feat(hermes): replace Dockerfile with python:3.11-slim based image with Chromium

ai/hermes-workspace/entrypoint-combined.sh

@@ -1,154 +0,0 @@
-#!/bin/bash
-# ── Hermes Workspace Combined Entrypoint ──
-# Waits for the Hermes gateway container (hermes:8642) to become healthy,
-# then starts the Hermes Workspace web UI in the foreground.
-# Supports graceful shutdown via SIGTERM/SIGINT.
-# ──────────────────────────────────────────
-
-set -euo pipefail
-
-# ── Configuration ──────────────────────────────────────────────
-GATEWAY_HOST="${GATEWAY_HOST:-hermes}"
-GATEWAY_PORT="${GATEWAY_PORT:-8642}"
-GATEWAY_URL="http://${GATEWAY_HOST}:${GATEWAY_PORT}"
-
-HEALTH_ENDPOINT="${HEALTH_ENDPOINT:-/health}"
-MAX_RETRIES="${HEALTH_MAX_RETRIES:-60}"
-RETRY_INTERVAL="${HEALTH_RETRY_INTERVAL:-2}"
-
-WORKSPACE_DIR="${WORKSPACE_DIR:-/workspace}"
-WORKSPACE_ENTRY="${WORKSPACE_ENTRY:-server-entry.js}"
-
-PID_FILE="${PID_FILE:-/tmp/workspace.pid}"
-
-# ── Logging ────────────────────────────────────────────────────
-log_info()  { echo "[$(date '+%Y-%m-%d %H:%M:%S')] [INFO]  $*"; }
-log_warn()  { echo "[$(date '+%Y-%m-%d %H:%M:%S')] [WARN]  $*"; }
-log_error() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] [ERROR] $*"; }
-
-# ── Graceful Shutdown ──────────────────────────────────────────
-_workspace_pid=""
-_shutting_down=false
-
-cleanup() {
-    if [ "$_shutting_down" = true ]; then
-        return
-    fi
-    _shutting_down=true
-
-    log_info "Shutdown signal received, cleaning up..."
-
-    # Stop workspace process if running
-    if [ -n "$_workspace_pid" ] && kill -0 "$_workspace_pid" 2>/dev/null; then
-        log_info "Stopping workspace (PID: $_workspace_pid)..."
-        kill -TERM "$_workspace_pid" 2>/dev/null || true
-
-        # Give it time to shut down gracefully
-        local wait_sec=10
-        while kill -0 "$_workspace_pid" 2>/dev/null && [ "$wait_sec" -gt 0 ]; do
-            sleep 1
-            wait_sec=$((wait_sec - 1))
-        done
-
-        # Force kill if still running
-        if kill -0 "$_workspace_pid" 2>/dev/null; then
-            log_warn "Workspace did not shut down gracefully, force killing..."
-            kill -KILL "$_workspace_pid" 2>/dev/null || true
-        fi
-    fi
-
-    # Clean up PID file
-    [ -f "$PID_FILE" ] && rm -f "$PID_FILE"
-
-    log_info "Shutdown complete."
-    exit 0
-}
-
-# Trap termination signals for graceful shutdown
-trap cleanup SIGTERM SIGINT
-
-# ── Gateway Health Check ───────────────────────────────────────
-wait_for_gateway() {
-    local url="${GATEWAY_URL}${HEALTH_ENDPOINT}"
-    local retries="$MAX_RETRIES"
-    local interval="$RETRY_INTERVAL"
-    local attempt=0
-
-    log_info "Waiting for Hermes gateway at ${GATEWAY_URL}..."
-    log_info "Max retries: ${retries}, interval: ${interval}s"
-
-    while [ "$attempt" -lt "$retries" ]; do
-        attempt=$((attempt + 1))
-
-        if curl -fsS "${url}" >/dev/null 2>&1; then
-            log_info "Gateway is healthy after ${attempt} attempt(s) (${GATEWAY_URL})"
-            return 0
-        fi
-
-        if [ "$attempt" -lt "$retries" ]; then
-            log_info "Gateway not ready yet (attempt ${attempt}/${retries}), retrying in ${interval}s..."
-            sleep "$interval"
-        fi
-    done
-
-    log_error "Gateway did not become healthy after ${retries} attempts ($((retries * interval))s)"
-    return 1
-}
-
-# ── Workspace Startup ──────────────────────────────────────────
-start_workspace() {
-    local entry="${WORKSPACE_DIR}/${WORKSPACE_ENTRY}"
-
-    if [ ! -d "$WORKSPACE_DIR" ]; then
-        log_error "Workspace directory not found: ${WORKSPACE_DIR}"
-        return 1
-    fi
-
-    if [ ! -f "$entry" ]; then
-        log_error "Workspace entry point not found: ${entry}"
-        return 1
-    fi
-
-    log_info "Starting Hermes Workspace web UI..."
-    log_info "  Directory: ${WORKSPACE_DIR}"
-    log_info "  Entry:     ${entry}"
-
-    cd "$WORKSPACE_DIR"
-
-    # Start workspace in background so we can trap signals
-    node --max-old-space-size=2048 "${entry}" &
-    _workspace_pid=$!
-    echo "$_workspace_pid" > "$PID_FILE"
-
-    log_info "Workspace started (PID: ${_workspace_pid})"
-
-    # Wait for workspace process
-    wait "$_workspace_pid"
-    local exit_code=$?
-
-    log_info "Workspace exited with code ${exit_code}"
-    return "$exit_code"
-}
-
-# ── Main ───────────────────────────────────────────────────────
-main() {
-    log_info "=== Hermes Workspace Combined Entrypoint ==="
-    log_info "Gateway:   ${GATEWAY_URL}"
-    log_info "Workspace: ${WORKSPACE_DIR}/${WORKSPACE_ENTRY}"
-    log_info "PID file:  ${PID_FILE}"
-
-    # Wait for gateway to be healthy
-    if ! wait_for_gateway; then
-        log_warn "Proceeding without confirmed gateway health..."
-    fi
-
-    # Start the workspace
-    start_workspace
-    local exit_code=$?
-
-    log_info "Entrypoint exiting with code ${exit_code}"
-    return "$exit_code"
-}
-
-# Run main; exit with its return code
-main "$@"

