Merge pull request 'fix(agent): cuDNN base image so onnxruntime-gpu loads' (#146) from dev into main

agent/Dockerfile

@@ -1,6 +1,8 @@
 # FabledCurator GPU agent — runs on the desktop with the GPU.
-# CUDA runtime so onnxruntime-gpu can use the card; ffmpeg for video frames.
-FROM nvidia/cuda:12.4.1-runtime-ubuntu22.04
+# CUDA + cuDNN 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.
+FROM nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04
 
 ENV DEBIAN_FRONTEND=noninteractive PYTHONUNBUFFERED=1
 RUN apt-get update \

agent/docker-compose.yml

@@ -0,0 +1,40 @@
+# FabledCurator GPU agent — desktop run via docker compose.
+#
+# Usage:
+#   1. Generate a token: FC → Settings → Tagging → GPU agent → Generate token.
+#   2. Create a .env next to this file:
+#        FC_URL=http://curator.traefik.internal
+#        FC_TOKEN=<paste-the-token>
+#        # optional: CCIP_MODEL=ccip-caformer_b36-24   (the F1-0.94 variant)
+#   3. docker compose up -d     (pulls the published image)
+#   4. Open http://localhost:8770 → Start. Pause/Stop hands the GPU back.
+#      docker compose down       to stop the container entirely.
+#
+# Needs the NVIDIA Container Toolkit installed on the host for --gpus.
+
+services:
+  fc-gpu-agent:
+    image: git.fabledsword.com/bvandeusen/fabledcurator-agent:latest
+    pull_policy: always
+    ports:
+      - "8770:8770"
+    environment:
+      FC_URL: ${FC_URL:-http://curator.traefik.internal}
+      FC_TOKEN: ${FC_TOKEN:?set FC_TOKEN in .env (FC → GPU agent → Generate token)}
+      CCIP_MODEL: ${CCIP_MODEL:-}
+      DETECTOR_LEVEL: ${DETECTOR_LEVEL:-m}
+      BATCH_SIZE: ${BATCH_SIZE:-4}
+    volumes:
+      # Persist the downloaded ONNX models so restarts are fast.
+      - fc-agent-models:/models
+    restart: unless-stopped
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+
+volumes:
+  fc-agent-models: