITY_ADMIN_PASSWORD: "${GRAFANA_ADMIN_PASSWORD}"
    ports:
      - "3002:3000"
    volumes:
      - /opt/grafana/data:/var/lib/grafana
      - /opt/grafana/provisioning:/etc/grafana/provisioning:ro
    depends_on:
      - prometheus
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3

  loki:
    image: docker.io/grafana/loki:latest
    container_name: loki
    restart: unless-stopped
    command: ["-config.file=/etc/loki/loki-config.yaml"]
    ports:
      - "3100:3100"
    volumes:
      - /opt/loki/config:/etc/loki
      - /opt/loki/data:/loki
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3100/ready"]
      interval: 30s
      timeout: 10s
      retries: 3

  alloy:
    image: docker.io/grafana/alloy:latest
    container_name: alloy
    restart: unless-stopped
    volumes:
      - /opt/alloy/config:/etc/alloy
      - /run/systemd/journal/socket:/run/systemd/journal/socket:ro
      - /var/log:/var/log:ro
      - /var/lib/containers:/var/lib/containers:ro
    depends_on:
      - loki
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:12345/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3

  node-exporter:
    image: docker.io/prom/node-exporter:latest
    container_name: node-exporter
    restart: unless-stopped
    network_mode: host
    pid: host
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - --path.procfs=/host/proc
      - --path.sysfs=/host/sys
      - --path.rootfs=/rootfs
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9100/metrics"]
      interval: 30s
      timeout: 10s
      retries: 3

  # --- Reverse proxy + homepage (the homelab's single Caddy) ---------------
  # The Caddyfile mounted here is the RENDERED copy (basicauth hash filled in
  # from the host .env by scripts/deploy.sh); the repo copy carries the
  # REPLACE_WITH_HASH placeholder. Certs/config live under
  # /home/dank/Containers/caddy (rootless-writable).
  caddy:
    # Locally built: stock Caddy + the Porkbun DNS provider
    # (dankclaw/caddy/Containerfile). See that file for build instructions.
    image: franksdank/caddy-porkbun:latest
    container_name: caddy
    restart: unless-stopped
    ports:
      - "80:80"
      - "443:443"
    environment:
      # Consumed by the Caddyfile's acme_dns block (DNS-01 wildcard certs).
      PORKBUN_API_KEY: ${PORKBUN_API_KEY}
      PORKBUN_API_SECRET_KEY: ${PORKBUN_API_SECRET_KEY}
    volumes:
      - /home/dank/Containers/caddy/Caddyfile:/etc/caddy/Caddyfile:ro
      - /home/dank/Containers/caddy/data:/data
      - /home/dank/Containers/caddy/config:/config
      - ../shared/homepage:/srv/homepage:ro
    depends_on:
      - comfyui
      - hermes
      - grafana
      - prometheus
      - loki
    healthcheck:
      # The bare-IP catch-all answers 302 (curl -f passes on <400); this
      # proves Caddy itself is serving without touching any upstream.
      test: ["CMD", "curl", "-sf", "-o", "/dev/null", "http://localhost:80/"]
      interval: 30s
      timeout: 10s
      retries: 3