# waterland studio — GPU watercolour render service.
#
# Build context is a CHECKOUT OF vh/waterland, not this directory. See
# compose.yaml: context is /opt/waterland-studio/src and this Dockerfile is
# passed out-of-context so `deploy-stack.sh --delete` can never eat the
# checkout. Refresh the checkout with ./update.sh.

FROM python:3.12-slim

# ffmpeg is not optional — the CLI shells out to it for the VP9 encode of the
# reveal animation. Without it, plate renders succeed and animated ones fail
# at the very end of a 30s GPU job.
RUN apt-get update \
    && apt-get install -y --no-install-recommends ffmpeg ca-certificates \
    && rm -rf /var/lib/apt/lists/*

COPY --from=ghcr.io/astral-sh/uv:0.9.9 /uv /usr/local/bin/uv

WORKDIR /app
COPY . /app

# ⚠️ BOTH extras are load-bearing. `gpu` carries cupy-cuda12x; a bare
# `uv sync` PRUNES it and the renderer silently drops to the numpy path at
# roughly 21x the wall time — it does not error, it just gets slow. `studio`
# carries fastapi/uvicorn/python-multipart.
RUN uv sync --frozen --extra studio --extra gpu

# ⚠️ CUDA HEADERS — the dependency the host never had to declare.
# cupy compiles kernels at runtime through NVRTC, which needs the CUDA toolkit
# HEADERS present, not just the driver and the runtime libs bundled in the
# cupy-cuda12x wheel. On irv-ml1 that requirement was invisible: a CUDA toolkit
# is installed system-wide, so the bare `nohup` process found headers by
# accident. In a slim image there are none, and every render dies 1.7s in with
#   RuntimeError: Failed to find CUDA headers.
# printed through argparse's usage banner, which makes it read like a CLI
# argument bug rather than a missing toolkit.
#
# The [ctk] extra pulls the header packages as wheels — a few hundred MB
# against ~6 GB for a -devel base image. It is installed AFTER the sync above
# because `uv sync` prunes anything it does not know about.
RUN uv pip install "cupy-cuda12x[ctk]"

ENV PATH="/app/.venv/bin:${PATH}" \
    # ⚠️ THE SAME PRUNE TRAP, AT RUNTIME. studio/jobs.py shells the renderer
    # out as a literal `uv run waterland ...` (cwd=WATERLAND_STUDIO_REPO), and
    # that invocation carries no --extra flags. Left to itself uv would
    # re-sync the project to its default extras and prune cupy right back out
    # from under the venv built above. UV_NO_SYNC stops it re-syncing;
    # UV_OFFLINE means that if the pin ever stops working the job fails LOUDLY
    # instead of quietly rebuilding a slower environment.
    UV_NO_SYNC=1 \
    UV_OFFLINE=1 \
    WATERLAND_STUDIO_REPO=/app \
    WATERLAND_STUDIO_DATA=/data \
    WATERLAND_STUDIO_BACKEND=cupy \
    # PCI_BUS_ID index of the A6000 *as seen inside the container*. The
    # compose file exposes exactly one GPU, so that GPU is index 0 here — even
    # though it is index 1 on the host. Do not copy the host's value.
    CUDA_VISIBLE_DEVICES_TARGET=0

EXPOSE 8410

# uvicorn is invoked from the venv directly rather than through `uv run`: the
# server has no reason to re-enter uv, and one less uv invocation is one less
# chance to trip the prune above. The app is a FACTORY, hence --factory.
CMD ["uvicorn", "--factory", "waterland.studio.app:app", \
     "--host", "0.0.0.0", "--port", "8410"]