# semif: SemIf option-logit decisions (github TheoLeeCJ/SemIf-OpenJev, MIT) behind semif-serve,
# on fv-ml1 GPU 1 (the utility card, beside vllm-coder and scriberr). Prime, 2026-09-27.
#
# One forward pass of a pinned Qwen3.5-4B (BF16) per decision; the answer is read from the
# option-letter logits, so there is no decoding. Service code + contract:
#   services/semif-serve/ (semif-serve.contract.md). Image built on fv-ml1 from that dir.
#
# ⚠ Scores are "conditional option score; uncalibrated as decision confidence". A caller
#   that needs thresholds brings labelled rows; we fit a per-workload temperature into
#   conf/calibration.json and the caller passes `workload`. See the README.
# ⚠ SEMIF_VRAM_CAP_GIB is a HARD cap (torch per-process memory fraction), sized from a
#   measured peak, so SemIf cannot squeeze scriberr or the vLLM seats on this card. A
#   request that needs more gets 503 out_of_memory and the service stays up.
#
# .env (tunables): IMAGE, PORT, GPU_ID, VRAM_CAP_GIB, HOST_IP, SEMIF_API_TOKEN (vault
#   semif/api-token, >= 32 chars).

name: semif

services:
  semif:
    image: ${IMAGE:?set IMAGE}
    container_name: semif
    restart: unless-stopped
    ports:
      - "${PORT:-8032}:8000"
    environment:
      SEMIF_API_TOKEN: ${SEMIF_API_TOKEN:?set SEMIF_API_TOKEN}
      SEMIF_DEVICE: cuda
      SEMIF_VRAM_CAP_GIB: ${VRAM_CAP_GIB:?set VRAM_CAP_GIB}
      SEMIF_MAX_TOKENS: ${MAX_TOKENS:-4096}
      SEMIF_MAX_DECISIONS: ${MAX_DECISIONS:-64}
      # POSTs in progress (queued + scoring) before new ones get 429 busy.
      SEMIF_MAX_QUEUE: ${MAX_QUEUE:-32}
      SEMIF_CALIBRATION: /conf/calibration.json
    volumes:
      # Pinned weights, read offline (HF_HUB_OFFLINE=1 in the image). Never downloads.
      - /tank/aimodels/huggingface:/hf:ro
      - /opt/docker/conf/semif:/conf:ro
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["${GPU_ID:-1}"]
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=5)"]
      interval: 30s
      timeout: 10s
      retries: 3
      # Startup loads ~9 GB of weights and scores one warm-up decision before it serves.
      start_period: 300s
    networks:
      - tnet
    labels:
      - homepage.group=AI - Eval & Retrieval
      - homepage.name=SemIf — option-logit decisions
      - homepage.icon=mdi-scale-balance
      - homepage.description=Typed decisions from one forward pass (Qwen3.5-4B, fv-ml1 GPU1)
      - homepage.href=http://${HOST_IP:-10.251.50.54}:${PORT:-8032}/health

networks:
  tnet:
    name: traefik-net
    external: true