1 files changed, 129 insertions, 0 deletions
diff --git a/scripts/health-check b/scripts/health-check
new file mode 100755
index 0000000..b1c34d0
--- /dev/null
+++ b/scripts/health-check
@@ -0,0 +1,129 @@
+#!/bin/bash
+#
+# Periodic health check for doot.terst.org and its sub-services, with recovery.
+#
+# The failure this exists for: doot itself stays green while a sub-service
+# behind the gateway is dead, so /scout/ returns 502 and nothing anywhere says
+# so. Scout and hawaii were down for three and a half weeks, and claudomator
+# crash-looped 426,000 times, before anyone opened the page and noticed.
+#
+# There is no mail/ntfy/apprise on this host, so "alerting" here means:
+#   * a loud, greppable line in the journal
+#   * a machine-readable status file the dashboard can surface later
+#   * a non-zero exit, which makes the systemd unit go failed and show up in
+#     `systemctl --failed`
+#
+# It also attempts recovery, because the common case (a unit that hit its
+# restart limit and gave up) is fixed by exactly two commands and waiting weeks
+# for a human to run them is the actual problem.
+#
+# Usage:
+#   scripts/health-check [--no-recover]
+
+set -uo pipefail
+
+cd "$(dirname "$0")/.."
+# shellcheck source=scripts/lib/site-checks.sh
+. "$(dirname "$0")/lib/site-checks.sh"
+
+STATUS_FILE="${STATUS_FILE:-${SITE_DIR}/data/health-status.json}"
+recover=1
+[ "${1:-}" = "--no-recover" ] && recover=0
+
+log() { printf '%s %s\n' "$(date -u '+%Y-%m-%dT%H:%M:%SZ')" "$*"; }
+
+rc=0
+recovered=()
+still_broken=()
+
+# ── binaries ──────────────────────────────────────────────────────────────────
+check_binaries; bin_rc=$?
+if [ $bin_rc -ne 0 ]; then
+    rc=1
+    if [ $recover -eq 1 ]; then
+        # A lost execute bit is recoverable in place and is the known failure
+        # mode here, so fix it rather than just reporting it.
+        for f in "${SITE_BINARIES[@]}"; do
+            if [ -f "$f" ] && [ ! -x "$f" ]; then
+                log "HEALTH recovering: chmod +x $f"
+                chmod +x "$f" && recovered+=("chmod +x $f")
+            fi
+        done
+    fi
+fi
+
+# ── services ──────────────────────────────────────────────────────────────────
+# Called directly, NOT in a command substitution: check_services sets
+# FAILED_SERVICES, and a subshell would populate the array then throw it away,
+# leaving the recovery loop below with nothing to do.
+check_services; svc_rc=$?
+if [ $svc_rc -ne 0 ]; then
+    rc=1
+    if [ $recover -eq 1 ]; then
+        for s in "${FAILED_SERVICES[@]}"; do
+            log "HEALTH recovering: restarting $s"
+            systemctl reset-failed "$s" 2>/dev/null || true
+            if systemctl start "$s" 2>/dev/null; then
+                sleep 3
+                if [ "$(systemctl is-active "$s" 2>/dev/null || true)" = "active" ]; then
+                    log "HEALTH recovered: $s is active"
+                    recovered+=("restarted $s")
+                else
+                    log "HEALTH ALERT: $s still not active after restart"
+                    still_broken+=("$s")
+                fi
+            else
+                log "HEALTH ALERT: failed to start $s"
+                still_broken+=("$s")
+            fi
+        done
+    fi
+fi
+
+# ── routes, re-checked after any recovery ─────────────────────────────────────
+check_routes; route_rc=$?
+[ $route_rc -ne 0 ] && rc=1
+
+# A recovered site is healthy now even though it was not a moment ago. Re-run
+# the checks so the final verdict describes the current state, not the state we
+# walked in on.
+if [ $rc -ne 0 ] && [ ${#recovered[@]} -gt 0 ]; then
+    echo "==> Re-checking after recovery..."
+    rc=0
+    check_binaries >/dev/null || rc=1
+    check_services >/dev/null || rc=1
+    check_routes   >/dev/null || rc=1
+fi
+
+# ── status file ───────────────────────────────────────────────────────────────
+mkdir -p "$(dirname "$STATUS_FILE")" 2>/dev/null || true
+{
+    printf '{\n'
+    printf '  "checked_at": "%s",\n' "$(date -u '+%Y-%m-%dT%H:%M:%SZ')"
+    printf '  "healthy": %s,\n' "$([ $rc -eq 0 ] && echo true || echo false)"
+    printf '  "recovered": ['
+    for i in "${!recovered[@]}"; do
+        [ "$i" -gt 0 ] && printf ', '
+        printf '"%s"' "${recovered[$i]}"
+    done
+    printf '],\n'
+    printf '  "still_broken": ['
+    for i in "${!still_broken[@]}"; do
+        [ "$i" -gt 0 ] && printf ', '
+        printf '"%s"' "${still_broken[$i]}"
+    done
+    printf ']\n}\n'
+} > "$STATUS_FILE" 2>/dev/null || log "HEALTH warn: could not write $STATUS_FILE"
+
+if [ $rc -eq 0 ]; then
+    if [ ${#recovered[@]} -gt 0 ]; then
+        log "HEALTH ALERT recovered: ${recovered[*]}"
+        # Deliberately non-zero is NOT used here: the site is healthy now. The
+        # ALERT line in the journal is the durable record that something had
+        # broken and was silently fixed.
+    fi
+    exit 0
+fi
+
+log "HEALTH ALERT: doot.terst.org is unhealthy; still broken: ${still_broken[*]:-see checks above}"
+exit 1