feat: add 7zz for CHM documentation extraction

Download static 7-Zip binary at Docker build time for extracting Microsoft Compiled HTML Help (.chm) files. Follows the same pattern as the existing Himalaya CLI installation. 7zz is scraped from 7-zip.org/download.html at build time.

ai/compose.yml

@@ -54,10 +54,6 @@ services:
       - TZ=America/Montreal
     volumes:
       - /mnt/HoardingCow_docker_data/Hermes/data:/opt/data
-      # Syncthing-shared org files — read-only view of user's agenda
-      - /mnt/HoardingCow_docker_data/Syncthing/telos-ro:/opt/data/telos-ro:ro
-      # Syncthing-shared inbox — write tasks here, they sync to user's laptop
-      - /mnt/HoardingCow_docker_data/Syncthing/telos-rw:/opt/data/telos-rw:rw
     devices:
       - /dev/kfd:/dev/kfd
       - /dev/dri:/dev/dri
@@ -67,35 +63,6 @@ services:
     networks:
       - ai_backend
 
-  syncthing:
-    image: syncthing/syncthing:latest
-    container_name: syncthing
-    hostname: syncthing
-    restart: always
-    ports:
-      - "8384:8384"
-      - "22000:22000"
-      - "21027:21027/udp"
-    environment:
-      - TZ=America/Montreal
-    volumes:
-      - /mnt/HoardingCow_docker_data/Syncthing/config:/var/syncthing/config
-      - /mnt/HoardingCow_docker_data/Syncthing/telos-ro:/telos-ro
-      - /mnt/HoardingCow_docker_data/Syncthing/telos-rw:/telos-rw
-    networks:
-      - ai_backend
-      - ai_net
-    labels:
-      - "traefik.enable=true"
-      - "traefik.http.routers.syncthing-http.rule=Host(`syncthing.lazyworkhorse.net`)"
-      - "traefik.http.routers.syncthing-http.entrypoints=web"
-      - "traefik.http.routers.syncthing-http.middlewares=redirect-to-https"
-      - "traefik.http.routers.syncthing-https.rule=Host(`syncthing.lazyworkhorse.net`)"
-      - "traefik.http.routers.syncthing-https.entrypoints=websecure"
-      - "traefik.http.routers.syncthing-https.tls=true"
-      - "traefik.http.routers.syncthing-https.tls.certresolver=njalla"
-      - "traefik.http.services.syncthing.loadbalancer.server.port=8384"
-
   ollama:
     build:
       context: ./ollama
@@ -112,7 +79,22 @@ services:
       - /mnt/HoardingCow_docker_data/Ollama/ollama:/root/.ollama
     environment:
       - OLLAMA_VULKAN=0
+      - HSA_OVERRIDE_GFX_VERSION=9.0.6
+      - HCC_AMDGPU_TARGET=gfx906
+      - HIP_VISIBLE_DEVICES=0,1
+      - ROCR_VISIBLE_DEVICES=0,1
+      - HSA_ENABLE_SDMA=0 
       - OLLAMA_HOST=0.0.0.0
+      - OLLAMA_DEBUG=1
+      - OLLAMA_FLASH_ATTENTION=1
+      - OLLAMA_NUM_PARALLEL=2
+    devices:
+      # Map the render nodes and KFD for ROCm to work inside the container
+      - /dev/kfd:/dev/kfd
+      - /dev/dri:/dev/dri
+    group_add:
+      - "303"
+      - "26"
 
 networks:
   ai_net:
@@ -122,40 +104,47 @@ networks:
     driver: bridge
     name: ai_backend
     
-  llama-cpp-hermes:
+  # llama_cpp_devstral:
-    image: llama-cpp:rocm-gfx906
+  #   image: ghcr.io/ggml-org/llama.cpp:server-rocm
-    container_name: llama-cpp-hermes
+  #   container_name: llama_cpp_devstral
-    restart: unless-stopped
+  #   restart: unless-stopped
-    networks:
+  #   networks:
-      - ai_backend
+  #     - ai_backend
-    ports:
+  #   ports:
-      - "127.0.0.1:8300:8080"
+  #     - "8300:8080"
-    ipc: host
+  #   ipc: host
-    devices:
+  #   devices:
-      - /dev/kfd:/dev/kfd
+  #     - "/dev/kfd:/dev/kfd"
-      - /dev/dri:/dev/dri
+  #     - "/dev/dri:/dev/dri"
-    group_add:
+  #   group_add:
-      - "303"
+  #     - "303" # video
-      - "26"
+  #     - "26"  # render
-    environment:
+  #   environment:
-      - HSA_OVERRIDE_GFX_VERSION=9.0.6
+  #     HSA_OVERRIDE_GFX_VERSION: 9.0.6
-      - HSA_ENABLE_SDMA=0
+  #     HIP_VISIBLE_DEVICES: 0,1
-      - HIP_VISIBLE_DEVICES=0,1
+  #     LLAMA_CACHE: /models
-      - LLAMA_CACHE=/models
+  #   volumes:
-    volumes:
+  #     - /mnt/HoardingCow_docker_data/Llama_cpp/models:/models
-      - /mnt/HoardingCow_docker_data/Llama_cpp/models:/models
+  #     - /mnt/HoardingCow_docker_data/Llama_cpp/devstral-agent.jinja:/template.jinja
-      - /mnt/HoardingCow_docker_data/Ollama/ollama/models/blobs/sha256-17823599694fa3503ef54bf748d5078c6ce881f4d01616cafa255dc05d215a08:/model.gguf:ro
+  #   command: >
-    command: >
+  #     -hf unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Devstral-Small-2-24B-Instruct-2512-Q8_0.gguf
-      -m /model.gguf
+  #     -a devstral-2-small-llama_cpp
-      --host 0.0.0.0
+  #     --chat-template-file /template.jinja
-      --port 8080
+  #     --host 0.0.0.0
-      --gpu-layers 99
+  #     --port 8080
-      --ctx-size 163840
+  #     --n-gpu-layers 99
-      -ctk f16 -ctv f16
+  #     --ctx-size 163840
-      --flash-attn on
+  #     --batch-size 4096
-      --split-mode layer
+  #     --ubatch-size 4096
-      --no-mmap
+  #     --cache-type-k f16
-      --n-predict -1
+  #     --cache-type-v f16
+  #     --cache-reuse 256
+  #     --flash-attn on
+  #     --context-shift
+  #     --split-mode layer
+  #     --no-mmap
+  #     --n-predict -1
+  #     --parallel 2
 
   # vllm:
   #   image: nalanzeyu/vllm-gfx906:v0.9.0-rocm6.3

ai/hermes/Dockerfile

@@ -78,6 +78,47 @@ PYEOF
 # ---------- Install himalaya-ro wrapper ----------
 COPY --chmod=0755 himalaya-ro.sh /usr/local/bin/himalaya-ro
 
+# ---------- Install 7-Zip for CHM extraction ----------
+RUN /opt/hermes/.venv/bin/python3 /dev/stdin << 'PYEOF'
+import urllib.request, tarfile, os, shutil, re, subprocess
+
+# Scrape 7-zip.org for latest Linux x64 binary
+url = 'https://7-zip.org/download.html'
+req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0'})
+r = urllib.request.urlopen(req, timeout=15)
+html = r.read().decode()
+
+links = re.findall(r'href="(a/7z[\d]+-linux-x64\.tar\.xz)"', html)
+if not links:
+    raise RuntimeError("Could not find 7z download link")
+
+dl_url = f'https://7-zip.org/{links[0]}'
+print(f'Downloading 7z from {dl_url}...')
+req = urllib.request.Request(dl_url, headers={'User-Agent': 'Mozilla/5.0'})
+r = urllib.request.urlopen(req, timeout=30)
+data = r.read()
+
+with open('/tmp/7z.tar.xz', 'wb') as f:
+    f.write(data)
+
+subprocess.run(['tar', '-xJf', '/tmp/7z.tar.xz', '-C', '/tmp/'], check=True)
+
+for root, dirs, files in os.walk('/tmp'):
+    for f in files:
+        if f == '7zz':
+            src = os.path.join(root, f)
+            shutil.move(src, '/usr/local/bin/7zz')
+            os.chmod('/usr/local/bin/7zz', 0o755)
+            print(f'7zz installed from {src}')
+            break
+
+os.remove('/tmp/7z.tar.xz')
+
+# Verify
+r = subprocess.run(['/usr/local/bin/7zz'], capture_output=True, text=True)
+print(f'7-Zip {r.stdout.strip()[:60]}')
+PYEOF
+
 
