reworked it all

2026-09-18 18:13:05 +02:00
parent fcd5aaeb6c
commit d7ef929160
8 changed files with 1199 additions and 254 deletions
@@ -0,0 +1,53 @@
+#!/bin/bash
+# slskd's stock healthcheck only asks "is the web server up?". slskd can sit
+# there for days, web UI fine, logged out of Soulseek, and Docker calls it
+# healthy, so autoheal never acts. This check asks the question that matters:
+#
+#   web API dead                          -> unhealthy (restart)
+#   logged in to Soulseek                 -> healthy
+#   logged out, gluetun unreachable       -> unhealthy: gluetun was restarted and this
+#                                            container is stuck in its old, dead network
+#                                            namespace. Only a restart re-attaches it.
+#   logged out, VPN tunnel down           -> healthy: nothing slskd can do, gluetun heals
+#                                            itself and slskd's VPN integration reconnects.
+#   logged out, VPN fine                  -> ask slskd to reconnect, report unhealthy.
+#                                            Docker needs several failures in a row before it
+#                                            flags the container, so a reconnect that works
+#                                            never causes a restart.
+
+PORT="${SLSKD_HTTP_PORT:-5030}"
+KEY="${SLSKD_API_KEY##*;}"            # tolerate the "role=..;cidr=..;key" form
+GLUETUN="${SLSKD_VPN_GLUETUN_URL:-http://localhost:8000}"
+API="http://localhost:${PORT}"
+
+get() { wget -q -T 5 -t 1 -O - "$@"; }
+
+get "${API}/health" >/dev/null || { echo "slskd web API is not responding"; exit 1; }
+
+# without an API key we cannot look any deeper; behave like the stock check
+[ -n "$KEY" ] || { echo "ok (SLSKD_API_KEY not set, Soulseek state not checked)"; exit 0; }
+
+state="$(get --header "X-API-Key: ${KEY}" "${API}/api/v0/server")" \
+  || { echo "cannot read Soulseek state from the API (wrong SLSKD_API_KEY?)"; exit 1; }
+
+if jq -e '.isConnected and .isLoggedIn' >/dev/null 2>&1 <<<"$state"; then
+  echo "ok: $(jq -r '.state' <<<"$state")"
+  exit 0
+fi
+
+if [ "${SLSKD_VPN:-false}" = "true" ]; then
+  vpn="$(get --header "X-API-Key: ${SLSKD_VPN_GLUETUN_API_KEY:-}" "${GLUETUN}/v1/publicip/ip")" \
+    || { echo "gluetun control server unreachable: stale network namespace, restart required"; exit 1; }
+  if [ -z "$(jq -r '.public_ip // empty' <<<"$vpn" 2>/dev/null)" ]; then
+    echo "VPN tunnel is down, waiting for gluetun"
+    exit 0
+  fi
+fi
+
+if jq -e '.isConnecting or .isLoggingIn' >/dev/null 2>&1 <<<"$state"; then
+  echo "Soulseek login in progress"
+else
+  get --method=PUT --body-data='' --header "X-API-Key: ${KEY}" "${API}/api/v0/server" >/dev/null
+  echo "logged out of Soulseek ($(jq -r '.state' <<<"$state")), reconnect requested"
+fi
+exit 1