Merge pull request 'fix: s6-overlay entrypoint crash — replace broken bash→tini→entrypoint.sh chain' (#56) from fix/hermes-s6-overlay-entrypoint-crash into master

Reviewed-on: #56

ai/compose.yml

@@ -6,19 +6,19 @@ services:
       ssh:
         - default
     container_name: hermes
-    entrypoint: ["/bin/bash", "-c",
-      "bash /usr/local/bin/run-multi-gateways.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
+    # Use the image default ENTRYPOINT ["/init", "/opt/hermes/docker/main-wrapper.sh"]
+    # for proper s6-overlay supervision. The CMD runs our multi-profile launcher
+    # which spawns per-profile gateways in background, then the default gateway
+    # in foreground (keeps the container alive).
+    command: ["/usr/local/bin/start-hermes.sh"]
     environment:
       - HERMES_UID=10000
       - HERMES_GID=10000
       - OLLAMA_HOST=http://ollama-cpu:11434
       - HERMES_DASHBOARD=1
       # Multi-profile: comma-separated list of profiles to run as gateways.
-      # The entrypoint reads this and starts one gateway per profile.
+      # start-hermes.sh reads this and starts one gateway per profile.
       # Add profiles here when they exist on disk (e.g. default,researcher,writer)
       - HERMES_PROFILES=ashley,claire,finn,matt,paul
       - API_SERVER_ENABLED=true

ai/hermes/Dockerfile

@@ -63,6 +63,11 @@ PYEOF
 # Launches one gateway process per profile (HERMES_PROFILES env var)
 COPY --chmod=0755 run-multi-gateways.sh /usr/local/bin/run-multi-gateways.sh
 
+# ---------- Install s6-overlay compatible startup script ----------
+# Runs as the CMD via s6-overlay's main-program model.
+# Replaces the old bash->tini->entrypoint.sh chain that caused SIGTERM crash loops.
+COPY --chmod=0755 start-hermes.sh /usr/local/bin/start-hermes.sh
+
 # ---------- Runtime ----------
 USER hermes
 ENV HERMES_HOME=/opt/data

ai/hermes/start-hermes.sh

@@ -0,0 +1,38 @@
+#!/bin/bash
+# Multi-profile + default gateway launcher — runs as the CMD via s6-overlay.
+#
+# The image's default ENTRYPOINT ["/init", "/opt/hermes/docker/main-wrapper.sh"]
+# starts the s6 supervision tree, then exec's main-wrapper.sh with the CMD args.
+# main-wrapper.sh sources the venv, drops to the hermes user via s6-setuidgid,
+# and exec's this script.
+#
+# This script:
+#   1. Launches per-profile background gateways (HERMES_PROFILES env var)
+#   2. Starts the default gateway in foreground (keeps the container alive)
+#
+# Replaces the old approach of chaining bash -> tini -g -> deprecated entrypoint.sh
+# which bypassed s6-overlay and caused the SIGTERM crash loop.
+
+set -e
+
+HERMES_BIN="/opt/hermes/.venv/bin/hermes"
+
+# --- Multi-profile gateways (background) ---
+if [ -n "${HERMES_PROFILES:-}" ]; then
+    echo "[start-hermes] Launching per-profile gateways: ${HERMES_PROFILES}"
+    IFS=',' read -ra PROFILES <<< "${HERMES_PROFILES}"
+    for profile in "${PROFILES[@]}"; do
+        profile="$(echo "${profile}" | xargs)"  # trim whitespace
+        [ -z "${profile}" ] && continue
+        echo "[start-hermes]  -> background gateway for profile '${profile}'"
+        # No gosu/s6-setuidgid needed — we're already running as the hermes user
+        # (main-wrapper.sh drops privileges before exec'ing this script).
+        nohup "${HERMES_BIN}" --profile "${profile}" gateway run \
+            >> "/opt/data/logs/gateway-${profile}.log" 2>&1 &
+    done
+    echo "[start-hermes] All profile gateways launched"
+fi
+
+# --- Default gateway (foreground — keeps container alive) ---
+echo "[start-hermes] Starting default gateway (foreground)"
+exec "${HERMES_BIN}" gateway run