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
3 changed files with 44 additions and 55 deletions

View File

@@ -96,61 +96,6 @@ services:
- "303"
- "26"
paperclip-db:
image: postgres:17-alpine
container_name: paperclip-db
restart: always
environment:
POSTGRES_USER: paperclip
POSTGRES_PASSWORD: ${PAPERCLIP_DB_PASSWORD:?PAPERCLIP_DB_PASSWORD must be set}
POSTGRES_DB: paperclip
healthcheck:
test: ["CMD-SHELL", "pg_isready -U paperclip -d paperclip"]
interval: 5s
timeout: 5s
retries: 10
volumes:
- /mnt/HoardingCow_docker_data/Paperclip/pgdata:/var/lib/postgresql/data
networks:
- ai_backend
paperclip:
image: ghcr.io/paperclipai/paperclip:v2026.517.0
container_name: paperclip
restart: always
ports:
- "127.0.0.1:3100:3100"
environment:
- HOST=0.0.0.0
- PORT=3100
- SERVE_UI=true
- DATABASE_URL=postgres://paperclip:${PAPERCLIP_DB_PASSWORD}@paperclip-db:5432/paperclip
- BETTER_AUTH_SECRET=${PAPERCLIP_AUTH_SECRET:?PAPERCLIP_AUTH_SECRET must be set}
- PAPERCLIP_PUBLIC_URL=https://paperclip.lazyworkhorse.net
- PAPERCLIP_DEPLOYMENT_MODE=authenticated
- PAPERCLIP_DEPLOYMENT_EXPOSURE=private
volumes:
- /mnt/HoardingCow_docker_data/Paperclip/data:/paperclip
depends_on:
paperclip-db:
condition: service_healthy
networks:
- ai_net
- ai_backend
labels:
- "traefik.enable=true"
- "traefik.http.routers.paperclip-http.rule=Host(`paperclip.lazyworkhorse.net`)"
- "traefik.http.routers.paperclip-http.entrypoints=web"
- "traefik.http.routers.paperclip-http.middlewares=redirect-to-https"
- "traefik.http.routers.paperclip-https.rule=Host(`paperclip.lazyworkhorse.net`)"
- "traefik.http.routers.paperclip-https.entrypoints=websecure"
- "traefik.http.routers.paperclip-https.tls=true"
- "traefik.http.routers.paperclip-https.tls.certresolver=njalla"
- "traefik.http.services.paperclip.loadbalancer.server.port=3100"
networks:
ai_net:
external: true

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: