Fix traffic map zoom and add paginated history with local city GeoIP

README.md

@@ -32,7 +32,7 @@ ssh root@192.168.0.10
 
 ```bash
 apt-get update
-apt-get install -y curl ca-certificates tar smartmontools iproute2 iputils-ping
+apt-get install -y curl ca-certificates tar smartmontools iproute2 iputils-ping ethtool
 
 cd /tmp
 curl -fL \
@@ -123,6 +123,11 @@ ss -lntp | grep 9105
 - изменение критичных SMART-счётчиков, результаты self-test и исчезновение дисков;
 - realtime read/write IOPS, MB/s, latency, utilization и глубину очереди каждого диска;
 - недельную историю IOPS/utilization и алерты при устойчивом I/O-давлении;
+- вероятный источник I/O: VM/LXC, процесс хоста или активная backup/snapshot/migration-задача;
+- отдельные пороги HDD, SATA SSD и NVMe с исключениями по имени или серийному номеру;
+- недельные baseline-аномалии IOPS, latency, температуры, RAM, ZFS и длительности backup;
+- корреляцию связанных событий в одну причинно-следственную цепочку;
+- время первого появления и последнего наблюдения каждого уведомления;
 - автоматический короткий SMART self-test раз в неделю для дисков без свежего теста;
 - datasets, vdev-классы, ошибки read/write/checksum, scrub и ARC ZFS;
 - доступность шлюза, DNS и интернета, packet loss, latency и внешний IP;
@@ -317,6 +322,78 @@ apcaccess status
 - `GET /api/events` — поток метрик SSE с интервалом две секунды.
 - `GET/POST/PUT/DELETE /api/services` — управление проверками сервисов.
 - `GET /api/services/history` — семидневная история доступности и отклика.
+- `GET/PUT/DELETE /api/settings/maintenance` — состояние, запуск и досрочное завершение плановых работ.
+- `GET/DELETE /api/agents` — подключённые гостевые агенты.
+- `POST /api/agents/enrollment-token` — одноразовый токен регистрации на 15 минут.
+
+## Maintenance-режим
+
+Во вкладке `Настройки → Maintenance` можно на заданное время отключить все
+алерты либо выбрать конкретные сервисы и VM/LXC. Подавленные события не
+отправляются по почте и не отображаются как активные, но сохраняются в истории
+с причиной плановых работ. После окончания окна обычный мониторинг включается
+автоматически.
+
+## Агенты VM и LXC
+
+Read-only агент показывает состояние Linux внутри VM/LXC: CPU, load average,
+память, корневой раздел, uptime, ОС, ядро, IP-адреса, systemd-службы, доступные
+APT-обновления и необходимость перезагрузки. Для Docker отображаются контейнеры,
+health-check, число перезапусков, CPU и память. Агент сам подключается к Dashboard
+каждые 10 секунд; открывать входящий порт внутри гостевой системы не нужно.
+
+В подробностях агента systemd-службы разделяются на системные, установленные
+дополнительно и локальные unit-файлы. Для каждой службы показываются пакет и путь
+unit-файла, время запуска, число перезапусков, последний exit code, память и
+накопленное CPU-время, когда соответствующий accounting доступен в systemd.
+
+Расширенная диагностика агента включает последние сообщения проблемных служб,
+`Requires`/`After`, PID, команду запуска и слушающие порты; выявляет частые
+рестарты, OOM-kill и процессы в D-state. Отдельно отображаются top процессов по
+CPU и RAM с накопленным I/O, swap, PSI pressure, все постоянные файловые системы,
+их заполнение и использование inode.
+
+Панель «Диагностика homelab» и карта сопоставляют известные IP и порты с VM/LXC,
+агентом, systemd-службой или Docker-контейнером и настроенной HTTP/TCP-проверкой.
+Связи по PID и порту считаются подтверждёнными; совпадения только по названию
+помечаются как предположение.
+
+Для сложных reverse proxy и Docker-сетей в управлении сервисами можно сохранить
+ручную связь `сервис → агент/VMID → systemd/Docker/процесс → порт`. Она имеет
+приоритет над автоматическим определением и используется для группировки
+связанных уведомлений по первопричине.
+
+Dashboard хранит семь дней истории CPU, RAM, swap, PSI и файловых систем каждого
+агента. Из подробностей агента доступны только заранее разрешённые действия:
+перезапуск известной systemd-службы или Docker-контейнера, `reset-failed` и
+обновление списка пакетов. Агент не принимает произвольные shell-команды; каждое
+действие требует подтверждения в браузере и сохраняется в журнале управления.
+
+Откройте `Настройки → Агенты`, укажите адрес Dashboard, доступный из VM/LXC, и
+VMID. Кнопка создаст готовую команду установки. Одноразовый токен действует 15
+минут и после регистрации заменяется индивидуальным секретом агента.
+
+После однократной установки агент обновляется автоматически вслед за Dashboard.
+Центральный сервер отдаёт агенту собственный бинарник и SHA-256; агент проверяет
+контрольную сумму, атомарно заменяет файл и перезапускается через systemd. Если
+агент был удалён из Dashboard, повторная команда с новым токеном автоматически
+выполнит новую регистрацию.
+
+В первой версии агент не выполняет команды и не перезапускает службы или
+контейнеры. Для чтения Docker ему требуется доступ к `/var/run/docker.sock`,
+поэтому служба устанавливается от root. Сам Dashboard пока не имеет
+авторизации: используйте локальную сеть или HTTPS через доверенный reverse
+proxy и не публикуйте агентские API напрямую в интернет.
+
+Полностью удалить агент из VM/LXC:
+
+```bash
+curl -fsSL https://git.myown.center/maxim/ProxmoxDash/raw/branch/main/scripts/uninstall-agent.sh | sh
+```
+
+Оформление, пороги, почта и обновления Dashboard находятся в обычных настройках.
+Рабочие инструменты — сервисы, агенты, плановые работы и UPS-сценарий — вынесены
+в отдельный раздел `Управление` в шапке Dashboard.
 
 ## Сборка
 
@@ -324,3 +401,267 @@ apcaccess status
 go test ./...
 GOOS=linux GOARCH=amd64 CGO_ENABLED=0 go build -o proxmox-cpu-dashboard .
 ```
+
+## Сетевые ошибки и температура CPU (v0.19.3)
+
+RX/TX drops отображаются отдельно как информационные счётчики. Их рост сам по
+себе не вызывает аварийный алерт: в том числе LLDP на Linux bridge. Настройки
+Keenetic, LLDP и group_fwd_mask менять не требуется. Для VM учитываются tap,
+для LXC — veth; fwbr/fwpr/fwln остаются в группе интерфейсов хоста.
+
+Новые rx_errors/tx_errors, CRC/frame/FIFO/missed, carrier/link-down вызывают
+критический алерт. Sysfs позволяет отделить rx_missed_errors от RX drops,
+которые в /proc/net/dev объединены. Для Atlantic дополнительно читаются
+InErrors, InDroppedDma, AllocFails, SkbAllocFails и Restarts через ethtool -S.
+Установите `ethtool` на существующем хосте для этой дополнительной диагностики.
+При отсутствии утилиты остаются стандартные счётчики sysfs. Счётчики ошибок
+могут пересекаться: их сумма — прирост счётчиков, а не число уникальных пакетов.
+После перезапуска и сброса счётчиков старые значения не создают новые алерты.
+
+Карточка CPU и новые точки истории показывают максимум доступных датчиков CPU,
+а не среднее Tctl/Tdie/CCD или ядер. На AMD Tctl может включать управляющее
+смещение; подписи и значения всех датчиков доступны в подробностях CPU.
+История снимается раз в минуту, а на диапазоне 7 дней усредняется по 10 минутам,
+поэтому короткие пики между измерениями не гарантированно попадут на график.
+Старые точки до обновления остаются средними: исходные значения датчиков в них
+не сохранены. Масштаб графика расширяется для значений выше 100 °C.
+
+Релиз Linux amd64 собирается с номером версии и без CGO:
+
+```bash
+./scripts/build-release.sh v0.19.3
+```
+
+Скрипт запускает тесты и создаёт в dist бинарник, SHA-256 и установочный архив,
+совместимые со встроенным обновлением из Gitea Releases.
+
+## Карта трафика NPM + CrowdSec (v0.20.0)
+
+С v0.20.1 страница помещается в высоту окна: карта и лента в центре,
+счётчики сверху, график и рейтинги снизу. На телефоне доступны вкладки
+«Карта / События / Статистика». Последние 100 событий листаются по страницам;
+нажатие на строку открывает полные подробности.
+
+Откройте **Настройки → Карта трафика**, включите страницу и выберите
+агент VM/LXC, где установлены Nginx Proxy Manager и CrowdSec. Например,
+`nginxproxymanager · VMID 102`. Необязательно выберите страну сервера для
+конечной точки линий на карте. Сохраните настройки: в шапке появится ссылка
+«Карта трафика», страница также доступна по `/traffic`.
+
+Функция **по умолчанию выключена**. Только выбранный агент получает команду
+включить сбор. При выключении или смене источника старый агент останавливает
+сбор после следующего успешного обычного отчёта; сервер сразу прекращает
+приём его событий. Выключенная страница и её API недоступны. Это глобальная
+настройка экземпляра Dashboard. Карта не создаёт общих алертов или писем.
+
+Агент автоматически обновляется вместе с Dashboard; для карты требуется
+v0.20.0 или новее. Он читает стандартные NPM access-логи из
+`/opt/npm/data/logs/*_access.log`, включая несжатые файлы ротации. Другой каталог
+задаётся переменной окружения службы `DASHBOARD_NPM_LOG_DIR`; значение `off`
+полностью запрещает сбор на конкретном агенте. Порт CrowdSec наружу открывать
+и новые API-ключи создавать не нужно: используется локальная команда
+`cscli alerts list --since 24h --limit 50 -o json` с существующими учётными
+данными машины. Права на логи и запуск cscli нужны службе агента.
+
+- Голубой: все записанные HTTP-запросы, включая обычные и локальные обращения.
+- Оранжевый: реальные (не simulated) срабатывания сценариев CrowdSec.
+- Розовый: решения CrowdSec, например ban или captcha. Это **не** счётчик
+  фактически отброшенных пакетов и не список действующих сейчас банов.
+- HTTP 401/403/502 сами по себе не считаются атакой или блокировкой.
+
+Карта показывает страны источников, живую ленту последних 100 событий,
+счётчики за последние 24 часа, уникальные IP HTTP-клиентов, график по минутам
+и средний req/s за последние 60 секунд. Есть фильтры типа события, домена и
+внешних IP, пауза и полный экран. Локальные адреса видны в ленте без страны.
+Все счётчики следуют выбранным фильтрам. Уникальный IP не равен человеку.
+
+Первое включение начинает чтение с конца логов, без импорта старых HTTP-запросов.
+Обычно обновление занимает несколько секунд; Nginx записывает запрос после
+его завершения. Это не карта открытых TCP-соединений. Позиции чтения и очередь
+до 500 событий сохраняются в `traffic-state.json` рядом с конфигом агента;
+повторы после обрыва связи устраняются на сервере. При переполнении очереди
+чтение ждёт отправки. Если за время длительного простоя логи уже сжаты или
+удалены, восстановить эти строки нельзя. Размер очереди чтения и ошибки
+парсинга отображаются на самой странице, без глобальных уведомлений.
+
+CrowdSec опрашивается каждые 15 секунд, до 50 последних alerts за 24 часа;
+при достижении лимита страница предупреждает о возможной неполноте истории.
+Связанный домен берётся из метаданных события, только если он однозначен.
+Новый ban не рисуется как новый запрос. Для наблюдения реально отброшенных
+firewall пакетов нужен отдельный источник: в этой версии его нет.
+
+В SQLite хранится до 24 часов и 200 000 событий; старые строки удаляются при
+приёме новых данных. Данные каждого выбранного агента фильтруются отдельно.
+Query string и fragment URL отбрасываются на агенте и повторно на сервере;
+заголовки, cookie и тела запросов не передаются. IP, домен и путь сохраняются.
+
+GeoIP работает локально: DB-IP Country Lite за октябрь 2026 встроена в бинарник,
+исходящие запросы с IP посетителей не выполняются. Координаты на карте — условные
+точки стран Natural Earth, а не точное местоположение посетителя. Дата базы
+видна внизу карты. Обновление базы требует нового релиза; автоматического
+скачивания нет. Лицензии и происхождение данных: `assets/NOTICE.md`.
+
+Локальный предпросмотр с явно обозначенными искусственными данными:
+
+```bash
+DASHBOARD_TRAFFIC_PREVIEW=1 go test -run '^TestTrafficPreview$' -timeout 30m
+# http://127.0.0.1:19105/traffic
+```
+
+## Сетевая активность TCP/UDP/ICMP (v0.21.0)
+
+В **Настройки → Карта трафика** включите дополнительный сбор TCP/UDP/ICMP.
+Он выполняется только выбранным агентом v0.21.0+; на странице карты появится
+кнопка **TCP / UDP**, открывающая `/network`. Основной выключатель карты
+отключает оба сборщика. Сетевой режим по умолчанию выключен и не создаёт
+общих алертов/писем.
+
+На Debian/Ubuntu агент **сам проверяет и устанавливает conntrack**, когда
+включён сетевой режим. Выполняются `apt-get update` и установка только
+`conntrack` с зависимостями (`--no-install-recommends --no-remove`), без
+обновления всей системы. Установка выполняется от root через отдельную
+systemd-службу, как существующие операции обновления агента, и не требует
+отключать его read-only sandbox. Начатая пакетная операция завершается даже
+при выключении сбора. Ход/ошибка видны в диагностике; повтор после ошибки —
+не чаще раза в 30 минут работы процесса. После перезапуска агента проверка
+выполняется заново. Если conntrack уже установлен, apt-get не запускается.
+
+На других системах, без root или systemd/apt-get, выводится инструкция для
+ручной установки. Для счётчиков CrowdSec требуется доступный `nft`; он
+обычно уже установлен вместе с nftables-bouncer и автоматически не ставится.
+
+Агенту нужны root/CAP_NET_ADMIN в сетевом namespace хоста. Установщик агента
+запускает службу от root. Чтение: `/proc/net/nf_conntrack`, если доступен,
+иначе `conntrack -L -f ipv4/ipv6 -o extended`. Ничего устанавливать на хост
+самого Dashboard не требуется. Firewall, NAT и sysctl сборщик не меняет.
+
+Страница показывает состояния TCP, UDP/ICMP-потоки, обе пары адресов до/после
+NAT (в том числе Docker), локальную GeoIP, топ инициаторов и портов, фильтры,
+поиск и детали потока. Список листается по страницам; переход на следующую
+фиксирует снимок, «К свежим» возвращает live. Для телефона — вкладки.
+
+Это **снимки таблицы примерно каждые 5 секунд**, не полный журнал соединений:
+короткие потоки между снимками могут быть пропущены. До 5 000 записей на
+снимок, 8 MiB вывода команды и таймаут 4 секунды; ограничения/ошибки видны в
+диагностике. Сохраняется только последний снимок каждого агента. Инициатор
+не обязательно внешний клиент: NPM → upstream — отдельный поток. Порт не
+доказывает протокол приложения; UDP ASSURED не означает TCP handshake.
+
+Байты/пакеты доступны только при включённом учёте conntrack для конкретных
+потоков. Это накопленные значения за жизнь потока, а не трафик за 24 часа.
+При отсутствии учёта интерфейс показывает «нет учёта». При необходимости
+администратор может включить `net.netfilter.nf_conntrack_acct=1`; изменение
+применяется к новым потокам и автоматически не выполняется.
+
+Firewall читается раз в 30 секунд командой `nft -j list ruleset`. Поддержаны
+анонимные счётчики непосредственно перед финальным `drop/reject` в таблице
+или цепочке с `crowdsec` в имени. Остальные счётчики не выдаются за блокировки.
+Это сумма пакетов/байтов выбранных правил с момента их создания, независимо
+от фильтров потоков; при пересоздании правил она может уменьшиться.
+Для iptables/ipset-only, именованных счётчиков и правил без счётчиков выводится
+«недоступно», а не ноль. Отброшенный пакет до подтверждения conntrack может
+отсутствовать в таблице потоков. Содержимое пакетов не перехватывается.
+
+## Сетевой слой карты и фильтр мониторинга (v0.22.0)
+
+При включённом сборе TCP/UDP/ICMP переключатель **Сеть на карте** показывает
+текущие потоки отдельным слоем: TCP — зелёный, UDP — розовый, ICMP/ICMPv6 —
+жёлтый. Импульсы означают новый снимок (~5 секунд), не отдельные пакеты или
+новые подключения. Входящие и исходящие потоки имеют разное направление.
+Локальные адреса и потоки без страны учитываются отдельно; при отсутствии
+свежего снимка 25 секунд сетевой слой гаснет. HTTP-статистика за 24 часа с
+текущими потоками не складывается. Фильтры домена и HTTP/CrowdSec относятся
+только к HTTP-слою; фильтры внешних IP и мониторинга действуют на оба слоя.
+
+В **Настройки → Карта трафика → Правила мониторинга** задайте по одному правилу
+на строку: `IP | домен | префикс пути`. IP точный, включая IPv6; домен и путь
+необязательны. Пример: `192.168.0.10` или `192.168.0.10 | example.org | /health`.
+Для сетевых потоков применяются только правила без домена/пути, к IP инициатора.
+При первом обновлении добавляется правило `192.168.0.10`; его можно изменить
+или полностью удалить. Сам фильтр по умолчанию выключен.
+
+**Скрыть мониторинг** на карте и `/network` исключает совпадения из отображения
+и соответствующей статистики. Настройка переключателя сохраняется в браузере.
+HTTP-проверки остаются в истории и возвращаются при выключении фильтра;
+новые правила сразу применяются и к старым записям. Срабатывания и решения
+CrowdSec, а также общие счётчики firewall, никогда не скрываются этим фильтром.
+Сетевые потоки по-прежнему хранятся только последним снимком, без истории.
+
+## Alpine LXC и Docker NPM/NPM+ (v0.23.0)
+
+Установщик агента поддерживает Linux **x86_64/amd64** с systemd или OpenRC
+(Alpine LXC). Для Alpine команда из настроек сначала устанавливает curl и
+CA-сертификаты, если curl отсутствует. Бинарник статический, без glibc;
+скачивание проверяется по SHA-256. OpenRC-служба включается в default runlevel
+и использует supervise-daemon: перезапускает агент после ошибки и обновления.
+Команды: `rc-service proxmox-dashboard-agent status/restart` (выберите одно
+действие). Журнал: `/var/log/proxmox-dashboard-agent.log`; его ротацию настройте
+средствами ОС. Удаление — штатным `scripts/uninstall-agent.sh`.
+
+Обновление пакетов ОС и управление systemd-службами из интерфейса остаются
+функциями Debian/Ubuntu/systemd; этот релиз добавляет установку и работу агента
+на OpenRC, а не эмуляцию systemd. Включённый сетевой сбор на Alpine ставит
+`conntrack-tools` через `apk add --no-cache`. Ограничения CAP_NET_ADMIN и
+сетевого namespace LXC сохраняются; никаких изменений конфигурации Proxmox,
+privileged/nesting, firewall или sysctl агент не делает.
+
+После выбора агента Docker-хоста и включения карты трафика агент автоматически:
+
+- проверяет стандартные каталоги NPM и NPM+;
+- находит запущенные контейнеры с nginx-proxy-manager/npmplus в имени образа
+  и определяет каталоги логов по mounts `/data`, включая именованные volumes
+  и вложенные bind mounts;
+- читает обычный формат NPM и формат NPM+ `access.log`, включая ротацию;
+- находит единственный контейнер образа `crowdsecurity/crowdsec` и выполняет
+  только `cscli alerts list` через локальный Docker socket. Docker CLI, новый
+  bouncer key и опубликованный LAPI не нужны. Если контейнера нет, используется
+  прежний локальный `cscli`.
+
+Поиск повторяется раз в минуту, поэтому пересоздание контейнеров подхватывается
+автоматически. При нескольких CrowdSec задайте точный контейнер вручную:
+`DASHBOARD_CROWDSEC_CONTAINER=имя` в `/etc/proxmox-dashboard-agent.env` и
+перезапустите агент. Каталог логов можно переопределить переменной
+`DASHBOARD_NPM_LOG_DIR=/путь/к/логам`; `off` выключает сбор трафика этого агента.
+Используется локальный `/var/run/docker.sock`; rootless/удалённые Docker engines
+и логи только в stdout этим обнаружением не поддерживаются.
+
+NPM+ должен действительно писать access-логи: включите `LOGROTATE=true` в его
+Compose и пересоздайте контейнер, если логирование выключено. Агент показывает
+подсказку при отсутствии логов, но не меняет Compose приложений. Это настройка
+[NPM+](https://github.com/ZoeyVid/NPMplus/blob/develop/README.md), а не Dashboard.
+Stream-логи NPM+ не считаются HTTP-запросами; сетевые потоки собираются conntrack.
+Как и раньше, первый запуск чтения начинается с конца существующих логов.
+
+## Интерактивная карта (v0.24.0)
+
+Карта трафика использует ту же настройку `proxmox-theme`, что и основной
+Dashboard. Кнопка солнца/луны меняет тему; выбор сохраняется в браузере.
+Светлая тема распространяется на карту, график, карточки и модальные окна.
+
+Масштаб карты — от 100% до 600%: кнопки +/−, колесо мыши или жест двумя
+пальцами. Увеличенную карту можно перетаскивать; ↺ возвращает весь мир.
+При фокусе на карте доступны клавиши +/−, 0 и стрелки. Наведение подсвечивает
+контур страны и показывает суточные счётчики, а нажатие открывает подробности.
+
+Четыре карточки статистики открывают окна с итогом, объяснением метрики,
+разбивкой по странам и примерами событий. Счётчики стран считаются сервером
+по всей доступной истории за 24 часа с текущими фильтрами. Начиная с v0.25.0
+история загружается целиком по страницам, без ограничения последними 100 событиями. Открытое
+окно фиксирует данные на момент открытия; временная отметка показана внутри.
+Сетевые потоки остаются отдельным текущим снимком, не суточной статистикой.
+
+## Карта и полная история (v0.25.0)
+
+Карта использует векторные границы стран: при зуме 100–600% они перерисовываются,
+а маркеры и подписи сохраняют размер. Это обзорная карта стран, не уличная карта.
+Карточки и окна стран загружают всю сохранённую историю за последние 24 часа
+по 50 записей; фильтры учитываются сервером. В карточке IP показаны все уникальные
+HTTP IP с количеством запросов. Переходы между страницами фиксируют снимок истории.
+
+Для городов откройте настройки карты и нажмите «Установить базу городов».
+Dashboard скачает DB-IP City Lite 2026-10 (~58 МБ сжатая, ~121 МБ на диске),
+проверит контрольную сумму и сохранит `dbip-city.mmdb` рядом с `DASHBOARD_DB_PATH`.
+IP посетителей не отправляются во внешние сервисы. Город и регион отображаются
+в истории и списке IP; местоположение приблизительное и может относиться к VPN
+или провайдеру. Для части IP город неизвестен. База устанавливается отдельно от
+релиза, автоматически каждый месяц не обновляется.

activity.go

@@ -57,7 +57,7 @@ func (c *activityCollector) collect(guests GuestsMetrics) ProxmoxActivity {
 	value := c.value
 	c.mu.RUnlock()
 	c.mu.Lock()
-	if !c.refreshing && time.Since(time.Unix(value.CheckedAt, 0)) > 10*time.Minute {
+	if !c.refreshing && time.Since(time.Unix(value.CheckedAt, 0)) > 15*time.Second {
 		c.refreshing = true
 		go c.refreshWithGuests(guests)
 	}

agent_actions.go

@@ -0,0 +1,346 @@
+package main
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net"
+	"net/http"
+	"os/exec"
+	"path/filepath"
+	"regexp"
+	"strings"
+	"time"
+)
+
+type AgentCommand struct {
+	ID     int64  `json:"id"`
+	Action string `json:"action"`
+	Target string `json:"target,omitempty"`
+}
+
+type AgentActionResult struct {
+	ID      int64  `json:"id"`
+	Success bool   `json:"success"`
+	Message string `json:"message"`
+}
+
+type AgentAction struct {
+	ID          int64  `json:"id"`
+	AgentID     string `json:"agentId"`
+	AgentName   string `json:"agentName"`
+	Action      string `json:"action"`
+	Target      string `json:"target"`
+	RequestedAt int64  `json:"requestedAt"`
+	StartedAt   *int64 `json:"startedAt,omitempty"`
+	CompletedAt *int64 `json:"completedAt,omitempty"`
+	Status      string `json:"status"`
+	Result      string `json:"result"`
+}
+
+var safeUnitName = regexp.MustCompile(`^[A-Za-z0-9_.@:-]+\.service$`)
+var safeContainerName = regexp.MustCompile(`^[A-Za-z0-9_.-]{1,128}$`)
+
+func (s *Store) QueueAgentAction(agentID, action, target string) (AgentAction, error) {
+	action, target = strings.TrimSpace(action), strings.TrimSpace(target)
+	var raw, name string
+	if err := s.db.QueryRow(`SELECT report_json,name FROM agents WHERE id=?`, agentID).Scan(&raw, &name); err != nil {
+		return AgentAction{}, fmt.Errorf("агент не найден")
+	}
+	var report AgentReport
+	_ = json.Unmarshal([]byte(raw), &report)
+	valid := false
+	switch action {
+	case "systemd-restart", "systemd-reset-failed":
+		if safeUnitName.MatchString(target) {
+			for _, service := range report.Services {
+				if service.Name == target {
+					valid = true
+					break
+				}
+			}
+		}
+	case "docker-restart", "docker-check", "docker-update", "docker-remove":
+		if safeContainerName.MatchString(target) {
+			for _, container := range report.Containers {
+				if (container.ID == target || container.Name == target) && (action != "docker-remove" || container.State != "running") {
+					valid = true
+					break
+				}
+			}
+		}
+	case "updates-refresh", "system-update", "system-reboot":
+		valid = target == ""
+	}
+	if !valid {
+		return AgentAction{}, fmt.Errorf("действие или цель не входят в разрешённый список")
+	}
+	now := time.Now().Unix()
+	result, err := s.db.Exec(`INSERT INTO agent_actions(agent_id,action,target,requested_at,status) VALUES(?,?,?,?, 'queued')`, agentID, action, target, now)
+	if err != nil {
+		return AgentAction{}, err
+	}
+	id, _ := result.LastInsertId()
+	return AgentAction{ID: id, AgentID: agentID, AgentName: name, Action: action, Target: target, RequestedAt: now, Status: "queued"}, nil
+}
+
+func (s *Store) DispatchAgentActions(agentID string) ([]AgentCommand, error) {
+	tx, err := s.db.Begin()
+	if err != nil {
+		return nil, err
+	}
+	defer tx.Rollback()
+	// Обновление пакетов и Docker-образов может быть долгим. Не выдаём одну
+	// команду повторно, пока предыдущий запуск ещё имеет шанс завершиться.
+	_, _ = tx.Exec(`UPDATE agent_actions SET status='queued',started_at=NULL WHERE agent_id=? AND status='running' AND started_at<?`, agentID, time.Now().Add(-45*time.Minute).Unix())
+	rows, err := tx.Query(`SELECT id,action,target FROM agent_actions WHERE agent_id=? AND status='queued' ORDER BY id LIMIT 3`, agentID)
+	if err != nil {
+		return nil, err
+	}
+	var commands []AgentCommand
+	for rows.Next() {
+		var c AgentCommand
+		if err = rows.Scan(&c.ID, &c.Action, &c.Target); err != nil {
+			rows.Close()
+			return nil, err
+		}
+		commands = append(commands, c)
+	}
+	rows.Close()
+	now := time.Now().Unix()
+	for _, c := range commands {
+		if _, err = tx.Exec(`UPDATE agent_actions SET status='running',started_at=? WHERE id=?`, now, c.ID); err != nil {
+			return nil, err
+		}
+	}
+	return commands, tx.Commit()
+}
+
+func (s *Store) CompleteAgentActions(agentID string, results []AgentActionResult) {
+	now := time.Now().Unix()
+	for _, result := range results {
+		status := "failed"
+		if result.Success {
+			status = "completed"
+		}
+		message := result.Message
+		if len(message) > 4000 {
+			message = message[:4000]
+		}
+		_, _ = s.db.Exec(`UPDATE agent_actions SET status=?,result=?,completed_at=? WHERE id=? AND agent_id=? AND status='running'`, status, message, now, result.ID, agentID)
+	}
+}
+
+func (s *Store) AgentActions(limit int) ([]AgentAction, error) {
+	if limit < 1 || limit > 200 {
+		limit = 100
+	}
+	rows, err := s.db.Query(`SELECT a.id,a.agent_id,g.name,a.action,a.target,a.requested_at,a.started_at,a.completed_at,a.status,a.result FROM agent_actions a JOIN agents g ON g.id=a.agent_id ORDER BY a.id DESC LIMIT ?`, limit)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	var out []AgentAction
+	for rows.Next() {
+		var v AgentAction
+		if err = rows.Scan(&v.ID, &v.AgentID, &v.AgentName, &v.Action, &v.Target, &v.RequestedAt, &v.StartedAt, &v.CompletedAt, &v.Status, &v.Result); err != nil {
+			return nil, err
+		}
+		out = append(out, v)
+	}
+	return out, rows.Err()
+}
+
+func executeAgentCommand(command AgentCommand) AgentActionResult {
+	result := AgentActionResult{ID: command.ID}
+	var output string
+	switch command.Action {
+	case "systemd-restart":
+		output = runAgentCombinedCommand(30*time.Second, "systemctl", "restart", command.Target)
+	case "systemd-reset-failed":
+		output = runAgentCombinedCommand(15*time.Second, "systemctl", "reset-failed", command.Target)
+	case "docker-restart":
+		output = restartAgentContainer(command.Target)
+	case "docker-update":
+		output = updateAgentContainer(command.Target, true)
+	case "docker-check":
+		output = updateAgentContainer(command.Target, false)
+	case "docker-remove":
+		output = removeAgentContainer(command.Target)
+	case "system-update":
+		output = updateAgentSystem()
+	case "system-reboot":
+		output = scheduleAgentReboot()
+	case "updates-refresh":
+		guestInventory.Lock()
+		guestInventory.value.CollectedAt = time.Time{}
+		guestInventory.Unlock()
+		result.Success = true
+		result.Message = "Проверка обновлений поставлена в очередь"
+		return result
+	default:
+		result.Message = "Команда не разрешена"
+		return result
+	}
+	result.Success = !strings.HasPrefix(output, "ERROR: ")
+	result.Message = strings.TrimSpace(output)
+	if result.Message == "" && result.Success {
+		result.Message = "Выполнено успешно"
+	}
+	return result
+}
+
+func removeAgentContainer(target string) string {
+	transport := &http.Transport{DialContext: func(ctx context.Context, _, _ string) (net.Conn, error) {
+		return (&net.Dialer{}).DialContext(ctx, "unix", "/var/run/docker.sock")
+	}}
+	defer transport.CloseIdleConnections()
+	request, _ := http.NewRequest(http.MethodDelete, "http://docker/containers/"+target+"?v=false&force=false", nil)
+	response, err := (&http.Client{Transport: transport, Timeout: 20 * time.Second}).Do(request)
+	if err != nil {
+		return "ERROR: " + err.Error()
+	}
+	defer response.Body.Close()
+	if response.StatusCode != http.StatusNoContent {
+		message, _ := io.ReadAll(io.LimitReader(response.Body, 2048))
+		return fmt.Sprintf("ERROR: Docker вернул %s: %s", response.Status, strings.TrimSpace(string(message)))
+	}
+	return "Остановленный контейнер удалён; volumes сохранены"
+}
+
+func updateAgentSystem() string {
+	aptGet, err := exec.LookPath("apt-get")
+	if err != nil {
+		return "ERROR: apt-get не найден; обновление поддерживается для Debian/Ubuntu"
+	}
+	if output := runPrivilegedTransient(5*time.Minute, "update-lists", aptGet, "update"); strings.HasPrefix(output, "ERROR: ") {
+		return explainSystemUpdateError(output)
+	}
+	message := runPrivilegedTransient(30*time.Minute, "upgrade", aptGet, "-y", "upgrade")
+	if strings.HasPrefix(message, "ERROR: ") {
+		return explainSystemUpdateError(message)
+	}
+	guestInventory.Lock()
+	guestInventory.value.CollectedAt = time.Time{}
+	guestInventory.Unlock()
+	return "Обновления системы установлены; список пакетов будет обновлён в следующем отчёте агента"
+}
+
+func explainSystemUpdateError(message string) string {
+	if strings.Contains(strings.ToLower(message), "read-only file system") {
+		return "ERROR: файловая система агента доступна только для чтения. Обновите Dashboard и агент до v0.19.2 или новее, затем повторите операцию."
+	}
+	if len(message) > 1800 {
+		message = message[len(message)-1800:]
+	}
+	return message
+}
+
+func runPrivilegedTransient(timeout time.Duration, suffix, name string, args ...string) string {
+	systemdRun, err := exec.LookPath("systemd-run")
+	if err != nil {
+		return "ERROR: systemd-run не найден; невозможно безопасно выйти из read-only sandbox агента"
+	}
+	unit := fmt.Sprintf("proxmox-dashboard-%s-%d", suffix, time.Now().UnixNano())
+	commandArgs := []string{"--quiet", "--wait", "--collect", "--pipe", "--unit=" + unit, "--setenv=DEBIAN_FRONTEND=noninteractive", name}
+	commandArgs = append(commandArgs, args...)
+	return runAgentCombinedCommand(timeout, systemdRun, commandArgs...)
+}
+
+func scheduleAgentReboot() string {
+	systemdRun, err := exec.LookPath("systemd-run")
+	if err != nil {
+		return "ERROR: systemd-run не найден"
+	}
+	systemctl, err := exec.LookPath("systemctl")
+	if err != nil {
+		return "ERROR: systemctl не найден"
+	}
+	unit := fmt.Sprintf("proxmox-dashboard-reboot-%d", time.Now().UnixNano())
+	output := runAgentCombinedCommand(15*time.Second, systemdRun, "--quiet", "--collect", "--unit="+unit, "--on-active=20s", systemctl, "reboot")
+	if strings.HasPrefix(output, "ERROR: ") {
+		return output
+	}
+	return "Перезагрузка запланирована через 20 секунд; кратковременный offline агента ожидаем"
+}
+
+func updateAgentContainer(target string, recreate bool) string {
+	transport := &http.Transport{DialContext: func(ctx context.Context, _, _ string) (net.Conn, error) {
+		return (&net.Dialer{}).DialContext(ctx, "unix", "/var/run/docker.sock")
+	}}
+	defer transport.CloseIdleConnections()
+	client := &http.Client{Transport: transport, Timeout: 10 * time.Second}
+	response, err := client.Get("http://docker/containers/" + target + "/json")
+	if err != nil {
+		return "ERROR: " + err.Error()
+	}
+	defer response.Body.Close()
+	var detail struct {
+		Config struct {
+			Labels map[string]string `json:"Labels"`
+		} `json:"Config"`
+	}
+	if response.StatusCode != http.StatusOK || json.NewDecoder(response.Body).Decode(&detail) != nil {
+		return "ERROR: не удалось получить Compose-конфигурацию контейнера"
+	}
+	labels := detail.Config.Labels
+	service := labels["com.docker.compose.service"]
+	workdir := labels["com.docker.compose.project.working_dir"]
+	files := strings.Split(labels["com.docker.compose.project.config_files"], ",")
+	if service == "" || workdir == "" || len(files) == 0 || !filepath.IsAbs(workdir) || !filepath.IsAbs(files[0]) {
+		return "ERROR: безопасное обновление доступно только для Docker Compose"
+	}
+	if _, err = exec.LookPath("docker"); err != nil {
+		return "ERROR: Docker CLI не найден"
+	}
+	commands := [][]string{{"compose", "-f", files[0], "pull", service}}
+	if recreate {
+		commands = append(commands, []string{"compose", "-f", files[0], "up", "-d", "--no-deps", service})
+	}
+	for _, args := range commands {
+		ctx, cancel := context.WithTimeout(context.Background(), 15*time.Minute)
+		command := exec.CommandContext(ctx, "docker", args...)
+		command.Dir = workdir
+		output, commandErr := command.CombinedOutput()
+		cancel()
+		if commandErr != nil {
+			return "ERROR: " + commandErr.Error() + ": " + strings.TrimSpace(string(output))
+		}
+	}
+	if recreate {
+		return "Образ загружен, Compose-контейнер пересоздан"
+	}
+	return "Проверка завершена: образ загружен; если digest изменился, карточка покажет доступное обновление"
+}
+
+func runAgentCombinedCommand(timeout time.Duration, name string, args ...string) string {
+	ctx, cancel := context.WithTimeout(context.Background(), timeout)
+	defer cancel()
+	output, err := exec.CommandContext(ctx, name, args...).CombinedOutput()
+	message := strings.TrimSpace(string(output))
+	if err != nil {
+		return "ERROR: " + err.Error() + ": " + message
+	}
+	return message
+}
+
+func restartAgentContainer(target string) string {
+	transport := &http.Transport{DialContext: func(ctx context.Context, _, _ string) (net.Conn, error) {
+		return (&net.Dialer{}).DialContext(ctx, "unix", "/var/run/docker.sock")
+	}}
+	defer transport.CloseIdleConnections()
+	client := &http.Client{Transport: transport, Timeout: 35 * time.Second}
+	request, _ := http.NewRequest(http.MethodPost, "http://docker/containers/"+target+"/restart?t=10", bytes.NewReader(nil))
+	response, err := client.Do(request)
+	if err != nil {
+		return "ERROR: " + err.Error()
+	}
+	defer response.Body.Close()
+	body, _ := io.ReadAll(io.LimitReader(response.Body, 4096))
+	if response.StatusCode >= 300 {
+		return "ERROR: Docker вернул " + response.Status + ": " + strings.TrimSpace(string(body))
+	}
+	return "Контейнер перезапущен"
+}

