From b6b151a5000c25de3427362b84f717f65819db38 Mon Sep 17 00:00:00 2001
From: Bryan Van Deusen <bryan.vandeusen@fabledsword.com>
Date: Mon, 29 Jun 2026 18:07:33 -0400
Subject: [PATCH 1/2] docs(agent): docker-compose for the GPU agent

compose file (pull the published image, GPU reservation, model-cache volume,
.env for the token) so the agent runs with `docker compose up -d` instead of a
long docker run. A copy + .env template also placed in ~/Documents/fc-gpu-agent.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
---
 agent/docker-compose.yml | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)
 create mode 100644 agent/docker-compose.yml

diff --git a/agent/docker-compose.yml b/agent/docker-compose.yml
new file mode 100644
index 0000000..9b1adb1
--- /dev/null
+++ b/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:
-- 
2.52.0


From 7b10f4caabaadab71b96019392938636518fae7c Mon Sep 17 00:00:00 2001
From: Bryan Van Deusen <bryan.vandeusen@fabledsword.com>
Date: Mon, 29 Jun 2026 18:47:59 -0400
Subject: [PATCH 2/2] fix(agent): cuDNN base image so onnxruntime-gpu loads
 (#114)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

onnxruntime-gpu needs cuDNN 9; the plain cuda:12.4.1-runtime image lacks it
(libcudnn.so.9 missing → CUDAExecutionProvider falls back to CPU). Switch to
the -cudnn-runtime variant which bundles cuDNN 9.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
---
 agent/Dockerfile | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/agent/Dockerfile b/agent/Dockerfile
index 2e3ca9f..f0a1e24 100644
--- a/agent/Dockerfile
+++ b/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 \
-- 
2.52.0