# FabledCurator GPU agent — runs on the desktop with the GPU.
# CUDA 12.9 + cuDNN 9 runtime so onnxruntime-gpu can use the card (it needs
# cuDNN 9 — the plain -runtime image lacks it: "libcudnn.so.9: cannot open
# shared object file"); ffmpeg for video frames. Ubuntu 24.04 → Python 3.12.
# Stays on the CUDA-12 / cuDNN-9 line the default onnxruntime-gpu + torch are
# built against (CUDA 13 has only nascent ONNX Runtime support).
FROM nvidia/cuda:12.9.2-cudnn-runtime-ubuntu24.04

# PIP_BREAK_SYSTEM_PACKAGES: Ubuntu 24.04 marks its system Python as externally
# managed (PEP 668), so a global `pip install` errors without this. It's a
# single-purpose container — we own the whole environment, so installing into
# the system site-packages is fine (and simplest — no venv on PATH to manage).
ENV DEBIAN_FRONTEND=noninteractive PYTHONUNBUFFERED=1 PIP_BREAK_SYSTEM_PACKAGES=1
RUN apt-get update \
    && apt-get install -y --no-install-recommends python3 python3-pip ffmpeg \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app
# torch from the CUDA-12.4 wheel index; its wheels bundle their own CUDA + cuDNN
# so they run on the 12.9 base and coexist with onnxruntime-gpu. Installed first
# + separately so the GPU build of torch is deterministic and layer-cached.
RUN pip3 install --no-cache-dir torch==2.6.0 --index-url https://download.pytorch.org/whl/cu124
COPY requirements.txt .
RUN pip3 install --no-cache-dir -r requirements.txt
COPY fc_agent ./fc_agent

# imgutils ONNX models + the transformers SigLIP weights both cache here; mount
# a volume to persist them across restarts (the SigLIP download is ~3.5 GB once).
ENV HF_HOME=/models
EXPOSE 8770

# The control UI; the worker is started from it (or POST /start).
CMD ["uvicorn", "fc_agent.app:app", "--host", "0.0.0.0", "--port", "8770"]