microdao-daarion/docker-compose.matrix-bridge-node1.yml

# Matrix Bridge DAGI — Phase M2.1 (multi-room + mixed routing)
# Include into the main NODA1 stack or run standalone:
#   docker compose -f docker-compose.node1.yml -f docker-compose.matrix-bridge-node1.yml up -d matrix-bridge-dagi

version: "3.9"

services:
  matrix-bridge-dagi:
    build:
      context: ./services/matrix-bridge-dagi
      args:
        BUILD_SHA: "${BUILD_SHA:-dev}"
        BUILD_TIME: "${BUILD_TIME:-local}"
    container_name: matrix-bridge-dagi-node1
    ports:
      - "127.0.0.1:7030:7030"       # internal only — not exposed publicly
    environment:
      - PORT=7030
      - ENV=prod
      - NODE_ID=NODA1
      - BUILD_SHA=${BUILD_SHA:-dev}
      - BUILD_TIME=${BUILD_TIME:-local}

      # ── Matrix homeserver ────────────────────────────────────────────────
      # Required: set in .env on NODA1 before first launch
      - MATRIX_HOMESERVER_URL=${MATRIX_HOMESERVER_URL:-}
      - MATRIX_ACCESS_TOKEN=${MATRIX_ACCESS_TOKEN:-}
      - MATRIX_USER_ID=${MATRIX_USER_ID:-}

      # ── Room → Agent mapping (M1: single room for Sofiia) ────────────────
      # Create the room manually, then paste the room_id here
      - SOFIIA_ROOM_ID=${SOFIIA_ROOM_ID:-}

      # ── DAGI backend — Router for /v1/agents/{id}/infer ─────────────────
      # Router internal port 8000 on dagi-network (ext port 9102 on host)
      - DAGI_GATEWAY_URL=http://dagi-router-node1:8000
      - DEFAULT_NODE_ID=NODA1

      # ── Sofiia Console (audit write) ─────────────────────────────────────
      - SOFIIA_CONSOLE_URL=http://dagi-sofiia-console-node1:8002
      - SOFIIA_INTERNAL_TOKEN=${SOFIIA_INTERNAL_TOKEN:-}

      # ── H2: Backpressure queue ───────────────────────────────────────────
      - QUEUE_MAX_EVENTS=100
      - WORKER_CONCURRENCY=2
      - QUEUE_DRAIN_TIMEOUT_S=5

      # ── Policy ───────────────────────────────────────────────────────────
      # M2.0+: multiple agents separated by comma
      - BRIDGE_ALLOWED_AGENTS=${BRIDGE_ALLOWED_AGENTS:-sofiia}
      # M2.0: "sofiia:!room1:server,helion:!room2:server" (1 room → 1 agent)
      - BRIDGE_ROOM_MAP=${BRIDGE_ROOM_MAP:-}
      - RATE_LIMIT_ROOM_RPM=20
      - RATE_LIMIT_SENDER_RPM=10

      # ── M2.1: Mixed rooms (1 room → N agents) ───────────────────────────
      # Format: "!roomX:server=sofiia,helion;!roomY:server=druid"
      - BRIDGE_MIXED_ROOM_MAP=${BRIDGE_MIXED_ROOM_MAP:-}
      # Override default agent per mixed room (optional):
      # "!roomX:server=helion;!roomY:server=druid"
      - BRIDGE_MIXED_DEFAULTS=${BRIDGE_MIXED_DEFAULTS:-}

      # ── M3.0: Operator control channel ──────────────────────────────────
      # Comma-separated Matrix user IDs allowed to issue !commands
      - BRIDGE_OPERATOR_ALLOWLIST=${BRIDGE_OPERATOR_ALLOWLIST:-}
      # Comma-separated room IDs designated as ops control channels
      - BRIDGE_CONTROL_ROOMS=${BRIDGE_CONTROL_ROOMS:-}
      # "ignore" (silent) | "reply_error" (⛔ reply to unauthorised attempts)
      - CONTROL_UNAUTHORIZED_BEHAVIOR=${CONTROL_UNAUTHORIZED_BEHAVIOR:-ignore}
      # ── M3.1: Runbook runner token ───────────────────────────────────────
      # X-Control-Token for POST /api/runbooks/internal/runs (sofiia-console)
      - SOFIIA_CONTROL_TOKEN=${SOFIIA_CONTROL_TOKEN:-}
      # M3.4: Control channel safety — rate limiting + cooldown
      - CONTROL_ROOM_RPM=${CONTROL_ROOM_RPM:-60}
      - CONTROL_OPERATOR_RPM=${CONTROL_OPERATOR_RPM:-30}
      - CONTROL_RUN_NEXT_RPM=${CONTROL_RUN_NEXT_RPM:-20}
      - CONTROL_COOLDOWN_S=${CONTROL_COOLDOWN_S:-2.0}
      # M2.3: Persistent event deduplication
      - PERSISTENT_DEDUPE=${PERSISTENT_DEDUPE:-1}
      - BRIDGE_DATA_DIR=${BRIDGE_DATA_DIR:-/app/data}
      - PROCESSED_EVENTS_TTL_H=${PROCESSED_EVENTS_TTL_H:-48}
      - PROCESSED_EVENTS_PRUNE_BATCH=${PROCESSED_EVENTS_PRUNE_BATCH:-5000}
      - PROCESSED_EVENTS_PRUNE_INTERVAL_S=${PROCESSED_EVENTS_PRUNE_INTERVAL_S:-3600}
      # M4.0: agent discovery
      - DISCOVERY_RPM=${DISCOVERY_RPM:-20}
      # M5.0: node-aware routing
      - BRIDGE_ALLOWED_NODES=${BRIDGE_ALLOWED_NODES:-NODA1}
      - BRIDGE_DEFAULT_NODE=${BRIDGE_DEFAULT_NODE:-NODA1}
      - BRIDGE_ROOM_NODE_MAP=${BRIDGE_ROOM_NODE_MAP:-}
      # M8.0: Node health + soft-failover thresholds
      - NODE_FAIL_CONSEC=${NODE_FAIL_CONSEC:-3}
      - NODE_LAT_EWMA_S=${NODE_LAT_EWMA_S:-12.0}
      - NODE_EWMA_ALPHA=${NODE_EWMA_ALPHA:-0.3}
      # M8.1: Sticky failover TTL (0 = disabled)
      - FAILOVER_STICKY_TTL_S=${FAILOVER_STICKY_TTL_S:-300}
      # M8.2: HA state persistence
      - HA_HEALTH_SNAPSHOT_INTERVAL_S=${HA_HEALTH_SNAPSHOT_INTERVAL_S:-60}
      - HA_HEALTH_MAX_AGE_S=${HA_HEALTH_MAX_AGE_S:-600}
      # M9.0: Two-step confirmation TTL for dangerous commands (0 = disabled)
      - CONFIRM_TTL_S=${CONFIRM_TTL_S:-120}
      - POLICY_EXPORT_RETENTION_DAYS=${POLICY_EXPORT_RETENTION_DAYS:-30}
      - POLICY_HISTORY_LIMIT=${POLICY_HISTORY_LIMIT:-100}
      # M11 soak: NEVER set to true in production
      - DEBUG_INJECT_ENABLED=${DEBUG_INJECT_ENABLED:-false}

      # ── M2.2: Mixed room guard rails ────────────────────────────────────
      # Fail-fast if any room defines more agents than this
      - MAX_AGENTS_PER_MIXED_ROOM=${MAX_AGENTS_PER_MIXED_ROOM:-5}
      # Reject slash commands longer than this (anti-garbage / injection guard)
      - MAX_SLASH_LEN=${MAX_SLASH_LEN:-32}
      # What to do when unknown /slash is used: "ignore" (silent) | "reply_error" (inform user)
      - UNKNOWN_AGENT_BEHAVIOR=${UNKNOWN_AGENT_BEHAVIOR:-ignore}
      # Max concurrent Router invocations per (room, agent) pair; 0 = unlimited
      - MIXED_CONCURRENCY_CAP=${MIXED_CONCURRENCY_CAP:-1}

    healthcheck:
      test:
        - "CMD"
        - "python3"
        - "-c"
        - "import urllib.request; urllib.request.urlopen('http://localhost:7030/health', timeout=5)"
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 15s

    networks:
      - dagi-network

    restart: unless-stopped

networks:
  dagi-network:
    external: true