ai/hermes/Dockerfile

@@ -1,93 +1,106 @@
 # syntax=docker/dockerfile:1
-# Hermes Agent -- custom fork build
-# Builds on top of official image + overlays our forked source from Gitea.
-# Requires Docker BuildKit. Pass SSH agent for git clone:
-#   docker compose build hermes
-# Or manually:
-#   DOCKER_BUILDKIT=1 docker build --ssh default -t hermes-agent:custom .
+# Hermes Agent with Chromium -- local browser tool support
+# Based on python:3.11-slim for minimal footprint.
+# Chromium installed via apt-get for system-level browser automation.
+#
+# Build:
+#   docker build -t hermes-agent:chromium .
+#
+# Environment variables:
+#   CHROME_EXECUTABLE  -- path to the Chromium binary
 
-# ---------- Base: official Hermes image (system deps, npm, uv, Playwright) ----------
-FROM nousresearch/hermes-agent:latest
+# ---------- Base image ----------
+FROM python:3.11-slim
 
-# ---------- Overlay our forked source ----------
-# 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/
+ENV DEBIAN_FRONTEND=noninteractive
+ENV PYTHONUNBUFFERED=1
 
-# ---------- Rebuild web UI ----------
-# Source files changed; node_modules (from base image) reused.
-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
+# ---------- System dependencies for Chromium ----------
+# The minimum set required to run headless Chromium on Linux.
+# python:3.11-slim is Debian Bookworm (12) -- package names without t64 suffix.
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-        libportaudio2 ca-certificates poppler-utils imagemagick \
-        texlive-latex-base texlive-latex-extra texlive-fonts-recommended \
-        texlive-xetex texlive-science \
-        qemu-user-static binfmt-support emacs-nox && \
-    rm -rf /var/lib/apt/lists/*
+        # Chromium and its launcher
+        chromium \
+        chromium-common \
+        chromium-sandbox \
+        # Font rendering for proper page rendering
+        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/*
 
-# ---------- UV ----------
-COPY --chmod=0755 --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/
+# ---------- Hermes Agent installation ----------
+# Install uv (fast Python package manager)
+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
 
-# ---------- Piper TTS ----------
-RUN . /opt/hermes/.venv/bin/activate && \
-    uv pip install --no-cache-dir piper-tts sounddevice numpy && \
-    mkdir -p /opt/hermes/.venv/share/piper/voices
+# Create hermes user (non-root runtime)
+RUN useradd -u 10000 -m -d /opt/data hermes
 
-RUN /opt/hermes/.venv/bin/python3 /dev/stdin << 'PYEOF'
-import urllib.request
-base = '/opt/hermes/.venv/share/piper/voices'
-url = 'https://huggingface.co/rhasspy/piper-voices/resolve/main/en/en_US/ryan/high/en_US-ryan-high.onnx'
-urllib.request.urlretrieve(url, base + '/en_US-ryan-high.onnx')
-urllib.request.urlretrieve(url + '.json', base + '/en_US-ryan-high.onnx.json')
-PYEOF
+# Install Hermes Agent from PyPI with gateway support for messaging
+RUN uv pip install --system --no-cache-dir \
+        'hermes-agent[gateway]' \
+        croniter && \
+    uv cache clean
 
-# ---------- Install Himalaya email CLI ----------
-RUN /opt/hermes/.venv/bin/python3 /dev/stdin << 'PYEOF'
-import urllib.request, tarfile, os, shutil
-url = 'https://github.com/pimalaya/himalaya/releases/download/v1.2.0/himalaya.x86_64-linux.tgz'
-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
+# Create the /opt/hermes directory structure expected by entrypoint
+RUN mkdir -p /opt/hermes/.venv/bin && \
+    mkdir -p /opt/hermes/docker && \
+    ln -sf /usr/local/bin/uv /opt/hermes/.venv/bin/uv && \
+    ln -sf /usr/local/bin/uvx /opt/hermes/.venv/bin/uvx
 
-# ---------- Install himalaya-ro wrapper ----------
-COPY --chmod=0755 himalaya-ro.sh /usr/local/bin/himalaya-ro
+# ---------- Entrypoint script ----------
+COPY entrypoint.sh /opt/hermes/docker/entrypoint.sh
+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
-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
+WORKDIR /opt/data
 
-# Ensure tools directory and toolsets.py are writable by the hermes runtime user
-# 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" ]
+ENTRYPOINT [ "/opt/hermes/docker/entrypoint.sh" ]
+CMD [ "gateway", "run" ]

ai/hermes/entrypoint.sh

@@ -0,0 +1,20 @@
+#!/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 -- "$@"