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 98 deletions

View File

@@ -1,65 +0,0 @@
FROM ghcr.io/astral-sh/uv:0.11.6-python3.13-trixie@sha256:b3c543b6c4f23a5f2df22866bd7857e5d304b67a564f4feab6ac22044dde719b AS uv_source
FROM tianon/gosu:1.19-trixie@sha256:3b176695959c71e123eb390d427efc665eeb561b1540e82679c15e992006b8b9 AS gosu_source
FROM debian:13.4
# Disable Python stdout buffering to ensure logs are printed immediately
ENV PYTHONUNBUFFERED=1
# Store Playwright browsers outside the volume mount so the build-time
# install survives the /opt/data volume overlay at runtime.
ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
# Install system dependencies in one layer, clear APT cache
# tini reaps orphaned zombie processes (MCP stdio subprocesses, git, bun, etc.)
# that would otherwise accumulate when hermes runs as PID 1. See #15012.
RUN apt-get update && \
apt-get install -y --no-install-recommends \
build-essential nodejs npm python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli tini \
curl poppler-utils imagemagick emacs-nox \
texlive-latex-base texlive-latex-extra texlive-fonts-recommended texlive-xetex texlive-science && \
rm -rf /var/lib/apt/lists/*
# Non-root user for runtime; UID can be overridden via HERMES_UID at runtime
RUN useradd -u 10000 -m -d /opt/data hermes
COPY --chmod=0755 --from=gosu_source /gosu /usr/local/bin/
COPY --chmod=0755 --from=uv_source /usr/local/bin/uv /usr/local/bin/uvx /usr/local/bin/
WORKDIR /opt/hermes
# ---------- Layer-cached dependency install ----------
# Copy only package manifests first so npm install + Playwright are cached
# unless the lockfiles themselves change.
COPY package.json package-lock.json ./
COPY web/package.json web/package-lock.json web/
RUN npm install --prefer-offline --no-audit && \
npx playwright install --with-deps chromium --only-shell && \
(cd web && npm install --prefer-offline --no-audit) && \
npm cache clean --force
# ---------- Source code ----------
# .dockerignore excludes node_modules, so the installs above survive.
COPY --chown=hermes:hermes . .
# Build web dashboard (Vite outputs to hermes_cli/web_dist/)
RUN cd web && npm run build
# ---------- Permissions ----------
# Make install dir world-readable so any HERMES_UID can read it at runtime.
# The venv needs to be traversable too.
USER root
RUN chmod -R a+rX /opt/hermes
# Start as root so the entrypoint can usermod/groupmod + gosu.
# If HERMES_UID is unset, the entrypoint drops to the default hermes user (10000).
# ---------- Python virtualenv ----------
RUN uv venv && \
uv pip install --no-cache-dir -e ".[all]"
# ---------- Runtime ----------
ENV HERMES_WEB_DIST=/opt/hermes/hermes_cli/web_dist
ENV HERMES_HOME=/opt/data
ENV PATH="/opt/data/.local/bin:${PATH}"
VOLUME [ "/opt/data" ]
ENTRYPOINT [ "/usr/bin/tini", "-g", "--", "/opt/hermes/docker/entrypoint.sh" ]

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: