feat: add 7zz for CHM documentation extraction

ai/Dockerfile

@@ -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" ]

ai/hermes/Dockerfile

@@ -79,6 +79,39 @@ PYEOF
 COPY --chmod=0755 himalaya-ro.sh /usr/local/bin/himalaya-ro
 
 
+# ---------- Install 7-Zip (7zz) 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 link
+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()
+match = re.search(r'href="(a/7z[\d]+-linux-x64\.tar\.xz)"', html)
+if not match:
+    raise RuntimeError('Could not find 7z Linux x64 download link on 7-zip.org')
+dl_url = f'https://7-zip.org/{match.group(1)}'
+
+# Follow Himalaya pattern: download, extract, install, verify
+xz = '/tmp/7z.tar.xz'
+urllib.request.urlretrieve(dl_url, xz)
+os.makedirs('/tmp/7z', exist_ok=True)
+with tarfile.open(xz, 'r:xz') as t:
+    t.extractall('/tmp/7z')
+shutil.move('/tmp/7z/7zz', '/usr/local/bin/7zz')
+os.chmod('/usr/local/bin/7zz', 0o755)
+shutil.rmtree('/tmp/7z', ignore_errors=True)
+os.remove(xz)
+
+# Verify
+result = subprocess.run(['/usr/local/bin/7zz'], capture_output=True, text=True)
+assert result.returncode == 0, f'7zz verify failed: {result.stderr}'
+version = result.stdout.split()[2] if result.stdout else 'unknown'
+print(f'7-Zip {version} installed successfully')
+PYEOF
+
+
 # ---------- Runtime ----------
 USER hermes
 ENV HERMES_HOME=/opt/data