# Optional local Docker image for the reverse-SynthID pixel scorer.
#
# Build from the repository root:
#   docker build -f Dockerfile.synthid -t watermarks-remover-synthid-scorer .
#
# The upstream code is fetched from source at build time and is NOT
# redistributed by this repository. Users must comply with the upstream
# project's non-commercial Research License.
#
# Vendored fork hardening:
#   - base image pinned by digest (no moving tag drift)
#   - upstream checkout pinned to a commit SHA (no moving branch)
#   - deps pinned exactly in requirements-synthid-scorer.txt
#   - pip itself pinned (no unpinned bootstrap step)
#   - runs as an unprivileged user (a parser bug in a crafted image can no
#     longer write files as root inside the container)

# Pinned upstream commit (2026-07-17). Keep in sync with setup_synthid.sh.
ARG REVERSE_SYNTHID_REF=b11083676fd3ee3ff97ce9d03c0e409e46905902

# python:3.11-slim linux/amd64 digest.
FROM python:3.14-slim@sha256:ce40764625a4ff50df3548277632e7f96c4e77fe75fa848aae9885476e7df5a4

ARG REVERSE_SYNTHID_REF

RUN apt-get update \
    && apt-get install -y --no-install-recommends \
        git \
        libgl1 \
        libglib2.0-0 \
        passwd \
    && rm -rf /var/lib/apt/lists/*

RUN git clone --depth 1 --filter=blob:none --sparse \
        https://github.com/aloshdenny/reverse-SynthID.git /opt/reverse-synthid \
    && cd /opt/reverse-synthid \
    && git fetch --depth 1 origin "${REVERSE_SYNTHID_REF}" \
    && git checkout --detach "${REVERSE_SYNTHID_REF}" \
    && git sparse-checkout set --no-cone \
        '/src/' \
        '/artifacts/spectral_codebook_v4.npz' \
        '/requirements.txt' \
        '/LICENSE' \
        '/README.md'

COPY skills/remove-ai-marks/scripts/requirements-synthid-scorer.txt /app/requirements-synthid-scorer.txt
COPY skills/remove-ai-marks/scripts/score_synthid.py /app/score_synthid.py

RUN python3 -m pip install --no-cache-dir "pip==26.2.1" \
    && python3 -m pip install --no-cache-dir -r /app/requirements-synthid-scorer.txt

# Unprivileged runtime user. The scorer only reads input files and writes to
# stdout, so nothing under /opt, /app, or the mounted data dir needs root.
RUN useradd --create-home --uid 10001 --shell /usr/sbin/nologin scorer
USER scorer

ENV REVERSE_SYNTHID_DIR=/opt/reverse-synthid \
    HOME=/home/scorer \
    PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1

WORKDIR /app
ENTRYPOINT ["python3", "/app/score_synthid.py"]