services:
  # ==========================================================================
  # PostgreSQL - Primary Database with pgvector for RAG
  # ==========================================================================
  postgres:
    image: pgvector/pgvector:pg16
    container_name: roboco-postgres
    restart: unless-stopped
    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 - Cache, Sessions, Event Bus
  # ==========================================================================
  redis:
    image: redis:8-alpine
    container_name: roboco-redis
    restart: unless-stopped
    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 - Local LLM and Embedding Server
  # ==========================================================================
  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:
      # Use ollama CLI (guaranteed available) to check if server is responding
      test: ["CMD", "ollama", "list"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s

  # Ollama model puller - pulls required models on startup
  # Uses streaming curl to wait for full model download
  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! ==="

  # ==========================================================================
  # Agent Base Image Builder (specialized images built on-demand by orchestrator)
  # ==========================================================================
  agent-base-image:
    build:
      context: .
      dockerfile: docker/agent-base.Dockerfile
    image: roboco-agent-base
    container_name: roboco-agent-base-builder
    entrypoint: ["/bin/sh", "-c", "echo 'Agent base image built successfully'"]
    restart: "no"

  # ==========================================================================
  # Agent PM Image Builder (specialized image built on-demand by orchestrator)
  # ==========================================================================
  agent-pm-image:
    build:
      context: .
      dockerfile: docker/agent-pm.Dockerfile
    image: roboco-agent-pm
    entrypoint: ["/bin/sh", "-c", "echo 'Agent PM image built'"]
    restart: "no"
    depends_on:
      - agent-base-image

  # ==========================================================================
  # Agent Backend Dev Image Builder (specialized image built on-demand by orchestrator)
  # ==========================================================================
  agent-dev-be-image:
    build:
      context: .
      dockerfile: docker/agent-dev-be.Dockerfile
    image: roboco-agent-dev-be
    entrypoint: ["/bin/sh", "-c", "echo 'Agent Backend Dev image built'"]
    restart: "no"
    depends_on:
      - agent-base-image

  # ==========================================================================
  # Agent Frontend Dev Image Builder (specialized image built on-demand by orchestrator)
  # ==========================================================================
  agent-dev-fe-image:
    build:
      context: .
      dockerfile: docker/agent-dev-fe.Dockerfile
    image: roboco-agent-dev-fe
    entrypoint: ["/bin/sh", "-c", "echo 'Agent Frontend Dev image built'"]
    restart: "no"
    depends_on:
      - agent-base-image

  # ==========================================================================
  # Agent Backend QA Image Builder (specialized image built on-demand by orchestrator)
  # ==========================================================================
  agent-qa-be-image:
    build:
      context: .
      dockerfile: docker/agent-qa-be.Dockerfile
    image: roboco-agent-qa-be
    entrypoint: ["/bin/sh", "-c", 'echo "Agent Backend QA image built"']
    restart: "no"
    depends_on:
      - agent-base-image

  # ==========================================================================
  # Agent Frontend QA Image Builder (specialized image built on-demand by orchestrator)
  # ==========================================================================
  agent-qa-fe-image:
    build:
      context: .
      dockerfile: docker/agent-qa-fe.Dockerfile
    image: roboco-agent-qa-fe
    entrypoint: ["/bin/sh", "-c", 'echo "Agent Frontend QA image built"']
    restart: "no"
    depends_on:
      - agent-base-image

  # ==========================================================================
  # Agent UX/UI Dev Image Builder (specialized image built on-demand by orchestrator)
  # ==========================================================================
  agent-ux-image:
    build:
      context: .
      dockerfile: docker/agent-ux.Dockerfile
    image: roboco-agent-ux
    entrypoint: ["/bin/sh", "-c", 'echo "Agent UX/UI image built"']
    restart: "no"
    depends_on:
      - agent-base-image

  # ==========================================================================
  # Agent Documenter Image Builder (specialized image built on-demand by orchestrator)
  # ==========================================================================
  agent-doc-image:
    build:
      context: .
      dockerfile: docker/agent-doc.Dockerfile
    image: roboco-agent-doc
    entrypoint: ["/bin/sh", "-c", 'echo "Agent Documenter image built"']
    restart: "no"
    depends_on:
      - agent-base-image

  # ==========================================================================
  # Agent Intake (Prompter) Image Builder (persistent Agent-SDK driver the CEO
  # chats with; not a one-shot `claude -p`)
  # ==========================================================================
  agent-prompter-image:
    build:
      context: .
      dockerfile: docker/agent-prompter.Dockerfile
    image: roboco-agent-prompter
    entrypoint: ["/bin/sh", "-c", 'echo "Agent Intake image built"']
    restart: "no"
    depends_on:
      - agent-base-image

  agent-secretary-image:
    build:
      context: .
      dockerfile: docker/agent-secretary.Dockerfile
    image: roboco-agent-secretary
    entrypoint: ["/bin/sh", "-c", 'echo "Agent Secretary image built"']
    restart: "no"
    depends_on:
      - agent-base-image

  # ==========================================================================
  # Agent PR Reviewer Image Builder (read-only reviewer of inbound external PRs)
  # ==========================================================================
  agent-pr-reviewer-image:
    build:
      context: .
      dockerfile: docker/agent-pr-reviewer.Dockerfile
    image: roboco-agent-pr-reviewer
    entrypoint: ["/bin/sh", "-c", 'echo "Agent PR Reviewer image built"']
    restart: "no"
    depends_on:
      - agent-base-image

  # ==========================================================================
  # Agent Grok Image Builder (xAI Grok Build via the official grok CLI)
  # ==========================================================================
  agent-grok-image:
    build:
      context: .
      dockerfile: docker/agent-grok.Dockerfile
    image: roboco-agent-grok
    entrypoint: ["/bin/sh", "-c", 'echo "Agent Grok image built"']
    restart: "no"
    depends_on:
      - agent-base-image

  # Interactive Grok roles (intake/secretary) — panel-driven grok-CLI sessions;
  # built FROM roboco-agent-grok, so they depend on the Grok runtime image.
  agent-grok-prompter-image:
    build:
      context: .
      dockerfile: docker/agent-grok-prompter.Dockerfile
    image: roboco-agent-grok-prompter
    entrypoint: ["/bin/sh", "-c", 'echo "Agent Grok Prompter image built"']
    restart: "no"
    depends_on:
      - agent-grok-image

  agent-grok-secretary-image:
    build:
      context: .
      dockerfile: docker/agent-grok-secretary.Dockerfile
    image: roboco-agent-grok-secretary
    entrypoint: ["/bin/sh", "-c", 'echo "Agent Grok Secretary image built"']
    restart: "no"
    depends_on:
      - agent-grok-image

  # ==========================================================================
  # Orchestrator - API Server + Agent Spawner
  # ==========================================================================
  orchestrator:
    build:
      context: .
      dockerfile: docker/orchestrator.Dockerfile
    image: roboco-orchestrator
    container_name: roboco-orchestrator
    restart: unless-stopped
    ports:
      - "8000:8000"
    environment:
      # Database (use container name, not localhost)
      ROBOCO_DATABASE_HOST: roboco-postgres
      ROBOCO_DATABASE_PORT: 5432
      ROBOCO_DATABASE_USER: roboco
      ROBOCO_DATABASE_PASSWORD: roboco
      ROBOCO_DATABASE_NAME: roboco
      # Redis (use container name)
      ROBOCO_REDIS_HOST: roboco-redis
      ROBOCO_REDIS_PORT: 6379
      # API
      ROBOCO_HOST: 0.0.0.0
      ROBOCO_PORT: 8000
      ROBOCO_ENCRYPTION_KEY: ${ROBOCO_ENCRYPTION_KEY:?ROBOCO_ENCRYPTION_KEY is required}
      # HMAC secret for agent auth tokens. Orchestrator signs tokens
      # per-agent at spawn; API middleware verifies them. Generate with:
      #   python -c 'import secrets; print(secrets.token_hex(32))'
      ROBOCO_AGENT_AUTH_SECRET: ${ROBOCO_AGENT_AUTH_SECRET:?ROBOCO_AGENT_AUTH_SECRET is required}
      # Set to "true" to require tokens on every API call (fail-closed).
      # Leave unset/false during rollout so the panel + curl still work.
      ROBOCO_AGENT_AUTH_REQUIRED: ${ROBOCO_AGENT_AUTH_REQUIRED:-false}
      # Ollama (use container name)
      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
      # Host paths for spawning agent containers (required for Docker-in-Docker)
      # IMPORTANT: These must be ABSOLUTE paths on the host filesystem
      ROBOCO_HOST_PROJECT_DIR: ${ROBOCO_HOST_PROJECT_DIR:-/volume1/roboco}
      ROBOCO_HOST_CLAUDE_DIR: ${ROBOCO_HOST_CLAUDE_DIR:-/home/renzof/.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/renzof/.grok}
      ROBOCO_HOST_DATA_DIR: ${ROBOCO_HOST_DATA_DIR:-/volume1/roboco/data}
      # Public base URL for commit-trailer links. Default 127.0.0.1 produces
      # unusable links in commit message bodies; set to NAS LAN IP so
      # f"{api_base}/tasks/{task_id}" renders a reachable URL.
      ROBOCO_PUBLIC_BASE_URL: "http://192.168.50.111:8000"
      # Production environment selects structlog's JSONRenderer (machine-
      # parseable logs) over the dev ConsoleRenderer.
      ROBOCO_ENVIRONMENT: production
      # Reaper timeouts raised to 30 min so a long agent task isn't reaped
      # mid-work. ROBOCO_CLAIM_STALE_SECONDS is the heartbeat-staleness window
      # _reap_stale_claims uses (the one that was killing in-progress work).
      ROBOCO_CLAIM_STALE_SECONDS: "1800"
      ROBOCO_STALE_CLAIM_REAP_SECONDS: "1800"
      # External-PR review. When on, the org discovers inbound external/fork PRs
      # and the PR reviewer posts one change-request — READ-ONLY (it never runs
      # contributor code). The supersede that fetches + builds their code is
      # separately CEO-triggered and stays gated by require_human_confirm.
      # Override either via .env. (Config default is off; this enables it here.)
      ROBOCO_EXTERNAL_PR_ENABLED: ${ROBOCO_EXTERNAL_PR_ENABLED:-true}
      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}
      # Agent runtime toolchain matching: provision each agent workspace with
      # the TARGET project's Python (uv resolves requires-python) and block a
      # delivery gate when the suite can't be executed instead of passing on a
      # source read. Config default is OFF; enabled HERE (personal deploy) but
      # deliberately left OFF in docker-compose.registry.yml so the published
      # default stays conservative until it's verified on a live run.
      ROBOCO_TOOLCHAIN_MATCH_ENABLED: ${ROBOCO_TOOLCHAIN_MATCH_ENABLED:-true}
      # Architectural conventions standard: gate where code lives (placement,
      # hygiene, modularity) via each project's .roboco/conventions.yml. Config
      # default is OFF; enabled HERE (personal deploy), deliberately left OFF in
      # docker-compose.registry.yml so the published default stays conservative.
      ROBOCO_CONVENTIONS_ENABLED: ${ROBOCO_CONVENTIONS_ENABLED:-true}
      # Autonomy engines shipped in 0.12.0 / 0.13.0 — all default-OFF in config;
      # ARMED here for the NAS deploy (our live test bed). Each is bounded +
      # CEO-gated by construction and overridable via .env. Left OFF in
      # docker-compose.registry.yml so the published default stays conservative.
      #   - CI-watch: opens a fix task when a watched project's default-branch CI
      #     goes red — only for projects with the per-project ci_watch_enabled
      #     column set; never auto-merges (rides the PR-review gate).
      #   - Dep-update bot: weekly lockfile-diff probe -> "update dependencies"
      #     task — only for projects with a dep_update_command set; never merges.
      #   - Release manager: deterministic readiness sweep -> ONE release proposal
      #     HELD for the CEO; the executor publishes only on CEO approval + green
      #     CI (reuses SELF_HEAL_PROJECT_SLUG as the RoboCo repo).
      #   - Org-memory loop: distils a completion lesson + auto-injects relevant
      #     past lessons/playbooks into each claim's briefing (local model only).
      ROBOCO_CI_WATCH_ENABLED: ${ROBOCO_CI_WATCH_ENABLED:-true}
      ROBOCO_DEP_UPDATE_ENABLED: ${ROBOCO_DEP_UPDATE_ENABLED:-true}
      ROBOCO_RELEASE_MANAGER_ENABLED: ${ROBOCO_RELEASE_MANAGER_ENABLED:-true}
      ROBOCO_ORG_MEMORY_ENABLED: ${ROBOCO_ORG_MEMORY_ENABLED:-true}
    volumes:
      # Docker socket - allows spawning agent containers
      - /var/run/docker.sock:/var/run/docker.sock
      # Claude Code auth - mount your ~/.claude directory
      - ${CLAUDE_AUTH_DIR:-/home/renzof/.claude}:/root/.claude
      # SuperGrok auth — mount the host ~/.grok at the SAME host path the
      # orchestrator passes to each Grok agent's `-v`, so its auth.json exists()
      # check passes here AND the agent bind resolves on the host. One canonical
      # var for source AND target (they must be equal in docker-in-docker).
      # Read-WRITE: the orchestrator auto-refreshes the ~6h token in place
      # (grok_auth.refresh_if_stale) so agents never mount a dead credential;
      # each agent's own auth.json mount stays read-only.
      - ${ROBOCO_HOST_GROK_DIR:-/home/renzof/.grok}:${ROBOCO_HOST_GROK_DIR:-/home/renzof/.grok}
      # Shared config directory for MCP configs (writable)
      - ${ROBOCO_DATA_DIR:-./data}/mcp-configs:/app/mcp-configs
      # Generated prompts directory - composed at runtime from layers
      - ${ROBOCO_DATA_DIR:-./data}/prompts-generated:/app/prompts-generated
      # Per-agent Claude settings (generated at spawn time)
      - ${ROBOCO_DATA_DIR:-./data}/agent-settings:/app/agent-settings
      # Agent workspaces (git clones) - persisted across restarts
      - ${ROBOCO_DATA_DIR:-./data}/workspaces:/data/workspaces
      # Per-agent GROK usage capture: each Grok agent writes usage.json under
      # <agent_id>/; the finalizer reads the captured tokens/cost back here.
      - ${ROBOCO_DATA_DIR:-./data}/grok-usage:/data/grok-usage
      # Persistent logs — survive `docker compose down/up`. Orchestrator and
      # each spawned agent write structured logs here so we can audit past
      # runs instead of relying on ephemeral `docker logs`.
      - ${ROBOCO_DATA_DIR:-./data}/logs:/data/logs
      # Per-agent SessionStart briefings (pre-rendered task context)
      - ${ROBOCO_DATA_DIR:-./data}/briefings:/app/briefings
      # Per-agent spawn manifests (role-scoped tool list) — written by the
      # orchestrator to /app/manifests, bind-mounted into each agent container
      # as /app/tool-manifest.json. Without this mount the file is written to
      # the orchestrator's ephemeral fs, never reaches the host, and agents
      # fall back to all-verbs registration.
      - ${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
    # Default agents to spawn (override in .env or command line)
    # command: ["--spawn", "main-pm", "be-dev-1", "be-qa"]

  # ==========================================================================
  # Next.js Control Panel (Frontend)
  # ==========================================================================
  # Not exposed directly - nginx is the single entry point (port 3000).
  # API/WS traffic is proxied to the orchestrator, everything else to panel.
  panel:
    build:
      context: .
      dockerfile: docker/panel.Dockerfile
    image: roboco-panel
    container_name: roboco-panel
    restart: unless-stopped
    expose:
      - "3000"
    depends_on:
      - orchestrator

  # ==========================================================================
  # Nginx - Reverse proxy fronting panel + orchestrator
  # ==========================================================================
  # Single entry point on port 3000 so the browser hits one origin and we
  # don't need CORS. /api/* and /ws/* go to the orchestrator, everything
  # else goes to the Next.js panel.
  nginx:
    image: nginx:alpine
    container_name: roboco-nginx
    restart: unless-stopped
    ports:
      - "3000:80"
    environment:
      # Rendered into the proxy config by the nginx image's envsubst
      # entrypoint so the human panel authenticates in secure mode. The
      # filter limits substitution to ROBOCO_* vars, leaving nginx's own
      # $host / $remote_addr runtime variables untouched. Get the value
      # with `make panel-token`.
      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