momentum-system/docker-compose.yml

# Full self-contained stack for the Momentum System.
#
#   docker compose up -d                      # postgres + loop + dashboard + qabot + transcripts + scheduler
#   docker compose --profile monitoring up -d # also start Grafana
#   docker compose run --rm nightly-tune      # run a job on demand
#
# Secrets come from .env (never baked into the image). DATABASE_URL is
# overridden below to the in-stack postgres so the stack is self-contained —
# migrating from the LAN Postgres (192.168.1.5) is a pg_dump/restore into the
# pg-data volume; see deploy/docker/README.md. To run the app services against
# the LAN Postgres instead (transition mode), comment out the DATABASE_URL
# override and let .env's value through.
#
# TZ is America/New_York in the image: the loop's market clock thinks in ET.

x-app: &app
  build: .
  image: momentum-app:latest
  env_file:
    - path: .env
      required: false
  volumes:
    - app-data:/app/data
  depends_on:
    postgres:
      condition: service_healthy
  restart: unless-stopped
  logging:
    driver: json-file
    options: { max-size: "20m", max-file: "3" }

x-app-env: &app-env
  # Self-contained default: the in-stack postgres. Overrides .env.
  DATABASE_URL: postgresql://${POSTGRES_USER:-momentum}:${POSTGRES_PASSWORD:-momentum}@postgres:5432/${POSTGRES_DB:-momentum}
  PG_SKIP_SCHEMA: "0"
  LIVE_BARS_INTERVAL_SECONDS: "5"
  TRIGGER_ARM_INTERVAL_SECONDS: "8"
  WATCHER_INTERVAL_SECONDS: "8"
  TRIGGER_INTERVAL_SECONDS: "2"
  # catalyst enrichment ON as a labeler FEATURE source (plan 009) — loop + scheduler
  # (labeler builds) both inherit this anchor. Needs a reachable Ollama (see .env);
  # enabled-but-down never impedes trading (fully gated).
  NEWS_ENRICH_ENABLED: "1"
  # Managed-exit config — matches deploy/docker/truenas-compose.yml so both
  # templates agree. Without these the loop runs code defaults (target 2R,
  # BE@+5%, NO trail) which scratches slow v1 winners at breakeven. prior_low
  # trailing after +1R lifts the win rate (counterfactual: v1 17%->24%). Only the
  # LOOP acts on these (ExitConfig.from_env, run_live_paper.py); other services
  # inherit them harmlessly.
  TRADING_EXIT_TRAIL_MODE: "prior_low"
  TRADING_EXIT_TRAIL_AFTER_R: "1.0"
  TRADING_EXIT_MANAGE_INTERVAL_SECONDS: '4'  # 12->4s: react to fast small-cap round-trips (was giving back gains)
  TRADING_EXIT_THREAD_ENABLED: '1'
  DISCOVER_THREAD_ENABLED: '1'
  TRADING_EXIT_THREAD_INTERVAL_SECONDS: '1.0'
  TRADING_EXIT_TRAIL_R_STEP: "0.25"
  TRADING_EXIT_BREAKEVEN_R: "1.0"
  TRADING_EXIT_PROFIT_TIERS: "8:3,15:9,25:18,40:30"
  # Regime gate (plan 011) LIVE: block fresh entries on sessions the walk-forward
  # metalabel scores unfavorable (sit out bad regimes). Only the LOOP acts on it;
  # fail-open (unfit model / error never blocks). Needs regime_features populated
  # (the scheduler builds them nightly). Set 0 to disable.
  TRADING_REGIME_GATE_ENABLED: "1"
  # Favorable threshold: block a session when P(profit) < this. 0.5 = code default
  # (matches the backtest). Lower (e.g. 0.4) trades MORE days; raise for fewer,
  # higher-confidence days. Optional — omit to use the 0.5 default.
  TRADING_REGIME_GATE_P_MIN: "0.5"

services:
  postgres:
    image: postgres:18
    environment:
      POSTGRES_USER: ${POSTGRES_USER:-momentum}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-momentum}
      POSTGRES_DB: ${POSTGRES_DB:-momentum}
      PGDATA: /var/lib/postgresql/data/pgdata
    volumes:
      - pg-data:/var/lib/postgresql/data
    ports:
      - "5432:5432"   # psql/Grafana-on-host debugging; remove if not needed
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-momentum} -d ${POSTGRES_DB:-momentum}"]
      interval: 10s
      timeout: 5s
      retries: 5
    restart: unless-stopped

  loop:
    <<: *app
    container_name: momentum-loop
    command: ["python", "-u", "run_live_paper.py", "--no-dashboard"]
    environment:
      <<: *app-env
    healthcheck:
      # heartbeat: the loop must have written SOME event in the last 5 minutes
      # (module ticks flow around the clock, not just market hours)
      # PG_SKIP_SCHEMA=1: a healthcheck must NOT re-apply schema DDL — the 60s
      # CREATE-IF-NOT-EXISTS lock burst cancelled minute_bars autovacuum forever
      # (2026-07-09 post-migration: stats rotted, dashboard queries crawled)
      test: ["CMD", "python", "-c", "import os; os.environ['PG_SKIP_SCHEMA']='1'; import datetime,sys; from research.multi_schema import open_research_db; r=open_research_db('market').execute('SELECT max(timestamp) FROM events').fetchall()[0][0]; sys.exit(0 if r and (datetime.datetime.now()-r).total_seconds()<300 else 1)"]
      interval: 60s
      timeout: 20s
      retries: 5
      start_period: 180s

  dashboard:
    <<: *app
    container_name: momentum-dashboard
    command: ["python", "-u", "dashboard_api.py"]
    environment:
      <<: *app-env
      DASHBOARD_HOST: "0.0.0.0"
      DASHBOARD_PORT: "8765"
      # read-only viewer: never re-apply the 473-line schema (the SSE change
      # detector holds one long-lived connection) — mirrors the loop healthcheck.
      PG_SKIP_SCHEMA: "1"
      # Shared secret required on every POST (approve/reject/exit + the command
      # bus). Empty = commands disabled and POSTs unauthenticated; set a value to
      # arm the kill switch. Reference by name only — never inline the secret.
      DASHBOARD_TOKEN: "${DASHBOARD_TOKEN:-}"
      # Gate the operator command bus on (also needs DASHBOARD_TOKEN set).
      COMMAND_BUS_ENABLED: "${COMMAND_BUS_ENABLED:-0}"
    ports:
      - "8765:8765"
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://localhost:8765/"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s

  qabot:
    <<: *app
    container_name: momentum-qabot
    command: ["python", "-u", "telegram_bot.py"]
    environment:
      <<: *app-env

  transcripts:
    <<: *app
    container_name: momentum-transcripts
    command: ["python", "-u", "-m", "youtube_claims.run", "run"]
    environment:
      <<: *app-env

  admin:
    <<: *app
    container_name: momentum-admin
    command: ["python", "-u", "admin_api.py"]
    environment:
      <<: *app-env
      ADMIN_PORT: "8767"
      # set ADMIN_TOKEN in .env — without it the panel is open on the LAN
    ports:
      - "8767:8767"
    volumes:
      - app-data:/app/data
      - /var/run/docker.sock:/var/run/docker.sock   # service status + restarts

  scheduler:
    # Weekday-evening premarket eval + DB/log housekeeping at 20:00 ET —
    # replaces the momentum-premarket-eval systemd timer.
    <<: *app
    container_name: momentum-scheduler
    environment:
      <<: *app-env
    command:
      - /bin/sh
      - -c
      - |
        echo "[scheduler] up; will fire 20:00 ET Mon-Fri"
        while true; do
          if [ "$$(date +%H:%M)" = "20:00" ] && [ "$$(date +%u)" -le 5 ]; then
            echo "[scheduler] premarket_eval $$(date)"
            python -m research.premarket_eval || echo "[scheduler] eval FAILED"
            # SPY/QQQ ingest -> forward source for the labeler's market-context features (plan 009)
            python -m research.ingestion.market_context || echo "[scheduler] market_context ingest FAILED"
            python -m research.eod_reconcile || echo "[scheduler] reconcile FAILED"
            # Flywheel: grow the whole-market dataset first, then fit the tuner on
            # it. 20:00 ET is after close, so replay of "today" is complete data —
            # NOT look-ahead (replay is a labeling job, not a live gate).
            python eod_replay.py || echo "[scheduler] eod_replay FAILED"
            python nightly_tune.py || echo "[scheduler] nightly_tune FAILED"
            # Regime gate (plan 011, ALL-SHADOW): a session-level metalabel
            # P(our ORB profits today). build-features labels each session from its
            # OWN realized expR; score writes the WALK-FORWARD favorable flag the
            # experiments' regime_gate intervention reads. Must run BEFORE
            # experiments run. Does NOT gate live trading (that is owner-gated).
            python -m research.regime build-features || echo "[scheduler] regime build-features FAILED"
            python -m research.regime score --model threshold_v1 || echo "[scheduler] regime score threshold FAILED"
            python -m research.regime score --model meta_v1 || echo "[scheduler] regime score meta FAILED"
            # Experiment OS (plan 006, ALL-SHADOW): replay running experiments over
            # newly-logged fires, then adjudicate against pre-registered bars.
            python -m research.experiments run || echo "[scheduler] experiments run FAILED"
            python -m research.experiments adjudicate || echo "[scheduler] experiments adjudicate FAILED"
            sleep 120
          fi
          sleep 20
        done

  db-backup:
    # Nightly pg_dump at 20:10 ET Mon-Fri (after the 20:00 scheduler pass).
    # Runs on the postgres:18 image — a version-matched pg_dump for free; the
    # app image has none. Backups land in the app-data volume under backups/.
    image: postgres:18
    container_name: momentum-db-backup
    restart: unless-stopped
    environment:
      # in-stack postgres, same value the app services use (NOT .env's
      # DATABASE_URL, which may point at the old LAN instance)
      DATABASE_URL: postgresql://${POSTGRES_USER:-momentum}:${POSTGRES_PASSWORD:-momentum}@postgres:5432/${POSTGRES_DB:-momentum}
      BACKUP_DIR: /data/backups
      BACKUP_KEEP_DAYS: "14"
      TZ: America/New_York   # the postgres image defaults to UTC; the 20:10 gate is ET
    volumes:
      - ./deploy/docker/backup_db.sh:/backup_db.sh:ro
      - app-data:/data
    depends_on:
      postgres:
        condition: service_healthy
    command:
      - /bin/bash
      - -c
      - |
        echo "[backup] up; fires 20:10 ET Mon-Fri"
        while true; do
          if [ "$$(date +%H:%M)" = "20:10" ] && [ "$$(date +%u)" -le 5 ]; then
            bash /backup_db.sh || echo "[backup] FAILED"
            sleep 120
          fi
          sleep 20
        done

  # ---- On-demand jobs: docker compose run --rm <name>
  journal:
    <<: *app
    profiles: ["jobs"]
    command: ["python", "momentum_cli.py", "journal"]
    environment: *app-env
    restart: "no"

  eod-replay:
    <<: *app
    profiles: ["jobs"]
    command: ["python", "eod_replay.py"]
    environment: *app-env
    restart: "no"

  nightly-tune:
    <<: *app
    profiles: ["jobs"]
    command: ["python", "nightly_tune.py"]
    environment: *app-env
    restart: "no"

  # ---- Grafana (optional): docker compose --profile monitoring up -d
  grafana:
    image: grafana/grafana:11.2.0
    profiles: ["monitoring"]
    environment:
      GF_AUTH_ANONYMOUS_ENABLED: "true"
      GF_AUTH_ANONYMOUS_ORG_ROLE: "Admin"
      GF_AUTH_DISABLE_LOGIN_FORM: "true"
      GF_DASHBOARDS_MIN_REFRESH_INTERVAL: "2s"
      PG_USER: ${POSTGRES_USER:-momentum}
      PG_PASSWORD: ${POSTGRES_PASSWORD:-momentum}
      PG_DATABASE: ${POSTGRES_DB:-momentum}
    ports:
      - "3000:3000"
    volumes:
      - ./deploy/compose/grafana/datasources:/etc/grafana/provisioning/datasources:ro
      - ./deploy/compose/grafana/dashboards:/etc/grafana/provisioning/dashboards:ro
      - grafana-data:/var/lib/grafana
    depends_on:
      postgres:
        condition: service_healthy
    restart: unless-stopped

volumes:
  pg-data:
  app-data:
  grafana-data: