Compare commits

..

1 Commits

Author SHA1 Message Date
c39174f0fe feat: add 7zz for CHM documentation extraction
Some checks failed
Build Hermes agent / build (pull_request) Has been cancelled
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.
2026-05-13 16:27:32 -04:00
4 changed files with 44 additions and 66 deletions

View File

@@ -1,33 +0,0 @@
FROM debian:13.4
# Install system dependencies for Hermes agent with headless browser automation
# Single RUN layer to minimize image size.
# PR #7 base: curl, poppler-utils, imagemagick for document processing
# New: chromium + xvfb for headless browser automation
# New: fonts for comprehensive Unicode/CJK/emoji coverage
# New: runtime libs required by Chromium
RUN apt-get update && \
apt-get install -y --no-install-recommends \
curl \
poppler-utils \
imagemagick \
chromium \
xvfb \
fonts-noto-color-emoji fonts-unifont fonts-liberation fonts-ipafont-gothic fonts-wqy-zenhei fonts-tlwg-loma-otf fonts-freefont-ttf \
libasound2t64 libatk-bridge2.0-0t64 libatk1.0-0t64 libatspi2.0-0t64 libcairo2 libcups2t64 libdbus-1-3 libdrm2 libgbm1 libglib2.0-0t64 libnspr4 libnss3 libpango-1.0-0 libx11-6 libxcb1 libxcomposite1 libxdamage1 libxext6 libxfixes3 libxkbcommon0 libxrandr2 && \
rm -rf /var/lib/apt/lists/*
# Install uv (Python package manager)
COPY --from=ghcr.io/astral-sh/uv:latest /usr/local/bin/uv /usr/local/bin/uv
RUN uv --version
# Verify all expected tools are available
RUN curl --version && \
pdftotext -v 2>&1 | head -1 && \
pdfinfo -v 2>&1 | head -1 && \
pdftoppm -v 2>&1 | head -1 && \
convert --version | head -1 && \
identify --version | head -1 && \
chromium --version
CMD ["/bin/bash"]

View File

@@ -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

View File

@@ -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

View File

@@ -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: