# augaman: the fleet's face-recognition service for Cicada (gitea pfi/augaman), on esh-ml1
# (CT 110 on esh-pve, RTX 2000E Ada 16 GB). Enroll, recognize, verify; buffalo_l (SCRFD +
# ArcFace w600k_r50) on ONNX Runtime CUDA. Canonical copy: this file in pfi/augaman; the
# eshpfi stack mirrors it as stacks/augaman.
#
# ⚠ BIOMETRIC DATA. The gallery volume holds face embeddings and crops of household members.
#   - The live SQLite stays on the local named volume. Never NFS (the service refuses it).
#   - esh-ml1 is OUTSIDE vzdump. The gallery reaches backup only through the backup CLI,
#     writing to BACKUP_DIR, a restic-covered host path. Wire the schedule and VERIFY A
#     RESTORE before real people are enrolled (operator ruling):
#       docker exec augaman python -m augaman.gallery.backup --db /data/gallery.db --dest /backup/gallery.db
#     It prints one JSON line and exits 0, or "backup failed: ..." and exits 1.
#   - BACKUP_DIR must be writable by uid 10001, the container user. Backups are mode 0600.
#
# Startup refuses to serve unless CUDA really runs every convolution: a profiled warmup plus
# ORT's CPU fallbacks turned off. /health reports backend "cuda" only then. Confirm once by the
# process in `nvidia-smi` on the host. Warmup, including the first CUDA inference, is covered
# by the healthcheck's start_period.
#
# Only AUGAMAN_* variables reach the app, and it refuses any it does not know, so compose's own
# variables below carry no AUGAMAN_ prefix and are never passed through wholesale (no env_file).
#
# .env (tunables): IMAGE, PORT (8040), BACKUP_DIR, HOST_IP (10.0.50.80), AUGAMAN_API_TOKEN
#   (>= 32 visible-ASCII characters; the source of truth is the vault).

name: augaman

services:
  augaman:
    image: ${IMAGE:?set IMAGE}
    container_name: augaman
    restart: unless-stopped
    ports:
      - "${PORT:-8040}:8040"
    environment:
      AUGAMAN_API_TOKEN: ${AUGAMAN_API_TOKEN:?set AUGAMAN_API_TOKEN}
      AUGAMAN_DEVICE: cuda
      AUGAMAN_CUDA_DEVICE_ID: "0"
    volumes:
      - gallery:/data
      - ${BACKUP_DIR:?set BACKUP_DIR}:/backup
    # Multipart spools of large uploads land here: RAM only, never persistent disk (api INV-A07).
    tmpfs:
      - /tmp:size=512m
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["0"]
              capabilities: [gpu]
    healthcheck:
      # 200 only when ready and not degraded; a 503 (degraded) fails the check.
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8040/health', timeout=5)"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 180s
    labels:
      - homepage.group=AI - Eval & Retrieval
      - homepage.name=augaman — face recognition
      - homepage.icon=mdi-face-recognition
      - homepage.description=Enroll, recognize, verify (buffalo_l on CUDA) for Cicada
      - homepage.href=http://${HOST_IP:-10.0.50.80}:${PORT:-8040}/health

volumes:
  gallery: