Реализованы задачи бэклога 1-5 (1я не до конца)

ops-monitoring/instructions.md

@@ -0,0 +1,17 @@
+# han-vm-metrics.sh
+Установка на ВМ
+sudo mkdir -p /opt/han-chat/ops
+Cкопировать han-vm-metrics.sh на сервер, затем:
+sudo chmod +x /opt/han-chat/ops/han-vm-metrics.sh
+sudo /opt/han-chat/ops/han-vm-metrics.sh
+JSON:
+
+sudo /opt/han-chat/ops/han-vm-metrics.sh --json
+Cron каждые 5 минут + лог + ненулевой exit при проблемах:
+
+echo '*/5 * * * * root /opt/han-chat/ops/han-vm-metrics.sh --alert --log /var/log/han-vm-metrics.log' | sudo tee /etc/cron.d/han-vm-metrics
+Пороги можно менять env: DISK_WARN_PCT, DISK_CRIT_PCT, MEM_WARN_PCT, CERT_WARN_DAYS, SSH_FAIL_WARN.
+
+# diagnose-han-chat.sh
+
+

ops-monitoring/message_lost_diagnostic.md

@@ -0,0 +1,36 @@
+cd /opt/han-chat/backend
+
+echo "=== CONTAINERS ==="
+docker compose --env-file .env ps
+
+echo "=== BITRIX STATUS ==="
+docker compose --env-file .env exec -T api-backend python - <<'PY'
+import json
+import os
+import urllib.request
+
+request = urllib.request.Request(
+    os.environ["BITRIX_LOCAL_APP_BASE_URL"] + "/internal/openlines/v1/status",
+    headers={
+        "Authorization": "Bearer "
+        + os.environ["BITRIX_LOCAL_APP_INTERNAL_TOKEN"]
+    },
+)
+print(json.dumps(
+    json.load(urllib.request.urlopen(request, timeout=10)),
+    ensure_ascii=False,
+    indent=2,
+))
+PY
+
+echo "=== BITRIX LOGS ==="
+docker compose --env-file .env logs \
+  --since=15m --timestamps bitrix-local-app
+
+echo "=== API LOGS ==="
+docker compose --env-file .env logs \
+  --since=15m --timestamps api-backend
+
+echo "=== NGINX LOGS ==="
+docker compose --env-file .env logs \
+  --since=15m --timestamps nginx