chore: move pm2-self-heal.sh into scripts/

All companion scripts now live under scripts/ for a single, discoverable location.
2026-07-02 20:36:37 +00:00
parent bb20637b32
commit 9101026a0d
1 changed files with 4 additions and 3 deletions
@@ -0,0 +1,69 @@
+#!/bin/bash
+# pm2-self-heal — hourly PM2 process check
+# Part of the pm2-self-heal prose contract
+# Only sends Zulip DM when action is taken or escalation needed
+# Field positions (awk -F'│'): $7=pid $8=uptime $9=restarts $10=status
+
+ZULIP_BOT="abiba-bot@chat.sysloggh.net"
+ZULIP_KEY="cKTDMZAPW08dk3zl05sStzO7HRztzyn8"
+ZULIP_SITE="https://chat.sysloggh.net"
+OWNER_ID=9
+LOG="/tmp/pm2-self-heal.log"
+
+send_alert() {
+    local subject="$1"
+    local body="$2"
+    curl -s -X POST "$ZULIP_SITE/api/v1/messages" \
+        -u "$ZULIP_BOT:$ZULIP_KEY" \
+        -d "type=stream" \
+        -d "to=agent-hub" \
+        -d "subject=alerts-pm2" \
+        -d "content=$subject\n$body" > /dev/null 2>&1
+    echo "[$(date '+%Y-%m-%d %H:%M:%S')] Alert sent to #agent-hub > alerts-pm2" >> "$LOG"
+}
+
+# Log-only mode: replaced by prose contract pm2-self-heal.prose.md
+# Only sends DM on actual failure (status != online), not just high restarts
+# This prevents the process from receiving alerts about itself
+
+# Parse PM2 status (--no-color to avoid ANSI escape codes in awk columns)
+STATUS=$(pm2 status --no-color 2>/dev/null)
+
+ALERTS=""
+
+# Check abiba-telegram (safe to auto-restart)
+TEL_LINE=$(echo "$STATUS" | grep "abiba-telegram")
+TEL_STATUS=$(echo "$TEL_LINE" | awk -F'│' '{print $10}' | xargs)
+TEL_RESTARTS=$(echo "$TEL_LINE" | awk -F'│' '{print $9}' | xargs)
+
+if [ "$TEL_STATUS" != "online" ]; then
+    pm2 restart abiba-telegram > /dev/null 2>&1
+    sleep 3
+    TEL_LINE2=$(pm2 status --no-color 2>/dev/null | grep "abiba-telegram")
+    TEL_STATUS2=$(echo "$TEL_LINE2" | awk -F'│' '{print $10}' | xargs)
+    if [ "$TEL_STATUS2" = "online" ]; then
+        ALERTS="${ALERTS}⚠️ abiba-telegram was **$TEL_STATUS** → restarted to online\n"
+    else
+        ALERTS="${ALERTS}🚨 abiba-telegram **failed restart** (was $TEL_STATUS, still $TEL_STATUS2)\n"
+    fi
+fi
+
+# Check abiba-zulip (read-only — never restart)
+ZUL_LINE=$(echo "$STATUS" | grep "abiba-zulip")
+ZUL_STATUS=$(echo "$ZUL_LINE" | awk -F'│' '{print $10}' | xargs)
+ZUL_RESTARTS=$(echo "$ZUL_LINE" | awk -F'│' '{print $9}' | xargs)
+
+if [ "$ZUL_STATUS" != "online" ]; then
+    ALERTS="${ALERTS}🚨 **abiba-zulip is $ZUL_STATUS** — needs investigation!\n"
+    ALERTS="${ALERTS}   NOT auto-restarting (runs this contract)\n"
+elif [ "$ZUL_RESTARTS" -gt 30 ] 2>/dev/null; then
+    ALERTS="${ALERTS}⚠️ abiba-zulip has **$ZUL_RESTARTS restarts** — may need attention\n"
+fi
+
+# Log check
+echo "[$(date '+%Y-%m-%d %H:%M:%S')] tel=$TEL_STATUS zul=$ZUL_STATUS alerts=${ALERTS:+yes}" >> "$LOG"
+
+# Only DM when there's something to report
+if [ -n "$ALERTS" ]; then
+    send_alert "**PM2 Self-Heal — $(date '+%H:%M UTC')**" "$ALERTS"
+fi