roboco/docker-compose.registry.yml

# ============================================================================
# RoboCo — pre-built (registry) deployment
# ============================================================================
# This is the "pull and run" compose for USERS: it runs the images the release
# workflow publishes (GHCR + Docker Hub) instead of building from source, so a
# host needs neither the repo's build context nor a build toolchain.
#
#   1. Copy `.env.example` to `.env` and fill in the required secrets.
#   2. docker compose -f docker-compose.registry.yml pull
#   3. docker compose -f docker-compose.registry.yml up -d
#
# Pick the registry + version with two env vars (defaults shown):
#   ROBOCO_REGISTRY=ghcr.io/rennf93     # or docker.io/renzof93
#   ROBOCO_VERSION=latest               # or a pinned release, e.g. 0.5.0
#
# The orchestrator spawns agent containers itself; ROBOCO_AGENT_IMAGE_REGISTRY
# + ROBOCO_AGENT_IMAGE_TAG below tell it to spawn the SAME pre-built agent
# images (it pulls any it doesn't already have). The one-shot agent-*-image
# services exist only so `docker compose pull` fetches every agent image up
# front; they pull then exit.
#
# NOTE: this file is the registry counterpart of docker-compose.yml — when you
# add or change a service there, mirror it here. The infra services
# (postgres/redis/ollama/nginx) are byte-identical to the build compose.
# ============================================================================
services:
  postgres:
    image: pgvector/pgvector:pg16
    container_name: roboco-postgres
    restart: unless-stopped
    # data-only network: agent containers (on roboco_default) cannot reach
    # the production DB; only the multi-homed orchestrator can. Host port
    # publishing (15432) is unaffected — roboco_data is a normal bridge.
    networks:
      - data
    environment:
      POSTGRES_USER: roboco
      POSTGRES_PASSWORD: roboco
      POSTGRES_DB: roboco
    ports:
      - "15432:5432"
    volumes:
      - ${ROBOCO_DATA_DIR:-./data}/postgres:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U roboco -d roboco"]
      interval: 10s
      timeout: 5s
      retries: 5

  redis:
    image: redis:8-alpine
    container_name: roboco-redis
    restart: unless-stopped
    # data-only network — see postgres. Redis has no auth, so network
    # membership is its ONLY containment against agent containers.
    networks:
      - data
    command: redis-server --appendonly yes
    ports:
      - "16379:6379"
    volumes:
      - ${ROBOCO_DATA_DIR:-./data}/redis:/data
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 5s
      retries: 5

  ollama:
    image: ollama/ollama:latest
    container_name: roboco-ollama
    restart: unless-stopped
    environment:
      OLLAMA_API_KEY: ${OLLAMA_API_KEY:-}
    ports:
      - "11435:11434"
    volumes:
      - ${ROBOCO_DATA_DIR:-./data}/ollama:/root/.ollama
    healthcheck:
      test: ["CMD", "ollama", "list"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s

  ollama-init:
    image: curlimages/curl:latest
    container_name: roboco-ollama-init
    depends_on:
      ollama:
        condition: service_healthy
    restart: "no"
    entrypoint: ["/bin/sh", "-c"]
    command:
      - |
        # NO `set -e`: pulls are best-effort. Cached models persist in the ollama
        # volume and MUST survive a slow/unreachable ollama registry — a manifest
        # re-check failure there must never down a fully-cached deployment (it
        # used to: a degraded registry made `ollama pull` fail under set -e, which
        # blocked the orchestrator's service_completed_successfully gate). Success
        # is gated on the models being PRESENT (verify step), not on the pull.
        # Note: $$ escapes $ for docker-compose variable substitution.
        echo "=== Pulling embedding model (qwen3-embedding:0.6b) — best-effort ==="
        curl -sN http://ollama:11434/api/pull -d '{"name":"qwen3-embedding:0.6b"}' | while read -r line; do
          status=$$(echo "$$line" | grep -o '"status":"[^"]*"' | cut -d'"' -f4)
          [ -n "$$status" ] && echo "  $$status"
        done || echo "  (pull failed — relying on the cached model)"
        echo "=== Pulling LLM model (glm-5.2:cloud) — best-effort ==="
        curl -sN http://ollama:11434/api/pull -d '{"name":"glm-5.2:cloud"}' | while read -r line; do
          status=$$(echo "$$line" | grep -o '"status":"[^"]*"' | cut -d'"' -f4)
          [ -n "$$status" ] && echo "  $$status"
        done || echo "  (pull failed — relying on the cached model)"
        echo "=== Verifying models are present (the real success gate) ==="
        curl -sf http://ollama:11434/api/tags | grep -q "qwen3-embedding" || { echo "FATAL: qwen3-embedding missing and could not be pulled"; exit 1; }
        curl -sf http://ollama:11434/api/tags | grep -q "glm-5.2" || { echo "FATAL: glm-5.2 missing and could not be pulled"; exit 1; }
        echo "=== All models ready! ==="