 # ---------- Runtime ----------
 USER hermes

ai/llama-cpp/Dockerfile

@@ -1,30 +0,0 @@
-# llama-cpp-rocm6/Dockerfile
-# Custom llama.cpp server with ROCm 6.1 + gfx906 (MI50) support.
-# Build: docker build -t llama-cpp:rocm-gfx906 .
-
-FROM rocm/dev-ubuntu-22.04:6.1.2-complete AS builder
-RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y curl git build-essential pkg-config cmake make && rm -rf /var/lib/apt/lists/*
-ARG LLAMACPP_VERSION=b9596
-RUN git clone --depth 1 --branch ${LLAMACPP_VERSION} https://github.com/ggml-org/llama.cpp.git /build
-WORKDIR /build
-ENV HIP_PATH=/opt/rocm ROCM_PATH=/opt/rocm PATH=/opt/rocm/bin:/opt/rocm/llvm/bin:${PATH} CMAKE_PREFIX_PATH=/opt/rocm
-RUN mkdir build && cd build && \
-    cmake .. -DGGML_HIP=ON -DCMAKE_BUILD_TYPE=Release \
-      -DAMDGPU_TARGETS="gfx906:xnack-" \
-      -DCMAKE_POSITION_INDEPENDENT_CODE=ON \
-      -DGGML_CUDA=OFF -DGGML_VULKAN=OFF -DGGML_METAL=OFF \
-      -DBUILD_SHARED_LIBS=OFF && \
-    cmake --build . --target llama-server -- -j $(nproc)
-
-FROM ubuntu:24.04
-RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
-    ca-certificates curl libstdc++6 libgomp1 libopenblas0 \
-    libnuma1 libelf1 libdrm2 libdrm-amdgpu1 \
-    && rm -rf /var/lib/apt/lists/*
-COPY --from=builder /opt/rocm/lib/ /opt/rocm/lib/
-COPY --from=builder /opt/rocm/share/ /opt/rocm/share/
-COPY --from=builder /build/build/bin/llama-server /usr/local/bin/llama-server
-RUN echo /opt/rocm/lib > /etc/ld.so.conf.d/rocm.conf && ldconfig
-ENV HSA_OVERRIDE_GFX_VERSION=9.0.6 HCC_AMDGPU_TARGET=gfx906 HSA_ENABLE_SDMA=0
-EXPOSE 8080
-ENTRYPOINT ["/usr/local/bin/llama-server"]

versioncontrol/compose.yml

@@ -8,10 +8,13 @@ services:
       - USER_GID=1000
       - GITEA__server__ROOT_URL=https://code.lazyworkhorse.net
       - GITEA__actions__ENABLED=true
+      - GITEA__actions__DEFAULT_ACTIONS_URL=off
       - SSH_PORT=2222
       - SSH_LISTEN_PORT=2222
       # Enable Gitea Actions (act_runner required on host)
       - GITEA__actions__ENABLED=true
+      # Don't fetch actions from GitHub (offline mode + local only)
+      - GITEA__actions__DEFAULT_ACTIONS_URL=off
     volumes:
       - /mnt/HoardingCow_docker_data/Gitea:/data
     networks: