# syntax=docker/dockerfile:1.7
# Parking VISION image: the Python/uv ANPR microservice. Build CONTEXT is apps/vision
# (self-contained Python package; no monorepo deps). Ships WITH the `alpr` extra (real
# fast-alpr/onnxruntime stack) but the engine is env-selected: VISION_RECOGNIZER=stub
# (default, boots anywhere) or fast_alpr (prod). See wiki/decisions/container-deployment.md,
# wiki/decisions/vision-service-packaging.md.

# uv-provided Python 3.12 (matches apps/vision/.python-version).
FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim AS base
WORKDIR /app
ENV UV_LINK_MODE=copy \
    UV_COMPILE_BYTECODE=1 \
    PYTHONUNBUFFERED=1

# System libs the recognizer stack needs (opencv/onnxruntime): GL + glib. Kept minimal.
RUN apt-get update \
    && apt-get install -y --no-install-recommends libgl1 libglib2.0-0 curl \
    && rm -rf /var/lib/apt/lists/*

# ---- deps: resolve + install the venv from the lockfile (cache-friendly) ----
# Manifests first so the heavy `uv sync` layer caches across source edits.
COPY pyproject.toml uv.lock .python-version ./
RUN --mount=type=cache,target=/root/.cache/uv \
    uv sync --frozen --no-install-project --extra alpr

# ---- project source ----
COPY vision_service/ ./vision_service/
COPY README.md ./
# Vehicle stage weights (phase A): YOLOX-S, Apache-2.0, ~36 MB, baked into the image so the
# air-gapped appliance never fetches at runtime and no operator-writable path holds a model
# (vision-service-hardening.md). Best-effort at build: without network the stage stays off.
ARG YOLOX_URL=https://github.com/Megvii-BaseDetection/YOLOX/releases/download/0.1.1rc0/yolox_s.onnx
RUN mkdir -p /app/models \
    && (curl -fsSL -o /app/models/yolox_s.onnx "$YOLOX_URL" \
        || (echo "[build] yolox weights not fetched (no network) — vehicle stage off" && rm -f /app/models/yolox_s.onnx))
# Phase B body-type classifier (apps/trainer output, published to the Gitea generic package
# registry — weights are not code, they never live in git). models/bodytype.version PINS the
# version this image carries: empty = no classifier (phase B off). A pinned version that
# cannot be fetched FAILS the build — the image must carry what git says it carries. The
# registry may need auth: pass a BuildKit secret `bodytype_auth` holding "user:token".
ARG BODYTYPE_BASE_URL=https://git.infra.msai.al/api/packages/mca/generic/parking-bodytype
COPY models/bodytype.version ./models/bodytype.version
RUN --mount=type=secret,id=bodytype_auth \
    v="$(tr -d '[:space:]' < /app/models/bodytype.version)"; \
    if [ -n "$v" ]; then \
      cfg=/tmp/curl.cfg; : > "$cfg"; \
      [ -f /run/secrets/bodytype_auth ] && printf 'user = "%s"\n' "$(cat /run/secrets/bodytype_auth)" > "$cfg"; \
      curl -fsSL -K "$cfg" -o /app/models/bodytype.onnx "$BODYTYPE_BASE_URL/$v/bodytype.onnx" \
        && curl -fsSL -K "$cfg" -o /app/models/bodytype.json "$BODYTYPE_BASE_URL/$v/bodytype.json" \
        && echo "[build] bodytype classifier $v baked" \
        || { echo "[build] bodytype classifier $v could not be fetched"; rm -f "$cfg"; exit 1; }; \
      rm -f "$cfg"; \
    else echo "[build] no bodytype version pinned — phase B off"; fi
RUN --mount=type=cache,target=/root/.cache/uv \
    uv sync --frozen --extra alpr

# Non-root runtime user, created BEFORE the model pre-warm so the weights cache lands in
# this user's HOME (~/.cache) — the SAME path the runtime reads. (fast-alpr's
# open-image-models caches under $HOME/.cache/open-image-models keyed to HOME, ignoring
# HF_HOME/XDG_CACHE_HOME — so the pre-warm MUST run as the runtime user, not root.)
RUN useradd --system --create-home --uid 999 vision \
    && chown -R vision:vision /app
USER vision

# Pre-warm the fast-alpr model weights INTO the image (as the vision user → /home/vision/
# .cache) so the prod recognizer is OFFLINE-first: ALPR() downloads weights on first
# construction, which would otherwise need network on the appliance's first scan. Best-effort
# — if the build host has no network this is skipped and weights fetch lazily at runtime.
# NB: NO --mount=type=cache here — a BuildKit cache mount at ~/.cache is NOT committed to the
# image layer, so the downloaded weights would vanish. They must write to the real layer.
RUN uv run python -c "from fast_alpr import ALPR; ALPR()" \
    || echo "[build] model pre-warm skipped (no network) — weights fetch at runtime"

# Default to the stub recognizer (offline, no model load); override to fast_alpr in prod.
ENV VISION_RECOGNIZER=stub \
    VISION_HOST=0.0.0.0 \
    VISION_PORT=8089 \
    VISION_VEHICLE_MODEL_PATH=/app/models/yolox_s.onnx \
    VISION_VEHICLE_CLASSIFIER_PATH=/app/models/bodytype.onnx
EXPOSE 8089
HEALTHCHECK --interval=30s --timeout=5s --start-period=20s --retries=3 \
  CMD python -c "import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://localhost:8089/health').status==200 else 1)" || exit 1

CMD ["uv", "run", "uvicorn", "vision_service.app:app", "--host", "0.0.0.0", "--port", "8089"]