  # --------------------------------------------------------------------------
  # Video Renderer - sidecar for the video-generation engine (renders
  # motion/ compositions to MP4 with HyperFrames). Harmless when idle — it
  # only renders when POSTed; the video_engine_* feature flags (off by
  # default in this compose) gate whether the orchestrator ever sends it
  # work. No DB access, no git, no credentials.
  # --------------------------------------------------------------------------
  video-renderer:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-video-renderer:${ROBOCO_VERSION:-latest}
    container_name: roboco-video-renderer
    restart: unless-stopped
    networks:
      - default
    # Chrome headless rendering can crash under Docker's default 64MB
    # /dev/shm ("Chrome crashed"); give it real shared memory.
    shm_size: "1gb"
    healthcheck:
      test: ["CMD", "node", "-e", "fetch('http://127.0.0.1:3001/health').then((r) => process.exit(r.ok ? 0 : 1)).catch(() => process.exit(1))"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s

  # --------------------------------------------------------------------------
  # Agent image pre-pull (one-shot). Each pulls its published image then exits,
  # so `docker compose pull` fetches every agent image up front. The
  # orchestrator spawns these same images at runtime.
  # --------------------------------------------------------------------------
  agent-base-image:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-base:${ROBOCO_VERSION:-latest}
    entrypoint: ["/bin/sh", "-c", "echo 'agent-base image present'"]
    restart: "no"

  agent-pm-image:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-pm:${ROBOCO_VERSION:-latest}
    entrypoint: ["/bin/sh", "-c", "echo 'agent-pm image present'"]
    restart: "no"

  agent-dev-be-image:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-dev-be:${ROBOCO_VERSION:-latest}
    entrypoint: ["/bin/sh", "-c", "echo 'agent-dev-be image present'"]
    restart: "no"

  agent-dev-fe-image:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-dev-fe:${ROBOCO_VERSION:-latest}
    entrypoint: ["/bin/sh", "-c", "echo 'agent-dev-fe image present'"]
    restart: "no"

  agent-qa-be-image:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-qa-be:${ROBOCO_VERSION:-latest}
    entrypoint: ["/bin/sh", "-c", "echo 'agent-qa-be image present'"]
    restart: "no"

  agent-qa-fe-image:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-qa-fe:${ROBOCO_VERSION:-latest}
    entrypoint: ["/bin/sh", "-c", "echo 'agent-qa-fe image present'"]
    restart: "no"

  agent-ux-image:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-ux:${ROBOCO_VERSION:-latest}
    entrypoint: ["/bin/sh", "-c", "echo 'agent-ux image present'"]
    restart: "no"

  agent-doc-image:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-doc:${ROBOCO_VERSION:-latest}
    entrypoint: ["/bin/sh", "-c", "echo 'agent-doc image present'"]
    restart: "no"

  agent-prompter-image:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-prompter:${ROBOCO_VERSION:-latest}
    entrypoint: ["/bin/sh", "-c", "echo 'agent-prompter image present'"]
    restart: "no"

  agent-secretary-image:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-secretary:${ROBOCO_VERSION:-latest}
    entrypoint: ["/bin/sh", "-c", "echo 'agent-secretary image present'"]
    restart: "no"

  agent-pr-reviewer-image:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-pr-reviewer:${ROBOCO_VERSION:-latest}
    entrypoint: ["/bin/sh", "-c", "echo 'agent-pr-reviewer image present'"]
    restart: "no"

  agent-grok-image:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-grok:${ROBOCO_VERSION:-latest}
    entrypoint: ["/bin/sh", "-c", "echo 'agent-grok image present'"]
    restart: "no"

  agent-grok-prompter-image:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-grok-prompter:${ROBOCO_VERSION:-latest}
    entrypoint: ["/bin/sh", "-c", "echo 'agent-grok-prompter image present'"]
    restart: "no"

  agent-grok-secretary-image:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-grok-secretary:${ROBOCO_VERSION:-latest}
    entrypoint: ["/bin/sh", "-c", "echo 'agent-grok-secretary image present'"]
    restart: "no"

  # --------------------------------------------------------------------------
  # Orchestrator — API server + agent spawner
  # --------------------------------------------------------------------------
  orchestrator:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-orchestrator:${ROBOCO_VERSION:-latest}
    container_name: roboco-orchestrator
    restart: unless-stopped
    # Multi-homed: the agent mesh (default) for spawned agents / panel /
    # ollama, plus the data network for postgres/redis.
    networks:
      - default
      - data
    ports:
      - "8000:8000"
    environment:
      # DB network isolation is LIVE in this file (postgres/redis on the
      # data-only network): suppress the legacy prod-creds gate-env
      # injection — agents can't reach roboco-postgres anyway. This flag
      # must always travel with the networks: topology.
      ROBOCO_DB_NETWORK_ISOLATED: ${ROBOCO_DB_NETWORK_ISOLATED:-true}
      ROBOCO_DATABASE_HOST: roboco-postgres
      ROBOCO_DATABASE_PORT: 5432
      ROBOCO_DATABASE_USER: roboco
      ROBOCO_DATABASE_PASSWORD: roboco
      ROBOCO_DATABASE_NAME: roboco
      ROBOCO_REDIS_HOST: roboco-redis
      ROBOCO_REDIS_PORT: 6379
      ROBOCO_HOST: 0.0.0.0
      ROBOCO_PORT: 8000
      ROBOCO_ENCRYPTION_KEY: ${ROBOCO_ENCRYPTION_KEY:?ROBOCO_ENCRYPTION_KEY is required}
      ROBOCO_AGENT_AUTH_SECRET: ${ROBOCO_AGENT_AUTH_SECRET:?ROBOCO_AGENT_AUTH_SECRET is required}
      ROBOCO_AGENT_AUTH_REQUIRED: ${ROBOCO_AGENT_AUTH_REQUIRED:-false}
      ROBOCO_LOCAL_LLM_BASE_URL: http://roboco-ollama:11434/v1
      ROBOCO_LOCAL_LLM_MODEL: glm-5.2:cloud
      ROBOCO_DEFAULT_EMBEDDING_MODEL: qwen3-embedding:0.6b
      ROBOCO_OLLAMA_BASE_URL: http://roboco-ollama:11434
      # Video renderer sidecar (use container name). The video engine
      # itself is default-off (video_engine_enabled); this just points the
      # client at the sidecar for when it's armed.
      ROBOCO_VIDEO_RENDERER_BASE_URL: http://roboco-video-renderer:3001
      # Spawn the PRE-BUILT agent images from the same registry instead of
      # building them from source (the orchestrator pulls any it lacks).
      ROBOCO_AGENT_IMAGE_REGISTRY: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}
      ROBOCO_AGENT_IMAGE_TAG: ${ROBOCO_VERSION:-latest}
      # Host paths for spawning agent containers (Docker-in-Docker). MUST be
      # absolute paths on the host. Default to this compose project's ./data.
      ROBOCO_HOST_PROJECT_DIR: ${ROBOCO_HOST_PROJECT_DIR:-/opt/roboco}
      ROBOCO_HOST_CLAUDE_DIR: ${ROBOCO_HOST_CLAUDE_DIR:-${HOME}/.claude}
      # SuperGrok auth (host ~/.grok) for Grok-CLI agents — the orchestrator
      # mounts <dir>/auth.json into each Grok agent. Run `grok login` on the host.
      ROBOCO_HOST_GROK_DIR: ${ROBOCO_HOST_GROK_DIR:-${HOME}/.grok}
      ROBOCO_HOST_DATA_DIR: ${ROBOCO_HOST_DATA_DIR:-/opt/roboco/data}
      # Reachable base URL for commit-trailer links — set to your host's LAN
      # address or domain so the links in commit bodies resolve.
      ROBOCO_PUBLIC_BASE_URL: ${ROBOCO_PUBLIC_BASE_URL:-http://localhost:8000}
      ROBOCO_ENVIRONMENT: production
      ROBOCO_CLAIM_STALE_SECONDS: "1800"
      ROBOCO_STALE_CLAIM_REAP_SECONDS: "1800"
      # Every optional feature ships OFF in this user-facing compose (the build
      # compose arms them for the personal deploy). External-PR review included —
      # arm it (and any other subsystem) via .env or Settings → Feature Flags.
      ROBOCO_EXTERNAL_PR_ENABLED: ${ROBOCO_EXTERNAL_PR_ENABLED:-false}
      ROBOCO_EXTERNAL_PR_REQUIRE_HUMAN_CONFIRM: ${ROBOCO_EXTERNAL_PR_REQUIRE_HUMAN_CONFIRM:-true}
      # ROBOCO_EXTERNAL_PR_POLL_INTERVAL_SECONDS: "300"
      # ROBOCO_EXTERNAL_PR_AUTHOR_ALLOWLIST: '["corey"]'   # empty = every external PR
      # Production self-healing ("engine 4"). RoboCo watches its OWN repo CI and,
      # when red, notifies the CEO and (with originate on) opens a PENDING fix
      # task that STOPS for the CEO's Approve-&-Start — it never self-deploys.
      # Both toggles default OFF (arm from Settings -> Feature Flags). Set
      # PROJECT_SLUG to the registered project that IS RoboCo; CI_WORKFLOW scopes
      # the signal to the real CI workflow (RoboCo has several workflows, so the
      # unscoped "latest run" would be unreliable).
      ROBOCO_SELF_HEAL_ENABLED: ${ROBOCO_SELF_HEAL_ENABLED:-false}
      ROBOCO_SELF_HEAL_ORIGINATE_ENABLED: ${ROBOCO_SELF_HEAL_ORIGINATE_ENABLED:-false}
      ROBOCO_SELF_HEAL_PROJECT_SLUG: ${ROBOCO_SELF_HEAL_PROJECT_SLUG:-roboco-api}
      ROBOCO_SELF_HEAL_CI_WORKFLOW: ${ROBOCO_SELF_HEAL_CI_WORKFLOW:-ci.yml}
      # Video engine (HyperFrames): NAS-default-on, OFF in public registry —
      # heavier optional feature. Arm via .env + uncomment the video-renders
      # bind mount above so renders persist.
      ROBOCO_VIDEO_ENGINE_ENABLED: ${ROBOCO_VIDEO_ENGINE_ENABLED:-false}
      ROBOCO_VIDEO_ON_RELEASE: ${ROBOCO_VIDEO_ON_RELEASE:-false}
      ROBOCO_VIDEO_ON_SPOTLIGHT: ${ROBOCO_VIDEO_ON_SPOTLIGHT:-false}
      # MinIO object storage for rendered videos is intentionally omitted from
      # this registry compose (NAS default-on, registry default-off — the
      # established pattern). The minio/minio-init services are absent here and
      # ROBOCO_MINIO_* is left unset, so minio_endpoint defaults to empty and the
      # media route falls back to FileResponse. Arm via a custom override file.
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock
      - ${CLAUDE_AUTH_DIR:-${HOME}/.claude}:/root/.claude
      # SuperGrok auth — mount host ~/.grok at the SAME host path the orchestrator
      # hands each Grok agent's `-v`, so its auth.json exists() check passes here
      # AND the agent bind resolves on the host. Read-WRITE: the orchestrator
      # auto-refreshes the ~6h token in place (grok_auth.refresh_if_stale) so
      # agents never mount a dead credential; the agent's own mount stays RO.
      - ${ROBOCO_HOST_GROK_DIR:-${HOME}/.grok}:${ROBOCO_HOST_GROK_DIR:-${HOME}/.grok}
      - ${ROBOCO_DATA_DIR:-./data}/mcp-configs:/app/mcp-configs
      - ${ROBOCO_DATA_DIR:-./data}/prompts-generated:/app/prompts-generated
      - ${ROBOCO_DATA_DIR:-./data}/agent-settings:/app/agent-settings
      - ${ROBOCO_DATA_DIR:-./data}/workspaces:/data/workspaces
      # Per-agent GROK usage capture (usage.json -> finalizer).
      - ${ROBOCO_DATA_DIR:-./data}/grok-usage:/data/grok-usage
      - ${ROBOCO_DATA_DIR:-./data}/logs:/data/logs
      # video engine: NAS-only bind mount, off by default in public registry.
      # Uncomment + set ROBOCO_VIDEO_ENGINE_ENABLED=true in .env to arm.
      # - ${ROBOCO_DATA_DIR:-./data}/video-renders:/data/video-renders
      - ${ROBOCO_DATA_DIR:-./data}/briefings:/app/briefings
      - ${ROBOCO_DATA_DIR:-./data}/manifests:/app/manifests
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
      ollama:
        condition: service_healthy
      ollama-init:
        condition: service_completed_successfully
      agent-base-image:
        condition: service_completed_successfully

  # --------------------------------------------------------------------------
  # Next.js control panel (fronted by nginx; not exposed directly)
  # --------------------------------------------------------------------------
  panel:
    image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-panel:${ROBOCO_VERSION:-latest}
    container_name: roboco-panel
    restart: unless-stopped
    expose:
      - "3000"
    depends_on:
      - orchestrator

  # --------------------------------------------------------------------------
  # Nginx — single entry point on port 3000
  # --------------------------------------------------------------------------
  nginx:
    image: nginx:alpine
    container_name: roboco-nginx
    restart: unless-stopped
    ports:
      - "3000:80"
    environment:
      ROBOCO_PANEL_AGENT_TOKEN: ${ROBOCO_PANEL_AGENT_TOKEN:-}
      NGINX_ENVSUBST_FILTER: "^ROBOCO_"
    volumes:
      - ./docker/nginx.conf:/etc/nginx/templates/default.conf.template:ro
    depends_on:
      - panel
      - orchestrator

networks:
  default:
    name: roboco_default
  # DB isolation: postgres/redis live ONLY here; the orchestrator is the
  # only service homed on both. Spawned agent containers + sandbox sidecars
  # join roboco_default (AGENT_NETWORK) and cannot resolve or reach the
  # production DB/Redis. Normal bridge (not internal) so host-published
  # ports keep working.
  data:
    name: roboco_data