feat(ai): add chromium, xvfb, fonts, and runtime libraries for headless browser automation

ai/Dockerfile

@@ -0,0 +1,33 @@
+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"]

ai/hermes/Dockerfile

@@ -1,106 +1,93 @@
 # syntax=docker/dockerfile:1
-# Hermes Agent with Chromium -- local browser tool support
+# Hermes Agent -- custom fork build
-# Based on python:3.11-slim for minimal footprint.
+# Builds on top of official image + overlays our forked source from Gitea.
-# Chromium installed via apt-get for system-level browser automation.
+# Requires Docker BuildKit. Pass SSH agent for git clone:
-#
+#   docker compose build hermes
-# Build:
+# Or manually:
-#   docker build -t hermes-agent:chromium .
+#   DOCKER_BUILDKIT=1 docker build --ssh default -t hermes-agent:custom .
-#
-# Environment variables:
-#   CHROME_EXECUTABLE  -- path to the Chromium binary
 
-# ---------- Base image ----------
+# ---------- Base: official Hermes image (system deps, npm, uv, Playwright) ----------
-FROM python:3.11-slim
+FROM nousresearch/hermes-agent:latest
 
-ENV DEBIAN_FRONTEND=noninteractive
+# ---------- Overlay our forked source ----------
-ENV PYTHONUNBUFFERED=1
+# Uses SSH agent forwarding from the build host (no key baked into image).
+# --exclude node_modules/.venv keeps the base image's pre-built layers intact.
+# Only the Python source, web UI source, and config change.
+RUN --mount=type=ssh \
+    mkdir -p /root/.ssh && \
+    ssh-keyscan -p 2222 code.lazyworkhorse.net >> /root/.ssh/known_hosts 2>/dev/null && \
+    cd /tmp && \
+    GIT_SSH_COMMAND='ssh -p 2222 -o StrictHostKeyChecking=no' \
+    git clone --depth 1 --branch main \
+    git@code.lazyworkhorse.net:gortium/hermes-agent.git fork && \
+    rsync -a --delete fork/ /opt/hermes/ \
+      --exclude node_modules \
+      --exclude .venv \
+      --exclude .git && \
+    rm -rf /tmp/fork /root/.ssh/
 
-# ---------- System dependencies for Chromium ----------
+# ---------- Rebuild web UI ----------
-# The minimum set required to run headless Chromium on Linux.
+# Source files changed; node_modules (from base image) reused.
-# python:3.11-slim is Debian Bookworm (12) -- package names without t64 suffix.
+RUN cd /opt/hermes && npm run build
+
+# ---------- Reinstall Python package (editable) ----------
+# Picks up source changes from our fork.
+RUN . /opt/hermes/.venv/bin/activate && \
+    uv pip install --no-cache-dir --no-deps -e /opt/hermes
+
+# ---------- Extra system deps ----------
+USER root
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-        # Chromium and its launcher
+        libportaudio2 ca-certificates poppler-utils imagemagick \
-        chromium \
+        texlive-latex-base texlive-latex-extra texlive-fonts-recommended \
-        chromium-common \
+        texlive-xetex texlive-science \
-        chromium-sandbox \
+        qemu-user-static binfmt-support emacs-nox && \
-        # Font rendering for proper page rendering
+    rm -rf /var/lib/apt/lists/*
-        fonts-liberation \
-        fonts-noto-color-emoji \
-        fonts-dejavu-core \
-        # System libraries required by Chromium at runtime
-        libnss3 \
-        libnspr4 \
-        libatk1.0-0 \
-        libatk-bridge2.0-0 \
-        libcups2 \
-        libdrm2 \
-        libxdamage1 \
-        libxfixes3 \
-        libxcomposite1 \
-        libxrandr2 \
-        libgbm1 \
-        libpango-1.0-0 \
-        libcairo2 \
-        libasound2 \
-        libxkbcommon0 \
-        libxshmfence1 \
-        # Virtual framebuffer for headless operation
-        xvfb \
-        # Process supervisor for orphan reaping
-        tini \
-        # Git for Hermes source operations
-        git \
-        # SSL certificates for HTTPS connections
-        ca-certificates \
-        # Curl for health checks
-        curl \
-    && rm -rf /var/lib/apt/lists/*
 
-# ---------- Hermes Agent installation ----------
+# ---------- UV ----------
-# Install uv (fast Python package manager)
+COPY --chmod=0755 --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/
-COPY --chmod=0755 --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv
-COPY --chmod=0755 --from=ghcr.io/astral-sh/uv:latest /uvx /usr/local/bin/uvx
 
-# Create hermes user (non-root runtime)
+# ---------- Piper TTS ----------
-RUN useradd -u 10000 -m -d /opt/data hermes
+RUN . /opt/hermes/.venv/bin/activate && \
+    uv pip install --no-cache-dir piper-tts sounddevice numpy && \
+    mkdir -p /opt/hermes/.venv/share/piper/voices
 
-# Install Hermes Agent from PyPI with gateway support for messaging
+RUN /opt/hermes/.venv/bin/python3 /dev/stdin << 'PYEOF'
-RUN uv pip install --system --no-cache-dir \
+import urllib.request
-        'hermes-agent[gateway]' \
+base = '/opt/hermes/.venv/share/piper/voices'
-        croniter && \
+url = 'https://huggingface.co/rhasspy/piper-voices/resolve/main/en/en_US/ryan/high/en_US-ryan-high.onnx'
-    uv cache clean
+urllib.request.urlretrieve(url, base + '/en_US-ryan-high.onnx')
+urllib.request.urlretrieve(url + '.json', base + '/en_US-ryan-high.onnx.json')
+PYEOF
 
-# Create the /opt/hermes directory structure expected by entrypoint
+# ---------- Install Himalaya email CLI ----------
-RUN mkdir -p /opt/hermes/.venv/bin && \
+RUN /opt/hermes/.venv/bin/python3 /dev/stdin << 'PYEOF'
-    mkdir -p /opt/hermes/docker && \
+import urllib.request, tarfile, os, shutil
-    ln -sf /usr/local/bin/uv /opt/hermes/.venv/bin/uv && \
+url = 'https://github.com/pimalaya/himalaya/releases/download/v1.2.0/himalaya.x86_64-linux.tgz'
-    ln -sf /usr/local/bin/uvx /opt/hermes/.venv/bin/uvx
+tgz = '/tmp/himalaya.tgz'
+urllib.request.urlretrieve(url, tgz)
+with tarfile.open(tgz) as t:
+    t.extractall('/tmp')
+shutil.move('/tmp/himalaya', '/usr/local/bin/himalaya')
+os.chmod('/usr/local/bin/himalaya', 0o755)
+os.remove(tgz)
+print('himalaya v1.2.0 installed')
+PYEOF
 
-# ---------- Entrypoint script ----------
+# ---------- Install himalaya-ro wrapper ----------
-COPY entrypoint.sh /opt/hermes/docker/entrypoint.sh
+COPY --chmod=0755 himalaya-ro.sh /usr/local/bin/himalaya-ro
-RUN chmod +x /opt/hermes/docker/entrypoint.sh
 
-# ---------- Environment variables ----------
-# Point browser tool to system Chromium (installed via apt-get)
-ENV CHROME_EXECUTABLE=/usr/bin/chromium
-
-# Hermes paths
-ENV HERMES_HOME=/opt/data
-ENV PATH="/opt/data/.local/bin:${PATH}"
-
-# Playwright browsers path (for agent-browser install at runtime)
-ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
-
-# Virtual framebuffer display for headless Chromium
-ENV DISPLAY=:99
-
-# ---------- Data volume ----------
-VOLUME [ "/opt/data" ]
 
 # ---------- Runtime ----------
 USER hermes
-WORKDIR /opt/data
+ENV HERMES_HOME=/opt/data
+ENV PATH="/opt/data/.local/bin:${PATH}"
+# Point browser tool to Playwright's Chromium (already in base image)
+ENV CHROME_EXECUTABLE=/opt/hermes/.playwright/chromium/chrome-linux/chrome
 
-ENTRYPOINT [ "/opt/hermes/docker/entrypoint.sh" ]
+# Ensure tools directory and toolsets.py are writable by the hermes runtime user
-CMD [ "gateway", "run" ]
+# so custom tools can be injected from the persistent volume at startup.
+RUN chown -R hermes:hermes /opt/hermes/tools /opt/hermes/toolsets.py
+
+VOLUME [ "/opt/data" ]

ai/hermes/entrypoint.sh

@@ -1,20 +0,0 @@
-#!/bin/bash
-set -e
-
-# Hermes Agent entrypoint script
-# Installs custom tools and runtime dependencies,
-# then delegates to the passed command (usually "gateway run").
-
-# Install custom tools from persistent volume if available
-if [ -f /opt/data/hermes-tools/install.sh ]; then
-    bash /opt/data/hermes-tools/install.sh
-fi
-
-# Install additional runtime deps (idempotent)
-if command -v uv &>/dev/null; then
-    uv pip install --system --no-cache-dir --quiet \
-        openai mautrix[encryption] 2>/dev/null || true
-fi
-
-# Execute the passed command with tini for proper signal handling
-exec tini -g -- "$@"