# FabledCurator GPU agent — runs on the desktop with the GPU.
#
# The `base` flavour, not `cudnn-runtime`: CUDA and cuDNN arrive as the
# `nvidia-*` pip packages torch and onnxruntime-gpu depend on, so the base only
# has to hand the container the driver (it sets NVIDIA_VISIBLE_DEVICES /
# NVIDIA_DRIVER_CAPABILITIES for the Container Toolkit). Until #1451 this was
# `12.9.2-cudnn-runtime` under a `torch==2.6.0+cu124` — and requirements.txt then
# REPLACED that torch with PyPI's CUDA-13 build (ultralytics pulls torchvision,
# which pulls its matching torch), beside a CUDA-13 onnxruntime-gpu. The image
# ran CUDA 13 on a CUDA-12 base, carrying ~3 GB of base libraries and a ~3 GB
# torch nothing loaded: 10 GB compressed.
#
# 13.0 because that is the line both wheels are built for (torch's cu130 index,
# onnxruntime-gpu's `nvidia-cuda-runtime~=13.0`). Needs an NVIDIA driver that
# supports CUDA 13 (580+); fc_agent/accel.py logs at startup whether torch and
# onnxruntime actually got the GPU, since both fall back to the CPU silently.
# ffmpeg for video frames. Ubuntu 24.04 → Python 3.12.
FROM nvidia/cuda:13.0.3-base-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 AND torchvision from the cu130 index, together and first. Installing
# torch alone is what let the next step swap it out: ultralytics needs
# torchvision, PyPI's torchvision pins its own torch, and pip replaced ours to
# match. With both present, requirements.txt finds them satisfied.
RUN pip3 install --no-cache-dir --index-url https://download.pytorch.org/whl/cu130 \
        torch torchvision
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

# Declared LAST on purpose, exactly as the web Dockerfile does: an ARG/ENV
# invalidates every layer below it, and these are the only values that differ
# between builds of otherwise identical source. Any earlier and the ~6.3 GB
# CUDA + torch layers could never be shared between the dev and main builds of
# one commit — which is the cost #3114 measured at 9m26s cold.
#
# Three values, never folded together (rule 149) — the NAME a person reads, the
# CHANNEL it came from, and the REVISION that identifies the content. See
# fc_agent/build_info.py; CI derives all three from scripts/artifacts.sh.
ARG FC_CHANNEL=""
ENV FC_CHANNEL=${FC_CHANNEL}
ARG FC_VERSION=""
ENV FC_VERSION=${FC_VERSION}
ARG FC_REVISION=""
ENV FC_REVISION=${FC_REVISION}

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"]