Merge pull request 'Modernise agent base → Ubuntu 24.04 / Python 3.12 / CUDA 12.9' (#170) from dev into main

agent/Dockerfile

@@ -1,18 +1,24 @@
 # FabledCurator GPU agent — runs on the desktop with the GPU.
-# CUDA + cuDNN runtime so onnxruntime-gpu can use the card (it needs cuDNN 9 —
+# CUDA 12.9 + cuDNN 9 runtime so onnxruntime-gpu can use the card (it needs
-# the plain -runtime image lacks it: "libcudnn.so.9: cannot open shared object
+# cuDNN 9 — the plain -runtime image lacks it: "libcudnn.so.9: cannot open
-# file"); ffmpeg for video frames.
+# shared object file"); ffmpeg for video frames. Ubuntu 24.04 → Python 3.12.
-FROM nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04
+# 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
 
-ENV DEBIAN_FRONTEND=noninteractive PYTHONUNBUFFERED=1
+# 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 (matches the base image); its wheels
+# torch from the CUDA-12.4 wheel index; its wheels bundle their own CUDA + cuDNN
-# bundle their own CUDA + cuDNN and coexist with onnxruntime-gpu. Installed
+# so they run on the 12.9 base and coexist with onnxruntime-gpu. Installed first
-# first + separately so the GPU build of torch is deterministic and layer-cached.
+# + 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

agent/fc_agent/app.py

@@ -15,7 +15,7 @@ from .worker import Worker
 # Bump on every agent change. The page embeds this and /status reports it; the UI
 # warns to reload when they differ — so a stale browser-cached page can't be
 # mistaken for "the new image didn't deploy". (Belt-and-braces with no-store.)
-VERSION = "2026-06-30.6 · submit-retry+py310"
+VERSION = "2026-06-30.7 · ubuntu24.04-py312-cuda12.9"
 
 logbuf.install()
 cfg = Config.from_env()

agent/ruff.toml

@@ -1,7 +1,7 @@
-# The agent runs on the CUDA base image's Python 3.10 — NOT the 3.14 that CI's
+# The agent runs on the CUDA base image's Python 3.12 (Ubuntu 24.04) — NOT the
-# ci-python image and the repo-root ruff.toml target. Pin the agent to py310 so
+# 3.14 that CI's ci-python image and the repo-root ruff.toml target. Pin the
-# ruff enforces 3.10 compatibility and never auto-applies a 3.11+/3.14-only fix
+# agent to py312 so ruff enforces 3.12 compatibility and never auto-applies a
-# (e.g. unquoting a self-referential annotation, which PEP 649 makes safe on 3.14
+# 3.14-only fix (e.g. unquoting a self-referential annotation, which PEP 649
-# but NameErrors on 3.10). Inherit the root lint rules.
+# makes safe on 3.14 but NameErrors on 3.12). Inherit the root lint rules.
 extend = "../ruff.toml"
-target-version = "py310"
+target-version = "py312"