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

Reviewed-on: #30

ai/compose.yml

@@ -31,6 +31,9 @@ services:
       ssh:
         - default
     container_name: hermes
+    entrypoint: ["/bin/bash", "-c",
+      "bash /opt/data/hermes-tools/install.sh && exec /usr/bin/tini -g -- /opt/hermes/docker/entrypoint.sh \"$@\"",
+      "hermes-entrypoint"]
     restart: always
     # Gateway run enables the internal API server on port 8642
     command: gateway run
@@ -51,6 +54,10 @@ services:
       - TZ=America/Montreal
     volumes:
       - /mnt/HoardingCow_docker_data/Hermes/data:/opt/data
+      # Syncthing-shared org files — read-only view of user's agenda
+      - /mnt/HoardingCow_docker_data/Syncthing/telos-ro:/opt/data/telos-ro:ro
+      # Syncthing-shared inbox — write tasks here, they sync to user's laptop
+      - /mnt/HoardingCow_docker_data/Syncthing/telos-rw:/opt/data/telos-rw:rw
     devices:
       - /dev/kfd:/dev/kfd
       - /dev/dri:/dev/dri
@@ -60,6 +67,35 @@ services:
     networks:
       - ai_backend
 
+  syncthing:
+    image: syncthing/syncthing:latest
+    container_name: syncthing
+    hostname: syncthing
+    restart: always
+    ports:
+      - "8384:8384"
+      - "22000:22000"
+      - "21027:21027/udp"
+    environment:
+      - TZ=America/Montreal
+    volumes:
+      - /mnt/HoardingCow_docker_data/Syncthing/config:/var/syncthing/config
+      - /mnt/HoardingCow_docker_data/Syncthing/telos-ro:/telos-ro
+      - /mnt/HoardingCow_docker_data/Syncthing/telos-rw:/telos-rw
+    networks:
+      - ai_backend
+      - ai_net
+    labels:
+      - "traefik.enable=true"
+      - "traefik.http.routers.syncthing-http.rule=Host(`syncthing.lazyworkhorse.net`)"
+      - "traefik.http.routers.syncthing-http.entrypoints=web"
+      - "traefik.http.routers.syncthing-http.middlewares=redirect-to-https"
+      - "traefik.http.routers.syncthing-https.rule=Host(`syncthing.lazyworkhorse.net`)"
+      - "traefik.http.routers.syncthing-https.entrypoints=websecure"
+      - "traefik.http.routers.syncthing-https.tls=true"
+      - "traefik.http.routers.syncthing-https.tls.certresolver=njalla"
+      - "traefik.http.services.syncthing.loadbalancer.server.port=8384"
+
   ollama:
     build:
       context: ./ollama

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 "$@"

ai/hermes/Dockerfile

@@ -86,7 +86,8 @@ 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
 
-VOLUME [ "/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
 
-COPY --chmod=0755 fix-permissions.sh /opt/hermes/fix-permissions.sh
-ENTRYPOINT [ "/usr/bin/tini", "-g", "--", "/opt/hermes/fix-permissions.sh" ]
+VOLUME [ "/opt/data" ]

ai/hermes/fix-permissions.sh

@@ -1,38 +0,0 @@
-#!/bin/bash
-# Startup permission fix + TTS patch.
-# Runs as root before the entrypoint drops to the hermes user.
-set -e
-
-HERMES_HOME="${HERMES_HOME:-/opt/data}"
-
-# Fix ownership on critical writable directories
-chown -R hermes:hermes \
-  "$HERMES_HOME/sessions" \
-  "$HERMES_HOME/checkpoints" \
-  "$HERMES_HOME/skills" \
-  "$HERMES_HOME/memories" \
-  "$HERMES_HOME/workspace" \
-  "$HERMES_HOME/pastes" \
-  "$HERMES_HOME/logs" \
-  "$HERMES_HOME/cron" \
-  "$HERMES_HOME/plans" \
-  "$HERMES_HOME/hooks" \
-  "$HERMES_HOME/cache" \
-  2>/dev/null || true
-
-# Fix data volume root ownership
-if [ "$(stat -c %u "$HERMES_HOME" 2>/dev/null)" != "$(id -u hermes)" ]; then
-  chown hermes:hermes "$HERMES_HOME" 2>/dev/null || true
-fi
-
-# ---------- Patch tts_tool.py: replace Edge TTS with Piper ----------
-# Fallback runtime patch in case the volume's site-packages differ from the image.
-# Idempotent: if already patched, the script does nothing.
-PATCH_SCRIPT="/opt/hermes/patch_tts_tool.py"
-if [ -f "$PATCH_SCRIPT" ]; then
-  echo "Applying TTS patch (Piper only, no Edge fallback)..."
-  /opt/hermes/.venv/bin/python3 "$PATCH_SCRIPT" 2>&1 || true
-fi
-
-# Chain to the official Hermes entrypoint
-exec /opt/hermes/docker/entrypoint.sh "$@"

versioncontrol/compose.yml

@@ -8,13 +8,10 @@ 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:

vpn/Dockerfile

@@ -0,0 +1,9 @@
+# Custom wg-easy with iptables-nft (nftables-backed iptables)
+# Fixes crash-loop when host kernel lacks legacy iptable_nat module.
+FROM ghcr.io/wg-easy/wg-easy:latest
+
+# The upstream image registers only iptables-legacy with update-alternatives.
+# iptables-nft binary exists but isn't registered as an alternative key.
+# Override the alternatives-managed symlinks directly.
+RUN ln -sf /usr/sbin/iptables-nft /usr/sbin/iptables && \
+    ln -sf /usr/sbin/ip6tables-nft /usr/sbin/ip6tables

vpn/compose.yml

@@ -2,7 +2,10 @@ version: "3.8"
 
 services:
   wireguard:
-    image: weejewel/wg-easy:latest
+    build:
+      context: .
+      dockerfile: Dockerfile
+    image: wg-easy-iptables-nft:latest
     container_name: wireguard
     cap_add:
       - NET_ADMIN