feat(hermes-workspace): add combined entrypoint script with gateway health check and graceful shutdown

ai/Dockerfile

@@ -1,69 +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 \
-        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 \
-        texlive-latex-base texlive-latex-extra texlive-fonts-recommended texlive-xetex texlive-science \
-        qemu-user-static binfmt-support qemu-user-binfmt \
-        emacs-nox && \
-    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-workspace/entrypoint-combined.sh

@@ -0,0 +1,154 @@
+#!/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 "$@"

env/.env.example.paperclip

@@ -1,26 +0,0 @@
-# Paperclip Environment Variables
-# Copy this file to your .env (at the compose root or docker-compose working directory)
-# and fill in the secrets.
-#
-#   cp env/.env.example.paperclip .env
-#
-# Then reference it from compose.yml:
-#   env_file:
-#     - path: .env
-#       required: true
-
-# ---------------------------------------------------------------------------
-# Database
-# ---------------------------------------------------------------------------
-# PostgreSQL password for the paperclip-db service.
-# Generate a strong random password:
-#   openssl rand -base64 32
-PAPERCLIP_DB_PASSWORD=change_me_to_a_strong_random_password
-
-# ---------------------------------------------------------------------------
-# Authentication
-# ---------------------------------------------------------------------------
-# Secret key used by Better Auth for signing and verifying tokens.
-# Generate a strong random secret:
-#   openssl rand -base64 32
-PAPERCLIP_AUTH_SECRET=change_me_to_a_strong_random_secret