agent_actions_test.go

@@ -0,0 +1,77 @@
+package main
+
+import (
+	"encoding/json"
+	"strings"
+	"testing"
+	"time"
+)
+
+func TestAgentActionAllowlistAndLifecycle(t *testing.T) {
+	store, err := openStore(":memory:")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer store.Close()
+	report, _ := json.Marshal(AgentReport{Services: []AgentService{{Name: "gitea.service"}}, Containers: []AgentContainer{{ID: "abc123", Name: "gitea", State: "running"}, {ID: "old123", Name: "old", State: "exited"}}})
+	_, err = store.db.Exec(`INSERT INTO agents(id,name,secret_hash,enrolled_at,last_seen,report_json) VALUES('a','agent','x',?,?,?)`, time.Now().Unix(), time.Now().Unix(), string(report))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if _, err = store.QueueAgentAction("a", "systemd-restart", "../../bad.service"); err == nil {
+		t.Fatal("unsafe unit accepted")
+	}
+	if _, err = store.QueueAgentAction("a", "docker-update", "gitea"); err != nil {
+		t.Fatalf("known Docker container rejected: %v", err)
+	}
+	if _, err = store.QueueAgentAction("a", "system-update", ""); err != nil {
+		t.Fatalf("system update rejected: %v", err)
+	}
+	if _, err = store.QueueAgentAction("a", "docker-remove", "gitea"); err == nil {
+		t.Fatal("running/unknown-state container accepted for removal")
+	}
+	action, err := store.QueueAgentAction("a", "docker-remove", "old")
+	if err != nil {
+		t.Fatalf("stopped container rejected for removal: %v", err)
+	}
+	commands, err := store.DispatchAgentActions("a")
+	if err != nil || len(commands) != 3 || commands[2].ID != action.ID {
+		t.Fatalf("commands=%#v err=%v", commands, err)
+	}
+	store.CompleteAgentActions("a", []AgentActionResult{{ID: action.ID, Success: true, Message: "ok"}})
+	items, err := store.AgentActions(10)
+	if err != nil || len(items) != 3 || items[0].Status != "completed" {
+		t.Fatalf("items=%#v err=%v", items, err)
+	}
+	if _, err = store.QueueAgentAction("a", "system-reboot", ""); err != nil {
+		t.Fatalf("system reboot rejected: %v", err)
+	}
+	if _, err = store.QueueAgentAction("a", "system-reboot", "now"); err == nil {
+		t.Fatal("system reboot with unexpected target accepted")
+	}
+}
+
+func TestManualServiceLinkGroupsOfflineAlerts(t *testing.T) {
+	metrics := dashboardMetrics{Agents: []ManagedAgent{{ID: "a", Name: "app", VMID: 105, Online: false}}, ServiceLinks: []ServiceLink{{ServiceID: 7, AgentID: "a", VMID: 105}}, Services: ServicesMetrics{Services: []ServiceStatus{{MonitoredService: MonitoredService{ID: 7, Name: "Gitea"}, Endpoints: []ServiceEndpointStatus{{Kind: "local", Up: false}}}}}}
+	alerts := []Alert{{ID: "agent-offline-a-105"}, {ID: "service-7-local"}, {ID: "other"}}
+	grouped := groupLinkedAlerts(metrics, alerts)
+	if len(grouped) != 2 {
+		t.Fatalf("grouped=%#v", grouped)
+	}
+	found := false
+	for _, alert := range grouped {
+		if alert.ID == "group-agent-offline-a-105" {
+			found = true
+		}
+	}
+	if !found {
+		t.Fatalf("group alert missing: %#v", grouped)
+	}
+}
+
+func TestExplainReadOnlySystemUpdateError(t *testing.T) {
+	message := explainSystemUpdateError("ERROR: apt failed: Read-only file system")
+	if !strings.Contains(message, "v0.19.2") {
+		t.Fatalf("read-only failure is not actionable: %s", message)
+	}
+}

agent_diagnostics.go

@@ -0,0 +1,336 @@
+package main
+
+import (
+	"bufio"
+	"encoding/json"
+	"net"
+	"os"
+	"path/filepath"
+	"regexp"
+	"runtime"
+	"sort"
+	"strconv"
+	"strings"
+	"sync"
+	"syscall"
+	"time"
+)
+
+type AgentLog struct {
+	Time    int64  `json:"time"`
+	Message string `json:"message"`
+}
+
+type AgentProcess struct {
+	PID         int     `json:"pid"`
+	Name        string  `json:"name"`
+	State       string  `json:"state"`
+	CPUPercent  float64 `json:"cpuPercent"`
+	CPUCores    float64 `json:"cpuCores"`
+	HostPercent float64 `json:"hostPercent"`
+	MemoryBytes uint64  `json:"memoryBytes"`
+	ReadBytes   uint64  `json:"readBytes"`
+	WriteBytes  uint64  `json:"writeBytes"`
+	Elapsed     int64   `json:"elapsedSeconds"`
+	Command     string  `json:"command"`
+}
+
+type AgentFilesystem struct {
+	Device        string  `json:"device"`
+	Mountpoint    string  `json:"mountpoint"`
+	Type          string  `json:"type"`
+	TotalBytes    uint64  `json:"totalBytes"`
+	UsedBytes     uint64  `json:"usedBytes"`
+	UsedPercent   float64 `json:"usedPercent"`
+	InodesTotal   uint64  `json:"inodesTotal"`
+	InodesUsed    uint64  `json:"inodesUsed"`
+	InodesPercent float64 `json:"inodesPercent"`
+}
+
+type AgentListenPort struct {
+	Protocol string `json:"protocol"`
+	Address  string `json:"address"`
+	Port     int    `json:"port"`
+	PID      int    `json:"pid,omitempty"`
+	Process  string `json:"process,omitempty"`
+}
+
+type AgentPressureValue struct {
+	Avg10  float64 `json:"avg10"`
+	Avg60  float64 `json:"avg60"`
+	Avg300 float64 `json:"avg300"`
+}
+
+type AgentPressure struct {
+	CPU    AgentPressureValue `json:"cpu"`
+	Memory AgentPressureValue `json:"memory"`
+	IO     AgentPressureValue `json:"io"`
+}
+
+var agentOOMCache struct {
+	sync.Mutex
+	value []AgentLog
+	at    time.Time
+}
+
+func compactSystemdExec(value string) string {
+	if pathAt := strings.Index(value, "path="); pathAt >= 0 {
+		value = value[pathAt+5:]
+	}
+	if end := strings.IndexAny(value, " ;}"); end > 0 {
+		value = value[:end]
+	}
+	if len(value) > 240 {
+		value = value[:240]
+	}
+	return strings.TrimSpace(value)
+}
+
+func limitedFields(value string, limit int) []string {
+	fields := strings.Fields(value)
+	if len(fields) > limit {
+		fields = fields[:limit]
+	}
+	return fields
+}
+
+func appendUniqueInt(items []int, value int) []int {
+	for _, item := range items {
+		if item == value {
+			return items
+		}
+	}
+	return append(items, value)
+}
+
+func collectAgentJournal(unit string, limit int, since string) []AgentLog {
+	args := []string{"--no-pager", "-o", "json", "--reverse", "-n", strconv.Itoa(limit), "--since", since}
+	if unit != "" {
+		args = append(args, "-u", unit)
+	}
+	output := runAgentCommand(6*time.Second, "journalctl", args...)
+	result := []AgentLog{}
+	for _, line := range strings.Split(output, "\n") {
+		var entry struct {
+			Message   any    `json:"MESSAGE"`
+			Timestamp string `json:"__REALTIME_TIMESTAMP"`
+		}
+		if json.Unmarshal([]byte(line), &entry) != nil {
+			continue
+		}
+		message, ok := entry.Message.(string)
+		if !ok || strings.TrimSpace(message) == "" {
+			continue
+		}
+		microseconds, _ := strconv.ParseInt(entry.Timestamp, 10, 64)
+		result = append(result, AgentLog{Time: microseconds / 1_000_000, Message: message})
+	}
+	return result
+}
+
+func cachedAgentOOMKills() []AgentLog {
+	agentOOMCache.Lock()
+	defer agentOOMCache.Unlock()
+	if time.Since(agentOOMCache.at) < time.Minute {
+		return agentOOMCache.value
+	}
+	output := runAgentCommand(6*time.Second, "journalctl", "-k", "--since", "24 hours ago", "--reverse", "--no-pager", "-o", "json", "-g", "Out of memory|Killed process")
+	result := []AgentLog{}
+	for _, line := range strings.Split(output, "\n") {
+		var entry struct {
+			Message   any    `json:"MESSAGE"`
+			Timestamp string `json:"__REALTIME_TIMESTAMP"`
+		}
+		if json.Unmarshal([]byte(line), &entry) != nil {
+			continue
+		}
+		message, ok := entry.Message.(string)
+		if !ok {
+			continue
+		}
+		microseconds, _ := strconv.ParseInt(entry.Timestamp, 10, 64)
+		result = append(result, AgentLog{Time: microseconds / 1_000_000, Message: message})
+		if len(result) >= 20 {
+			break
+		}
+	}
+	agentOOMCache.value, agentOOMCache.at = result, time.Now()
+	return result
+}
+
+func collectAgentProcesses() []AgentProcess {
+	result := []AgentProcess{}
+	seen := map[int]bool{}
+	for _, sortBy := range []string{"-pcpu", "-rss"} {
+		output := runAgentCommand(5*time.Second, "ps", "-eo", "pid=,comm=,state=,pcpu=,rss=,etimes=,args=", "--sort="+sortBy)
+		added := 0
+		for _, line := range strings.Split(output, "\n") {
+			fields := strings.Fields(line)
+			if len(fields) < 7 {
+				continue
+			}
+			pid, err := strconv.Atoi(fields[0])
+			if err != nil || seen[pid] {
+				continue
+			}
+			seen[pid] = true
+			cpu, _ := strconv.ParseFloat(fields[3], 64)
+			rss, _ := strconv.ParseUint(fields[4], 10, 64)
+			elapsed, _ := strconv.ParseInt(fields[5], 10, 64)
+			cpuCount := runtime.NumCPU()
+			if cpuCount < 1 {
+				cpuCount = 1
+			}
+			item := AgentProcess{PID: pid, Name: fields[1], State: fields[2], CPUPercent: cpu, CPUCores: cpu / 100, HostPercent: cpu / float64(cpuCount), MemoryBytes: rss * 1024, Elapsed: elapsed, Command: strings.Join(fields[6:], " ")}
+			item.ReadBytes, item.WriteBytes = readAgentProcessIO(pid)
+			result = append(result, item)
+			added++
+			if added >= 12 || len(result) >= 24 {
+				break
+			}
+		}
+	}
+	return result
+}
+
+func readAgentProcessIO(pid int) (uint64, uint64) {
+	data, err := os.ReadFile(filepath.Join("/proc", strconv.Itoa(pid), "io"))
+	if err != nil {
+		return 0, 0
+	}
+	values := map[string]uint64{}
+	for _, line := range strings.Split(string(data), "\n") {
+		fields := strings.Fields(line)
+		if len(fields) != 2 {
+			continue
+		}
+		values[strings.TrimSuffix(fields[0], ":")], _ = strconv.ParseUint(fields[1], 10, 64)
+	}
+	return values["read_bytes"], values["write_bytes"]
+}
+
+func collectAgentFilesystems() []AgentFilesystem {
+	file, err := os.Open("/proc/self/mounts")
+	if err != nil {
+		return nil
+	}
+	defer file.Close()
+	excluded := map[string]bool{"proc": true, "sysfs": true, "devtmpfs": true, "devpts": true, "tmpfs": true, "cgroup": true, "cgroup2": true, "overlay": true, "squashfs": true, "nsfs": true, "tracefs": true, "debugfs": true, "securityfs": true, "pstore": true, "mqueue": true, "hugetlbfs": true, "fusectl": true, "configfs": true, "autofs": true, "rpc_pipefs": true}
+	seen := map[string]bool{}
+	result := []AgentFilesystem{}
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		fields := strings.Fields(scanner.Text())
+		if len(fields) < 3 || excluded[fields[2]] || seen[fields[1]] {
+			continue
+		}
+		mountpoint := strings.ReplaceAll(fields[1], `\040`, " ")
+		var stat syscall.Statfs_t
+		if syscall.Statfs(mountpoint, &stat) != nil || stat.Blocks == 0 {
+			continue
+		}
+		seen[mountpoint] = true
+		total := stat.Blocks * uint64(stat.Bsize)
+		free := stat.Bavail * uint64(stat.Bsize)
+		used := total - free
+		item := AgentFilesystem{Device: fields[0], Mountpoint: mountpoint, Type: fields[2], TotalBytes: total, UsedBytes: used, UsedPercent: float64(used) / float64(total) * 100, InodesTotal: stat.Files}
+		if stat.Files > stat.Ffree {
+			item.InodesUsed = stat.Files - stat.Ffree
+			item.InodesPercent = float64(item.InodesUsed) / float64(stat.Files) * 100
+		}
+		result = append(result, item)
+		if len(result) >= 30 {
+			break
+		}
+	}
+	sort.Slice(result, func(i, j int) bool { return result[i].Mountpoint < result[j].Mountpoint })
+	return result
+}
+
+var ssPIDPattern = regexp.MustCompile(`pid=([0-9]+)`)
+var ssNamePattern = regexp.MustCompile(`users:\(\(\"([^\"]+)\"`)
+
+func collectAgentListenPorts() []AgentListenPort {
+	output := runAgentCommand(5*time.Second, "ss", "-H", "-lntup")
+	result := []AgentListenPort{}
+	seen := map[string]bool{}
+	for _, line := range strings.Split(output, "\n") {
+		fields := strings.Fields(line)
+		if len(fields) < 5 {
+			continue
+		}
+		protocol := strings.ToLower(fields[0])
+		local := ""
+		for _, field := range fields[1:] {
+			if strings.Contains(field, ":") && !strings.Contains(field, "users:") {
+				local = field
+				break
+			}
+		}
+		if local == "" {
+			continue
+		}
+		address, portText, err := net.SplitHostPort(local)
+		if err != nil {
+			idx := strings.LastIndex(local, ":")
+			if idx < 0 {
+				continue
+			}
+			address, portText = local[:idx], local[idx+1:]
+		}
+		port, _ := strconv.Atoi(portText)
+		if port <= 0 {
+			continue
+		}
+		pid := 0
+		if match := ssPIDPattern.FindStringSubmatch(line); len(match) > 1 {
+			pid, _ = strconv.Atoi(match[1])
+		}
+		process := ""
+		if match := ssNamePattern.FindStringSubmatch(line); len(match) > 1 {
+			process = match[1]
+		}
+		key := protocol + "|" + address + "|" + portText + "|" + strconv.Itoa(pid)
+		if seen[key] {
+			continue
+		}
+		seen[key] = true
+		result = append(result, AgentListenPort{Protocol: protocol, Address: address, Port: port, PID: pid, Process: process})
+	}
+	sort.Slice(result, func(i, j int) bool {
+		if result[i].Port == result[j].Port {
+			return result[i].Protocol < result[j].Protocol
+		}
+		return result[i].Port < result[j].Port
+	})
+	return result
+}
+
+func collectAgentPressure() AgentPressure {
+	return AgentPressure{CPU: readPressure("/proc/pressure/cpu"), Memory: readPressure("/proc/pressure/memory"), IO: readPressure("/proc/pressure/io")}
+}
+
+func readPressure(path string) AgentPressureValue {
+	data, err := os.ReadFile(path)
+	if err != nil {
+		return AgentPressureValue{}
+	}
+	line := strings.SplitN(string(data), "\n", 2)[0]
+	value := AgentPressureValue{}
+	for _, field := range strings.Fields(line) {
+		key, raw, ok := strings.Cut(field, "=")
+		if !ok {
+			continue
+		}
+		number, _ := strconv.ParseFloat(raw, 64)
+		switch key {
+		case "avg10":
+			value.Avg10 = number
+		case "avg60":
+			value.Avg60 = number
+		case "avg300":
+			value.Avg300 = number
+		}
+	}
+	return value
+}

agent_installer_test.go

@@ -0,0 +1,82 @@
+package main
+
+import (
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+// Run the real installer in a temporary tree with package/service/download
+// commands stubbed. This must never touch the host's init system or packages.
+func TestAgentInstallerOpenRC(t *testing.T) {
+	for _, init := range []string{"openrc", "systemd"} {
+		t.Run(init, func(t *testing.T) {
+			root := t.TempDir()
+			bin := filepath.Join(root, "bin")
+			os.MkdirAll(bin, 0755)
+			write := func(name, body string) {
+				t.Helper()
+				if err := os.WriteFile(filepath.Join(bin, name), []byte("#!/bin/sh\nset -eu\n"+body), 0755); err != nil {
+					t.Fatal(err)
+				}
+			}
+			write("id", "echo 0\n")
+			write("uname", "echo x86_64\n")
+			hash := strings.Repeat("a", 64)
+			write("curl", `case "$1" in -fsSL) ;; *) exit 4 ;; esac
+if [ "$#" = 2 ]; then printf '%s' '{"browser_download_url":"https://example.test/proxmox-dashboard-linux-amd64"}'; exit; fi
+case "$2" in *.sha256) printf '%s\n' '`+hash+`  proxmox-dashboard-linux-amd64' > "$4" ;; *) printf '#!/bin/sh\nprintf "%%s\\n" "$@" > "$CAPTURE"\n' > "$4" ;; esac
+`)
+			write("sha256sum", "printf '%s\\n' '"+hash+"  binary'\n")
+			for _, name := range []string{"systemctl", "rc-service", "rc-update", "supervise-daemon"} {
+				write(name, `printf '%s %s\n' "$(basename "$0")" "$*" >> "$CALLS"`+"\n")
+			}
+			raw, err := os.ReadFile("scripts/install-agent.sh")
+			if err != nil {
+				t.Fatal(err)
+			}
+			// Redirect every persistent absolute path, including those in generated scripts.
+			s := string(raw)
+			for _, prefix := range []string{"/etc/", "/var/lib/", "/usr/local/", "/run/", "/var/log/"} {
+				s = strings.ReplaceAll(s, prefix, root+prefix)
+			}
+			for _, dir := range []string{"etc/systemd/system", "etc/init.d", "var/log"} {
+				os.MkdirAll(filepath.Join(root, dir), 0755)
+			}
+			if init == "systemd" {
+				os.MkdirAll(filepath.Join(root, "run/systemd/system"), 0755)
+			}
+			script := filepath.Join(root, "install.sh")
+			os.WriteFile(script, []byte(s), 0700)
+			env := append(os.Environ(), "PATH="+bin+":"+os.Getenv("PATH"), "DASHBOARD_URL=https://dashboard.test", "ENROLL_TOKEN=token", "AGENT_NAME=Alpine $(touch should-not-exist)", "VMID=102", "CALLS="+root+"/calls", "CAPTURE="+root+"/args")
+			cmd := exec.Command("sh", script)
+			cmd.Env = env
+			if out, err := cmd.CombinedOutput(); err != nil {
+				t.Fatalf("%v: %s", err, out)
+			}
+			calls, _ := os.ReadFile(root + "/calls")
+			if init == "openrc" {
+				if strings.Contains(string(calls), "systemctl") || !strings.Contains(string(calls), "rc-update add proxmox-dashboard-agent default") || !strings.Contains(string(calls), "rc-service proxmox-dashboard-agent restart") {
+					t.Fatalf("%s", calls)
+				}
+				cmd = exec.Command("sh", root+"/usr/local/sbin/proxmox-dashboard-agent-run")
+				cmd.Env = env
+				if out, err := cmd.CombinedOutput(); err != nil {
+					t.Fatalf("launcher: %v %s", err, out)
+				}
+				args, _ := os.ReadFile(root + "/args")
+				if !strings.Contains(string(args), "Alpine $(touch should-not-exist)\n") {
+					t.Fatalf("name was not passed literally: %s", args)
+				}
+			} else if !strings.Contains(string(calls), "systemctl restart proxmox-dashboard-agent.service") {
+				t.Fatalf("%s", calls)
+			}
+			info, _ := os.Stat(root + "/etc/proxmox-dashboard-agent.env")
+			if info.Mode().Perm() != 0600 {
+				t.Fatalf("credentials permissions: %v", info.Mode())
+			}
+		})
+	}
+}

agent_network.go

@@ -0,0 +1,271 @@
+package main
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net"
+	"net/http"
+	"os"
+	"os/exec"
+	"runtime"
+	"strconv"
+	"strings"
+	"time"
+)
+
+// Bounded command output and deadline keep large conntrack tables from exhausting the agent.
+type networkBuffer struct {
+	bytes.Buffer
+	limit int
+}
+
+func (b *networkBuffer) Write(p []byte) (int, error) {
+	if len(p) > b.limit-b.Len() {
+		return 0, errors.New("output limit exceeded")
+	}
+	return b.Buffer.Write(p)
+}
+func networkCommand(ctx context.Context, name string, args ...string) ([]byte, error) {
+	ctx, cancel := context.WithTimeout(ctx, 4*time.Second)
+	defer cancel()
+	cmd := exec.CommandContext(ctx, name, args...)
+	out := &networkBuffer{limit: 8 << 20}
+	stderr := &networkBuffer{limit: 4096}
+	cmd.Stdout = out
+	cmd.Stderr = stderr
+	if err := cmd.Run(); err != nil {
+		return nil, fmt.Errorf("%s: %v %s", name, err, trafficText(stderr.String(), 240))
+	}
+	return out.Bytes(), nil
+}
+func parseNetworkFlow(line string) (NetworkFlow, bool) {
+	var f NetworkFlow
+	fields := strings.Fields(line)
+	protoIndex := -1
+	for i, v := range fields {
+		if v == "tcp" || v == "udp" || v == "icmp" || v == "icmpv6" {
+			f.Protocol = v
+			protoIndex = i
+			break
+		}
+	}
+	if protoIndex < 0 {
+		return f, false
+	}
+	values := map[string][]string{}
+	for _, v := range fields[protoIndex+1:] {
+		if k, val, ok := strings.Cut(v, "="); ok {
+			values[k] = append(values[k], val)
+		}
+	}
+	get := func(k string, i int) string {
+		if len(values[k]) > i {
+			return values[k][i]
+		}
+		return ""
+	}
+	integer := func(k string, i int) int { n, _ := strconv.Atoi(get(k, i)); return n }
+	number := func(k string, i int) uint64 { n, _ := strconv.ParseUint(get(k, i), 10, 64); return n }
+	f.Source = get("src", 0)
+	f.Destination = get("dst", 0)
+	f.ReplySource = get("src", 1)
+	f.ReplyDestination = get("dst", 1)
+	if net.ParseIP(f.Source) == nil || net.ParseIP(f.Destination) == nil || net.ParseIP(f.ReplySource) == nil || net.ParseIP(f.ReplyDestination) == nil {
+		return f, false
+	}
+	f.SourcePort = integer("sport", 0)
+	f.DestinationPort = integer("dport", 0)
+	f.ReplySourcePort = integer("sport", 1)
+	f.ReplyDestinationPort = integer("dport", 1)
+	f.State = "TRACKED"
+	if f.Protocol == "tcp" && len(fields) > protoIndex+3 && !strings.Contains(fields[protoIndex+3], "=") {
+		f.State = fields[protoIndex+3]
+	}
+	if strings.Contains(line, "[UNREPLIED]") {
+		f.State = "UNREPLIED"
+		if f.Protocol == "tcp" && len(fields) > protoIndex+3 {
+			f.State = fields[protoIndex+3]
+		}
+	}
+	if f.Protocol == "udp" && strings.Contains(line, "[ASSURED]") {
+		f.State = "ASSURED"
+	}
+	f.Accounting = len(values["bytes"]) == 2 && len(values["packets"]) == 2
+	f.Bytes = number("bytes", 0)
+	f.ReplyBytes = number("bytes", 1)
+	f.Packets = number("packets", 0)
+	f.ReplyPackets = number("packets", 1)
+	f.Zone = get("zone", 0)
+	return f, true
+}
+func appendNetworkFlows(snapshot *NetworkSnapshot, raw []byte) {
+	for _, line := range strings.Split(string(raw), "\n") {
+		if strings.TrimSpace(line) == "" {
+			continue
+		}
+		f, ok := parseNetworkFlow(line)
+		if !ok {
+			if strings.Contains(line, "src=") {
+				snapshot.ParseErrors++
+			}
+			continue
+		}
+		if len(snapshot.Flows) >= 5000 {
+			snapshot.Limited = true
+			continue
+		}
+		snapshot.Flows = append(snapshot.Flows, f)
+	}
+}
+
+// Only counters immediately before a terminal drop/reject in a CrowdSec table/chain
+// are reported as blocked packets. General chain and set counters are not summed.
+func parseFirewallCounters(raw []byte) ([]FirewallCounter, error) {
+	var doc struct {
+		NFTables []struct {
+			Rule *struct {
+				Family string                       `json:"family"`
+				Table  string                       `json:"table"`
+				Chain  string                       `json:"chain"`
+				Handle int                          `json:"handle"`
+				Expr   []map[string]json.RawMessage `json:"expr"`
+			} `json:"rule"`
+		} `json:"nftables"`
+	}
+	if err := json.Unmarshal(raw, &doc); err != nil {
+		return nil, err
+	}
+	result := []FirewallCounter{}
+	for _, item := range doc.NFTables {
+		r := item.Rule
+		if r == nil || !strings.Contains(strings.ToLower(r.Table+" "+r.Chain), "crowdsec") {
+			continue
+		}
+		if len(r.Expr) < 2 {
+			continue
+		}
+		last := r.Expr[len(r.Expr)-1]
+		_, drop := last["drop"]
+		_, reject := last["reject"]
+		if !drop && !reject {
+			continue
+		}
+		counter, ok := r.Expr[len(r.Expr)-2]["counter"]
+		if !ok {
+			continue
+		}
+		var c struct {
+			Packets uint64 `json:"packets"`
+			Bytes   uint64 `json:"bytes"`
+		}
+		if json.Unmarshal(counter, &c) != nil || len(counter) == 0 || counter[0] != '{' {
+			continue
+		}
+		result = append(result, FirewallCounter{Name: fmt.Sprintf("%s/%s/%s #%d", r.Family, r.Table, r.Chain, r.Handle), Packets: c.Packets, Bytes: c.Bytes})
+		if len(result) == 128 {
+			break
+		}
+	}
+	return result, nil
+}
+func collectNetwork(ctx context.Context) NetworkSnapshot {
+	s := NetworkSnapshot{At: time.Now().Unix(), Flows: []NetworkFlow{}}
+	if runtime.GOOS != "linux" {
+		s.Error = "Сбор conntrack поддерживается только на Linux"
+		return s
+	}
+	// Proc contains both address families when available. Modern kernels often expose only netlink.
+	for _, path := range []string{"/proc/net/nf_conntrack", "/proc/net/ip_conntrack"} {
+		f, err := os.Open(path)
+		if err != nil {
+			continue
+		}
+		raw, err := io.ReadAll(io.LimitReader(f, (8<<20)+1))
+		f.Close()
+		if err != nil {
+			s.Error = err.Error()
+			return s
+		}
+		if len(raw) > 8<<20 {
+			s.Error = "Таблица conntrack превышает лимит чтения 8 MiB"
+			return s
+		}
+		appendNetworkFlows(&s, raw)
+		return s
+	}
+	for _, family := range []string{"ipv4", "ipv6"} {
+		raw, err := networkCommand(ctx, "conntrack", "-L", "-f", family, "-o", "extended")
+		if err != nil {
+			s.Error += "Conntrack " + family + ": нужен пакет conntrack и права root/CAP_NET_ADMIN. " + err.Error() + "; "
+			continue
+		}
+		appendNetworkFlows(&s, raw)
+	}
+	return s
+}
+func startAgentNetwork(config agentConfig) func() {
+	ctx, cancel := context.WithCancel(context.Background())
+	done := make(chan struct{})
+	go func() {
+		defer close(done)
+		client := &http.Client{Timeout: 10 * time.Second}
+		ticker := time.NewTicker(5 * time.Second)
+		defer ticker.Stop()
+		var firewall []FirewallCounter
+		var firewallAt int64
+		var firewallErr string
+		lastFirewall := time.Time{}
+		for {
+			if ctx.Err() != nil {
+				return
+			}
+			snapshot := NetworkSnapshot{At: time.Now().Unix(), Flows: []NetworkFlow{}}
+			if message := ensureNetworkDependency(); message != "" {
+				snapshot.Error = message
+			} else {
+				snapshot = collectNetwork(ctx)
+			}
+			if time.Since(lastFirewall) >= 30*time.Second {
+				lastFirewall = time.Now()
+				raw, err := networkCommand(ctx, "nft", "-j", "list", "ruleset")
+				firewall = nil
+				firewallAt = 0
+				firewallErr = ""
+				if err == nil {
+					firewall, err = parseFirewallCounters(raw)
+				}
+				if err != nil {
+					firewallErr = "Счётчики nftables недоступны: " + err.Error()
+				} else if len(firewall) == 0 {
+					firewallErr = "В правилах CrowdSec нет поддерживаемых счётчиков перед drop/reject. Это не означает отсутствие блокировок."
+				} else {
+					firewallAt = time.Now().Unix()
+				}
+			}
+			snapshot.Firewall = firewall
+			snapshot.FirewallAt = firewallAt
+			snapshot.FirewallError = firewallErr
+			data, _ := json.Marshal(snapshot)
+			req, err := http.NewRequestWithContext(ctx, "POST", config.Server+"/api/agent/network", bytes.NewReader(data))
+			if err != nil {
+				return
+			}
+			req.Header.Set("Authorization", "Bearer "+config.ID+"."+config.Secret)
+			req.Header.Set("Content-Type", "application/json")
+			if res, err := client.Do(req); err == nil {
+				io.Copy(io.Discard, io.LimitReader(res.Body, 4096))
+				res.Body.Close()
+			}
+			select {
+			case <-ctx.Done():
+				return
+			case <-ticker.C:
+			}
+		}
+	}()
+	return func() { cancel(); <-done }
+}

agent_network_setup.go

@@ -0,0 +1,99 @@
+package main
+
+import (
+	"fmt"
+	"os"
+	"os/exec"
+	"runtime"
+	"strings"
+	"sync"
+	"time"
+)
+
+// Package work runs in a transient systemd unit, as do existing agent update
+// actions. It must not inherit ProtectSystem=strict from the reporting agent.
+// A started package transaction is allowed to finish if collection is disabled.
+type networkDependencyState struct {
+	sync.Mutex
+	running     bool
+	nextAttempt time.Time
+	message     string
+}
+
+var networkDependency networkDependencyState
+
+func (d *networkDependencyState) ensure(now time.Time, present bool, install func() error) string {
+	d.Lock()
+	defer d.Unlock()
+	if present {
+		return ""
+	}
+	if d.running {
+		return "Автоустановка conntrack… Сбор начнётся после установки пакета."
+	}
+	if now.Before(d.nextAttempt) {
+		return d.message + " Повторная попытка не раньше " + d.nextAttempt.Format("15:04:05") + " (время агента)."
+	}
+	d.running = true
+	d.nextAttempt = now.Add(30 * time.Minute)
+	go func() {
+		err := install()
+		d.Lock()
+		defer d.Unlock()
+		d.running = false
+		if err != nil {
+			d.message = "Не удалось установить conntrack: " + trafficText(err.Error(), 400)
+		} else {
+			d.message = "Установка завершена; ожидается появление conntrack в PATH"
+		}
+	}()
+	return "Автоустановка conntrack… Сбор начнётся после установки пакета."
+}
+func ensureNetworkDependency() string {
+	if runtime.GOOS != "linux" {
+		return "Сбор conntrack поддерживается только на Linux"
+	}
+	_, err := exec.LookPath("conntrack")
+	return networkDependency.ensure(time.Now(), err == nil, installNetworkDependency)
+}
+func installNetworkDependency() error {
+	if os.Geteuid() != 0 {
+		return fmt.Errorf("для автоустановки нужны права root")
+	}
+	if apk, err := exec.LookPath("apk"); err == nil {
+		out := runAgentCombinedCommand(10*time.Minute, apk, "add", "--no-cache", "conntrack-tools")
+		if strings.HasPrefix(out, "ERROR: ") {
+			return fmt.Errorf("%s", out)
+		}
+		if _, err := exec.LookPath("conntrack"); err != nil {
+			return fmt.Errorf("apk завершился, но conntrack не найден")
+		}
+		return nil
+	}
+	apt, err := exec.LookPath("apt-get")
+	if err != nil {
+		return fmt.Errorf("автоустановка поддерживается на Debian/Ubuntu с apt-get; установите conntrack вручную")
+	}
+	run := func(suffix string, args ...string) error {
+		out := runPrivilegedTransient(10*time.Minute, suffix, apt, args...)
+		if strings.HasPrefix(out, "ERROR: ") {
+			return fmt.Errorf("%s", explainSystemUpdateError(out))
+		}
+		return nil
+	}
+	return installConntrackPackage(run, func() bool { _, err := exec.LookPath("conntrack"); return err == nil })
+}
+func installConntrackPackage(run func(string, ...string) error, present func() bool) error {
+	// No upgrade, autoremove, firewall changes, or runtime sysctl changes.
+	options := []string{"-o", "DPkg::Lock::Timeout=30", "-o", "Acquire::Retries=1", "-o", "Acquire::http::Timeout=20", "-o", "Acquire::https::Timeout=20"}
+	if err := run("conntrack-lists", append(append([]string{}, options...), "update")...); err != nil {
+		return err
+	}
+	if err := run("conntrack-install", append(append([]string{}, options...), "-y", "--no-install-recommends", "--no-remove", "install", "conntrack")...); err != nil {
+		return err
+	}
+	if !present() {
+		return fmt.Errorf("apt-get завершился, но conntrack не найден в PATH")
+	}
+	return nil
+}

agent_test.go

@@ -0,0 +1,152 @@
+package main
+
+import (
+	"os"
+	"testing"
+	"time"
+)
+
+func TestAgentEnrollmentTokenIsSingleUse(t *testing.T) {
+	store, err := openStore(":memory:")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer store.Close()
+	token, err := store.CreateAgentEnrollmentToken()
+	if err != nil {
+		t.Fatal(err)
+	}
+	credentials, err := store.EnrollAgent(agentEnrollmentRequest{Token: token, Name: "docker-01", Hostname: "vm105", VMID: 105})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if credentials.ID == "" || credentials.Secret == "" {
+		t.Fatal("credentials were not generated")
+	}
+	if _, err = store.EnrollAgent(agentEnrollmentRequest{Token: token, Hostname: "duplicate"}); err == nil {
+		t.Fatal("token was accepted twice")
+	}
+}
+
+func TestCurrentAgentUpdateManifestMatchesExecutable(t *testing.T) {
+	manifest, path, err := currentAgentUpdate()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if manifest.URL != "/api/agent/binary" || len(manifest.SHA256) != 64 {
+		t.Fatalf("unexpected manifest: %#v", manifest)
+	}
+	if _, err = os.Stat(path); err != nil {
+		t.Fatal(err)
+	}
+}
+
+func TestAgentOnlyInstallsNewerVersion(t *testing.T) {
+	if !newerAgentVersion("v0.14.0", "v0.13.0") {
+		t.Fatal("new version was not detected")
+	}
+	if newerAgentVersion("v0.12.0", "v0.13.0") {
+		t.Fatal("downgrade was allowed")
+	}
+	if newerAgentVersion("v0.13.0", "v0.13.0") {
+		t.Fatal("same version was offered")
+	}
+}
+
+func TestShortDockerDigest(t *testing.T) {
+	if got := shortDockerDigest("sha256:1234567890abcdef"); got != "1234567890ab" {
+		t.Fatalf("unexpected short digest: %q", got)
+	}
+}
+
+func TestParseAgentIssues(t *testing.T) {
+	issues := parseAgentIssues(`{"MESSAGE":"disk error","_SYSTEMD_UNIT":"worker.service","__REALTIME_TIMESTAMP":"1722960000000000"}` + "\n" + `{"MESSAGE":"network error","__REALTIME_TIMESTAMP":"1722960001000000"}`)
+	if len(issues) != 2 || issues[0].Unit != "worker.service" || issues[1].Unit != "system" || issues[0].Time != 1722960000 {
+		t.Fatalf("unexpected issues: %#v", issues)
+	}
+}
+
+func TestClassifyAgentService(t *testing.T) {
+	cases := []struct{ path, pkg, priority, want string }{{"/lib/systemd/system/cron.service", "cron", "important", "system"}, {"/lib/systemd/system/jellyfin.service", "jellyfin", "optional", "added"}, {"/etc/systemd/system/my.service", "", "", "local"}, {"/run/systemd/system/transient.service", "", "", "runtime"}}
+	for _, tc := range cases {
+		if got := classifyAgentService(tc.path, tc.pkg, tc.priority); got != tc.want {
+			t.Errorf("%s: got %s want %s", tc.path, got, tc.want)
+		}
+	}
+}
+
+func TestAgentServiceDiagnosticsHelpers(t *testing.T) {
+	if got := compactSystemdExec(`{ path=/usr/bin/example ; argv[]=/usr/bin/example --serve ; }`); got != "/usr/bin/example" {
+		t.Fatalf("unexpected executable: %q", got)
+	}
+	fields := limitedFields("a b c d", 2)
+	if len(fields) != 2 || fields[0] != "a" || fields[1] != "b" {
+		t.Fatalf("unexpected limited fields: %#v", fields)
+	}
+	ports := appendUniqueInt([]int{80}, 80)
+	ports = appendUniqueInt(ports, 443)
+	if len(ports) != 2 || ports[1] != 443 {
+		t.Fatalf("unexpected ports: %#v", ports)
+	}
+}
+
+func TestAgentReportAuthenticationAndOfflineState(t *testing.T) {
+	store, err := openStore(":memory:")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer store.Close()
+	token, _ := store.CreateAgentEnrollmentToken()
+	credentials, _ := store.EnrollAgent(agentEnrollmentRequest{Token: token, Name: "docker", Hostname: "vm", VMID: 101})
+	report := AgentReport{Hostname: "vm", Version: "test", DockerAvailable: true, Containers: []AgentContainer{{ID: "abc", Name: "web", State: "running"}}}
+	if err = store.SaveAgentReport(credentials.ID, "wrong", "127.0.0.1", report); err == nil {
+		t.Fatal("invalid secret accepted")
+	}
+	if err = store.SaveAgentReport(credentials.ID, credentials.Secret, "127.0.0.1", report); err != nil {
+		t.Fatal(err)
+	}
+	agents, err := store.Agents()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(agents) != 1 || !agents[0].Online || len(agents[0].Report.Containers) != 1 {
+		t.Fatalf("unexpected agents: %#v", agents)
+	}
+	_, _ = store.db.Exec(`UPDATE agents SET last_seen=? WHERE id=?`, time.Now().Add(-time.Minute).Unix(), credentials.ID)
+	agents, _ = store.Agents()
+	if agents[0].Online {
+		t.Fatal("stale agent is online")
+	}
+}
+
+func TestAgentProblemsBecomeMaintenanceAwareAlerts(t *testing.T) {
+	metrics := dashboardMetrics{Agents: []ManagedAgent{{ID: "node", Name: "app", VMID: 105, Online: true, Report: AgentReport{
+		Services:   []AgentService{{Name: "postgres.service", State: "failed", SubState: "failed"}},
+		Containers: []AgentContainer{{ID: "dead", Name: "web", State: "exited", Status: "Exited (1)"}}, DockerAvailable: true,
+	}}}}
+	alerts := evaluateAlerts(metrics, defaultThresholds())
+	window := MaintenanceWindow{Active: true, VMIDs: []int{105}}
+	active, planned := splitMaintenanceAlerts(alerts, window)
+	if len(planned) != 2 || len(active) != 0 {
+		t.Fatalf("active=%d planned=%d alerts=%#v", len(active), len(planned), alerts)
+	}
+}
+
+func TestAgentDiagnosticsBecomeAlerts(t *testing.T) {
+	metrics := dashboardMetrics{Agents: []ManagedAgent{{ID: "node", Name: "app", VMID: 105, Online: true, Report: AgentReport{
+		Services:    []AgentService{{Name: "web.service", State: "active", Flapping: true, Restarts: 8, StartedAt: time.Now().Unix()}},
+		Filesystems: []AgentFilesystem{{Mountpoint: "/data", TotalBytes: 1000, UsedBytes: 950, UsedPercent: 95}},
+	}}}}
+	alerts := evaluateAlerts(metrics, defaultThresholds())
+	wanted := map[string]bool{"agent-flapping-node-web.service-105": false, "agent-filesystem-node-/data-105": false}
+	for _, alert := range alerts {
+		if _, ok := wanted[alert.ID]; ok {
+			wanted[alert.ID] = true
+		}
+	}
+	for id, found := range wanted {
+		if !found {
+			t.Fatalf("missing alert %s in %#v", id, alerts)
+		}
+	}
+}

agent_traffic.go

@@ -0,0 +1,420 @@
+package main
+
+import (
+	"bufio"
+	"bytes"
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net"
+	"net/http"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"regexp"
+	"sort"
+	"strconv"
+	"strings"
+	"syscall"
+	"time"
+)
+
+var npmTrafficPattern = regexp.MustCompile(`^\[([^]]+)\] .*? (\d{3}) - ([A-Z]+) (?:https?|HTTP) (\S+) "([^"]*)" \[Client ([^]]+)\]`)
+
+func parseNPMTraffic(line string) (TrafficEvent, bool) {
+	m := npmTrafficPattern.FindStringSubmatch(line)
+	if m == nil {
+		return parseNPMPlusTraffic(line)
+	}
+	ip := net.ParseIP(m[6])
+	if ip == nil {
+		return TrafficEvent{}, false
+	}
+	ts, err := time.Parse("02/Jan/2006:15:04:05 -0700", m[1])
+	if err != nil {
+		return TrafficEvent{}, false
+	}
+	status, _ := strconv.Atoi(m[2])
+	return TrafficEvent{Time: ts.Unix(), Kind: "request", IP: ip.String(), Domain: trafficText(m[4], 253), Method: m[3], Path: trafficPath(m[5]), Status: status}, true
+}
+
+type trafficCursor struct {
+	Offset     int64 `json:"offset"`
+	Generation int64 `json:"generation"`
+	Seen       int64 `json:"seen"`
+}
+type trafficAgentState struct {
+	BacklogBytes int64                    `json:"backlogBytes"`
+	Initialized  bool                     `json:"initialized"`
+	StartedAt    int64                    `json:"startedAt"`
+	Cursors      map[string]trafficCursor `json:"cursors"`
+	Pending      []TrafficEvent           `json:"pending"`
+	ParseErrors  uint64                   `json:"parseErrors"`
+	CrowdSeen    map[string]int64         `json:"crowdSeen"`
+}
+
+func (state *trafficAgentState) readLogs(dirs ...string) (int, error) {
+	state.BacklogBytes = 0
+	var paths []string
+	seenPaths := map[string]bool{}
+	for _, dir := range dirs {
+		for _, pattern := range []string{"*_access.log*", "access.log*"} {
+			matches, err := filepath.Glob(filepath.Join(dir, pattern))
+			if err != nil {
+				return 0, err
+			}
+			for _, path := range matches {
+				if !seenPaths[path] {
+					paths = append(paths, path)
+					seenPaths[path] = true
+				}
+			}
+		}
+	}
+	sort.Strings(paths)
+	files := 0
+	budget := int64(1 << 20)
+	now := time.Now().Unix()
+	var firstErr error
+	for _, path := range paths {
+		if strings.HasSuffix(path, ".gz") {
+			continue
+		}
+		f, err := os.Open(path)
+		if err != nil {
+			firstErr = err
+			continue
+		}
+		info, err := f.Stat()
+		if err != nil || !info.Mode().IsRegular() {
+			f.Close()
+			continue
+		}
+		st, ok := info.Sys().(*syscall.Stat_t)
+		if !ok {
+			f.Close()
+			continue
+		}
+		active := strings.HasSuffix(path, "_access.log") || filepath.Base(path) == "access.log"
+		if active {
+			files++
+		}
+		key := fmt.Sprintf("%d:%d", st.Dev, st.Ino)
+		cursor, known := state.Cursors[key]
+		if !known {
+			if !state.Initialized || !active {
+				cursor.Offset = info.Size()
+			}
+			cursor.Generation = now
+		}
+		cursor.Seen = now
+		if info.Size() < cursor.Offset {
+			cursor.Offset = 0
+			cursor.Generation++
+		}
+		if len(state.Pending) < 400 && budget > 0 {
+			_, err = f.Seek(cursor.Offset, io.SeekStart)
+			if err == nil {
+				reader := bufio.NewReaderSize(io.LimitReader(f, budget), 64<<10)
+				for len(state.Pending) < 400 && budget > 0 {
+					line, readErr := reader.ReadString('\n')
+					// Keep an unfinished line for the next poll. Bound malformed huge lines.
+					if readErr != nil {
+						if len(line) >= 64<<10 {
+							cursor.Offset += int64(len(line))
+							state.ParseErrors++
+						}
+						break
+					}
+					offset := cursor.Offset
+					cursor.Offset += int64(len(line))
+					budget -= int64(len(line))
+					if len(line) > 64<<10 {
+						state.ParseErrors++
+						continue
+					}
+					e, ok := parseNPMTraffic(line)
+					if !ok {
+						state.ParseErrors++
+						continue
+					}
+					if e.Time < now-86400 {
+						continue
+					}
+					e.ID = fmt.Sprintf("npm:%s:%d:%d", key, cursor.Generation, offset)
+					state.Pending = append(state.Pending, e)
+				}
+			} else {
+				firstErr = err
+			}
+		}
+		if info.Size() > cursor.Offset {
+			state.BacklogBytes += info.Size() - cursor.Offset
+		}
+		state.Cursors[key] = cursor
+		f.Close()
+	}
+	for key, cursor := range state.Cursors {
+		if cursor.Seen < now-7*86400 {
+			delete(state.Cursors, key)
+		}
+	}
+	if files > 0 {
+		state.Initialized = true
+	}
+	if firstErr != nil {
+		return files, errors.New("Не удалось прочитать часть access-логов NPM")
+	}
+	if files == 0 {
+		return files, errors.New("Access-логи NPM не найдены")
+	}
+	return files, nil
+}
+
+type crowdTrafficAlert struct {
+	ID        int64  `json:"id"`
+	UUID      string `json:"uuid"`
+	CreatedAt string `json:"created_at"`
+	Scenario  string `json:"scenario"`
+	Simulated bool   `json:"simulated"`
+	Source    struct {
+		IP string `json:"ip"`
+	} `json:"source"`
+	Events []struct {
+		Meta []struct {
+			Key   string `json:"key"`
+			Value string `json:"value"`
+		} `json:"meta"`
+	} `json:"events"`
+	Decisions []struct {
+		ID        int64  `json:"id"`
+		Type      string `json:"type"`
+		Value     string `json:"value"`
+		Simulated bool   `json:"simulated"`
+	} `json:"decisions"`
+}
+
+func parseCrowdTraffic(data []byte) ([]TrafficEvent, error) {
+	var alerts []crowdTrafficAlert
+	if err := json.Unmarshal(data, &alerts); err != nil {
+		return nil, err
+	}
+	out := []TrafficEvent{}
+	for _, a := range alerts {
+		if a.Simulated || net.ParseIP(a.Source.IP) == nil {
+			continue
+		}
+		ts, err := time.Parse(time.RFC3339Nano, a.CreatedAt)
+		if err != nil {
+			continue
+		}
+		id := a.UUID
+		if id == "" {
+			id = fmt.Sprintf("%d:%d", a.ID, ts.Unix())
+		}
+		// An alert may span multiple domains. Do not invent a one-to-one link.
+		domains := map[string]bool{}
+		for _, event := range a.Events {
+			for _, m := range event.Meta {
+				if m.Key == "target_fqdn" {
+					domains[m.Value] = true
+				}
+			}
+		}
+		domain := ""
+		if len(domains) == 1 {
+			for d := range domains {
+				domain = d
+			}
+		}
+		out = append(out, TrafficEvent{ID: "cs-alert:" + id, Time: ts.Unix(), Kind: "alert", IP: a.Source.IP, Domain: domain, Reason: a.Scenario})
+		for _, d := range a.Decisions {
+			if !d.Simulated && net.ParseIP(d.Value) != nil {
+				out = append(out, TrafficEvent{ID: fmt.Sprintf("cs-decision:%s:%d", id, d.ID), Time: ts.Unix(), Kind: "decision", IP: d.Value, Domain: domain, Reason: d.Type + ": " + a.Scenario})
+			}
+		}
+	}
+	return out, nil
+}
+
+// cscli uses the existing local machine credentials. No new bouncer key or
+// public LAPI port is needed, and only the read-only alerts list is executed.
+func collectCrowdTraffic(ctx context.Context, container ...string) ([]TrafficEvent, bool, error) {
+	ctx, cancel := context.WithTimeout(ctx, 6*time.Second)
+	defer cancel()
+	var data []byte
+	if len(container) > 0 && container[0] != "" {
+		var err error
+		data, err = dockerCrowdOutput(ctx, container[0])
+		if err != nil {
+			return nil, false, errors.New("CrowdSec в Docker недоступен; проверьте контейнер и Docker socket")
+		}
+	} else {
+		cmd := exec.CommandContext(ctx, "cscli", "alerts", "list", "--since", "24h", "--limit", "50", "-o", "json")
+		var output limitedTrafficOutput
+		cmd.Stdout = &output
+		if err := cmd.Run(); err != nil {
+			return nil, false, errors.New("cscli недоступен на хосте; контейнер CrowdSec не обнаружен")
+		}
+		data = output.Bytes()
+	}
+	events, err := parseCrowdTraffic(data)
+	if err != nil {
+		return nil, false, errors.New("Не удалось разобрать JSON CrowdSec")
+	}
+	var raw []json.RawMessage
+	json.Unmarshal(data, &raw)
+	return events, len(raw) >= 50, nil
+}
+
+type limitedTrafficOutput struct{ bytes.Buffer }
+
+func (b *limitedTrafficOutput) Write(p []byte) (int, error) {
+	if b.Len()+len(p) > 4<<20 {
+		return 0, errors.New("CrowdSec response too large")
+	}
+	return b.Buffer.Write(p)
+}
+
+func saveTrafficAgentState(path string, state trafficAgentState) error {
+	data, err := json.Marshal(state)
+	if err != nil {
+		return err
+	}
+	f, err := os.CreateTemp(filepath.Dir(path), ".traffic-")
+	if err != nil {
+		return err
+	}
+	name := f.Name()
+	defer os.Remove(name)
+	if err = f.Chmod(0600); err == nil {
+		_, err = f.Write(data)
+	}
+	if err == nil {
+		err = f.Sync()
+	}
+	closeErr := f.Close()
+	if err != nil {
+		return err
+	}
+	if closeErr != nil {
+		return closeErr
+	}
+	return os.Rename(name, path)
+}
+func runAgentTraffic(ctx context.Context, config agentConfig, stateDir string) {
+	dir := os.Getenv("DASHBOARD_NPM_LOG_DIR")
+	if dir == "off" {
+		return
+	}
+
+	statePath := filepath.Join(stateDir, "traffic-state.json")
+	state := trafficAgentState{StartedAt: time.Now().Unix(), Cursors: map[string]trafficCursor{}, CrowdSeen: map[string]int64{}}
+	if data, err := os.ReadFile(statePath); err == nil {
+		if json.Unmarshal(data, &state) != nil {
+			fmt.Fprintln(os.Stderr, "traffic: invalid checkpoint; collector stopped")
+			return
+		}
+	} else if !os.IsNotExist(err) {
+		fmt.Fprintln(os.Stderr, "traffic: checkpoint unreadable")
+		return
+	}
+	if state.Cursors == nil {
+		state.Cursors = map[string]trafficCursor{}
+	}
+	if state.CrowdSeen == nil {
+		state.CrowdSeen = map[string]int64{}
+	}
+	client := &http.Client{Timeout: 10 * time.Second}
+	lastCrowd := time.Time{}
+	lastDiscovery := time.Time{}
+	discovery := trafficDiscovery{}
+	crowdAt := int64(0)
+	crowdError := ""
+	crowdLimited := false
+	ticker := time.NewTicker(2 * time.Second)
+	defer ticker.Stop()
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		default:
+		}
+		if time.Since(lastDiscovery) >= time.Minute {
+			discovery = discoverTraffic(ctx)
+			lastDiscovery = time.Now()
+		}
+		files, logErr := state.readLogs(discovery.Dirs...)
+		if logErr != nil {
+			logErr = fmt.Errorf("%s; проверьте access-логи и LOGROTATE=true у NPM+", logErr)
+		}
+		if len(state.Pending) < 400 && time.Since(lastCrowd) >= 15*time.Second {
+			events, limited, err := collectCrowdTraffic(ctx, discovery.CrowdContainer)
+			if discovery.Error != "" {
+				if _, localErr := exec.LookPath("cscli"); localErr != nil {
+					err = errors.New(discovery.Error)
+				}
+			}
+			crowdLimited = limited
+			lastCrowd = time.Now()
+			if err != nil {
+				crowdError = err.Error()
+			} else {
+				crowdError = ""
+				crowdAt = time.Now().Unix()
+				for _, e := range events {
+					if _, seen := state.CrowdSeen[e.ID]; !seen && len(state.Pending) < 500 {
+						state.Pending = append(state.Pending, e)
+						state.CrowdSeen[e.ID] = e.Time
+					}
+				}
+				for id, ts := range state.CrowdSeen {
+					if ts < time.Now().Unix()-86400 {
+						delete(state.CrowdSeen, id)
+					}
+				}
+			}
+		}
+		// Persist the pending batch AND offsets before sending. A retry/restart may
+		// resend events; the server's (agent,event_id) unique key makes it idempotent.
+		if err := saveTrafficAgentState(statePath, state); err != nil {
+			fmt.Fprintln(os.Stderr, "traffic: checkpoint write failed; collector stopped")
+			return
+		}
+		batch := TrafficBatch{BacklogBytes: state.BacklogBytes, CrowdSecLimited: crowdLimited, Events: state.Pending, Files: files, ParseErrors: state.ParseErrors, CrowdSecAt: crowdAt, CrowdSecError: crowdError, StartedAt: state.StartedAt}
+		if logErr != nil {
+			batch.LogError = logErr.Error()
+		}
+		data, _ := json.Marshal(batch)
+		req, err := http.NewRequestWithContext(ctx, "POST", config.Server+"/api/agent/traffic", bytes.NewReader(data))
+		if err != nil {
+			return
+		}
+		req.Header.Set("Authorization", "Bearer "+config.ID+"."+config.Secret)
+		req.Header.Set("Content-Type", "application/json")
+		if res, err := client.Do(req); err == nil {
+			io.Copy(io.Discard, io.LimitReader(res.Body, 4096))
+			res.Body.Close()
+			if res.StatusCode == 200 {
+				state.Pending = nil
+				if saveTrafficAgentState(statePath, state) != nil {
+					return
+				}
+			}
+		}
+		select {
+		case <-ctx.Done():
+			return
+		case <-ticker.C:
+		}
+	}
+}
+
+func startAgentTraffic(config agentConfig, stateDir string) func() {
+	ctx, cancel := context.WithCancel(context.Background())
+	done := make(chan struct{})
+	go func() { defer close(done); runAgentTraffic(ctx, config, stateDir) }()
+	return func() { cancel(); <-done }
+}

agent_traffic_discovery.go

@@ -0,0 +1,209 @@
+package main
+
+import (
+	"bytes"
+	"context"
+	"encoding/binary"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net"
+	"net/http"
+	"os"
+	"path/filepath"
+	"regexp"
+	"strconv"
+	"strings"
+	"time"
+)
+
+type trafficDockerContainer struct {
+	ID     string `json:"Id"`
+	Image  string
+	Names  []string
+	Mounts []struct{ Source, Destination string }
+}
+type trafficDiscovery struct {
+	Dirs           []string
+	CrowdContainer string
+	Error          string
+}
+
+func trafficDockerClient() *http.Client {
+	return &http.Client{Timeout: 8 * time.Second, Transport: &http.Transport{DialContext: func(ctx context.Context, _, _ string) (net.Conn, error) {
+		return (&net.Dialer{}).DialContext(ctx, "unix", "/var/run/docker.sock")
+	}}}
+}
+func discoverTraffic(ctx context.Context) trafficDiscovery {
+	d := trafficDiscovery{Dirs: []string{"/opt/npm/data/logs", "/opt/npmplus/nginx/logs", "/opt/npmplus/nginx"}}
+	client := trafficDockerClient()
+	defer client.CloseIdleConnections()
+	req, _ := http.NewRequestWithContext(ctx, "GET", "http://docker/containers/json", nil)
+	res, err := client.Do(req)
+	if err == nil {
+		defer res.Body.Close()
+		var containers []trafficDockerContainer
+		if res.StatusCode == 200 && json.NewDecoder(io.LimitReader(res.Body, 2<<20)).Decode(&containers) == nil {
+			d = trafficSources(containers, d.Dirs)
+		} else {
+			d.Error = "Не удалось прочитать список Docker-контейнеров"
+		}
+	} else if _, e := os.Stat("/var/run/docker.sock"); e == nil {
+		d.Error = "Docker socket недоступен агенту"
+	}
+	if dir := os.Getenv("DASHBOARD_NPM_LOG_DIR"); dir != "" {
+		d.Dirs = []string{dir}
+	}
+	if container := os.Getenv("DASHBOARD_CROWDSEC_CONTAINER"); container != "" {
+		d.CrowdContainer = container
+		d.Error = ""
+	}
+	return d
+}
+func trafficSources(containers []trafficDockerContainer, defaults []string) trafficDiscovery {
+	d := trafficDiscovery{Dirs: append([]string{}, defaults...)}
+	var crowd []string
+	for _, c := range containers {
+		img := strings.ToLower(c.Image)
+		if strings.Contains(img, "crowdsecurity/crowdsec:") || strings.HasSuffix(img, "crowdsecurity/crowdsec") || strings.Contains(img, "crowdsecurity/crowdsec@") {
+			crowd = append(crowd, c.ID)
+		}
+		if !strings.Contains(img, "nginx-proxy-manager") && !strings.Contains(img, "npmplus") {
+			continue
+		}
+		for _, target := range []string{"/data/logs", "/data/nginx/logs", "/data/nginx"} {
+			// Use the most specific mount, including a nested bind or named volume.
+			best, source := "", ""
+			for _, m := range c.Mounts {
+				dst := filepath.Clean(m.Destination)
+				if filepath.IsAbs(m.Source) && (target == dst || strings.HasPrefix(target, dst+"/")) && len(dst) > len(best) {
+					best = dst
+					source = filepath.Join(m.Source, strings.TrimPrefix(target, dst))
+				}
+			}
+			if source != "" {
+				d.Dirs = append(d.Dirs, source)
+			}
+		}
+	}
+	if len(crowd) == 1 {
+		d.CrowdContainer = crowd[0]
+	} else if len(crowd) > 1 {
+		d.Error = "Найдено несколько CrowdSec: задайте DASHBOARD_CROWDSEC_CONTAINER"
+	}
+	unique := map[string]bool{}
+	dirs := []string{}
+	for _, dir := range d.Dirs {
+		dir = filepath.Clean(dir)
+		if !unique[dir] {
+			unique[dir] = true
+			dirs = append(dirs, dir)
+		}
+	}
+	d.Dirs = dirs
+	return d
+}
+
+// Docker exec uses a fixed read-only command; no shell, credential extraction or published LAPI.
+func dockerCrowdOutput(ctx context.Context, container string) ([]byte, error) {
+	client := trafficDockerClient()
+	defer client.CloseIdleConnections()
+	return dockerCrowdWithClient(ctx, container, client)
+}
+func dockerCrowdWithClient(ctx context.Context, container string, client *http.Client) ([]byte, error) {
+	if !safeContainerName.MatchString(container) || strings.HasPrefix(container, "-") {
+		return nil, fmt.Errorf("некорректный контейнер CrowdSec")
+	}
+	call := func(path string, payload any) (*http.Response, error) {
+		raw, _ := json.Marshal(payload)
+		req, _ := http.NewRequestWithContext(ctx, "POST", "http://docker"+path, bytes.NewReader(raw))
+		req.Header.Set("Content-Type", "application/json")
+		return client.Do(req)
+	}
+	res, err := call("/containers/"+container+"/exec", map[string]any{"AttachStdout": true, "AttachStderr": true, "Tty": false, "Cmd": []string{"cscli", "alerts", "list", "--since", "24h", "--limit", "50", "-o", "json"}})
+	if err != nil {
+		return nil, err
+	}
+	var created struct{ ID string }
+	err = json.NewDecoder(io.LimitReader(res.Body, 4096)).Decode(&created)
+	res.Body.Close()
+	if err != nil || res.StatusCode != 201 || !safeContainerName.MatchString(created.ID) {
+		return nil, fmt.Errorf("Docker не создал cscli exec")
+	}
+	res, err = call("/exec/"+created.ID+"/start", map[string]any{"Detach": false, "Tty": false})
+	if err != nil {
+		return nil, err
+	}
+	defer res.Body.Close()
+	if res.StatusCode != 200 {
+		return nil, fmt.Errorf("Docker cscli exec: %s", res.Status)
+	}
+	output, err := readDockerTrafficOutput(res.Body)
+	if err != nil {
+		return nil, err
+	}
+	req, _ := http.NewRequestWithContext(ctx, "GET", "http://docker/exec/"+created.ID+"/json", nil)
+	check, err := client.Do(req)
+	if err != nil {
+		return nil, err
+	}
+	defer check.Body.Close()
+	var status struct {
+		Running  bool
+		ExitCode int
+	}
+	if check.StatusCode != 200 || json.NewDecoder(io.LimitReader(check.Body, 4096)).Decode(&status) != nil || status.Running || status.ExitCode != 0 {
+		return nil, fmt.Errorf("cscli внутри Docker завершился с ошибкой")
+	}
+	return output, nil
+}
+func readDockerTrafficOutput(r io.Reader) ([]byte, error) {
+	var out bytes.Buffer
+	total := uint32(0)
+	for {
+		var header [8]byte
+		_, err := io.ReadFull(r, header[:])
+		if err == io.EOF {
+			return out.Bytes(), nil
+		}
+		if err != nil {
+			return nil, err
+		}
+		n := binary.BigEndian.Uint32(header[4:])
+		if n > 4<<20 || total+n > 4<<20 {
+			return nil, fmt.Errorf("Docker output too large")
+		}
+		total += n
+		if header[0] != 1 && header[0] != 2 {
+			return nil, fmt.Errorf("invalid Docker stream")
+		}
+		if header[0] == 1 {
+			_, err = io.CopyN(&out, r, int64(n))
+		} else {
+			_, err = io.CopyN(io.Discard, r, int64(n))
+		}
+		if err != nil {
+			return nil, err
+		}
+	}
+}
+
+var npmPlusTrafficPattern = regexp.MustCompile(`^\[([^]]+)\] (\S+) (\S+) [0-9.]+ "([A-Z]+) ([^" ]+) HTTP/[0-9.]+" (\d{3}) `)
+
+func parseNPMPlusTraffic(line string) (TrafficEvent, bool) {
+	m := npmPlusTrafficPattern.FindStringSubmatch(line)
+	if m == nil {
+		return TrafficEvent{}, false
+	}
+	ip := net.ParseIP(m[3])
+	ts, err := time.Parse("02/Jan/2006:15:04:05 -0700", m[1])
+	if ip == nil || err != nil {
+		return TrafficEvent{}, false
+	}
+	host := m[2]
+	if h, _, err := net.SplitHostPort(host); err == nil {
+		host = h
+	}
+	status, _ := strconv.Atoi(m[6])
+	return TrafficEvent{Time: ts.Unix(), Kind: "request", IP: ip.String(), Domain: trafficText(host, 253), Method: m[4], Path: trafficPath(m[5]), Status: status}, true
+}

agent_traffic_discovery_test.go

@@ -0,0 +1,134 @@
+package main
+
+import (
+	"bytes"
+	"context"
+	"encoding/binary"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+)
+
+func TestNPMPlusTraffic(t *testing.T) {
+	for _, ip := range []string{"8.8.8.8", "2001:4860:4860::8888"} {
+		line := `[14/Oct/2026:16:24:17 +0000] example.test:8443 ` + ip + ` 0.001 "GET /health?token=secret HTTP/3.0" 200 123 "-" "test" "-" "text/html" TLSv1.3 - - -`
+		e, ok := parseNPMTraffic(line)
+		if !ok || e.IP != ip || e.Domain != "example.test" || e.Path != "/health" || e.Status != 200 {
+			t.Fatalf("%+v %v", e, ok)
+		}
+	}
+	if _, ok := parseNPMTraffic(`[14/Oct/2026:16:24:17 +0000] 443 8.8.8.8 UDP - 200 10 20 0.001`); ok {
+		t.Fatal("stream counted as HTTP")
+	}
+}
+func TestDockerTrafficDiscovery(t *testing.T) {
+	var containers []trafficDockerContainer
+	json.Unmarshal([]byte(`[{"Id":"aaa","Image":"ghcr.io/zoeyvid/npmplus:latest","Mounts":[{"Source":"/var/lib/docker/volumes/npm/_data","Destination":"/data"},{"Source":"/srv/logs","Destination":"/data/nginx/logs"}]},{"Id":"bbb","Image":"crowdsecurity/crowdsec:latest"}]`), &containers)
+	d := trafficSources(containers, nil)
+	if d.CrowdContainer != "bbb" || d.Error != "" || strings.Join(d.Dirs, ",") != "/var/lib/docker/volumes/npm/_data/logs,/srv/logs,/var/lib/docker/volumes/npm/_data/nginx" {
+		t.Fatalf("%+v", d)
+	}
+	containers = append(containers, containers[1])
+	d = trafficSources(containers, nil)
+	if d.CrowdContainer != "" || d.Error == "" {
+		t.Fatal("ambiguous CrowdSec silently chosen")
+	}
+}
+func TestDockerTrafficDemux(t *testing.T) {
+	var b bytes.Buffer
+	for _, frame := range []struct {
+		stream byte
+		text   string
+	}{{2, "diagnostic"}, {1, "["}, {1, "]"}} {
+		h := []byte{frame.stream, 0, 0, 0, 0, 0, 0, 0}
+		binary.BigEndian.PutUint32(h[4:], uint32(len(frame.text)))
+		b.Write(h)
+		b.WriteString(frame.text)
+	}
+	out, err := readDockerTrafficOutput(&b)
+	if err != nil || string(out) != "[]" {
+		t.Fatalf("%q %v", out, err)
+	}
+	if _, err := readDockerTrafficOutput(bytes.NewReader([]byte{1, 0, 0})); err == nil {
+		t.Fatal("truncation accepted")
+	}
+	if _, err := readDockerTrafficOutput(bytes.NewReader([]byte{1, 0, 0, 0, 255, 255, 255, 255})); err == nil {
+		t.Fatal("oversized frame accepted")
+	}
+}
+func TestTrafficMultipleDirectoriesAndNPMPlusRotation(t *testing.T) {
+	a, b := t.TempDir(), t.TempDir()
+	p := filepath.Join(b, "access.log")
+	os.WriteFile(filepath.Join(a, "proxy-host-1_access.log"), nil, 0600)
+	os.WriteFile(p, nil, 0600)
+	s := trafficAgentState{Cursors: map[string]trafficCursor{}}
+	if n, err := s.readLogs(a, b, a); err != nil || n != 2 {
+		t.Fatalf("files %d: %v", n, err)
+	}
+	line := "[" + time.Now().UTC().Format("02/Jan/2006:15:04:05 -0700") + `] example.test 8.8.8.8 0.1 "GET / HTTP/2.0" 200 123 "-"` + "\n"
+	os.WriteFile(p, []byte(line), 0600)
+	s.readLogs(a, b)
+	if len(s.Pending) != 1 {
+		t.Fatal("NPM+ event missing")
+	}
+	s.Pending = nil
+	os.Rename(p, p+".1")
+	os.WriteFile(p, []byte(line), 0600)
+	s.readLogs(a, b)
+	if len(s.Pending) != 1 {
+		t.Fatalf("rotation duplicated/lost events: %d", len(s.Pending))
+	}
+}
+
+type trafficRoundTrip func(*http.Request) (*http.Response, error)
+
+func (f trafficRoundTrip) RoundTrip(r *http.Request) (*http.Response, error) { return f(r) }
+func TestDockerCrowdExec(t *testing.T) {
+	for _, exitCode := range []int{0, 1} {
+		calls := 0
+		client := &http.Client{Transport: trafficRoundTrip(func(r *http.Request) (*http.Response, error) {
+			calls++
+			body := ""
+			status := 200
+			switch calls {
+			case 1:
+				if r.Method != "POST" || r.URL.Path != "/containers/crowdsec/exec" {
+					t.Fatalf("unexpected %s %s", r.Method, r.URL)
+				}
+				var payload struct {
+					Cmd []string
+					Tty bool
+				}
+				json.NewDecoder(r.Body).Decode(&payload)
+				if strings.Join(payload.Cmd, " ") != "cscli alerts list --since 24h --limit 50 -o json" || payload.Tty {
+					t.Fatalf("unexpected command %+v", payload)
+				}
+				status = 201
+				body = `{"Id":"exec123"}`
+			case 2:
+				if r.URL.Path != "/exec/exec123/start" {
+					t.Fatal(r.URL)
+				}
+				body = string([]byte{1, 0, 0, 0, 0, 0, 0, 2}) + "[]"
+			case 3:
+				if r.Method != "GET" || r.URL.Path != "/exec/exec123/json" {
+					t.Fatal(r.URL)
+				}
+				body = fmt.Sprintf(`{"Running":false,"ExitCode":%d}`, exitCode)
+			default:
+				t.Fatal("extra Docker request")
+			}
+			return &http.Response{StatusCode: status, Body: io.NopCloser(strings.NewReader(body)), Header: make(http.Header)}, nil
+		})}
+		out, err := dockerCrowdWithClient(context.Background(), "crowdsec", client)
+		if calls != 3 || (exitCode == 0 && (err != nil || string(out) != "[]")) || (exitCode != 0 && err == nil) {
+			t.Fatalf("calls=%d output=%s err=%v", calls, out, err)
+		}
+	}
+}

alert_events.go

@@ -6,16 +6,18 @@ import (
 )
 
 type AlertEvent struct {
-	EventID        int64  `json:"eventId"`
+	EventID           int64  `json:"eventId"`
-	ID             string `json:"id"`
+	ID                string `json:"id"`
-	Severity       string `json:"severity"`
+	Severity          string `json:"severity"`
-	Source         string `json:"source"`
+	Source            string `json:"source"`
-	Title          string `json:"title"`
+	Title             string `json:"title"`
-	Message        string `json:"message"`
+	Message           string `json:"message"`
-	FirstSeen      int64  `json:"firstSeen"`
+	FirstSeen         int64  `json:"firstSeen"`
-	LastSeen       int64  `json:"lastSeen"`
+	LastSeen          int64  `json:"lastSeen"`
-	ResolvedAt     *int64 `json:"resolvedAt,omitempty"`
+	ResolvedAt        *int64 `json:"resolvedAt,omitempty"`
-	AcknowledgedAt *int64 `json:"acknowledgedAt,omitempty"`
+	AcknowledgedAt    *int64 `json:"acknowledgedAt,omitempty"`
+	Planned           bool   `json:"planned"`
+	MaintenanceReason string `json:"maintenanceReason,omitempty"`
 }
 
 type RecoveryEvent struct {
@@ -24,13 +26,17 @@ type RecoveryEvent struct {
 }
 
 func (s *Store) SyncAlerts(alerts []Alert) ([]Alert, error) {
+	return s.SyncAlertsWithMaintenance(alerts, nil, "")
+}
+
+func (s *Store) SyncAlertsWithMaintenance(alerts, plannedAlerts []Alert, maintenanceReason string) ([]Alert, error) {
 	tx, err := s.db.Begin()
 	if err != nil {
 		return alerts, err
 	}
 	defer tx.Rollback()
 	now := time.Now().Unix()
-	rows, err := tx.Query(`SELECT id,alert_key FROM alert_events WHERE resolved_at IS NULL`)
+	rows, err := tx.Query(`SELECT id,alert_key,planned FROM alert_events WHERE resolved_at IS NULL`)
 	if err != nil {
 		return alerts, err
 	}
@@ -38,28 +44,43 @@ func (s *Store) SyncAlerts(alerts []Alert) ([]Alert, error) {
 	for rows.Next() {
 		var id int64
 		var key string
-		if err := rows.Scan(&id, &key); err != nil {
+		var planned bool
+		if err := rows.Scan(&id, &key, &planned); err != nil {
 			rows.Close()
 			return alerts, err
 		}
-		active[key] = id
+		active[alertEventKey(key, planned)] = id
 	}
 	rows.Close()
 	seen := map[string]bool{}
-	for _, alert := range alerts {
+	syncGroup := func(group []Alert, planned bool) error {
-		seen[alert.ID] = true
+		for _, alert := range group {
-		if id, ok := active[alert.ID]; ok {
+			key := alertEventKey(alert.ID, planned)
-			_, err = tx.Exec(`UPDATE alert_events SET severity=?,source=?,title=?,message=?,last_seen=? WHERE id=?`, alert.Severity, alert.Source, alert.Title, alert.Message, now, id)
+			seen[key] = true
-		} else {
+			reason := ""
-			result, insertErr := tx.Exec(`INSERT INTO alert_events(alert_key,severity,source,title,message,first_seen,last_seen) VALUES(?,?,?,?,?,?,?)`, alert.ID, alert.Severity, alert.Source, alert.Title, alert.Message, now, now)
+			if planned {
-			if insertErr != nil {
+				reason = maintenanceReason
-				return alerts, insertErr
+			}
+			if id, ok := active[key]; ok {
+				_, err = tx.Exec(`UPDATE alert_events SET severity=?,source=?,title=?,message=?,last_seen=?,maintenance_reason=? WHERE id=?`, alert.Severity, alert.Source, alert.Title, alert.Message, now, reason, id)
+			} else {
+				result, insertErr := tx.Exec(`INSERT INTO alert_events(alert_key,severity,source,title,message,first_seen,last_seen,planned,maintenance_reason) VALUES(?,?,?,?,?,?,?,?,?)`, alert.ID, alert.Severity, alert.Source, alert.Title, alert.Message, now, now, planned, reason)
+				if insertErr != nil {
+					return insertErr
+				}
+				active[key], _ = result.LastInsertId()
+			}
+			if err != nil {
+				return err
 			}
-			active[alert.ID], _ = result.LastInsertId()
-		}
-		if err != nil {
-			return alerts, err
 		}
+		return nil
+	}
+	if err = syncGroup(alerts, false); err != nil {
+		return alerts, err
+	}
+	if err = syncGroup(plannedAlerts, true); err != nil {
+		return alerts, err
 	}
 	for key, id := range active {
 		if !seen[key] {
@@ -74,7 +95,7 @@ func (s *Store) SyncAlerts(alerts []Alert) ([]Alert, error) {
 	if err = tx.Commit(); err != nil {
 		return alerts, err
 	}
-	rows, err = s.db.Query(`SELECT id,alert_key,severity,source,title,message FROM alert_events WHERE resolved_at IS NULL AND acknowledged_at IS NULL ORDER BY CASE severity WHEN 'critical' THEN 0 WHEN 'warning' THEN 1 ELSE 2 END,first_seen DESC`)
+	rows, err = s.db.Query(`SELECT id,alert_key,severity,source,title,message,first_seen,last_seen FROM alert_events WHERE resolved_at IS NULL AND acknowledged_at IS NULL AND planned=0 ORDER BY CASE severity WHEN 'critical' THEN 0 WHEN 'warning' THEN 1 ELSE 2 END,first_seen DESC`)
 	if err != nil {
 		return alerts, err
 	}
@@ -82,7 +103,7 @@ func (s *Store) SyncAlerts(alerts []Alert) ([]Alert, error) {
 	var visible []Alert
 	for rows.Next() {
 		var a Alert
-		if err = rows.Scan(&a.EventID, &a.ID, &a.Severity, &a.Source, &a.Title, &a.Message); err != nil {
+		if err = rows.Scan(&a.EventID, &a.ID, &a.Severity, &a.Source, &a.Title, &a.Message, &a.FirstSeen, &a.LastSeen); err != nil {
 			return alerts, err
 		}
 		visible = append(visible, a)
@@ -90,16 +111,35 @@ func (s *Store) SyncAlerts(alerts []Alert) ([]Alert, error) {
 	return visible, rows.Err()
 }
 
+func alertEventKey(id string, planned bool) string {
+	if planned {
+		return id + "\x00planned"
+	}
+	return id + "\x00active"
+}
+
 func (s *Store) AcknowledgeAlert(eventID int64) error {
 	_, err := s.db.Exec(`UPDATE alert_events SET acknowledged_at=? WHERE id=? AND acknowledged_at IS NULL`, time.Now().Unix(), eventID)
 	return err
 }
 
 func (s *Store) AlertHistory(limit int) ([]AlertEvent, error) {
+	return s.AlertHistoryBetween(limit, 0, 0)
+}
+
+func (s *Store) AlertHistoryBetween(limit int, from, to int64) ([]AlertEvent, error) {
 	if limit < 1 || limit > 500 {
 		limit = 200
 	}
-	rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message,first_seen,last_seen,resolved_at,acknowledged_at FROM alert_events ORDER BY first_seen DESC LIMIT ?`, limit)
+	query := `SELECT id,alert_key,severity,source,title,message,first_seen,last_seen,resolved_at,acknowledged_at,planned,maintenance_reason FROM alert_events`
+	args := []any{}
+	if from > 0 && to > from {
+		query += ` WHERE first_seen>=? AND first_seen<?`
+		args = append(args, from, to)
+	}
+	query += ` ORDER BY first_seen DESC LIMIT ?`
+	args = append(args, limit)
+	rows, err := s.db.Query(query, args...)
 	if err != nil {
 		return nil, err
 	}
@@ -108,7 +148,7 @@ func (s *Store) AlertHistory(limit int) ([]AlertEvent, error) {
 	for rows.Next() {
 		var e AlertEvent
 		var resolved, acked sql.NullInt64
-		if err = rows.Scan(&e.EventID, &e.ID, &e.Severity, &e.Source, &e.Title, &e.Message, &e.FirstSeen, &e.LastSeen, &resolved, &acked); err != nil {
+		if err = rows.Scan(&e.EventID, &e.ID, &e.Severity, &e.Source, &e.Title, &e.Message, &e.FirstSeen, &e.LastSeen, &resolved, &acked, &e.Planned, &e.MaintenanceReason); err != nil {
 			return nil, err
 		}
 		if resolved.Valid {
@@ -123,7 +163,7 @@ func (s *Store) AlertHistory(limit int) ([]AlertEvent, error) {
 }
 
 func (s *Store) PendingEmailAlerts() ([]Alert, error) {
-	rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message FROM alert_events WHERE resolved_at IS NULL AND acknowledged_at IS NULL AND email_sent_at IS NULL ORDER BY first_seen`)
+	rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message FROM alert_events WHERE resolved_at IS NULL AND acknowledged_at IS NULL AND email_sent_at IS NULL AND planned=0 ORDER BY first_seen`)
 	if err != nil {
 		return nil, err
 	}
@@ -155,7 +195,7 @@ func (s *Store) MarkAlertsEmailed(alerts []Alert) error {
 }
 
 func (s *Store) PendingImmediateAlerts() ([]Alert, error) {
-	rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message FROM alert_events WHERE resolved_at IS NULL AND acknowledged_at IS NULL AND email_sent_at IS NULL AND (severity='critical' OR alert_key='ups-battery') ORDER BY first_seen`)
+	rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message FROM alert_events WHERE resolved_at IS NULL AND acknowledged_at IS NULL AND email_sent_at IS NULL AND planned=0 AND (severity='critical' OR alert_key='ups-battery') ORDER BY first_seen`)
 	if err != nil {
 		return nil, err
 	}
@@ -171,7 +211,7 @@ func (s *Store) PendingImmediateAlerts() ([]Alert, error) {
 	return out, rows.Err()
 }
 func (s *Store) PendingRecoveries() ([]RecoveryEvent, error) {
-	rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message FROM alert_events WHERE resolved_at IS NOT NULL AND email_sent_at IS NOT NULL AND recovery_sent_at IS NULL ORDER BY resolved_at`)
+	rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message FROM alert_events WHERE resolved_at IS NOT NULL AND email_sent_at IS NOT NULL AND recovery_sent_at IS NULL AND planned=0 ORDER BY resolved_at`)
 	if err != nil {
 		return nil, err
 	}

alert_events_test.go

@@ -10,7 +10,7 @@ func TestAlertLifecycle(t *testing.T) {
 	defer store.Close()
 	alert := Alert{ID: "disk", Severity: "warning", Source: "Диски", Title: "SMART", Message: "Проверьте диск"}
 	visible, err := store.SyncAlerts([]Alert{alert})
-	if err != nil || len(visible) != 1 || visible[0].EventID == 0 {
+	if err != nil || len(visible) != 1 || visible[0].EventID == 0 || visible[0].FirstSeen == 0 || visible[0].LastSeen == 0 {
 		t.Fatalf("unexpected new alert: %+v %v", visible, err)
 	}
 	firstID := visible[0].EventID

alerts.go

@@ -8,12 +8,14 @@ import (
 )
 
 type Alert struct {
-	EventID  int64  `json:"eventId,omitempty"`
+	EventID   int64  `json:"eventId,omitempty"`
-	ID       string `json:"id"`
+	ID        string `json:"id"`
-	Severity string `json:"severity"`
+	Severity  string `json:"severity"`
-	Source   string `json:"source"`
+	Source    string `json:"source"`
-	Title    string `json:"title"`
+	Title     string `json:"title"`
-	Message  string `json:"message"`
+	Message   string `json:"message"`
+	FirstSeen int64  `json:"firstSeen,omitempty"`
+	LastSeen  int64  `json:"lastSeen,omitempty"`
 }
 
 func evaluateAlerts(metrics dashboardMetrics, thresholds AlertThresholds) []Alert {
@@ -61,10 +63,21 @@ func evaluateAlerts(metrics dashboardMetrics, thresholds AlertThresholds) []Aler
 		add("root-storage", "warning", "Storage", "Мало места на системном разделе", fmt.Sprintf("Раздел / заполнен на %.1f%%.", metrics.Storage.UsagePercent))
 	}
 	for _, disk := range metrics.Disks {
+		diskExcluded := false
+		for _, value := range strings.Split(thresholds.DiskIOExcluded, ",") {
+			value = strings.TrimSpace(value)
+			if value != "" && (strings.EqualFold(value, disk.Name) || strings.EqualFold(value, disk.Serial)) {
+				diskExcluded = true
+				break
+			}
+		}
 		if disk.SMARTStatus == "Ошибка" {
 			add("disk-smart-"+disk.Name, "critical", "Диски", disk.Model+": ошибка SMART", joinReasons(disk.AttentionReasons, "SMART сообщает о неисправности диска."))
 		} else if disk.SMARTStatus == "Требует внимания" {
-			add("disk-smart-"+disk.Name, "warning", "Диски", disk.Model+": SMART требует внимания", joinReasons(disk.AttentionReasons, "Проверьте SMART-показатели диска."))
+			reasons := withoutReason(disk.AttentionReasons, "SMART self-test ещё ни разу не запускался")
+			if len(reasons) > 0 {
+				add("disk-smart-"+disk.Name, "warning", "Диски", disk.Model+": SMART требует внимания", joinReasons(reasons, "Проверьте SMART-показатели диска."))
+			}
 		}
 		if disk.Temperature != nil {
 			limit := thresholds.DiskTempWarning
@@ -78,12 +91,16 @@ func evaluateAlerts(metrics dashboardMetrics, thresholds AlertThresholds) []Aler
 		if len(disk.CounterChanges) > 0 {
 			add("disk-growth-"+disk.Name, "critical", "Диски", disk.Model+": ухудшились SMART-счётчики", strings.Join(disk.CounterChanges, " · "))
 		}
-		if disk.IOPressureSeconds >= 60 {
+		if !diskExcluded && disk.IOPressureSeconds >= thresholds.DiskIODuration {
 			severity := "warning"
 			if disk.Utilization >= 98 || disk.LatencyMs >= 100 {
 				severity = "critical"
 			}
-			add("disk-io-pressure-"+disk.Name, severity, "Диски", disk.Model+": длительная I/O-нагрузка", fmt.Sprintf("Нагрузка держится %.0f сек.: %.0f IOPS, %.1f MB/s, latency %.1f ms, util %.1f%%, очередь %.1f.", disk.IOPressureSeconds, disk.ReadIOPS+disk.WriteIOPS, (disk.ReadBytesPerSec+disk.WriteBytesPerSec)/1048576, disk.LatencyMs, disk.Utilization, disk.AverageQueue))
+			cause := disk.IOCause
+			if cause == "" {
+				cause = "источник пока не определён"
+			}
+			add("disk-io-pressure-"+disk.Name, severity, "Диски", disk.Model+": длительная I/O-нагрузка", fmt.Sprintf("%s занят на %.1f%%; вероятная причина: %s (уверенность %d%%). %.0f IOPS, %.1f MB/s, latency %.1f ms, очередь %.1f.", disk.Name, disk.Utilization, cause, disk.IOConfidence, disk.ReadIOPS+disk.WriteIOPS, (disk.ReadBytesPerSec+disk.WriteBytesPerSec)/1048576, disk.LatencyMs, disk.AverageQueue))
 		}
 		if disk.SelfTestNeverRun {
 			add("disk-selftest-"+disk.Name, "warning", "Диски", disk.Model+": нет завершённого SMART self-test", "Короткий тест будет автоматически запущен; проверьте его результат после завершения.")
@@ -183,6 +200,50 @@ func evaluateAlerts(metrics dashboardMetrics, thresholds AlertThresholds) []Aler
 			add("guests-stopped", "info", "VM/LXC", "Есть остановленные гости", fmt.Sprintf("Остановлено VM/LXC: %d. Это уведомление информационное.", stopped))
 		}
 	}
+	for _, agent := range metrics.Agents {
+		vmSuffix := fmt.Sprintf("-%d", agent.VMID)
+		if !agent.Online {
+			add("agent-offline-"+agent.ID+vmSuffix, "critical", "Агенты", agent.Name+": агент не отвечает", fmt.Sprintf("Последний heartbeat: %s назад. VMID %d.", time.Since(time.Unix(agent.LastSeen, 0)).Round(time.Second), agent.VMID))
+			continue
+		}
+		if agent.Report.DockerAvailable {
+			for _, container := range agent.Report.Containers {
+				if container.State != "running" {
+					add("agent-container-stopped-"+agent.ID+"-"+container.ID+vmSuffix, "warning", "Docker", agent.Name+": контейнер "+container.Name+" остановлен", fmt.Sprintf("%s · VMID %d.", container.Status, agent.VMID))
+				} else if container.Health == "unhealthy" {
+					add("agent-container-health-"+agent.ID+"-"+container.ID+vmSuffix, "critical", "Docker", agent.Name+": контейнер "+container.Name+" unhealthy", fmt.Sprintf("Docker health-check не проходит · VMID %d.", agent.VMID))
+				}
+			}
+		}
+		for _, service := range agent.Report.Services {
+			if service.State == "failed" || service.SubState == "failed" {
+				add("agent-systemd-"+agent.ID+"-"+service.Name+vmSuffix, "critical", "Агенты", agent.Name+": упала служба "+service.Name, fmt.Sprintf("%s · VMID %d.", firstNonEmpty(service.Description, service.SubState), agent.VMID))
+			} else if service.Flapping {
+				add("agent-flapping-"+agent.ID+"-"+service.Name+vmSuffix, "warning", "Агенты", agent.Name+": служба постоянно перезапускается", fmt.Sprintf("%s: %d рестартов, последний запуск %s · VMID %d.", service.Name, service.Restarts, time.Unix(service.StartedAt, 0).Format("15:04:05"), agent.VMID))
+			}
+		}
+		for _, filesystem := range agent.Report.Filesystems {
+			if filesystem.UsedPercent >= 90 {
+				add("agent-filesystem-"+agent.ID+"-"+filesystem.Mountpoint+vmSuffix, "critical", "Агенты", agent.Name+": заканчивается место "+filesystem.Mountpoint, fmt.Sprintf("Заполнено %.1f%%, свободно %.1f GB · VMID %d.", filesystem.UsedPercent, float64(filesystem.TotalBytes-filesystem.UsedBytes)/1073741824, agent.VMID))
+			}
+			if filesystem.InodesPercent >= 90 {
+				add("agent-inodes-"+agent.ID+"-"+filesystem.Mountpoint+vmSuffix, "critical", "Агенты", agent.Name+": заканчиваются inode "+filesystem.Mountpoint, fmt.Sprintf("Использовано %.1f%% inode · VMID %d.", filesystem.InodesPercent, agent.VMID))
+			}
+		}
+		if len(agent.Report.OOMKills) > 0 {
+			latest := agent.Report.OOMKills[0]
+			add("agent-oom-"+agent.ID+vmSuffix, "critical", "Агенты", agent.Name+": ядро завершало процессы из-за нехватки памяти", fmt.Sprintf("%s · %s · VMID %d.", time.Unix(latest.Time, 0).Format("02.01 15:04"), latest.Message, agent.VMID))
+		}
+		if agent.Report.RebootRequired {
+			add("agent-reboot-"+agent.ID+vmSuffix, "info", "Агенты", agent.Name+": требуется перезагрузка", fmt.Sprintf("Обновления системы запросили перезагрузку · VMID %d.", agent.VMID))
+		}
+		if agent.Report.MemoryTotal > 0 && float64(agent.Report.MemoryUsed)/float64(agent.Report.MemoryTotal)*100 >= 95 {
+			add("agent-memory-"+agent.ID+vmSuffix, "warning", "Агенты", agent.Name+": почти закончилась память", fmt.Sprintf("Используется %.1f%% RAM · VMID %d.", float64(agent.Report.MemoryUsed)/float64(agent.Report.MemoryTotal)*100, agent.VMID))
+		}
+		if agent.Report.RootTotal > 0 && float64(agent.Report.RootUsed)/float64(agent.Report.RootTotal)*100 >= 90 {
+			add("agent-storage-"+agent.ID+vmSuffix, "critical", "Агенты", agent.Name+": мало места на системном разделе", fmt.Sprintf("Раздел / заполнен на %.1f%% · VMID %d.", float64(agent.Report.RootUsed)/float64(agent.Report.RootTotal)*100, agent.VMID))
+		}
+	}
 	for _, service := range metrics.Services.Services {
 		for _, endpoint := range service.Endpoints {
 			if !endpoint.Up {
@@ -202,10 +263,13 @@ func evaluateAlerts(metrics dashboardMetrics, thresholds AlertThresholds) []Aler
 	}
 	var networkErrors uint64
 	for _, iface := range metrics.Network.Interfaces {
-		networkErrors += iface.ReceiveErrors + iface.TransmitErrors + iface.ReceiveDrops + iface.TransmitDrops
+		networkErrors += iface.NewErrors + iface.NewFaults
+		if iface.LinkDown {
+			add("network-link-"+iface.Name, "critical", "Сеть", iface.Name+": нет линка", "Используемый интерфейс потерял carrier или перешёл в down.")
+		}
 	}
 	if networkErrors > 0 {
-		add("network-errors", "warning", "Сеть", "Сетевые ошибки и потери пакетов", fmt.Sprintf("Суммарный счётчик интерфейсов: %d.", networkErrors))
+		add("network-errors", "critical", "Сеть", "Появились новые сетевые ошибки", fmt.Sprintf("Прирост счётчиков ошибок: %d (счётчики могут пересекаться). Software RX/TX drops показаны отдельно и не создают этот алерт.", networkErrors))
 	}
 	if !metrics.Network.Health.CheckedAt.IsZero() && !metrics.Network.Health.GatewayUp {
 		add("network-gateway", "critical", "Сеть", "Недоступен локальный шлюз", firstNonEmpty(metrics.Network.Health.Gateway, "Default gateway не определён."))
@@ -225,20 +289,10 @@ func evaluateAlerts(metrics dashboardMetrics, thresholds AlertThresholds) []Aler
 	for _, name := range metrics.Network.Health.DisappearedInterfaces {
 		add("network-interface-missing-"+name, "warning", "Сеть", "Исчез сетевой интерфейс", name+" больше не присутствует в /proc/net/dev.")
 	}
-	for _, iface := range metrics.Network.Interfaces {
+
-		if iface.Kind == "Physical" && !iface.Carrier && (iface.Master != "" || iface.ReceiveBytes+iface.TransmitBytes > 0) {
-			add("network-link-"+iface.Name, "warning", "Сеть", iface.Name+": нет carrier", "Физический линк не поднят.")
-		}
-		if (iface.Kind == "Bridge" || iface.Kind == "Bond" || iface.Kind == "VLAN") && iface.State == "down" {
-			add("network-state-"+iface.Name, "warning", "Сеть", iface.Name+": интерфейс выключен", iface.Kind+" находится в состоянии down.")
-		}
-	}
 	if !metrics.Monitor.LastSuccessfulCollection.IsZero() && time.Since(metrics.Monitor.LastSuccessfulCollection) > 30*time.Second {
 		add("monitor-stale", "critical", "Dashboard", "Данные мониторинга устарели", "Последний успешный сбор был "+time.Since(metrics.Monitor.LastSuccessfulCollection).Round(time.Second).String()+" назад.")
 	}
-	if metrics.Monitor.SlowCollector {
-		add("monitor-slow", "warning", "Dashboard", "Сбор метрик выполняется слишком долго", fmt.Sprintf("Последний цикл занял %d ms.", metrics.Monitor.CollectionDurationMs))
-	}
 	if metrics.Monitor.HistoryWriteError != "" {
 		add("monitor-history", "critical", "Dashboard", "Ошибка записи истории", metrics.Monitor.HistoryWriteError)
 	}
@@ -266,6 +320,9 @@ func evaluateAlerts(metrics dashboardMetrics, thresholds AlertThresholds) []Aler
 			add("task-failed-"+task.UPID, severity, "Proxmox", task.Type+": задача завершилась ошибкой", fmt.Sprintf("VMID %s, пользователь %s, статус %s.", task.ID, task.User, task.Status))
 		}
 	}
+	for _, trend := range metrics.Trends {
+		add(trend.ID, trend.Severity, trend.Source, trend.Title, trend.Message)
+	}
 
 	priority := map[string]int{"critical": 0, "warning": 1, "info": 2}
 	sort.SliceStable(alerts, func(i, j int) bool {
@@ -277,9 +334,64 @@ func evaluateAlerts(metrics dashboardMetrics, thresholds AlertThresholds) []Aler
 	return alerts
 }
 
+func correlateAlerts(metrics dashboardMetrics, alerts []Alert) []Alert {
+	pressureAlerts := map[string]bool{}
+	for _, a := range alerts {
+		if strings.HasPrefix(a.ID, "disk-io-pressure-") {
+			pressureAlerts[strings.TrimPrefix(a.ID, "disk-io-pressure-")] = true
+		}
+	}
+	var pressure []DiskMetrics
+	for _, d := range metrics.Disks {
+		if pressureAlerts[d.Name] && d.IOCause != "" {
+			pressure = append(pressure, d)
+		}
+	}
+	if len(pressure) == 0 {
+		return alerts
+	}
+	var down []string
+	for _, service := range metrics.Services.Services {
+		for _, endpoint := range service.Endpoints {
+			if !endpoint.Up {
+				down = append(down, service.Name)
+				break
+			}
+		}
+	}
+	d := pressure[0]
+	chain := d.IOCause + " → " + d.Name + fmt.Sprintf(" util %.1f%% → latency %.1f ms", d.Utilization, d.LatencyMs)
+	if len(down) > 0 {
+		chain += " → недоступны/медленны сервисы: " + strings.Join(down, ", ")
+	}
+	severity := "warning"
+	if len(down) > 0 || d.Utilization >= 98 {
+		severity = "critical"
+	}
+	correlated := Alert{ID: "correlation-io-" + d.Name, Severity: severity, Source: "Корреляция", Title: "Обнаружена связанная цепочка I/O-событий", Message: chain + fmt.Sprintf(". Уверенность причины %d%%.", d.IOConfidence)}
+	filtered := []Alert{correlated}
+	for _, a := range alerts {
+		if strings.HasPrefix(a.ID, "disk-io-pressure-") || strings.HasPrefix(a.ID, "service-") {
+			continue
+		}
+		filtered = append(filtered, a)
+	}
+	return filtered
+}
+
 func joinReasons(reasons []string, fallback string) string {
 	if len(reasons) == 0 {
 		return fallback
 	}
 	return strings.Join(reasons, " · ")
 }
+
+func withoutReason(reasons []string, excluded string) []string {
+	filtered := make([]string, 0, len(reasons))
+	for _, reason := range reasons {
+		if reason != excluded {
+			filtered = append(filtered, reason)
+		}
+	}
+	return filtered
+}

alerts_test.go

@@ -16,3 +16,26 @@ func TestEvaluateAlerts(t *testing.T) {
 		t.Fatalf("неверная сортировка уведомлений: %+v", alerts)
 	}
 }
+
+func TestSlowCollectionDoesNotCreateAlert(t *testing.T) {
+	metrics := dashboardMetrics{Monitor: MonitorHealth{SlowCollector: true, CollectionDurationMs: 12308}}
+	for _, alert := range evaluateAlerts(metrics, defaultThresholds()) {
+		if alert.ID == "monitor-slow" {
+			t.Fatalf("медленный цикл не должен создавать уведомление: %+v", alert)
+		}
+	}
+}
+
+func TestNeverRunSelfTestCreatesOneAlert(t *testing.T) {
+	metrics := dashboardMetrics{Disks: []DiskMetrics{{
+		Name:             "nvme0n1",
+		Model:            "Test NVMe",
+		SMARTStatus:      "Требует внимания",
+		SelfTestNeverRun: true,
+		AttentionReasons: []string{"SMART self-test ещё ни разу не запускался"},
+	}}}
+	alerts := evaluateAlerts(metrics, defaultThresholds())
+	if len(alerts) != 1 || alerts[0].ID != "disk-selftest-nvme0n1" {
+		t.Fatalf("ожидалось одно точное уведомление о self-test, получено: %+v", alerts)
+	}
+}

assets/NOTICE.md

@@ -0,0 +1,20 @@
+# Map data
+
+`world.json` is derived from Natural Earth 1:110m admin-0 countries (coordinates
+rounded to two decimal places; only country codes, labels and boundaries kept).
+Natural Earth data is public domain: https://www.naturalearthdata.com/about/terms-of-use/
+Source: https://github.com/nvkelso/natural-earth-vector/blob/master/geojson/ne_110m_admin_0_countries.geojson
+
+`dbip-country-lite-2026-10.mmdb.gz`: IP Geolocation by DB-IP, October 2026.
+Source: https://download.db-ip.com/free/dbip-country-lite-2026-10.mmdb.gz
+License: Creative Commons Attribution 4.0 International (CC BY 4.0).
+https://creativecommons.org/licenses/by/4.0/
+https://db-ip.com/db/download/ip-to-country-lite
+The database is unmodified. The traffic page displays the required DB-IP link.
+Countries are approximate; plotted positions are country labels, not exact IP locations.
+
+Optional DB-IP City Lite October 2026 is downloaded separately through Settings.
+Source: https://download.db-ip.com/free/dbip-city-lite-2026-10.mmdb.gz
+License: CC BY 4.0, https://creativecommons.org/licenses/by/4.0/
+https://db-ip.com/db/download/ip-to-city-lite
+The database is unmodified; city and region are approximate.

assets/network.html

@@ -0,0 +1,40 @@
+<!doctype html><html lang="ru"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1"><title>Сетевая активность · Proxmox Dashboard</title><style>
+:root{color-scheme:dark;--bg:#090e15;--panel:#111b26;--line:#293846;--muted:#92a8ba;--lime:#c0ee86;--blue:#70dcec}*{box-sizing:border-box}html,body{margin:0;height:100%;overflow:hidden}body{background:radial-gradient(ellipse at 30% 30%,#142738,transparent 65%),var(--bg);color:#e9f0f6;font:13px system-ui,sans-serif;padding:22px;display:grid;grid-template-rows:54px 32px 82px 36px minmax(0,1fr) 22px;gap:12px}header{display:flex;align-items:center;justify-content:space-between;gap:12px}h1{font-size:26px;letter-spacing:-1px;margin:0}small,.muted{color:var(--muted)}.eyebrow{font-size:9px;letter-spacing:2px;color:var(--lime)}nav{display:flex;gap:15px;align-items:center}a{color:var(--blue);text-decoration:none}button,input,select{font:inherit;color:inherit;background:#182430;border:1px solid var(--line);padding:7px 10px;border-radius:8px;min-width:0}button{cursor:pointer}button:disabled{opacity:.35;cursor:default}button:hover{border-color:var(--blue)}:focus-visible{outline:2px solid var(--blue);outline-offset:2px}.status{display:flex;align-items:center;gap:10px;color:var(--muted);min-width:0}.status span{overflow:hidden;white-space:nowrap;text-overflow:ellipsis}.badge{font-size:10px;color:var(--lime);border:1px solid #496036;padding:5px 8px;border-radius:20px;white-space:nowrap}.badge.warn{color:#ffbd80;border-color:#875d36}.metrics{display:grid;grid-template-columns:repeat(4,1fr);gap:12px}.metric,.panel{border:1px solid var(--line);background:#101a24d9;border-radius:14px;min-width:0;min-height:0;overflow:hidden}.metric{padding:12px 16px}.metric small{font-size:11px}.metric b{display:block;font-size:28px;line-height:1.3;letter-spacing:-1px}.filters{display:flex;gap:8px}.filters input{flex:1}.filters label{display:flex;align-items:center;gap:6px;font-size:11px;color:var(--muted)}.filters label input{accent-color:var(--lime);flex:none;width:13px;height:13px;margin:0;grid-column:auto;grid-row:auto}main{display:grid;grid-template-columns:minmax(0,1fr) 290px;gap:12px;min-height:0}.flows{display:grid;grid-template-rows:40px 27px minmax(0,1fr) 38px;padding:0 14px}.heading{display:flex;align-items:center;justify-content:space-between;gap:8px}h2{font-size:12px;font-weight:600;margin:0}.table-head,.flow{display:grid;grid-template-columns:minmax(0,1.25fr) minmax(0,1.25fr) 80px 108px 95px;gap:12px;align-items:center}.table-head{color:var(--muted);font-size:10px}.flow{height:55px;border-top:1px solid #21303d;cursor:pointer;font:12px ui-monospace,monospace}.flow:hover{background:#20344566}.flow>div{min-width:0}.flow strong{font-weight:500;color:var(--blue);display:block;white-space:nowrap;overflow:hidden;text-overflow:ellipsis}.flow small{font:10px system-ui;display:block;margin-top:4px;white-space:nowrap;overflow:hidden;text-overflow:ellipsis}.state{font-size:10px}.state.ok{color:var(--lime)}.state.pending{color:#ffc085}#rows{min-height:0;overflow:hidden}.pager{display:flex;align-items:center;gap:12px;color:var(--muted);font-size:11px;border-top:1px solid var(--line)}.pager button{padding:3px 8px}.pager #resume{margin-left:auto;color:var(--lime)}aside{display:grid;grid-template-rows:1fr 1fr 1fr;gap:12px;min-height:0}aside .panel{padding:12px 14px}aside h2{margin-bottom:9px}.rank{display:flex;justify-content:space-between;gap:10px;font-size:11px;line-height:22px}.rank span{overflow:hidden;text-overflow:ellipsis;white-space:nowrap}.rank b{font-weight:500;color:var(--blue)}.block-value{font-size:24px;color:#c4a9ff;margin:8px 0}.help{font-size:10px;color:var(--muted);line-height:1.5}.empty{color:var(--muted);padding:20px 0;line-height:1.7;font-size:12px}.footer{display:flex;justify-content:space-between;font-size:10px;color:var(--muted);gap:10px}.link-button{background:none;border:0;padding:0;color:var(--blue);font-size:11px}dialog{width:min(650px,calc(100vw - 24px));max-height:85dvh;overflow:auto;border:1px solid #455969;border-radius:18px;background:#141f2b;color:#e9f0f6;padding:22px}dialog::backdrop{background:#03080ccc;backdrop-filter:blur(5px)}dialog .heading{margin-bottom:16px}dialog h2{font-size:19px}.detail{padding:10px 0;border-top:1px solid var(--line);overflow-wrap:anywhere}.detail small{display:block;margin-bottom:4px}dialog p{line-height:1.7}#tabs{display:none}.filters #port{width:110px}
+@media(max-width:1100px){main{grid-template-columns:minmax(0,1fr) 220px}.table-head,.flow{grid-template-columns:1fr 1fr 55px 83px;gap:8px}.flow .volume,.table-head .volume{display:none}.flow{font-size:11px}nav{gap:9px}body{padding:14px}aside .panel{padding:9px}aside .rank{line-height:19px}}
+@media(max-height:700px) and (min-width:761px){body{padding:12px;gap:8px;grid-template-rows:40px 26px 64px 32px minmax(0,1fr) 18px}.metric{padding:8px 12px}.metric b{font-size:22px}.flow{height:46px}aside{grid-template-rows:1fr 1fr 1fr;gap:6px}aside .rank{line-height:17px}.block-value{font-size:20px;margin:3px 0}aside h2{margin-bottom:4px}.help{font-size:9px}}
+@media(max-width:760px){body{padding:10px;gap:8px;grid-template-rows:45px 30px 104px auto 28px minmax(0,1fr) 18px}h1{font-size:18px;white-space:nowrap}.eyebrow{font-size:7px}nav a{font-size:0}nav a:before{content:"HTTP ↗";font-size:11px}nav .dashboard{display:none}.metrics{grid-template-columns:1fr 1fr;gap:6px}.metric{padding:6px 10px}.metric small{font-size:9px}.metric b{font-size:22px}.filters{display:grid;grid-template-columns:1fr 100px;gap:5px}.filters label{grid-row:3;white-space:nowrap;font-size:10px}#netMonitoringControl{grid-column:1}#netExternalControl{grid-column:2}.filters #search{grid-column:1/-1;grid-row:2}.filters select{font-size:11px;padding:6px}.filters #port{width:100%}#tabs{display:flex;gap:6px}#tabs button{flex:1;padding:4px;font-size:11px}#tabs button.active{border-color:var(--blue)}main{display:block}.flows{height:100%;padding:0 10px;grid-template-rows:34px 24px minmax(0,1fr) 36px}aside{display:none;height:100%;grid-template-columns:1fr 1fr;grid-template-rows:minmax(0,1fr) 105px}aside .firewall{grid-column:1/-1}body[data-tab=stats] .flows{display:none}body[data-tab=stats] aside{display:grid}.flow,.table-head{grid-template-columns:1fr 1fr 60px}.flow .protocol,.table-head .protocol{display:none}.flow{height:59px;font-size:10px}.state{font-size:9px}.flow small{font-size:9px}.status{font-size:10px}.status button{font-size:10px}.footer{font-size:8px}.footer .link-button{font-size:9px}aside .rank{line-height:19px}.block-value{display:inline-block;font-size:20px;margin:0 10px 0 0}.help{font-size:9px}.firewall h2{margin-bottom:4px}}
+</style></head><body data-tab="flows">
+<header><div><div class="eyebrow">PROXMOX / NETWORK OBSERVATORY</div><h1>Сетевая активность<span style="color:var(--lime)">.</span></h1></div><nav><a href="/traffic">HTTP / CrowdSec ↗</a><a class="dashboard" href="/">Dashboard</a><button id="pause">Пауза</button></nav></header>
+<div class="status"><b id="live" class="badge warn">ОЖИДАНИЕ</b><span id="source">Подключение к агенту…</span><button class="link-button" id="statusDetails">Диагностика ⓘ</button></div>
+<section class="metrics"><div class="metric"><small>TCP · ESTABLISHED</small><b id="established">—</b></div><div class="metric"><small>TCP · SYN_SENT / SYN_RECV</small><b id="pending">—</b></div><div class="metric"><small>UDP · отслеживаемые потоки</small><b id="udp">—</b></div><div class="metric"><small>ICMP / ICMPv6 · записи</small><b id="icmp">—</b></div></section>
+<div class="filters"><select id="protocol" aria-label="Протокол"><option value="">Все протоколы</option><option value="tcp">TCP</option><option value="udp">UDP</option><option value="icmp">ICMP / ICMPv6</option></select><select id="port" aria-label="Порт назначения"><option value="">Все порты</option></select><input id="search" placeholder="Найти IP или состояние…" aria-label="Поиск IP или состояния"><label id="netMonitoringControl"><input id="hideMonitoring" type="checkbox">Скрыть мониторинг</label><label id="netExternalControl"><input id="external" type="checkbox">Внешние IP</label></div>
+<nav id="tabs"><button class="active" data-tab="flows">Потоки</button><button data-tab="stats">Статистика</button></nav>
+<main><section class="panel flows"><div class="heading"><h2>Текущая таблица conntrack</h2><small id="count">—</small></div><div class="table-head"><span>Инициатор</span><span>Назначение / NAT</span><span class="protocol">Протокол</span><span>Состояние</span><span class="volume">Байты → / ←</span></div><div id="rows"><div class="empty">Ожидание первого снимка…</div></div><div class="pager"><button id="prev" aria-label="Предыдущие потоки">←</button><span id="page">—</span><button id="next" aria-label="Следующие потоки">→</button><button id="resume">К свежим ↗</button></div></section>
+<aside><section class="panel"><h2>Топ инициаторов · потоки</h2><div id="topIPs"></div></section><section class="panel"><h2>Топ портов назначения</h2><div id="topPorts"></div></section><section class="panel firewall"><div class="heading"><h2>CrowdSec · firewall</h2><button class="link-button" id="firewallDetails">ⓘ</button></div><div id="blocked" class="block-value">—</div><div class="help" id="firewallNote">Ожидание счётчиков</div></section></aside></main>
+<footer class="footer"><span>Снимки ~5 с · короткие потоки могут быть пропущены</span><button class="link-button" id="about">Как читать данные ⓘ</button><a href="/#traffic-settings">Настройки ↗</a></footer>
+<dialog id="dialog"><div class="heading"><h2 id="title"></h2><button id="close" aria-label="Закрыть">×</button></div><div id="details"></div></dialog>
+<script>
+const el=id=>document.getElementById(id),safe=v=>String(v??'').replace(/[&<>"']/g,c=>({'&':'&amp;','<':'&lt;','>':'&gt;','"':'&quot;',"'":'&#39;'}[c])),num=v=>Number(v||0).toLocaleString('ru-RU'),bytes=n=>{n=Number(n||0);return n>=1073741824?(n/1073741824).toFixed(1)+' GiB':n>=1048576?(n/1048576).toFixed(1)+' MiB':n>=1024?(n/1024).toFixed(1)+' KiB':n+' B'},endpoint=(ip,p)=>p?(ip.includes(':')?'['+ip+']':ip)+':'+p:ip;
+const names=new Intl.DisplayNames(['ru'],{type:'region'}),country=c=>c==='LAN'?'Локальная сеть':c&&/^[A-Z]{2}$/.test(c)?names.of(c):'Без геолокации';
+try{el('hideMonitoring').checked=localStorage.getItem('proxmox-hide-monitoring')==='1'}catch{}
+let snapshot=null,frozen=null,page=0,visible=[],paused=false,busy=false,networkError='';
+const show=(title,html)=>{el('title').textContent=title;el('details').innerHTML=html;el('dialog').showModal()},fields=rows=>rows.map(([k,v])=>'<div class="detail"><small>'+safe(k)+'</small>'+safe(v)+'</div>').join('');
+function filterFlows(){const p=el('protocol').value,port=el('port').value,q=el('search').value.trim().toLowerCase();return ((frozen||snapshot)?.flows||[]).filter(f=>(!p||(p==='icmp'?f.protocol.startsWith('icmp'):f.protocol===p))&&(!port||String(f.destinationPort)===port)&&(!el('external').checked||f.external)&&(!q||[f.source,f.destination,f.replySource,f.replyDestination,f.state].join(' ').toLowerCase().includes(q)))}
+function rank(id,items){const counts=new Map();items.forEach(v=>counts.set(v,(counts.get(v)||0)+1));const h=el(id).parentElement.clientHeight;const limit=Math.max(1,Math.min(5,Math.floor((h-44)/22)));el(id).innerHTML=[...counts].sort((a,b)=>b[1]-a[1]||a[0].localeCompare(b[0])).slice(0,limit).map(([k,v])=>'<div class="rank"><span title="'+safe(k)+'">'+safe(k)+'</span><b>'+num(v)+'</b></div>').join('')||'<div class="help">Нет потоков</div>'}
+function render(){if(!snapshot)return;const data=frozen||snapshot,items=filterFlows();el('established').textContent=num(items.filter(f=>f.protocol==='tcp'&&f.state==='ESTABLISHED').length);el('pending').textContent=num(items.filter(f=>f.protocol==='tcp'&&['SYN_SENT','SYN_RECV'].includes(f.state)).length);el('udp').textContent=num(items.filter(f=>f.protocol==='udp').length);el('icmp').textContent=num(items.filter(f=>f.protocol.startsWith('icmp')).length);
+ if(!data.receivedAt||(data.error&&!(data.flows||[]).length)){['established','pending','udp','icmp'].forEach(id=>el(id).textContent='—')}
+ const fresh=snapshot.receivedAt&&Date.now()/1000-snapshot.receivedAt<25;el('live').textContent=networkError?'НЕТ СВЯЗИ':paused?'ПАУЗА':frozen?'СНИМОК':!fresh?'НЕТ ДАННЫХ':snapshot.error||snapshot.limited||snapshot.parseErrors?'НЕПОЛНЫЕ ДАННЫЕ':'● LIVE';el('live').classList.toggle('warn',!!networkError||!fresh||paused||!!snapshot.error||snapshot.limited||!!snapshot.parseErrors);el('source').textContent=(snapshot.agentName||'Агент')+' · '+(snapshot.at?new Date(data.at*1000).toLocaleTimeString('ru-RU'):'ожидание')+(snapshot.error?' · '+snapshot.error:snapshot.limited?' · лимит 5 000 потоков':'');
+ const rowHeight=innerWidth<=760?59:innerHeight<=700?46:55,count=Math.max(1,Math.floor(el('rows').clientHeight/rowHeight)),pages=Math.max(1,Math.ceil(items.length/count));page=Math.min(page,pages-1);visible=items.slice(page*count,(page+1)*count);el('count').textContent=num(items.length)+' / '+num(data.flows?.length)+(data.monitoringHidden?' · скрыто '+num(data.monitoringHidden):'')+' · '+(frozen?'снимок':'live');
+ el('rows').innerHTML=visible.map((f,i)=>{const nat=f.destination!==f.replySource||f.destinationPort!==f.replySourcePort;return '<article class="flow" role="button" tabindex="0" data-flow="'+i+'" aria-label="Поток '+safe(endpoint(f.source,f.sourcePort))+'"><div><strong>'+safe(endpoint(f.source,f.sourcePort))+'</strong><small>'+safe(country(f.country))+(f.monitoring?' · мониторинг':'')+'</small></div><div><strong>'+safe(endpoint(f.destination,f.destinationPort))+'</strong><small>'+safe(nat?'NAT → '+endpoint(f.replySource,f.replySourcePort):country(f.destinationCountry))+'</small></div><div class="protocol">'+safe(f.protocol.toUpperCase())+'</div><div class="state '+(f.state==='ESTABLISHED'?'ok':f.state.includes('SYN')?'pending':'')+'">'+safe(f.state)+'<small>'+safe(f.protocol.toUpperCase())+'</small></div><div class="volume">'+(f.accounting?bytes(f.bytes)+'<small>'+bytes(f.replyBytes)+'</small>':'<small>нет учёта</small>')+'</div></article>'}).join('')||'<div class="empty">'+safe(snapshot.error||'Нет потоков по выбранным фильтрам')+'</div>';
+ el('page').textContent=(page+1)+' / '+pages;el('prev').disabled=page===0;el('next').disabled=page>=pages-1;rank('topIPs',items.map(f=>f.source));rank('topPorts',items.filter(f=>f.destinationPort).map(f=>f.protocol.toUpperCase()+' / '+f.destinationPort));
+ const counters=snapshot.firewall||[];el('blocked').textContent=counters.length?num(counters.reduce((a,c)=>a+c.packets,0))+' пак.':'—';el('firewallNote').textContent=counters.length?'С начала жизни счётчиков · '+bytes(counters.reduce((a,c)=>a+c.bytes,0))+' · '+new Date(snapshot.firewallAt*1000).toLocaleTimeString('ru-RU'):snapshot.firewallError||'Счётчики ещё не получены';
+}
+function openFlow(target){const row=target.closest('[data-flow]');if(!row)return;const f=visible[+row.dataset.flow];if(!f)return;show('Поток '+f.protocol.toUpperCase(),fields([['Инициатор',endpoint(f.source,f.sourcePort)+' · '+country(f.country)],['Исходное назначение',endpoint(f.destination,f.destinationPort)],['Обратное направление (NAT)',endpoint(f.replySource,f.replySourcePort)+' → '+endpoint(f.replyDestination,f.replyDestinationPort)],['Мониторинг',f.monitoring?'Да — правило по IP инициатора':'Нет'],['Состояние / зона',f.state+' / '+(f.zone||'0')],['Инициатор → назначение',f.accounting?bytes(f.bytes)+' · '+num(f.packets)+' пакетов':'Учёт пакетов/байтов не включён для этого потока'],['Ответное направление',f.accounting?bytes(f.replyBytes)+' · '+num(f.replyPackets)+' пакетов':'Нет данных'],['Время снимка',new Date((frozen||snapshot).at*1000).toLocaleString('ru-RU')]]))}
+el('rows').onclick=e=>openFlow(e.target);el('rows').onkeydown=e=>{if(e.key==='Enter'||e.key===' '){e.preventDefault();openFlow(e.target)}};el('close').onclick=()=>el('dialog').close();
+el('statusDetails').onclick=()=>show('Диагностика агента',fields([['Сбор',snapshot?.error||'Ошибок conntrack не сообщено'],['Связь',networkError||'Последний ответ получен'],['Получен сервером',snapshot?.receivedAt?new Date(snapshot.receivedAt*1000).toLocaleString('ru-RU'):'Ещё не получен'],['Ограничения',snapshot?.limited?'Достигнут лимит 5 000 записей; статистика частичная':'До 5 000 записей в снимке'],['Нераспознанные строки',num(snapshot?.parseErrors)],['Firewall',snapshot?.firewallError||'Поддерживаемые счётчики получены']])+ '<p>На Debian/Ubuntu агент автоматически устанавливает отсутствующий <code>conntrack</code> через apt-get и systemd. Службе нужны root; для чтения таблицы — root/CAP_NET_ADMIN. Ошибка установки повторяется не чаще раза в 30 минут. Для firewall нужен <code>nft</code>. При выключенном учёте conntrack байты недоступны; sysctl и правила автоматически не изменяются.</p>');
+el('firewallDetails').onclick=()=>show('Счётчики блокировок',fields((snapshot?.firewall||[]).map(c=>[c.name,num(c.packets)+' пакетов · '+bytes(c.bytes)]))+'<p>'+safe(snapshot?.firewallError||'Накопительные счётчики правил CrowdSec непосредственно перед drop/reject. Сбрасываются при пересоздании правил. Не зависят от фильтров списка потоков; не показывают количество людей или HTTP-запросов.')+'</p>');
+el('about').onclick=()=>show('Как читать сетевые данные','<p>Это текущие отслеживаемые потоки TCP, UDP, ICMP и ICMPv6, а не журнал всех пакетов. Снимки делаются примерно раз в 5 секунд: короткие потоки могут быть пропущены. TIME_WAIT и другие состояния закрытия остаются в таблице до истечения таймера.</p><p>Инициатор и назначение — исходное направление conntrack. Обратная пара адресов показывает трансляцию NAT, включая Docker. Соединение NPM с upstream — отдельный поток; оно не считается ещё одним посетителем.</p><p>UDP ASSURED — отметка conntrack, не TCP-соединение. Порт 443 сам по себе не доказывает HTTPS или QUIC. SYN_SENT/SYN_RECV не означают атаку.</p><p>Байты и пакеты накоплены за жизнь конкретного потока, если учёт был включён при его создании. Длительность соединения и точный поток новых подключений по этим снимкам не вычисляются.</p><p>Фильтры влияют на карточки и топы. Firewall показывает отдельные накопительные счётчики без фильтров. Приватные и локальные IP не геолокируются. «Скрыть мониторинг» применяет правила по IP инициатора; домен/путь относятся только к HTTP. Геолокация: <a href="https://db-ip.com">DB-IP</a>, CC BY 4.0.</p>');
+function reset(){frozen=null;page=0;render()};['protocol','port','external'].forEach(id=>el(id).onchange=reset);el('search').oninput=reset;el('hideMonitoring').onchange=()=>{try{localStorage.setItem('proxmox-hide-monitoring',el('hideMonitoring').checked?'1':'0')}catch{}frozen=null;page=0;poll(true)};el('next').onclick=()=>{if(!frozen)frozen=snapshot;page++;render()};el('prev').onclick=()=>{page--;render()};el('resume').onclick=reset;el('pause').onclick=()=>{paused=!paused;el('pause').textContent=paused?'Продолжить':'Пауза';render();if(!paused)poll()};document.querySelectorAll('[data-tab]').forEach(b=>{if(b.tagName==='BUTTON')b.onclick=()=>{document.body.dataset.tab=b.dataset.tab;document.querySelectorAll('#tabs button').forEach(t=>t.classList.toggle('active',t===b));render()}});window.addEventListener('resize',render);
+async function poll(force=false){if((paused&&!force)||busy||document.hidden)return;busy=true;try{const response=await fetch('/api/network?hideMonitoring='+(el('hideMonitoring').checked?'1':'0'));if(response.status===404){location.replace('/traffic');return}if(!response.ok)throw Error('HTTP '+response.status);snapshot=await response.json();networkError='';const current=el('port').value,ports=[...new Set((snapshot.flows||[]).map(f=>f.destinationPort).filter(Boolean))];if(current&&!ports.includes(+current))ports.push(+current);ports.sort((a,b)=>a-b);el('port').innerHTML='<option value="">Все порты</option>'+ports.map(p=>'<option value="'+p+'">'+p+'</option>').join('');el('port').value=current;render()}catch(e){networkError='Не удалось обновить: '+e.message;el('source').textContent=networkError;el('live').textContent='НЕТ СВЯЗИ';el('live').classList.add('warn')}finally{busy=false}}
+poll();setInterval(poll,5000);document.addEventListener('visibilitychange',()=>{if(!document.hidden)poll()});
+</script></body></html>

cpu.go

@@ -3,6 +3,7 @@ package main
 import (
 	"bufio"
 	"fmt"
+	"math"
 	"os"
 	"path/filepath"
 	"strconv"
@@ -33,14 +34,16 @@ type CPUStatic struct {
 
 type CPUMetrics struct {
 	CPUStatic
-	UsagePercent float64       `json:"usagePercent"`
+	UsagePercent       float64        `json:"usagePercent"`
-	FrequencyMHz float64       `json:"frequencyMhz"`
+	FrequencyMHz       float64        `json:"frequencyMhz"`
-	Load1        float64       `json:"load1"`
+	Load1              float64        `json:"load1"`
-	Load5        float64       `json:"load5"`
+	Load5              float64        `json:"load5"`
-	Load15       float64       `json:"load15"`
+	Load15             float64        `json:"load15"`
-	Uptime       uint64        `json:"uptimeSeconds"`
+	Uptime             uint64         `json:"uptimeSeconds"`
-	Temperatures []Temperature `json:"temperatures"`
+	TemperatureCelsius *float64       `json:"temperatureCelsius"`
-	CollectedAt  time.Time     `json:"collectedAt"`
+	Temperatures       []Temperature  `json:"temperatures"`
+	TopProcesses       []AgentProcess `json:"topProcesses"`
+	CollectedAt        time.Time      `json:"collectedAt"`
 }
 
 type Temperature struct {
@@ -89,10 +92,11 @@ func (c *cpuCollector) collect() (CPUMetrics, error) {
 	load1, load5, load15, _ := readLoadAverage()
 	uptime, _ := readUptime()
 
+	temperatures := readTemperatures()
 	return CPUMetrics{
 		CPUStatic: c.static, UsagePercent: usage, FrequencyMHz: frequency,
 		Load1: load1, Load5: load5, Load15: load15, Uptime: uptime,
-		Temperatures: readTemperatures(), CollectedAt: time.Now(),
+		Temperatures: temperatures, TemperatureCelsius: cpuTemperature(temperatures), TopProcesses: collectAgentProcesses(), CollectedAt: time.Now(),
 	}, nil
 }
 
@@ -284,3 +288,19 @@ func isCPUTemperatureChip(name string) bool {
 		return false
 	}
 }
+
+// cpuTemperature is the hottest CPU sensor, shared by live and historical views.
+// Do not average Tctl/Tdie with cooler cores or CCDs.
+func cpuTemperature(temperatures []Temperature) *float64 {
+	var hottest *float64
+	for _, t := range temperatures {
+		if math.IsNaN(t.Celsius) || math.IsInf(t.Celsius, 0) || t.Celsius <= 0 {
+			continue
+		}
+		if hottest == nil || t.Celsius > *hottest {
+			value := t.Celsius
+			hottest = &value
+		}
+	}
+	return hottest
+}

cpu_temperature_test.go

@@ -0,0 +1,24 @@
+package main
+
+import (
+	"math"
+	"testing"
+)
+
+func TestCPUTemperatureSharedWithHistory(t *testing.T) {
+	temperatures := []Temperature{{Label: "k10temp · Tctl", Celsius: 62}, {Label: "k10temp · Tccd1", Celsius: 38}, {Label: "k10temp · Tccd2", Celsius: 41}}
+	live := cpuTemperature(temperatures)
+	point := historyPointFromMetrics(dashboardMetrics{CPU: CPUMetrics{Temperatures: temperatures}})
+	if live == nil || *live != 62 || point.CPUTemperature != *live {
+		t.Fatalf("live/history disagree: %v, %+v", live, point)
+	}
+}
+
+func TestCPUTemperatureInvalidSensors(t *testing.T) {
+	if cpuTemperature([]Temperature{{Celsius: math.NaN()}, {Celsius: math.Inf(1)}, {Celsius: 0}}) != nil {
+		t.Fatal("invalid temperature selected")
+	}
+	if cpuTemperature(nil) != nil {
+		t.Fatal("missing sensor should stay missing")
+	}
+}

disks.go

@@ -13,42 +13,48 @@ import (
 )
 
 type DiskMetrics struct {
-	Name              string   `json:"name"`
+	Name              string       `json:"name"`
-	Path              string   `json:"path"`
+	Path              string       `json:"path"`
-	Model             string   `json:"model"`
+	Model             string       `json:"model"`
-	Serial            string   `json:"serial"`
+	Serial            string       `json:"serial"`
-	Type              string   `json:"type"`
+	Type              string       `json:"type"`
-	Protocol          string   `json:"protocol"`
+	Protocol          string       `json:"protocol"`
-	SizeBytes         uint64   `json:"sizeBytes"`
+	SizeBytes         uint64       `json:"sizeBytes"`
-	UsedBytes         *uint64  `json:"usedBytes"`
+	UsedBytes         *uint64      `json:"usedBytes"`
-	UsagePercent      *float64 `json:"usagePercent"`
+	UsagePercent      *float64     `json:"usagePercent"`
-	SMARTStatus       string   `json:"smartStatus"`
+	SMARTStatus       string       `json:"smartStatus"`
-	SMARTAvailable    bool     `json:"smartAvailable"`
+	SMARTAvailable    bool         `json:"smartAvailable"`
-	AttentionReasons  []string `json:"attentionReasons"`
+	AttentionReasons  []string     `json:"attentionReasons"`
-	Temperature       *float64 `json:"temperatureCelsius"`
+	SMARTHistory      []string     `json:"smartHistory"`
-	PowerOnHours      *uint64  `json:"powerOnHours"`
+	Temperature       *float64     `json:"temperatureCelsius"`
-	WearUsedPercent   *float64 `json:"wearUsedPercent"`
+	PowerOnHours      *uint64      `json:"powerOnHours"`
-	Reallocated       uint64   `json:"reallocated"`
+	WearUsedPercent   *float64     `json:"wearUsedPercent"`
-	Pending           uint64   `json:"pending"`
+	Reallocated       uint64       `json:"reallocated"`
-	Uncorrectable     uint64   `json:"uncorrectable"`
+	Pending           uint64       `json:"pending"`
-	CRCErrors         uint64   `json:"crcErrors"`
+	Uncorrectable     uint64       `json:"uncorrectable"`
-	MediaErrors       uint64   `json:"mediaErrors"`
+	CRCErrors         uint64       `json:"crcErrors"`
-	CounterChanges    []string `json:"counterChanges"`
+	MediaErrors       uint64       `json:"mediaErrors"`
-	LastSelfTest      string   `json:"lastSelfTest"`
+	SMARTErrorCount   uint64       `json:"smartErrorCount"`
-	LastSelfTestAt    string   `json:"lastSelfTestAt"`
+	CounterChanges    []string     `json:"counterChanges"`
-	SelfTestNeverRun  bool     `json:"selfTestNeverRun"`
+	LastSelfTest      string       `json:"lastSelfTest"`
-	ShortTestStarted  bool     `json:"shortTestStarted"`
+	LastSelfTestAt    string       `json:"lastSelfTestAt"`
-	ReadIOPS          float64  `json:"readIops"`
+	SelfTestNeverRun  bool         `json:"selfTestNeverRun"`
-	WriteIOPS         float64  `json:"writeIops"`
+	ShortTestStarted  bool         `json:"shortTestStarted"`
-	ReadBytesPerSec   float64  `json:"readBytesPerSec"`
+	ReadIOPS          float64      `json:"readIops"`
-	WriteBytesPerSec  float64  `json:"writeBytesPerSec"`
+	WriteIOPS         float64      `json:"writeIops"`
-	ReadLatencyMs     float64  `json:"readLatencyMs"`
+	ReadBytesPerSec   float64      `json:"readBytesPerSec"`
-	WriteLatencyMs    float64  `json:"writeLatencyMs"`
+	WriteBytesPerSec  float64      `json:"writeBytesPerSec"`
-	LatencyMs         float64  `json:"latencyMs"`
+	ReadLatencyMs     float64      `json:"readLatencyMs"`
-	Utilization       float64  `json:"utilizationPercent"`
+	WriteLatencyMs    float64      `json:"writeLatencyMs"`
-	QueueDepth        uint64   `json:"queueDepth"`
+	LatencyMs         float64      `json:"latencyMs"`
-	AverageQueue      float64  `json:"averageQueue"`
+	Utilization       float64      `json:"utilizationPercent"`
-	IOPressureSeconds float64  `json:"ioPressureSeconds"`
+	QueueDepth        uint64       `json:"queueDepth"`
+	AverageQueue      float64      `json:"averageQueue"`
+	IOPressureSeconds float64      `json:"ioPressureSeconds"`
+	IOCause           string       `json:"ioCause"`
+	IOCauseDetail     string       `json:"ioCauseDetail"`
+	IOConfidence      int          `json:"ioConfidence"`
+	TopConsumers      []IOConsumer `json:"topConsumers"`
 }
 
 type diskIOSnapshot struct{ reads, readSectors, readMS, writes, writeSectors, writeMS, inFlight, ioMS, weightedMS uint64 }
@@ -65,11 +71,11 @@ type diskCollector struct {
 	ioPressureSince map[string]time.Time
 }
 
-func (c *diskCollector) collect() []DiskMetrics {
+func (c *diskCollector) collect(thresholds AlertThresholds) []DiskMetrics {
 	c.mu.Lock()
 	defer c.mu.Unlock()
 	if time.Since(c.updatedAt) < time.Minute && c.cached != nil {
-		c.applyDiskIO(c.cached)
+		c.applyDiskIO(c.cached, thresholds)
 		return c.cached
 	}
 	current := readPhysicalDisks()
@@ -104,12 +110,12 @@ func (c *diskCollector) collect() []DiskMetrics {
 		}
 	}
 	c.cached = current
-	c.applyDiskIO(c.cached)
+	c.applyDiskIO(c.cached, thresholds)
 	c.updatedAt = time.Now()
 	return c.cached
 }
 
-func (c *diskCollector) applyDiskIO(disks []DiskMetrics) {
+func (c *diskCollector) applyDiskIO(disks []DiskMetrics, thresholds AlertThresholds) {
 	now := time.Now()
 	snapshots := readDiskIOStats("/proc/diskstats")
 	if c.ioPrevious == nil {
@@ -144,11 +150,13 @@ func (c *diskCollector) applyDiskIO(disks []DiskMetrics) {
 			}
 			disk.Utilization = min(float64(current.ioMS-old.ioMS)/(elapsed*10), 100)
 			disk.AverageQueue = float64(current.weightedMS-old.weightedMS) / (elapsed * 1000)
-			latencyLimit := 20.0
+			utilLimit, latencyLimit, queueLimit := thresholds.DiskSSDUtil, thresholds.DiskSSDLatency, thresholds.DiskSSDQueue
 			if disk.Type == "HDD" {
-				latencyLimit = 50
+				utilLimit, latencyLimit, queueLimit = thresholds.DiskHDDUtil, thresholds.DiskHDDLatency, thresholds.DiskHDDQueue
+			} else if strings.Contains(disk.Type, "NVMe") {
+				utilLimit, latencyLimit, queueLimit = thresholds.DiskNVMeUtil, thresholds.DiskNVMeLatency, thresholds.DiskNVMeQueue
 			}
-			pressured := disk.Utilization >= 90 || (disk.LatencyMs >= latencyLimit && disk.ReadIOPS+disk.WriteIOPS >= 1) || disk.AverageQueue >= 4
+			pressured := disk.Utilization >= utilLimit || (disk.LatencyMs >= latencyLimit && disk.ReadIOPS+disk.WriteIOPS >= 1) || disk.AverageQueue >= queueLimit
 			if pressured {
 				if c.ioPressureSince[disk.Name].IsZero() {
 					c.ioPressureSince[disk.Name] = now
@@ -197,7 +205,7 @@ func diskCounterChanges(old, current DiskMetrics) []string {
 	checks := []struct {
 		label    string
 		old, now uint64
-	}{{"Reallocated вырос", old.Reallocated, current.Reallocated}, {"Pending вырос", old.Pending, current.Pending}, {"Uncorrectable вырос", old.Uncorrectable, current.Uncorrectable}, {"CRC-ошибки выросли", old.CRCErrors, current.CRCErrors}, {"Media errors выросли", old.MediaErrors, current.MediaErrors}}
+	}{{"Reallocated вырос", old.Reallocated, current.Reallocated}, {"Pending вырос", old.Pending, current.Pending}, {"Uncorrectable вырос", old.Uncorrectable, current.Uncorrectable}, {"CRC-ошибки выросли", old.CRCErrors, current.CRCErrors}, {"Media errors выросли", old.MediaErrors, current.MediaErrors}, {"Ошибки SMART-журнала выросли", old.SMARTErrorCount, current.SMARTErrorCount}}
 	var changes []string
 	for _, check := range checks {
 		if check.now > check.old {
@@ -383,6 +391,17 @@ type smartctlJSON struct {
 			} `json:"table"`
 		} `json:"standard"`
 	} `json:"ata_smart_self_test_log"`
+	NVMeSelfTestLog struct {
+		Table []struct {
+			SelfTestCode struct {
+				String string `json:"string"`
+			} `json:"self_test_code"`
+			SelfTestResult struct {
+				String string `json:"string"`
+			} `json:"self_test_result"`
+			PowerOnHours uint64 `json:"power_on_hours"`
+		} `json:"table"`
+	} `json:"nvme_self_test_log"`
 	NVMeHealth *struct {
 		Temperature     float64 `json:"temperature"`
 		PercentageUsed  float64 `json:"percentage_used"`
@@ -402,6 +421,10 @@ func applySMART(disk *DiskMetrics) {
 	if len(output) == 0 {
 		return
 	}
+	applySMARTJSON(disk, output)
+}
+
+func applySMARTJSON(disk *DiskMetrics, output []byte) {
 	var smart smartctlJSON
 	if json.Unmarshal(output, &smart) != nil {
 		return
@@ -443,12 +466,20 @@ func applySMART(disk *DiskMetrics) {
 			disk.AttentionReasons = append(disk.AttentionReasons, "Ошибки целостности носителя: "+strconv.FormatUint(smart.NVMeHealth.MediaErrors, 10))
 		}
 	}
-	if len(smart.ATASelfTestLog.Standard.Table) > 0 {
+	if len(smart.NVMeSelfTestLog.Table) > 0 {
+		last := smart.NVMeSelfTestLog.Table[0]
+		description := strings.TrimSpace(last.SelfTestCode.String)
+		result := firstNonEmpty(strings.TrimSpace(last.SelfTestResult.String), "Результат неизвестен")
+		if description != "" {
+			disk.LastSelfTest = description + " · " + result
+		} else {
+			disk.LastSelfTest = result
+		}
+		setLastSelfTestAt(disk, last.PowerOnHours)
+	} else if len(smart.ATASelfTestLog.Standard.Table) > 0 {
 		last := smart.ATASelfTestLog.Standard.Table[0]
 		disk.LastSelfTest = firstNonEmpty(last.Status.String, "Результат неизвестен")
-		if disk.PowerOnHours != nil && *disk.PowerOnHours >= last.LifetimeHours {
+		setLastSelfTestAt(disk, last.LifetimeHours)
-			disk.LastSelfTestAt = time.Now().Add(-time.Duration(*disk.PowerOnHours-last.LifetimeHours) * time.Hour).Format(time.RFC3339)
-		}
 	} else {
 		disk.SelfTestNeverRun = true
 		disk.LastSelfTest = "Никогда не запускался"
@@ -461,6 +492,12 @@ func applySMART(disk *DiskMetrics) {
 	}
 }
 
+func setLastSelfTestAt(disk *DiskMetrics, testPowerOnHours uint64) {
+	if disk.PowerOnHours != nil && *disk.PowerOnHours >= testPowerOnHours {
+		disk.LastSelfTestAt = time.Now().Add(-time.Duration(*disk.PowerOnHours-testPowerOnHours) * time.Hour).Format(time.RFC3339)
+	}
+}
+
 func applyATAAttributes(disk *DiskMetrics, smart smartctlJSON) {
 	wearNames := map[string]bool{
 		"Percent_Lifetime_Remain": true, "SSD_Life_Left": true,
@@ -482,16 +519,23 @@ func applyATAAttributes(disk *DiskMetrics, smart smartctlJSON) {
 			wear := float64(100 - attribute.Value)
 			disk.WearUsedPercent = &wear
 		}
-		if attribute.WhenFailed != "" && attribute.WhenFailed != "-" {
+		if strings.EqualFold(attribute.WhenFailed, "FAILING_NOW") {
 			reason := attribute.Name + " вышел за порог"
 			if attribute.Raw.String != "" {
 				reason += " (" + attribute.Raw.String + ")"
 			}
 			disk.AttentionReasons = append(disk.AttentionReasons, reason)
+		} else if attribute.WhenFailed != "" && attribute.WhenFailed != "-" {
+			reason := attribute.Name + " ранее выходил за порог"
+			if attribute.Raw.String != "" {
+				reason += " (" + attribute.Raw.String + ")"
+			}
+			disk.SMARTHistory = append(disk.SMARTHistory, reason)
 		}
 	}
 	if smart.ATAErrorLog.Summary.Count > 0 {
-		disk.AttentionReasons = append(disk.AttentionReasons, "Ошибок в SMART-журнале: "+strconv.Itoa(smart.ATAErrorLog.Summary.Count))
+		disk.SMARTErrorCount = uint64(smart.ATAErrorLog.Summary.Count)
+		disk.SMARTHistory = append(disk.SMARTHistory, "Записей в SMART-журнале: "+strconv.Itoa(smart.ATAErrorLog.Summary.Count))
 	}
 }
 
@@ -505,12 +549,12 @@ func applySMARTExitStatus(disk *DiskMetrics, status int) {
 		disk.AttentionReasons = append(disk.AttentionReasons, "Критический SMART-атрибут достиг порога")
 	}
 	if status&32 != 0 {
-		disk.AttentionReasons = append(disk.AttentionReasons, "SMART-атрибут ранее находился ниже порога")
+		disk.SMARTHistory = append(disk.SMARTHistory, "SMART-атрибут ранее находился ниже порога")
 	}
 	if status&64 != 0 {
-		disk.AttentionReasons = append(disk.AttentionReasons, "В журнале SMART обнаружены ошибки")
+		disk.SMARTHistory = append(disk.SMARTHistory, "В журнале SMART есть старые записи об ошибках")
 	}
 	if status&128 != 0 {
-		disk.AttentionReasons = append(disk.AttentionReasons, "В журнале самотестирования есть ошибки")
+		disk.SMARTHistory = append(disk.SMARTHistory, "В журнале самотестирования есть старые ошибки")
 	}
 }

disks_test.go

@@ -4,9 +4,46 @@ import (
 	"encoding/json"
 	"os"
 	"path/filepath"
+	"strings"
 	"testing"
+	"time"
 )
 
+func TestApplySMARTJSONReadsNVMeSelfTestHistory(t *testing.T) {
+	disk := DiskMetrics{Path: "/dev/nvme0n1"}
+	output := []byte(`{
+		"model_name":"ADATA LEGEND 900",
+		"smart_status":{"passed":true},
+		"power_on_time":{"hours":960},
+		"nvme_self_test_log":{
+			"current_self_test_operation":{"value":0,"string":"No self-test in progress"},
+			"table":[{
+				"self_test_code":{"value":1,"string":"Short"},
+				"self_test_result":{"value":0,"string":"Completed without error"},
+				"power_on_hours":959
+			}]
+		}
+	}`)
+
+	before := time.Now().Add(-2 * time.Hour)
+	applySMARTJSON(&disk, output)
+	after := time.Now()
+
+	if disk.SelfTestNeverRun {
+		t.Fatal("завершённый NVMe self-test ошибочно отмечен как никогда не запускавшийся")
+	}
+	if disk.LastSelfTest != "Short · Completed without error" {
+		t.Fatalf("неожиданный результат self-test: %q", disk.LastSelfTest)
+	}
+	parsed, err := time.Parse(time.RFC3339, disk.LastSelfTestAt)
+	if err != nil || parsed.Before(before) || parsed.After(after) {
+		t.Fatalf("неверно вычислено время self-test: %q, err=%v", disk.LastSelfTestAt, err)
+	}
+	if len(disk.AttentionReasons) != 0 || disk.SMARTStatus != "Исправен" {
+		t.Fatalf("исправный NVMe требует внимания: %+v", disk)
+	}
+}
+
 func TestIsPhysicalDiskName(t *testing.T) {
 	tests := map[string]bool{
 		"sda": true, "sdb": true, "nvme0n1": true,
@@ -68,3 +105,37 @@ func TestApplyATAWearAndReason(t *testing.T) {
 		t.Fatalf("причина предупреждения не добавлена: %+v", disk)
 	}
 }
+
+func TestHistoricalATAFailureDoesNotRequireAttention(t *testing.T) {
+	var smart smartctlJSON
+	attribute := struct {
+		Name       string `json:"name"`
+		Value      int    `json:"value"`
+		Threshold  int    `json:"thresh"`
+		WhenFailed string `json:"when_failed"`
+		Raw        struct {
+			String string `json:"string"`
+			Value  int64  `json:"value"`
+		} `json:"raw"`
+	}{Name: "Airflow_Temperature_Cel", WhenFailed: "In_the_past"}
+	attribute.Raw.String = "46 (Min/Max 26/47 #15)"
+	smart.ATAAttributes.Table = append(smart.ATAAttributes.Table, attribute)
+	disk := DiskMetrics{}
+	applyATAAttributes(&disk, smart)
+	applySMARTExitStatus(&disk, 32|64|128)
+	if len(disk.AttentionReasons) != 0 {
+		t.Fatalf("историческая ошибка стала активной: %+v", disk.AttentionReasons)
+	}
+	if len(disk.SMARTHistory) != 4 {
+		t.Fatalf("история SMART потеряна: %+v", disk.SMARTHistory)
+	}
+}
+
+func TestSMARTErrorLogGrowthRequiresAttention(t *testing.T) {
+	old := DiskMetrics{SMARTErrorCount: 2}
+	current := DiskMetrics{SMARTErrorCount: 3}
+	changes := diskCounterChanges(old, current)
+	if len(changes) != 1 || !strings.Contains(changes[0], "2 → 3") {
+		t.Fatalf("рост журнала не обнаружен: %+v", changes)
+	}
+}

go.mod

@@ -2,7 +2,10 @@ module proxmox-host-info
 
 go 1.25.0
 
-require modernc.org/sqlite v1.54.0
+require (
+	github.com/oschwald/maxminddb-golang v1.13.1
+	modernc.org/sqlite v1.54.0
+)
 
 require (
 	github.com/dustin/go-humanize v1.0.1 // indirect

go.sum

@@ -1,3 +1,5 @@
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
+github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
 github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
 github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e h1:ijClszYn+mADRFY17kjQEVQ1XRhq2/JR1M3sGqeJoxs=
@@ -10,8 +12,14 @@ github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWE
 github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
 github.com/ncruces/go-strftime v1.0.0 h1:HMFp8mLCTPp341M/ZnA4qaf7ZlsbTc+miZjCLOFAw7w=
 github.com/ncruces/go-strftime v1.0.0/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls=
+github.com/oschwald/maxminddb-golang v1.13.1 h1:G3wwjdN9JmIK2o/ermkHM+98oX5fS+k5MbwsmL4MRQE=
+github.com/oschwald/maxminddb-golang v1.13.1/go.mod h1:K4pgV9N/GcK694KSTmVSDTODk4IsCNThNdTmnaBZ/F8=
+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
+github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
 github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
+github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
+github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
 golang.org/x/mod v0.37.0 h1:vF1DjpVEshcIqoEaauuHebaLk1O1forxjxBaVn884JQ=
 golang.org/x/mod v0.37.0/go.mod h1:m8S8VeM9r4dzDwjrKO0a1sZP3YjeMamRRlD+fmR2Q/0=
 golang.org/x/sync v0.21.0 h1:HLII4xRRTtCRkxYp4HNFF0Js/Og6q2i++KXbg0gHCwM=
@@ -21,6 +29,8 @@ golang.org/x/sys v0.46.0 h1:noSf2Fq6F8DBgS+LysIkx7rIExoNHJsxOAtPp4rthXw=
 golang.org/x/sys v0.46.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
 golang.org/x/tools v0.47.0 h1:7Kn5x/d1svx/PzryTsqeoZN4TZwqeH5pGWjefhLi/1Q=
 golang.org/x/tools v0.47.0/go.mod h1:dFHnyTvFWY212G+h7ZY4Vsp/K3U4/7W9TyVaAul8uCA=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 modernc.org/cc/v4 v4.29.0 h1:CXgwL8cvxmyzBQZzbSl/6xFtMCryb6u8IOqDci39cgc=
 modernc.org/cc/v4 v4.29.0/go.mod h1:OnovgIhbbMXMu1aISnJ0wvVD1KnW+cAUJkIrAWh+kVI=
 modernc.org/ccgo/v4 v4.34.6 h1:sBgfIwyN0TQ9C5hwIeuqyeAKyMWnbvj2fvpF4L11uzU=

history.go

@@ -47,6 +47,8 @@ func (s *Store) AddEntityMetrics(metrics dashboardMetrics) {
 		iops := d.ReadIOPS + d.WriteIOPS
 		util := d.Utilization
 		s.AddEntityHistory("disk-io", d.Name+" · "+d.Model, ts, &iops, &util)
+		latency := d.LatencyMs
+		s.AddEntityHistory("disk-latency", d.Name+" · "+d.Model, ts, &latency, nil)
 		if d.Temperature == nil {
 			continue
 		}
@@ -56,6 +58,36 @@ func (s *Store) AddEntityMetrics(metrics dashboardMetrics) {
 		}
 		s.AddEntityHistory("disk", d.Name+" · "+d.Model, ts, d.Temperature, wear)
 	}
+	for _, task := range metrics.Activity.Tasks {
+		if task.Type == "vzdump" && task.Duration > 0 && task.EndTime >= time.Now().Add(-15*time.Minute).Unix() {
+			duration := float64(task.Duration)
+			s.AddEntityHistory("backup-duration", "VMID "+task.ID, ts, &duration, nil)
+		}
+	}
+	for _, agent := range metrics.Agents {
+		if !agent.Online {
+			continue
+		}
+		name := agent.ID + " · " + agent.Name
+		cpu := agent.Report.CPUPercent
+		memory := float64(0)
+		if agent.Report.MemoryTotal > 0 {
+			memory = float64(agent.Report.MemoryUsed) / float64(agent.Report.MemoryTotal) * 100
+		}
+		swap := float64(0)
+		if agent.Report.SwapTotal > 0 {
+			swap = float64(agent.Report.SwapUsed) / float64(agent.Report.SwapTotal) * 100
+		}
+		s.AddEntityHistory("agent-resource", name, ts, &cpu, &memory)
+		s.AddEntityHistory("agent-swap", name, ts, &swap, nil)
+		pressure := agent.Report.Pressure.IO.Avg10
+		s.AddEntityHistory("agent-pressure", name, ts, &pressure, nil)
+		for _, filesystem := range agent.Report.Filesystems {
+			used := filesystem.UsedPercent
+			inodes := filesystem.InodesPercent
+			s.AddEntityHistory("agent-filesystem", name+" · "+filesystem.Mountpoint, ts, &used, &inodes)
+		}
+	}
 	s.PruneEntityHistory()
 }
 
@@ -67,12 +99,10 @@ func historyPointFromMetrics(metrics dashboardMetrics) HistoryPoint {
 		NetworkTransmit: metrics.Network.TransmitPerSec, UPSCharge: metrics.UPS.ChargePercent,
 		UPSLoad: metrics.UPS.LoadPercent,
 	}
-	if len(metrics.CPU.Temperatures) > 0 {
+	if temperature := cpuTemperature(metrics.CPU.Temperatures); temperature != nil {
-		for _, temperature := range metrics.CPU.Temperatures {
+		point.CPUTemperature = *temperature
-			point.CPUTemperature += temperature.Celsius
-		}
-		point.CPUTemperature /= float64(len(metrics.CPU.Temperatures))
 	}
+
 	var zfsSize, zfsUsed uint64
 	for _, pool := range metrics.ZFS.Pools {
 		zfsSize += pool.SizeBytes

history_test.go

@@ -8,7 +8,7 @@ func TestHistoryPointFromMetrics(t *testing.T) {
 		Guests: GuestsMetrics{Guests: []GuestMetrics{{Status: "running", CPU: .5, MaxCPU: 4, MemoryBytes: 50, MaxMemory: 100}}},
 	}
 	point := historyPointFromMetrics(metrics)
-	if point.CPUTemperature != 50 || point.GuestsCPU != 50 || point.GuestsMemory != 50 {
+	if point.CPUTemperature != 60 || point.GuestsCPU != 50 || point.GuestsMemory != 50 {
 		t.Fatalf("неожиданная историческая точка: %+v", point)
 	}
 }

io_attribution.go

@@ -0,0 +1,178 @@
+package main
+
+import (
+	"os"
+	"path/filepath"
+	"regexp"
+	"sort"
+	"strconv"
+	"strings"
+	"sync"
+	"time"
+)
+
+type IOConsumer struct {
+	Kind             string  `json:"kind"`
+	Name             string  `json:"name"`
+	VMID             int     `json:"vmid,omitempty"`
+	ReadBytesPerSec  float64 `json:"readBytesPerSec"`
+	WriteBytesPerSec float64 `json:"writeBytesPerSec"`
+	SharePercent     float64 `json:"sharePercent"`
+}
+type processIOSnapshot struct {
+	read, write           uint64
+	name, cmdline, cgroup string
+}
+type ioAttributionCollector struct {
+	mu        sync.Mutex
+	previous  map[int]processIOSnapshot
+	updatedAt time.Time
+	cached    []IOConsumer
+}
+
+var qemuIDPattern = regexp.MustCompile(`(?:^|\s)-id\s+(\d+)`)
+var lxcIDPattern = regexp.MustCompile(`(?:lxc(?:\.payload)?[./-]|pve-container@)(\d+)`)
+
+func (c *ioAttributionCollector) collect(guests GuestsMetrics) []IOConsumer {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+	now := time.Now()
+	current := readProcessIO()
+	elapsed := now.Sub(c.updatedAt).Seconds()
+	if c.previous == nil || elapsed <= 0 {
+		c.previous = current
+		c.updatedAt = now
+		return nil
+	}
+	names := map[int]string{}
+	for _, g := range guests.Guests {
+		names[g.VMID] = g.Name
+	}
+	grouped := map[string]*IOConsumer{}
+	var total float64
+	for pid, snapshot := range current {
+		old, ok := c.previous[pid]
+		if !ok || snapshot.read < old.read || snapshot.write < old.write {
+			continue
+		}
+		read := float64(snapshot.read-old.read) / elapsed
+		write := float64(snapshot.write-old.write) / elapsed
+		if read+write < 1024 {
+			continue
+		}
+		kind, name, vmid := classifyIOProcess(snapshot, names)
+		key := kind + ":" + strconv.Itoa(vmid) + ":" + name
+		consumer := grouped[key]
+		if consumer == nil {
+			consumer = &IOConsumer{Kind: kind, Name: name, VMID: vmid}
+			grouped[key] = consumer
+		}
+		consumer.ReadBytesPerSec += read
+		consumer.WriteBytesPerSec += write
+		total += read + write
+	}
+	var result []IOConsumer
+	for _, v := range grouped {
+		if total > 0 {
+			v.SharePercent = (v.ReadBytesPerSec + v.WriteBytesPerSec) / total * 100
+		}
+		result = append(result, *v)
+	}
+	sort.Slice(result, func(i, j int) bool {
+		return result[i].ReadBytesPerSec+result[i].WriteBytesPerSec > result[j].ReadBytesPerSec+result[j].WriteBytesPerSec
+	})
+	if len(result) > 8 {
+		result = result[:8]
+	}
+	c.previous = current
+	c.updatedAt = now
+	c.cached = result
+	return result
+}
+
+func classifyIOProcess(p processIOSnapshot, names map[int]string) (kind, name string, vmid int) {
+	if match := qemuIDPattern.FindStringSubmatch(p.cmdline); len(match) > 1 {
+		vmid, _ = strconv.Atoi(match[1])
+		return "VM", firstNonEmpty(names[vmid], "VM "+match[1]), vmid
+	}
+	if match := lxcIDPattern.FindStringSubmatch(p.cgroup); len(match) > 1 {
+		vmid, _ = strconv.Atoi(match[1])
+		return "LXC", firstNonEmpty(names[vmid], "LXC "+match[1]), vmid
+	}
+	return "Процесс", firstNonEmpty(p.name, "PID"), 0
+}
+
+func readProcessIO() map[int]processIOSnapshot {
+	result := map[int]processIOSnapshot{}
+	entries, _ := filepath.Glob("/proc/[0-9]*/io")
+	for _, path := range entries {
+		pid, _ := strconv.Atoi(filepath.Base(filepath.Dir(path)))
+		data, err := os.ReadFile(path)
+		if err != nil {
+			continue
+		}
+		var item processIOSnapshot
+		for _, line := range strings.Split(string(data), "\n") {
+			key, value, ok := strings.Cut(line, ":")
+			if !ok {
+				continue
+			}
+			n, _ := strconv.ParseUint(strings.TrimSpace(value), 10, 64)
+			if key == "read_bytes" {
+				item.read = n
+			} else if key == "write_bytes" {
+				item.write = n
+			}
+		}
+		comm, _ := os.ReadFile(filepath.Join(filepath.Dir(path), "comm"))
+		cmd, _ := os.ReadFile(filepath.Join(filepath.Dir(path), "cmdline"))
+		cg, _ := os.ReadFile(filepath.Join(filepath.Dir(path), "cgroup"))
+		item.name = strings.TrimSpace(string(comm))
+		item.cmdline = strings.ReplaceAll(string(cmd), "\x00", " ")
+		item.cgroup = string(cg)
+		result[pid] = item
+	}
+	return result
+}
+
+func attributeDiskIO(metrics *dashboardMetrics, consumers []IOConsumer) {
+	active := activeIOOperation(metrics.Activity.Tasks)
+	for i := range metrics.Disks {
+		disk := &metrics.Disks[i]
+		disk.TopConsumers = append([]IOConsumer(nil), consumers...)
+		if active != "" {
+			disk.IOCause = active
+			disk.IOCauseDetail = "Активная задача Proxmox совпадает по времени с дисковой нагрузкой"
+			disk.IOConfidence = 75
+		} else if len(consumers) > 0 {
+			top := consumers[0]
+			disk.IOCause = top.Kind + " · " + top.Name
+			disk.IOCauseDetail = "Крупнейший потребитель host I/O: " + strconv.FormatFloat(top.SharePercent, 'f', 1, 64) + "%"
+			disk.IOConfidence = 55
+		}
+	}
+}
+
+func activeIOOperation(tasks []ProxmoxTask) string {
+	for _, task := range tasks {
+		if task.EndTime != 0 && task.Status != "" {
+			continue
+		}
+		label := ""
+		switch task.Type {
+		case "vzdump":
+			label = "Backup"
+		case "qmigrate":
+			label = "Миграция"
+		case "qmsnapshot", "vzsnapshot":
+			label = "Snapshot"
+		}
+		if label != "" {
+			if task.ID != "" {
+				label += " VM/LXC " + task.ID
+			}
+			return label
+		}
+	}
+	return ""
+}

io_attribution_test.go

@@ -0,0 +1,33 @@
+package main
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestClassifyQEMUAndLXCIO(t *testing.T) {
+	kind, name, vmid := classifyIOProcess(processIOSnapshot{name: "qemu", cmdline: "qemu-system-x86_64 -id 105 -name guest=test"}, map[int]string{105: "Gitea"})
+	if kind != "VM" || name != "Gitea" || vmid != 105 {
+		t.Fatalf("unexpected qemu attribution: %s %s %d", kind, name, vmid)
+	}
+	kind, name, vmid = classifyIOProcess(processIOSnapshot{name: "worker", cgroup: "0::/lxc.payload.220/ns"}, map[int]string{220: "db"})
+	if kind != "LXC" || name != "db" || vmid != 220 {
+		t.Fatalf("unexpected lxc attribution: %s %s %d", kind, name, vmid)
+	}
+}
+
+func TestActiveIOOperation(t *testing.T) {
+	value := activeIOOperation([]ProxmoxTask{{Type: "vzdump", ID: "105", Status: "", EndTime: 0}})
+	if !strings.Contains(value, "Backup") || !strings.Contains(value, "105") {
+		t.Fatalf("unexpected operation: %s", value)
+	}
+}
+
+func TestCorrelateAlerts(t *testing.T) {
+	metrics := dashboardMetrics{Disks: []DiskMetrics{{Name: "sda", IOCause: "Backup VM/LXC 105", IOConfidence: 90, Utilization: 98, LatencyMs: 80}}, Services: ServicesMetrics{Services: []ServiceStatus{{MonitoredService: MonitoredService{Name: "Gitea"}, Endpoints: []ServiceEndpointStatus{{Up: false}}}}}}
+	alerts := []Alert{{ID: "disk-io-pressure-sda", Severity: "critical"}, {ID: "service-1-public", Severity: "critical"}, {ID: "other", Severity: "warning"}}
+	result := correlateAlerts(metrics, alerts)
+	if len(result) != 2 || result[0].Source != "Корреляция" || !strings.Contains(result[0].Message, "Gitea") {
+		t.Fatalf("unexpected correlation: %+v", result)
+	}
+}

main.go

@@ -20,11 +20,23 @@ var version = "dev"
 
 func main() {
 	showVersion := flag.Bool("version", false, "show version")
+	agentMode := flag.Bool("agent", false, "run as a read-only guest agent")
+	agentServer := flag.String("agent-server", "", "dashboard URL used by the guest agent")
+	agentEnrollToken := flag.String("agent-enroll-token", "", "one-time enrollment token")
+	agentName := flag.String("agent-name", "", "agent display name")
+	agentVMID := flag.Int("agent-vmid", 0, "Proxmox VM/LXC ID")
+	agentConfig := flag.String("agent-config", "/var/lib/proxmox-dashboard-agent/agent.json", "agent configuration path")
 	flag.Parse()
 	if *showVersion {
 		fmt.Println(version)
 		return
 	}
+	if *agentMode {
+		if err := runGuestAgent(agentOptions{Server: *agentServer, EnrollmentToken: *agentEnrollToken, Name: *agentName, VMID: *agentVMID, ConfigPath: *agentConfig}); err != nil {
+			log.Fatalf("Ошибка агента: %v", err)
+		}
+		return
+	}
 
 	address := os.Getenv("DASHBOARD_ADDR")
 	if address == "" {

maintenance_window.go

@@ -0,0 +1,170 @@
+package main
+
+import (
+	"encoding/json"
+	"fmt"
+	"strconv"
+	"strings"
+	"time"
+)
+
+type MaintenanceWindow struct {
+	Enabled    bool    `json:"enabled"`
+	Active     bool    `json:"active"`
+	StartedAt  int64   `json:"startedAt"`
+	EndsAt     int64   `json:"endsAt"`
+	Reason     string  `json:"reason"`
+	AllAlerts  bool    `json:"allAlerts"`
+	ServiceIDs []int64 `json:"serviceIds"`
+	VMIDs      []int   `json:"vmids"`
+	Automatic  bool    `json:"automatic"`
+	Source     string  `json:"source,omitempty"`
+}
+
+func automaticBackupMaintenance(activity ProxmoxActivity, links []ServiceLink, now time.Time) MaintenanceWindow {
+	vmids := []int{}
+	backupRunning := false
+	for _, task := range activity.Tasks {
+		if task.Type != "vzdump" || task.EndTime > 0 || (task.Status != "" && !strings.EqualFold(task.Status, "running")) {
+			continue
+		}
+		backupRunning = true
+		if vmid := backupTaskVMID(task); vmid > 0 {
+			vmids = append(vmids, vmid)
+		}
+	}
+	vmids = uniqueInt(vmids)
+	if !backupRunning {
+		return MaintenanceWindow{}
+	}
+	selected := map[int]bool{}
+	for _, vmid := range vmids {
+		selected[vmid] = true
+	}
+	serviceIDs := []int64{}
+	for _, link := range links {
+		if selected[link.VMID] {
+			serviceIDs = append(serviceIDs, link.ServiceID)
+		}
+	}
+	return MaintenanceWindow{Enabled: true, Active: true, StartedAt: now.Unix(), EndsAt: now.Add(2 * time.Minute).Unix(), Reason: "Автоматически: выполняется backup VM/LXC", VMIDs: vmids, ServiceIDs: uniqueInt64(serviceIDs), AllAlerts: len(vmids) == 0, Automatic: true, Source: "backup"}
+}
+
+func backupTaskVMID(task ProxmoxTask) int {
+	if vmid, err := strconv.Atoi(strings.TrimSpace(task.ID)); err == nil && vmid > 0 {
+		return vmid
+	}
+	parts := strings.Split(task.UPID, ":")
+	for i, part := range parts {
+		if part == "vzdump" && i+1 < len(parts) {
+			vmid, _ := strconv.Atoi(parts[i+1])
+			return vmid
+		}
+	}
+	return 0
+}
+
+func (s *Store) MaintenanceWindow() MaintenanceWindow {
+	var value string
+	var window MaintenanceWindow
+	if s.db.QueryRow(`SELECT value FROM settings WHERE key='maintenance_window'`).Scan(&value) == nil {
+		_ = json.Unmarshal([]byte(value), &window)
+	}
+	now := time.Now().Unix()
+	window.Active = window.Enabled && window.StartedAt <= now && window.EndsAt > now
+	if window.Enabled && window.EndsAt <= now {
+		window.Enabled = false
+		data, _ := json.Marshal(window)
+		_, _ = s.db.Exec(`INSERT INTO settings(key,value) VALUES('maintenance_window',?) ON CONFLICT(key) DO UPDATE SET value=excluded.value`, string(data))
+	}
+	return window
+}
+
+func (s *Store) SaveMaintenanceWindow(window MaintenanceWindow) (MaintenanceWindow, error) {
+	now := time.Now()
+	window.Reason = strings.TrimSpace(window.Reason)
+	if window.Reason == "" {
+		return window, fmt.Errorf("укажите причину плановых работ")
+	}
+	if window.EndsAt <= now.Unix() || window.EndsAt > now.Add(30*24*time.Hour).Unix() {
+		return window, fmt.Errorf("окончание должно быть в будущем, максимум через 30 дней")
+	}
+	if !window.AllAlerts && len(window.ServiceIDs) == 0 && len(window.VMIDs) == 0 {
+		return window, fmt.Errorf("выберите сервис, VM/LXC или все алерты")
+	}
+	window.Enabled = true
+	window.Active = true
+	window.StartedAt = now.Unix()
+	window.ServiceIDs = uniqueInt64(window.ServiceIDs)
+	window.VMIDs = uniqueInt(window.VMIDs)
+	data, _ := json.Marshal(window)
+	_, err := s.db.Exec(`INSERT INTO settings(key,value) VALUES('maintenance_window',?) ON CONFLICT(key) DO UPDATE SET value=excluded.value`, string(data))
+	return window, err
+}
+
+func (s *Store) StopMaintenanceWindow() (MaintenanceWindow, error) {
+	window := s.MaintenanceWindow()
+	window.Enabled = false
+	window.Active = false
+	window.EndsAt = time.Now().Unix()
+	data, _ := json.Marshal(window)
+	_, err := s.db.Exec(`INSERT INTO settings(key,value) VALUES('maintenance_window',?) ON CONFLICT(key) DO UPDATE SET value=excluded.value`, string(data))
+	return window, err
+}
+
+func splitMaintenanceAlerts(alerts []Alert, window MaintenanceWindow) (active, planned []Alert) {
+	if !window.Active {
+		return alerts, nil
+	}
+	for _, alert := range alerts {
+		if maintenanceMatchesAlert(window, alert) {
+			planned = append(planned, alert)
+		} else {
+			active = append(active, alert)
+		}
+	}
+	return active, planned
+}
+
+func maintenanceMatchesAlert(window MaintenanceWindow, alert Alert) bool {
+	if window.AllAlerts {
+		return true
+	}
+	for _, id := range window.ServiceIDs {
+		value := strconv.FormatInt(id, 10)
+		if strings.HasPrefix(alert.ID, "service-"+value+"-") || strings.HasPrefix(alert.ID, "service-tls-"+value+"-") {
+			return true
+		}
+	}
+	for _, vmid := range window.VMIDs {
+		value := strconv.Itoa(vmid)
+		if strings.HasSuffix(alert.ID, "-"+value) || strings.Contains(alert.Message, "VMID "+value) {
+			return true
+		}
+	}
+	return false
+}
+
+func uniqueInt64(values []int64) []int64 {
+	seen := map[int64]bool{}
+	result := make([]int64, 0, len(values))
+	for _, value := range values {
+		if value > 0 && !seen[value] {
+			seen[value] = true
+			result = append(result, value)
+		}
+	}
+	return result
+}
+
+func uniqueInt(values []int) []int {
+	seen := map[int]bool{}
+	result := make([]int, 0, len(values))
+	for _, value := range values {
+		if value > 0 && !seen[value] {
+			seen[value] = true
+			result = append(result, value)
+		}
+	}
+	return result
+}

maintenance_window_test.go

@@ -0,0 +1,75 @@
+package main
+
+import (
+	"testing"
+	"time"
+)
+
+func TestMaintenanceFiltersSelectedTargets(t *testing.T) {
+	window := MaintenanceWindow{Active: true, ServiceIDs: []int64{7}, VMIDs: []int{105}}
+	alerts := []Alert{
+		{ID: "service-7-local"},
+		{ID: "service-tls-8-public"},
+		{ID: "backup-old-105"},
+		{ID: "task-failed-x", Message: "VMID 105, status error"},
+		{ID: "cpu-usage"},
+	}
+	active, planned := splitMaintenanceAlerts(alerts, window)
+	if len(active) != 2 || len(planned) != 3 {
+		t.Fatalf("неверное разделение: active=%+v planned=%+v", active, planned)
+	}
+}
+
+func TestMaintenanceExpiresAutomatically(t *testing.T) {
+	store, err := openStore(":memory:")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer store.Close()
+	window, err := store.SaveMaintenanceWindow(MaintenanceWindow{EndsAt: time.Now().Add(time.Hour).Unix(), Reason: "Обновление", AllAlerts: true})
+	if err != nil || !window.Active {
+		t.Fatalf("режим не включён: %+v %v", window, err)
+	}
+	if _, err = store.db.Exec(`UPDATE settings SET value=? WHERE key='maintenance_window'`, `{"enabled":true,"startedAt":1,"endsAt":2,"reason":"test","allAlerts":true}`); err != nil {
+		t.Fatal(err)
+	}
+	if expired := store.MaintenanceWindow(); expired.Active || expired.Enabled {
+		t.Fatalf("просроченный режим остался активным: %+v", expired)
+	}
+}
+
+func TestRunningBackupCreatesScopedAutomaticMaintenance(t *testing.T) {
+	now := time.Now()
+	window := automaticBackupMaintenance(ProxmoxActivity{Tasks: []ProxmoxTask{{Type: "vzdump", ID: "105"}, {Type: "vzdump", ID: "106", EndTime: now.Unix()}}}, []ServiceLink{{ServiceID: 7, VMID: 105}, {ServiceID: 8, VMID: 999}}, now)
+	if !window.Active || !window.Automatic || window.Source != "backup" || len(window.VMIDs) != 1 || window.VMIDs[0] != 105 || len(window.ServiceIDs) != 1 || window.ServiceIDs[0] != 7 {
+		t.Fatalf("неверное автоматическое окно: %+v", window)
+	}
+}
+
+func TestRunningBackupWithoutVMIDSuppressesAllAlerts(t *testing.T) {
+	window := automaticBackupMaintenance(ProxmoxActivity{Tasks: []ProxmoxTask{{Type: "vzdump", UPID: "unknown"}}}, nil, time.Now())
+	if !window.Active || !window.AllAlerts {
+		t.Fatalf("backup с неизвестной целью должен безопасно подавить алерты: %+v", window)
+	}
+}
+
+func TestPlannedAlertOnlyAppearsInHistory(t *testing.T) {
+	store, err := openStore(":memory:")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer store.Close()
+	alert := Alert{ID: "service-7-local", Severity: "critical", Source: "Сервисы", Title: "Недоступен"}
+	visible, err := store.SyncAlertsWithMaintenance(nil, []Alert{alert}, "Обновление")
+	if err != nil || len(visible) != 0 {
+		t.Fatalf("плановый алерт стал активным: %+v %v", visible, err)
+	}
+	history, err := store.AlertHistory(10)
+	if err != nil || len(history) != 1 || !history[0].Planned || history[0].MaintenanceReason != "Обновление" {
+		t.Fatalf("плановое событие не сохранено: %+v %v", history, err)
+	}
+	pending, err := store.PendingEmailAlerts()
+	if err != nil || len(pending) != 0 {
+		t.Fatalf("плановое событие попало в почту: %+v %v", pending, err)
+	}
+}

network.go

@@ -3,6 +3,7 @@ package main
 import (
 	"bufio"
 	"context"
+	"fmt"
 	"io"
 	"net"
 	"net/http"
@@ -36,27 +37,37 @@ type NetworkHealth struct {
 	ExternalIPChanged     bool      `json:"externalIpChanged"`
 	DisappearedInterfaces []string  `json:"disappearedInterfaces"`
 	CheckedAt             time.Time `json:"checkedAt"`
+	Summary               string    `json:"summary"`
+	LikelyCause           string    `json:"likelyCause"`
+	RecommendedAction     string    `json:"recommendedAction"`
 }
 
 type NetworkInterface struct {
-	Name           string  `json:"name"`
+	Name             string            `json:"name"`
-	ReceiveBytes   uint64  `json:"receiveBytes"`
+	ReceiveBytes     uint64            `json:"receiveBytes"`
-	TransmitBytes  uint64  `json:"transmitBytes"`
+	TransmitBytes    uint64            `json:"transmitBytes"`
-	ReceiveErrors  uint64  `json:"receiveErrors"`
+	ReceiveErrors    uint64            `json:"receiveErrors"`
-	TransmitErrors uint64  `json:"transmitErrors"`
+	TransmitErrors   uint64            `json:"transmitErrors"`
-	ReceiveDrops   uint64  `json:"receiveDrops"`
+	ReceiveDrops     uint64            `json:"receiveDrops"`
-	TransmitDrops  uint64  `json:"transmitDrops"`
+	TransmitDrops    uint64            `json:"transmitDrops"`
-	ReceivePerSec  float64 `json:"receivePerSec"`
+	NewErrors        uint64            `json:"newErrors"`
-	TransmitPerSec float64 `json:"transmitPerSec"`
+	NewReceiveDrops  uint64            `json:"newReceiveDrops"`
-	VMID           int     `json:"vmid,omitempty"`
+	NewTransmitDrops uint64            `json:"newTransmitDrops"`
-	GuestName      string  `json:"guestName,omitempty"`
+	FaultCounters    map[string]uint64 `json:"faultCounters,omitempty"`
-	GuestType      string  `json:"guestType,omitempty"`
+	NewFaults        uint64            `json:"newFaults"`
-	Kind           string  `json:"kind"`
+	LinkDown         bool              `json:"linkDown"`
-	State          string  `json:"state"`
+	NewDrops         uint64            `json:"newDrops"`
-	Carrier        bool    `json:"carrier"`
+	ReceivePerSec    float64           `json:"receivePerSec"`
-	SpeedMbps      int     `json:"speedMbps,omitempty"`
+	TransmitPerSec   float64           `json:"transmitPerSec"`
-	Duplex         string  `json:"duplex,omitempty"`
+	VMID             int               `json:"vmid,omitempty"`
-	Master         string  `json:"master,omitempty"`
+	GuestName        string            `json:"guestName,omitempty"`
+	GuestType        string            `json:"guestType,omitempty"`
+	Kind             string            `json:"kind"`
+	State            string            `json:"state"`
+	Carrier          bool              `json:"carrier"`
+	SpeedMbps        int               `json:"speedMbps,omitempty"`
+	Duplex           string            `json:"duplex,omitempty"`
+	Master           string            `json:"master,omitempty"`
 }
 
 type networkSnapshot struct {
@@ -77,13 +88,14 @@ type networkCollector struct {
 }
 
 func newNetworkCollector(path string) (*networkCollector, error) {
-	snapshot, _, _, err := readNetworkSnapshot(path)
+	snapshot, _, details, err := readNetworkSnapshot(path)
 	if err != nil {
 		return nil, err
 	}
-	_, _, details, _ := readNetworkSnapshot(path)
 	previous := map[string]NetworkInterface{}
 	for _, v := range details {
+		decorateInterface(&v)
+		collectInterfaceFaults(&v)
 		previous[v.Name] = v
 	}
 	known := map[string]bool{}
@@ -110,10 +122,11 @@ func (c *networkCollector) collect() (NetworkMetrics, error) {
 	for i := range details {
 		v := &details[i]
 		decorateInterface(v)
-		if old, ok := c.previousInterfaces[v.Name]; ok && elapsed > 0 && v.ReceiveBytes >= old.ReceiveBytes && v.TransmitBytes >= old.TransmitBytes {
+		collectInterfaceFaults(v)
-			v.ReceivePerSec = float64(v.ReceiveBytes-old.ReceiveBytes) / elapsed
+		if old, ok := c.previousInterfaces[v.Name]; ok {
-			v.TransmitPerSec = float64(v.TransmitBytes-old.TransmitBytes) / elapsed
+			updateInterfaceDeltas(v, old, elapsed)
 		}
+		v.LinkDown = interfaceLinkDown(*v)
 	}
 	c.previousInterfaces = map[string]NetworkInterface{}
 	for _, v := range details {
@@ -138,12 +151,41 @@ func (c *networkCollector) collect() (NetworkMetrics, error) {
 		}
 	}
 	c.knownInterfaces = currentNames
+	explainNetworkHealth(&c.health, details)
 	return NetworkMetrics{
 		Interface: strings.Join(interfaceNames, ", "), Interfaces: details, ReceiveBytes: current.received,
 		TransmitBytes: current.sent, ReceivePerSec: receivedRate, TransmitPerSec: sentRate, Health: c.health,
 	}, nil
 }
 
+func explainNetworkHealth(health *NetworkHealth, interfaces []NetworkInterface) {
+	health.Summary, health.LikelyCause, health.RecommendedAction = "Сеть работает штатно", "Проблем не обнаружено", "Действий не требуется"
+	switch {
+	case health.Gateway == "":
+		health.Summary, health.LikelyCause, health.RecommendedAction = "Не найден маршрут в локальную сеть", "На хосте отсутствует default gateway", "Проверьте адрес шлюза и конфигурацию bridge/VLAN"
+	case !health.GatewayUp:
+		health.Summary, health.LikelyCause, health.RecommendedAction = "Хост не видит локальный шлюз", "Проблема между Proxmox и роутером: линк, bridge, bond или VLAN", "Проверьте кабель, carrier и настройки vmbr/bond/VLAN"
+	case health.PacketLoss > 0:
+		health.Summary = fmt.Sprintf("Нестабильная локальная сеть: потеряно %.1f%% пакетов", health.PacketLoss)
+		health.LikelyCause, health.RecommendedAction = "Перегрузка или ошибки линка между Proxmox и шлюзом", "Проверьте аппаратные ошибки, кабель, порт коммутатора и duplex"
+	case !health.DNSUp && health.InternetUp:
+		health.Summary, health.LikelyCause, health.RecommendedAction = "Интернет доступен, но DNS не отвечает", "Проблема DNS-сервера или /etc/resolv.conf", "Проверьте настроенные DNS и попробуйте разрешить домен вручную"
+	case health.DNSUp && !health.InternetUp:
+		health.Summary, health.LikelyCause, health.RecommendedAction = "Локальная сеть и DNS работают, но внешняя проверка недоступна", "Проблема выше роутера, блокировка HTTPS или недоступность провайдера", "Проверьте маршрут наружу, firewall и доступ к внешним адресам"
+	}
+	for _, v := range interfaces {
+		if v.LinkDown {
+			health.Summary, health.LikelyCause, health.RecommendedAction = v.Name+": линк не поднят", "Нет carrier либо интерфейс административно выключен", "Проверьте кабель, порт коммутатора и состояние интерфейса"
+			return
+		}
+		if v.NewErrors+v.NewFaults > 0 {
+			health.Summary = fmt.Sprintf("%s: за последний интервал появилось %d изменений счётчиков сетевых ошибок", v.Name, v.NewErrors+v.NewFaults)
+			health.LikelyCause, health.RecommendedAction = "Счётчики интерфейса сейчас растут из-за перегрузки, кабеля, MTU или duplex", "Проверьте скорость и duplex, кабель, порт коммутатора и MTU на обоих концах"
+			return
+		}
+	}
+}
+
 func decorateInterface(v *NetworkInterface) {
 	base := filepath.Join("/sys/class/net", v.Name)
 	v.State = readTrimmed(filepath.Join(base, "operstate"))
@@ -154,6 +196,10 @@ func decorateInterface(v *NetworkInterface) {
 		v.Master = filepath.Base(target)
 	}
 	switch {
+	case strings.HasPrefix(v.Name, "fwbr"):
+		v.Kind = "Firewall bridge"
+	case strings.HasPrefix(v.Name, "fwpr") || strings.HasPrefix(v.Name, "fwln"):
+		v.Kind = "Firewall link"
 	case strings.HasPrefix(v.Name, "vmbr"):
 		v.Kind = "Bridge"
 	case strings.HasPrefix(v.Name, "bond"):
@@ -232,7 +278,7 @@ func readNetworkSnapshot(path string) (networkSnapshot, []string, []NetworkInter
 			continue
 		}
 		fields := strings.Fields(values)
-		if len(fields) < 9 {
+		if len(fields) < 16 {
 			continue
 		}
 		rx, errRX := strconv.ParseUint(fields[0], 10, 64)

network_faults.go

@@ -0,0 +1,103 @@
+package main
+
+import (
+	"context"
+	"os/exec"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"time"
+)
+
+func counterDelta(current, previous uint64) uint64 {
+	if current < previous {
+		return 0
+	}
+	return current - previous
+}
+
+func updateInterfaceDeltas(v *NetworkInterface, old NetworkInterface, elapsed float64) {
+	if elapsed <= 0 {
+		return
+	}
+	v.ReceivePerSec = float64(counterDelta(v.ReceiveBytes, old.ReceiveBytes)) / elapsed
+	v.TransmitPerSec = float64(counterDelta(v.TransmitBytes, old.TransmitBytes)) / elapsed
+	v.NewErrors = counterDelta(v.ReceiveErrors, old.ReceiveErrors) + counterDelta(v.TransmitErrors, old.TransmitErrors)
+	v.NewReceiveDrops = counterDelta(v.ReceiveDrops, old.ReceiveDrops)
+	v.NewTransmitDrops = counterDelta(v.TransmitDrops, old.TransmitDrops)
+	v.NewDrops = v.NewReceiveDrops + v.NewTransmitDrops
+	for name, value := range v.FaultCounters {
+		if previous, ok := old.FaultCounters[name]; ok {
+			v.NewFaults += counterDelta(value, previous)
+		}
+	}
+	// A transition matters even if the interface has not carried traffic yet.
+	v.LinkDown = old.Carrier && !v.Carrier
+}
+
+func interfaceLinkDown(v NetworkInterface) bool {
+	if v.Kind == "Firewall bridge" || v.Kind == "Firewall link" {
+		return false
+	}
+	if v.LinkDown {
+		return true
+	}
+	used := v.Master != "" || v.ReceiveBytes+v.TransmitBytes > 0
+	if v.Kind == "Physical" {
+		return used && (!v.Carrier || v.State == "down")
+	}
+	return used && v.State == "down"
+}
+
+func collectInterfaceFaults(v *NetworkInterface) {
+	base := filepath.Join("/sys/class/net", v.Name)
+	// /proc/net/dev folds missed packets into RX drop. Sysfs keeps software
+	// drops separate from rx_missed_errors, which must still trigger an alert.
+	if n, err := strconv.ParseUint(readTrimmed(filepath.Join(base, "statistics/rx_dropped")), 10, 64); err == nil {
+		v.ReceiveDrops = n
+	}
+	v.FaultCounters = map[string]uint64{}
+	for _, name := range []string{"rx_crc_errors", "rx_frame_errors", "rx_fifo_errors", "rx_missed_errors", "tx_fifo_errors", "tx_carrier_errors", "carrier_down_count"} {
+		path := filepath.Join(base, "statistics", name)
+		if name == "carrier_down_count" {
+			path = filepath.Join(base, name)
+		}
+		if n, err := strconv.ParseUint(readTrimmed(path), 10, 64); err == nil {
+			v.FaultCounters[name] = n
+		}
+	}
+	// Only Atlantic exposes the driver-specific names below. No configuration
+	// changes, and a missing ethtool is not itself a network failure.
+	driver, err := filepath.EvalSymlinks(filepath.Join(base, "device/driver"))
+	if err != nil || filepath.Base(driver) != "atlantic" {
+		return
+	}
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second)
+	defer cancel()
+	if out, err := exec.CommandContext(ctx, "ethtool", "-S", v.Name).Output(); err == nil {
+		for k, n := range parseAtlanticFaults(string(out)) {
+			v.FaultCounters["atlantic:"+k] = n
+		}
+	}
+}
+
+func parseAtlanticFaults(output string) map[string]uint64 {
+	result := map[string]uint64{}
+	for _, line := range strings.Split(output, "\n") {
+		key, value, ok := strings.Cut(strings.TrimSpace(line), ":")
+		if !ok {
+			continue
+		}
+		fields := strings.Fields(key)
+		if len(fields) == 0 {
+			continue
+		}
+		switch fields[len(fields)-1] {
+		case "InErrors", "InDroppedDma", "AllocFails", "SkbAllocFails", "Restarts":
+			if n, err := strconv.ParseUint(strings.TrimSpace(value), 10, 64); err == nil {
+				result[key] = n
+			}
+		}
+	}
+	return result
+}

network_faults_test.go

@@ -0,0 +1,67 @@
+package main
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestNetworkDropsDoNotAlert(t *testing.T) {
+	for _, name := range []string{"enp6s0", "vmbr0", "fwbr100i0", "tap100i0"} {
+		v := NetworkInterface{Name: name, Carrier: true, State: "up", NewDrops: 15, NewReceiveDrops: 15}
+		metrics := dashboardMetrics{Network: NetworkMetrics{Interfaces: []NetworkInterface{v}}}
+		for _, a := range evaluateAlerts(metrics, AlertThresholds{}) {
+			if a.ID == "network-errors" {
+				t.Fatalf("%s: drops triggered alert", name)
+			}
+		}
+		v.NewErrors = 1
+		metrics.Network.Interfaces[0] = v
+		found := false
+		for _, a := range evaluateAlerts(metrics, AlertThresholds{}) {
+			if a.ID == "network-errors" {
+				found = a.Severity == "critical"
+			}
+		}
+		if !found {
+			t.Fatalf("%s: errors did not trigger critical alert", name)
+		}
+	}
+}
+
+func TestNetworkHardwareFaultAndLinkAlerts(t *testing.T) {
+	for _, v := range []NetworkInterface{{Name: "eth0", NewFaults: 1}, {Name: "eth0", LinkDown: true}} {
+		found := false
+		for _, a := range evaluateAlerts(dashboardMetrics{Network: NetworkMetrics{Interfaces: []NetworkInterface{v}}}, AlertThresholds{}) {
+			if strings.HasPrefix(a.ID, "network-") && a.Severity == "critical" {
+				found = true
+			}
+		}
+		if !found {
+			t.Fatalf("no critical alert for %+v", v)
+		}
+	}
+}
+
+func TestNetworkCounterResetsAndFaultBaselines(t *testing.T) {
+	old := NetworkInterface{ReceiveBytes: 100, ReceiveErrors: 20, TransmitErrors: 4, ReceiveDrops: 8, FaultCounters: map[string]uint64{"rx_missed_errors": 10, "atlantic:InErrors": 9}, Carrier: true}
+	next := NetworkInterface{ReceiveBytes: 1, ReceiveErrors: 1, TransmitErrors: 6, ReceiveDrops: 10, FaultCounters: map[string]uint64{"rx_missed_errors": 12, "atlantic:InErrors": 1, "new": 100}, Carrier: false}
+	updateInterfaceDeltas(&next, old, 2)
+	if next.NewErrors != 2 || next.NewFaults != 2 || next.NewReceiveDrops != 2 || next.ReceivePerSec != 0 || !next.LinkDown {
+		t.Fatalf("bad deltas: %+v", next)
+	}
+}
+
+func TestAtlanticFaults(t *testing.T) {
+	got := parseAtlanticFaults("NIC statistics:\n InErrors: 2\n InDroppedDma: 3\n Queue[0] AllocFails: 4\n Queue[1] SkbAllocFails: 5\n Queue[0] Restarts: 6\n Queue[0] InErrors: 7\n InPackets: 100\n Queue[0] XdpDrop: 50\n InErrorsBad: nope")
+	if len(got) != 6 || got["InDroppedDma"] != 3 || got["Queue[0] Restarts"] != 6 {
+		t.Fatalf("bad counters: %v", got)
+	}
+}
+
+func TestFirewallNotAttributedToGuest(t *testing.T) {
+	n := NetworkMetrics{Interfaces: []NetworkInterface{{Name: "fwbr100i0", ReceiveDrops: 100}, {Name: "tap100i0"}}}
+	decorateNetworkInterfaces(&n, GuestsMetrics{})
+	if n.Interfaces[0].VMID != 0 || n.Interfaces[1].VMID != 100 {
+		t.Fatalf("bad VM attribution: %+v", n)
+	}
+}

network_flows.go

@@ -0,0 +1,162 @@
+package main
+
+import (
+	_ "embed"
+	"encoding/json"
+	"errors"
+	"io"
+	"net"
+	"net/http"
+	"time"
+)
+
+//go:embed assets/network.html
+var networkHTML string
+
+// Original and reply tuples describe one conntrack entry, not two connections.
+type NetworkFlow struct {
+	Monitoring           bool   `json:"monitoring"`
+	External             bool   `json:"external"`
+	Protocol             string `json:"protocol"`
+	Source               string `json:"source"`
+	Destination          string `json:"destination"`
+	SourcePort           int    `json:"sourcePort"`
+	DestinationPort      int    `json:"destinationPort"`
+	ReplySource          string `json:"replySource"`
+	ReplyDestination     string `json:"replyDestination"`
+	ReplySourcePort      int    `json:"replySourcePort"`
+	ReplyDestinationPort int    `json:"replyDestinationPort"`
+	State                string `json:"state"`
+	Country              string `json:"country"`
+	DestinationCountry   string `json:"destinationCountry"`
+	Packets              uint64 `json:"packets"`
+	ReplyPackets         uint64 `json:"replyPackets"`
+	Bytes                uint64 `json:"bytes"`
+	ReplyBytes           uint64 `json:"replyBytes"`
+	Accounting           bool   `json:"accounting"`
+	Zone                 string `json:"zone,omitempty"`
+}
+type FirewallCounter struct {
+	Name    string `json:"name"`
+	Packets uint64 `json:"packets"`
+	Bytes   uint64 `json:"bytes"`
+}
+type NetworkSnapshot struct {
+	MonitoringHidden int               `json:"monitoringHidden"`
+	At               int64             `json:"at"`
+	ReceivedAt       int64             `json:"receivedAt"`
+	Flows            []NetworkFlow     `json:"flows"`
+	Error            string            `json:"error,omitempty"`
+	Limited          bool              `json:"limited"`
+	ParseErrors      int               `json:"parseErrors"`
+	Firewall         []FirewallCounter `json:"firewall"`
+	FirewallAt       int64             `json:"firewallAt"`
+	FirewallError    string            `json:"firewallError,omitempty"`
+	AgentName        string            `json:"agentName"`
+}
+
+func networkExternalIP(value string) bool {
+	ip := net.ParseIP(value)
+	if ip == nil || !ip.IsGlobalUnicast() || ip.IsPrivate() || ip.IsLoopback() || ip.IsLinkLocalUnicast() {
+		return false
+	}
+	if v4 := ip.To4(); v4 != nil && v4[0] == 100 && v4[1] >= 64 && v4[1] <= 127 {
+		return false
+	}
+	return true
+}
+func (s *Store) SaveNetwork(agent string, snapshot NetworkSnapshot) error {
+	if len(snapshot.Flows) > 5000 || len(snapshot.Firewall) > 128 {
+		return errors.New("network snapshot too large")
+	}
+	if snapshot.At < time.Now().Unix()-120 || snapshot.At > time.Now().Unix()+60 {
+		return errors.New("invalid snapshot time")
+	}
+	for i := range snapshot.Flows {
+		f := &snapshot.Flows[i]
+		if net.ParseIP(f.Source) == nil || net.ParseIP(f.Destination) == nil || net.ParseIP(f.ReplySource) == nil || net.ParseIP(f.ReplyDestination) == nil {
+			return errors.New("invalid network address")
+		}
+		for _, p := range []int{f.SourcePort, f.DestinationPort, f.ReplySourcePort, f.ReplyDestinationPort} {
+			if p < 0 || p > 65535 {
+				return errors.New("invalid network port")
+			}
+		}
+		if f.Protocol != "tcp" && f.Protocol != "udp" && f.Protocol != "icmp" && f.Protocol != "icmpv6" {
+			return errors.New("invalid protocol")
+		}
+		f.State = trafficText(f.State, 32)
+		f.Zone = trafficText(f.Zone, 16)
+		f.External = networkExternalIP(f.Source) || networkExternalIP(f.Destination)
+		f.Country = lookupTrafficCountry(f.Source)
+		f.DestinationCountry = lookupTrafficCountry(f.Destination)
+	}
+	snapshot.Error = trafficText(snapshot.Error, 600)
+	snapshot.FirewallError = trafficText(snapshot.FirewallError, 600)
+	for i := range snapshot.Firewall {
+		snapshot.Firewall[i].Name = trafficText(snapshot.Firewall[i].Name, 200)
+	}
+	snapshot.MonitoringHidden = 0
+	snapshot.ReceivedAt = time.Now().Unix()
+	snapshot.AgentName = ""
+	raw, err := json.Marshal(snapshot)
+	if err != nil {
+		return err
+	}
+	_, err = s.db.Exec(`INSERT INTO network_sources(agent,snapshot) VALUES(?,?) ON CONFLICT(agent) DO UPDATE SET snapshot=excluded.snapshot`, agent, string(raw))
+	return err
+}
+func networkRoutes(mux *http.ServeMux, s *Store) {
+	enabled := func() bool { c := s.TrafficSettings(); return c.Enabled && c.NetworkEnabled }
+	mux.HandleFunc("/network", func(w http.ResponseWriter, r *http.Request) {
+		if !enabled() {
+			http.Error(w, "Включите TCP/UDP в настройках карты трафика", 404)
+			return
+		}
+		w.Header().Set("Content-Type", "text/html; charset=utf-8")
+		w.Write([]byte(networkHTML))
+	})
+	mux.HandleFunc("/api/network", func(w http.ResponseWriter, r *http.Request) {
+		if r.Method != "GET" {
+			w.WriteHeader(405)
+			return
+		}
+		if !enabled() {
+			http.Error(w, "Сбор сети отключён", 404)
+			return
+		}
+		settings := s.TrafficSettings()
+		snapshot, err := s.ReadNetworkSnapshot(settings.AgentID, settings.MonitoringRules, r.URL.Query().Get("hideMonitoring") == "1")
+		if err != nil {
+			writeJSON(w, nil, err)
+			return
+		}
+		writeJSON(w, snapshot, nil)
+	})
+	mux.HandleFunc("/api/agent/network", func(w http.ResponseWriter, r *http.Request) {
+		if r.Method != "POST" {
+			w.WriteHeader(405)
+			return
+		}
+		id, secret, ok := agentCredentials(r)
+		if !ok || !s.AuthenticateAgent(id, secret) {
+			http.Error(w, "Unauthorized", 401)
+			return
+		}
+		c := s.TrafficSettings()
+		if !c.Enabled || !c.NetworkEnabled || c.AgentID != id {
+			http.Error(w, "Источник отключён", 403)
+			return
+		}
+		var snapshot NetworkSnapshot
+		if json.NewDecoder(io.LimitReader(r.Body, 4<<20)).Decode(&snapshot) != nil {
+			http.Error(w, "Invalid snapshot", 400)
+			return
+		}
+		if err := s.SaveNetwork(id, snapshot); err != nil {
+			http.Error(w, err.Error(), 400)
+			return
+		}
+		writeJSON(w, map[string]bool{"accepted": true}, nil)
+	})
+}

network_flows_test.go

@@ -0,0 +1,189 @@
+package main
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+	"time"
+)
+
+const networkNATLine = "ipv4 2 tcp 6 431999 ESTABLISHED src=8.8.8.8 dst=192.168.0.12 sport=51000 dport=443 packets=12 bytes=1500 src=172.18.0.2 dst=8.8.8.8 sport=443 dport=51000 packets=16 bytes=2500 [ASSURED] mark=0 zone=2 use=1"
+
+func TestNetworkConntrackTuples(t *testing.T) {
+	f, ok := parseNetworkFlow(networkNATLine)
+	if !ok || f.Source != "8.8.8.8" || f.Destination != "192.168.0.12" || f.ReplySource != "172.18.0.2" || f.SourcePort != 51000 || f.ReplySourcePort != 443 || f.State != "ESTABLISHED" || !f.Accounting || f.Bytes != 1500 || f.ReplyBytes != 2500 || f.Zone != "2" {
+		t.Fatalf("NAT tuple corrupted: %+v", f)
+	}
+	udp, ok := parseNetworkFlow("ipv6 10 udp 17 29 src=2001:4860:4860::8888 dst=fd00::2 sport=51000 dport=53 [UNREPLIED] src=fd00::2 dst=2001:4860:4860::8888 sport=53 dport=51000 mark=0 use=1")
+	if !ok || udp.State != "UNREPLIED" || udp.Accounting || udp.Protocol != "udp" {
+		t.Fatalf("UDP: %+v", udp)
+	}
+	icmp, ok := parseNetworkFlow("icmp 1 29 src=8.8.8.8 dst=192.168.0.12 type=8 code=0 id=3 src=192.168.0.12 dst=8.8.8.8 type=0 code=0 id=3 use=1")
+	if !ok || icmp.SourcePort != 0 || icmp.State != "TRACKED" {
+		t.Fatalf("ICMP: %+v", icmp)
+	}
+	if _, ok := parseNetworkFlow("tcp 6 20 SYN_SENT src=not-an-ip dst=192.168.0.12"); ok {
+		t.Fatal("invalid accepted")
+	}
+}
+func TestNetworkSnapshotLimit(t *testing.T) {
+	var s NetworkSnapshot
+	appendNetworkFlows(&s, []byte(strings.Repeat(networkNATLine+"\n", 5001)))
+	if len(s.Flows) != 5000 || !s.Limited {
+		t.Fatalf("limit not enforced %d", len(s.Flows))
+	}
+	b := networkBuffer{limit: 2}
+	if _, err := b.Write([]byte("123")); err == nil || b.Len() != 0 {
+		t.Fatal("output unbounded")
+	}
+}
+func TestFirewallOnlyConfirmedDropCounters(t *testing.T) {
+	raw := `{"nftables":[{"rule":{"family":"ip","table":"crowdsec","chain":"crowdsec-chain","handle":3,"expr":[{"match":{}},{"counter":{"packets":10,"bytes":1000}},{"drop":null}]}},{"rule":{"table":"crowdsec","expr":[{"counter":{"packets":99}},{"accept":null}]}},{"rule":{"table":"other","expr":[{"counter":{"packets":99}},{"drop":null}]}},{"rule":{"table":"crowdsec","expr":[{"counter":{"packets":99}},{"match":{}},{"drop":null}]}},{"rule":{"table":"crowdsec","expr":[{"counter":"named-counter"},{"drop":null}]}}]}`
+	counters, err := parseFirewallCounters([]byte(raw))
+	if err != nil || len(counters) != 1 || counters[0].Packets != 10 || counters[0].Bytes != 1000 {
+		t.Fatalf("invented blocks: %+v %v", counters, err)
+	}
+	if _, err := parseFirewallCounters([]byte("invalid")); err == nil {
+		t.Fatal("invalid nft JSON accepted")
+	}
+}
+func TestNetworkRouteAuthorizationAndSourceSelection(t *testing.T) {
+	s, a := trafficFixture(t)
+	s.SaveTrafficSettings(TrafficSettings{Enabled: true, AgentID: a.ID})
+	mux := http.NewServeMux()
+	trafficRoutes(mux, s)
+	flow, _ := parseNetworkFlow(networkNATLine)
+	snapshot := NetworkSnapshot{At: time.Now().Unix(), Flows: []NetworkFlow{flow}}
+	raw, _ := json.Marshal(snapshot)
+	post := func(token string) int {
+		r := httptest.NewRequest("POST", "/api/agent/network", bytes.NewReader(raw))
+		r.Header.Set("Authorization", "Bearer "+token)
+		w := httptest.NewRecorder()
+		mux.ServeHTTP(w, r)
+		return w.Code
+	}
+	if got := post(a.ID + "." + a.Secret); got != 403 {
+		t.Fatalf("disabled accepts data: %d", got)
+	}
+	s.SaveTrafficSettings(TrafficSettings{Enabled: true, NetworkEnabled: true, AgentID: a.ID})
+	if got := post("wrong.token"); got != 401 {
+		t.Fatalf("unauthenticated: %d", got)
+	}
+	if got := post(a.ID + "." + a.Secret); got != 200 {
+		t.Fatalf("valid: %d", got)
+	}
+	w := httptest.NewRecorder()
+	mux.ServeHTTP(w, httptest.NewRequest("GET", "/api/network", nil))
+	var got NetworkSnapshot
+	json.Unmarshal(w.Body.Bytes(), &got)
+	if w.Code != 200 || len(got.Flows) != 1 || got.Flows[0].Country == "" || got.ReceivedAt == 0 {
+		t.Fatalf("bad snapshot: %s", w.Body.String())
+	}
+	token, _ := s.CreateAgentEnrollmentToken()
+	other, _ := s.EnrollAgent(agentEnrollmentRequest{Token: token, Name: "other"})
+	s.SaveTrafficSettings(TrafficSettings{Enabled: true, NetworkEnabled: true, AgentID: other.ID})
+	if code := post(a.ID + "." + a.Secret); code != 403 {
+		t.Fatalf("old source accepted: %d", code)
+	}
+	w = httptest.NewRecorder()
+	mux.ServeHTTP(w, httptest.NewRequest("GET", "/api/network", nil))
+	json.Unmarshal(w.Body.Bytes(), &got)
+	if len(got.Flows) != 0 {
+		t.Fatal("old source data leaked")
+	}
+	s.SaveTrafficSettings(TrafficSettings{Enabled: false, NetworkEnabled: true, AgentID: a.ID})
+	for _, path := range []string{"/network", "/api/network"} {
+		w = httptest.NewRecorder()
+		mux.ServeHTTP(w, httptest.NewRequest("GET", path, nil))
+		if w.Code != 404 {
+			t.Fatalf("disabled page: %s", path)
+		}
+	}
+}
+func TestNetworkRejectBadSnapshots(t *testing.T) {
+	s, a := trafficFixture(t)
+	if err := s.SaveNetwork(a.ID, NetworkSnapshot{At: time.Now().Unix() - 300}); err == nil {
+		t.Fatal("stale timestamp")
+	}
+	f, _ := parseNetworkFlow(networkNATLine)
+	f.SourcePort = 99999
+	if err := s.SaveNetwork(a.ID, NetworkSnapshot{At: time.Now().Unix(), Flows: []NetworkFlow{f}}); err == nil {
+		t.Fatal("invalid port")
+	}
+}
+func TestNetworkCommandCancellation(t *testing.T) {
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel()
+	if _, err := networkCommand(ctx, "conntrack", "-L"); err == nil {
+		t.Fatal("cancelled command ran")
+	}
+}
+
+func TestNetworkExternalAddresses(t *testing.T) {
+	for _, ip := range []string{"192.168.1.1", "127.0.0.1", "100.64.0.1", "224.0.0.1", "ff02::1", "fe80::1", "fd00::1", "::"} {
+		if networkExternalIP(ip) {
+			t.Fatalf("not external: %s", ip)
+		}
+	}
+	for _, ip := range []string{"8.8.8.8", "2001:4860:4860::8888"} {
+		if !networkExternalIP(ip) {
+			t.Fatalf("external: %s", ip)
+		}
+	}
+}
+
+func TestConntrackInstallerOnlyInstallsRequestedPackage(t *testing.T) {
+	var calls [][]string
+	err := installConntrackPackage(func(name string, args ...string) error {
+		calls = append(calls, append([]string{name}, args...))
+		return nil
+	}, func() bool { return true })
+	if err != nil || len(calls) != 2 {
+		t.Fatalf("installer: %v %v", calls, err)
+	}
+	if calls[0][len(calls[0])-1] != "update" || strings.Join(calls[1][len(calls[1])-5:], " ") != "-y --no-install-recommends --no-remove install conntrack" {
+		t.Fatalf("unexpected apt operation: %v", calls)
+	}
+	calls = nil
+	err = installConntrackPackage(func(name string, args ...string) error { calls = append(calls, args); return fmt.Errorf("apt locked") }, func() bool { return true })
+	if err == nil || len(calls) != 1 {
+		t.Fatal("continued after failed apt update")
+	}
+}
+func TestConntrackDependencySingleInstallAndBackoff(t *testing.T) {
+	var d networkDependencyState
+	now := time.Now()
+	started := make(chan struct{})
+	finish := make(chan struct{})
+	installer := func() error { close(started); <-finish; return fmt.Errorf("offline") }
+	if got := d.ensure(now, true, installer); got != "" {
+		t.Fatal("installed tool should be skipped")
+	}
+	d.ensure(now, false, installer)
+	<-started
+	// A second call must not start a second installer (which would panic closing started).
+	d.ensure(now, false, installer)
+	close(finish)
+	deadline := time.Now().Add(time.Second)
+	for {
+		d.Lock()
+		running := d.running
+		d.Unlock()
+		if !running {
+			break
+		}
+		if time.Now().After(deadline) {
+			t.Fatal("installer stuck")
+		}
+		time.Sleep(time.Millisecond)
+	}
+	got := d.ensure(now.Add(time.Minute), false, installer)
+	if !strings.Contains(got, "offline") || !strings.Contains(got, "Повторная") {
+		t.Fatalf("backoff missing: %s", got)
+	}
+}

network_test.go

@@ -3,6 +3,7 @@ package main
 import (
 	"os"
 	"path/filepath"
+	"strings"
 	"testing"
 )
 
@@ -33,8 +34,28 @@ func TestReadNetworkSnapshot(t *testing.T) {
 	}
 }
 
+func TestExplainNetworkHealthDistinguishesDNSFailure(t *testing.T) {
+	health := NetworkHealth{Gateway: "192.168.0.1", GatewayUp: true, InternetUp: true, DNSUp: false}
+	explainNetworkHealth(&health, nil)
+	if !strings.Contains(health.Summary, "DNS") || health.RecommendedAction == "" {
+		t.Fatalf("непонятная диагностика: %+v", health)
+	}
+}
+
+func TestExplainNetworkHealthIgnoresOldInterfaceCounters(t *testing.T) {
+	health := NetworkHealth{Gateway: "192.168.0.1", GatewayUp: true, InternetUp: true, DNSUp: true}
+	explainNetworkHealth(&health, []NetworkInterface{{Name: "eno1", Carrier: true, State: "up", ReceiveDrops: 42}})
+	if health.Summary != "Сеть работает штатно" {
+		t.Fatalf("старый накопленный счётчик вызвал текущую тревогу: %+v", health)
+	}
+	explainNetworkHealth(&health, []NetworkInterface{{Name: "eno1", Carrier: true, State: "up", ReceiveDrops: 43, NewDrops: 1}})
+	if health.Summary != "Сеть работает штатно" {
+		t.Fatalf("software drops вызвали тревогу: %+v", health)
+	}
+}
+
 func TestInterfaceVMID(t *testing.T) {
-	for name, want := range map[string]int{"tap100i0": 100, "veth108i0": 108, "fwbr113i0": 113, "vmbr0": 0, "enp6s0": 0} {
+	for name, want := range map[string]int{"tap100i0": 100, "veth108i0": 108, "fwbr113i0": 0, "vmbr0": 0, "enp6s0": 0} {
 		if got := interfaceVMID(name); got != want {
 			t.Fatalf("%s: got %d want %d", name, got, want)
 		}

scripts/build-release.sh

@@ -0,0 +1,17 @@
+#!/bin/sh
+set -eu
+version=${1:?Usage: build-release.sh vX.Y.Z}
+cd "$(dirname "$0")/.."
+go test ./...
+mkdir -p dist
+GOOS=linux GOARCH=amd64 CGO_ENABLED=0 go build -trimpath -ldflags "-s -w -X main.version=$version" -o dist/proxmox-dashboard-linux-amd64 .
+(cd dist && shasum -a 256 proxmox-dashboard-linux-amd64 > proxmox-dashboard-linux-amd64.sha256)
+stage=$(mktemp -d)
+trap 'rm -rf "$stage"' EXIT INT TERM
+package="$stage/proxmox-dashboard-install"
+mkdir -p "$package/dist" "$package/scripts"
+cp dist/proxmox-dashboard-linux-amd64 dist/proxmox-dashboard-linux-amd64.sha256 "$package/dist/"
+cp scripts/install.sh scripts/install-agent.sh scripts/uninstall-agent.sh scripts/proxmox-dashboard-update "$package/scripts/"
+cp assets/NOTICE.md "$package/MAP-DATA-NOTICE.md"
+cp ./*.service ./*.timer ./*.path README.md "$package/"
+tar -czf dist/proxmox-dashboard-install-amd64.tar.gz -C "$stage" proxmox-dashboard-install

scripts/install-agent.sh

@@ -0,0 +1,120 @@
+#!/bin/sh
+set -eu
+
+if [ "$(id -u)" -ne 0 ]; then
+  echo "Запустите команду установки от root." >&2
+  exit 1
+fi
+if [ -z "${DASHBOARD_URL:-}" ] || [ -z "${ENROLL_TOKEN:-}" ]; then
+  echo "Не заданы DASHBOARD_URL и ENROLL_TOKEN. Создайте команду в настройках Dashboard." >&2
+  exit 1
+fi
+
+case "$(uname -m)" in x86_64|amd64) ;; *) echo "Поддерживается Linux amd64 (x86_64)." >&2; exit 1 ;; esac
+if command -v systemctl >/dev/null 2>&1 && [ -d /run/systemd/system ]; then
+  agent_init=systemd
+elif command -v rc-service >/dev/null 2>&1 && command -v supervise-daemon >/dev/null 2>&1; then
+  agent_init=openrc
+else
+  echo "Нужен работающий systemd или OpenRC с supervise-daemon." >&2; exit 1
+fi
+if ! command -v curl >/dev/null 2>&1; then
+  if command -v apk >/dev/null 2>&1; then apk add --no-cache curl ca-certificates; else echo "Установите curl и ca-certificates." >&2; exit 1; fi
+fi
+
+GITEA_URL=${GITEA_URL:-https://git.myown.center}
+GITEA_REPOSITORY=${GITEA_REPOSITORY:-maxim/ProxmoxDash}
+VMID=${VMID:-0}
+AGENT_NAME=${AGENT_NAME:-$(hostname)}
+
+case "$DASHBOARD_URL$ENROLL_TOKEN$AGENT_NAME$VMID" in
+  *'
+'*) echo "Параметры установки не должны содержать переносы строк." >&2; exit 1 ;;
+esac
+
+release_json=$(curl -fsSL "$GITEA_URL/api/v1/repos/$GITEA_REPOSITORY/releases/latest")
+download_url=$(printf '%s' "$release_json" | sed -n 's/.*"browser_download_url":"\([^"]*\/proxmox-dashboard-linux-amd64\)".*/\1/p' | head -n 1)
+if [ -z "$download_url" ]; then
+  echo "В последнем релизе не найден Linux-бинарник." >&2
+  exit 1
+fi
+
+install -d -m 0700 /var/lib/proxmox-dashboard-agent
+temporary_binary=$(mktemp /tmp/proxmox-dashboard-agent.XXXXXX)
+trap 'rm -f "$temporary_binary" "$temporary_binary.sha256"' EXIT
+curl -fsSL "$download_url" -o "$temporary_binary"
+curl -fsSL "$download_url.sha256" -o "$temporary_binary.sha256"
+expected_hash=$(awk 'NR==1 {print $1}' "$temporary_binary.sha256")
+actual_hash=$(sha256sum "$temporary_binary" | awk '{print $1}')
+if [ "${#expected_hash}" -ne 64 ] || [ "$expected_hash" != "$actual_hash" ]; then echo "SHA-256 загрузки не совпал." >&2; exit 1; fi
+install -m 0755 "$temporary_binary" /var/lib/proxmox-dashboard-agent/proxmox-dashboard-agent
+
+umask 077
+{
+  printf 'DASHBOARD_URL=%s\n' "$DASHBOARD_URL"
+  printf 'ENROLL_TOKEN=%s\n' "$ENROLL_TOKEN"
+  printf 'AGENT_NAME=%s\n' "$AGENT_NAME"
+  printf 'VMID=%s\n' "$VMID"
+} > /etc/proxmox-dashboard-agent.env
+
+if [ "$agent_init" = systemd ]; then
+cat > /etc/systemd/system/proxmox-dashboard-agent.service <<'UNIT'
+[Unit]
+Description=Proxmox Dashboard read-only guest agent
+After=network-online.target docker.service
+Wants=network-online.target
+
+[Service]
+Type=simple
+EnvironmentFile=/etc/proxmox-dashboard-agent.env
+ExecStart=/var/lib/proxmox-dashboard-agent/proxmox-dashboard-agent --agent --agent-server ${DASHBOARD_URL} --agent-enroll-token ${ENROLL_TOKEN} --agent-name ${AGENT_NAME} --agent-vmid ${VMID}
+Restart=always
+RestartSec=5
+NoNewPrivileges=true
+ProtectHome=true
+PrivateTmp=true
+ProtectSystem=strict
+ReadWritePaths=/var/lib/proxmox-dashboard-agent
+
+[Install]
+WantedBy=multi-user.target
+UNIT
+
+systemctl daemon-reload
+systemctl enable proxmox-dashboard-agent.service
+systemctl restart proxmox-dashboard-agent.service
+else
+  mkdir -p /usr/local/sbin /etc/init.d
+  cat > /usr/local/sbin/proxmox-dashboard-agent-run <<'RUN'
+#!/bin/sh
+set -eu
+# Parse literal key=value records, never evaluate configuration as shell code.
+while IFS='=' read -r key value; do
+  case "$key" in DASHBOARD_URL|ENROLL_TOKEN|AGENT_NAME|VMID|DASHBOARD_NPM_LOG_DIR|DASHBOARD_CROWDSEC_CONTAINER) export "$key=$value" ;; esac
+done < /etc/proxmox-dashboard-agent.env
+exec /var/lib/proxmox-dashboard-agent/proxmox-dashboard-agent --agent --agent-server "$DASHBOARD_URL" --agent-enroll-token "$ENROLL_TOKEN" --agent-name "$AGENT_NAME" --agent-vmid "$VMID"
+RUN
+  chmod 0755 /usr/local/sbin/proxmox-dashboard-agent-run
+  cat > /etc/init.d/proxmox-dashboard-agent <<'OPENRC'
+#!/sbin/openrc-run
+description="Proxmox Dashboard guest agent"
+command="/usr/local/sbin/proxmox-dashboard-agent-run"
+supervisor="supervise-daemon"
+respawn_delay=5
+respawn_max=0
+output_log="/var/log/proxmox-dashboard-agent.log"
+error_log="/var/log/proxmox-dashboard-agent.log"
+depend() {
+  need net
+  after docker
+}
+start_pre() {
+  checkpath --file --mode 0600 /var/log/proxmox-dashboard-agent.log
+}
+OPENRC
+  chmod 0755 /etc/init.d/proxmox-dashboard-agent
+  rc-update add proxmox-dashboard-agent default
+  rc-service proxmox-dashboard-agent restart
+fi
+rm -f /usr/local/bin/proxmox-dashboard-agent
+echo "Агент установлен. Через несколько секунд он появится в Dashboard."

scripts/uninstall-agent.sh

@@ -0,0 +1,21 @@
+#!/bin/sh
+set -eu
+
+if [ "$(id -u)" -ne 0 ]; then
+  echo "Запустите удаление от root." >&2
+  exit 1
+fi
+
+if command -v rc-service >/dev/null 2>&1 && [ -f /etc/init.d/proxmox-dashboard-agent ]; then
+  rc-service proxmox-dashboard-agent stop || true
+  rc-update del proxmox-dashboard-agent default || true
+fi
+systemctl disable --now proxmox-dashboard-agent.service 2>/dev/null || true
+rm -f /etc/init.d/proxmox-dashboard-agent /usr/local/sbin/proxmox-dashboard-agent-run
+rm -f /etc/systemd/system/proxmox-dashboard-agent.service
+rm -f /etc/proxmox-dashboard-agent.env
+rm -f /usr/local/bin/proxmox-dashboard-agent
+rm -rf /var/lib/proxmox-dashboard-agent
+systemctl daemon-reload 2>/dev/null || true
+systemctl reset-failed proxmox-dashboard-agent.service 2>/dev/null || true
+echo "Агент и его локальные учётные данные удалены."

service_links.go

@@ -0,0 +1,110 @@
+package main
+
+import (
+	"fmt"
+	"sort"
+	"strings"
+)
+
+type ServiceLink struct {
+	ServiceID     int64  `json:"serviceId"`
+	AgentID       string `json:"agentId"`
+	VMID          int    `json:"vmid"`
+	ComponentType string `json:"componentType"`
+	ComponentName string `json:"componentName"`
+	Port          int    `json:"port"`
+}
+
+func (s *Store) ServiceLinks() ([]ServiceLink, error) {
+	rows, err := s.db.Query(`SELECT service_id,agent_id,vmid,component_type,component_name,port FROM service_links ORDER BY service_id`)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	var out []ServiceLink
+	for rows.Next() {
+		var v ServiceLink
+		if err = rows.Scan(&v.ServiceID, &v.AgentID, &v.VMID, &v.ComponentType, &v.ComponentName, &v.Port); err != nil {
+			return nil, err
+		}
+		out = append(out, v)
+	}
+	return out, rows.Err()
+}
+
+func (s *Store) SaveServiceLink(v ServiceLink) (ServiceLink, error) {
+	v.AgentID = strings.TrimSpace(v.AgentID)
+	v.ComponentType = strings.TrimSpace(v.ComponentType)
+	v.ComponentName = strings.TrimSpace(v.ComponentName)
+	if v.ServiceID <= 0 {
+		return v, fmt.Errorf("выберите сервис")
+	}
+	if v.AgentID == "" && v.VMID <= 0 {
+		return v, fmt.Errorf("выберите агент или VMID")
+	}
+	if v.ComponentType != "" && v.ComponentType != "systemd" && v.ComponentType != "docker" && v.ComponentType != "process" {
+		return v, fmt.Errorf("неизвестный тип компонента")
+	}
+	if v.Port < 0 || v.Port > 65535 {
+		return v, fmt.Errorf("некорректный порт")
+	}
+	_, err := s.db.Exec(`INSERT INTO service_links(service_id,agent_id,vmid,component_type,component_name,port) VALUES(?,?,?,?,?,?) ON CONFLICT(service_id) DO UPDATE SET agent_id=excluded.agent_id,vmid=excluded.vmid,component_type=excluded.component_type,component_name=excluded.component_name,port=excluded.port`, v.ServiceID, v.AgentID, v.VMID, v.ComponentType, v.ComponentName, v.Port)
+	return v, err
+}
+func (s *Store) DeleteServiceLink(serviceID int64) error {
+	_, err := s.db.Exec(`DELETE FROM service_links WHERE service_id=?`, serviceID)
+	return err
+}
+
+func groupLinkedAlerts(metrics dashboardMetrics, alerts []Alert) []Alert {
+	if len(metrics.ServiceLinks) == 0 {
+		return alerts
+	}
+	agentOffline := map[string]ManagedAgent{}
+	for _, agent := range metrics.Agents {
+		if !agent.Online {
+			agentOffline[agent.ID] = agent
+		}
+	}
+	affected := map[string][]string{}
+	remove := map[string]bool{}
+	for _, link := range metrics.ServiceLinks {
+		agent, offline := agentOffline[link.AgentID]
+		if !offline {
+			continue
+		}
+		for _, service := range metrics.Services.Services {
+			if service.ID != link.ServiceID {
+				continue
+			}
+			for _, endpoint := range service.Endpoints {
+				if !endpoint.Up {
+					key := fmt.Sprintf("service-%d-%s", service.ID, endpoint.Kind)
+					remove[key] = true
+					affected[agent.ID] = append(affected[agent.ID], service.Name)
+				}
+			}
+		}
+	}
+	if len(affected) == 0 {
+		return alerts
+	}
+	out := make([]Alert, 0, len(alerts))
+	for _, alert := range alerts {
+		skip := remove[alert.ID]
+		for agentID := range affected {
+			if alert.ID == "agent-offline-"+agentID+fmt.Sprintf("-%d", agentOffline[agentID].VMID) {
+				skip = true
+			}
+		}
+		if !skip {
+			out = append(out, alert)
+		}
+	}
+	for agentID, names := range affected {
+		sort.Strings(names)
+		agent := agentOffline[agentID]
+		out = append(out, Alert{ID: "group-agent-offline-" + agentID + fmt.Sprintf("-%d", agent.VMID), Severity: "critical", Source: "Корреляция", Title: agent.Name + ": агент недоступен, связанные сервисы не отвечают", Message: fmt.Sprintf("VMID %d. Затронуто сервисов: %d — %s. Вероятная первопричина: недоступна гостевая система или агент.", agent.VMID, len(names), strings.Join(names, ", "))})
+	}
+	return out
+}

services.go

@@ -74,6 +74,20 @@ type ServiceHistoryPoint struct {
 	LatencyMS float64 `json:"latencyMs"`
 }
 
+var serviceHTTPTransport = &http.Transport{
+	Proxy:                 http.ProxyFromEnvironment,
+	DialContext:           (&net.Dialer{Timeout: 10 * time.Second, KeepAlive: 30 * time.Second}).DialContext,
+	ForceAttemptHTTP2:     true,
+	MaxIdleConns:          32,
+	MaxIdleConnsPerHost:   2,
+	IdleConnTimeout:       30 * time.Second,
+	TLSHandshakeTimeout:   10 * time.Second,
+	ExpectContinueTimeout: time.Second,
+	TLSClientConfig:       &tls.Config{InsecureSkipVerify: true, MinVersion: tls.VersionTLS12},
+}
+
+var serviceHTTPClient = &http.Client{Transport: serviceHTTPTransport}
+
 func (s *Store) Services() ([]MonitoredService, error) {
 	rows, err := s.db.Query(`SELECT id,name,url,local_address,check_type,expected_code,expected_text,timeout_seconds,enabled FROM services ORDER BY id`)
 	if err != nil {
@@ -296,14 +310,12 @@ func checkServiceEndpoint(v MonitoredService, kind, label, target string) Servic
 			st.Error = strings.TrimSpace(string(out))
 		}
 	default:
-		tr := &http.Transport{TLSClientConfig: &tls.Config{InsecureSkipVerify: true, MinVersion: tls.VersionTLS12}}
-		client := &http.Client{Transport: tr, Timeout: time.Duration(v.TimeoutSeconds) * time.Second}
 		req, err := http.NewRequestWithContext(ctx, http.MethodGet, target, nil)
 		if err != nil {
 			st.Error = err.Error()
 			break
 		}
-		resp, err := client.Do(req)
+		resp, err := serviceHTTPClient.Do(req)
 		if err != nil {
 			st.Error = err.Error()
 		} else {

services_test.go

@@ -1,6 +1,9 @@
 package main
 
-import "testing"
+import (
+	"testing"
+	"time"
+)
 
 func TestServiceCRUD(t *testing.T) {
 	store, err := openStore(":memory:")
@@ -38,3 +41,15 @@ func TestValidateServiceChecksBothHTTPAddresses(t *testing.T) {
 		t.Fatal(err)
 	}
 }
+
+func TestHTTPServiceTransportHasBoundedIdlePool(t *testing.T) {
+	if serviceHTTPClient.Transport != serviceHTTPTransport {
+		t.Fatal("проверки сервисов должны использовать общий HTTP transport")
+	}
+	if serviceHTTPTransport.IdleConnTimeout < time.Second {
+		t.Fatal("idle-соединения должны автоматически закрываться")
+	}
+	if serviceHTTPTransport.MaxIdleConnsPerHost < 1 || serviceHTTPTransport.MaxIdleConnsPerHost > 4 {
+		t.Fatalf("небезопасный размер пула на хост: %d", serviceHTTPTransport.MaxIdleConnsPerHost)
+	}
+}

store.go

@@ -31,6 +31,17 @@ type AlertThresholds struct {
 	NVMeTempWarning   float64 `json:"nvmeTempWarning"`
 	UPSChargeCritical float64 `json:"upsChargeCritical"`
 	BackupMaxAgeHours float64 `json:"backupMaxAgeHours"`
+	DiskHDDUtil       float64 `json:"diskHddUtil"`
+	DiskHDDLatency    float64 `json:"diskHddLatency"`
+	DiskHDDQueue      float64 `json:"diskHddQueue"`
+	DiskSSDUtil       float64 `json:"diskSsdUtil"`
+	DiskSSDLatency    float64 `json:"diskSsdLatency"`
+	DiskSSDQueue      float64 `json:"diskSsdQueue"`
+	DiskNVMeUtil      float64 `json:"diskNvmeUtil"`
+	DiskNVMeLatency   float64 `json:"diskNvmeLatency"`
+	DiskNVMeQueue     float64 `json:"diskNvmeQueue"`
+	DiskIODuration    float64 `json:"diskIoDuration"`
+	DiskIOExcluded    string  `json:"diskIoExcluded"`
 }
 
 func defaultThresholds() AlertThresholds {
@@ -40,6 +51,7 @@ func defaultThresholds() AlertThresholds {
 		StorageWarning: 85, StorageCritical: 95, ZFSWarning: 80, ZFSCritical: 90,
 		DiskTempWarning: 60, NVMeTempWarning: 75, UPSChargeCritical: 30,
 		BackupMaxAgeHours: 48,
+		DiskHDDUtil:       90, DiskHDDLatency: 50, DiskHDDQueue: 4, DiskSSDUtil: 90, DiskSSDLatency: 20, DiskSSDQueue: 4, DiskNVMeUtil: 95, DiskNVMeLatency: 10, DiskNVMeQueue: 8, DiskIODuration: 60,
 	}
 }
 
@@ -94,6 +106,7 @@ func openStore(path string) (*Store, error) {
 	}
 	db.SetMaxOpenConns(1)
 	statements := []string{
+		trafficSchema,
 		`PRAGMA journal_mode=WAL`,
 		`PRAGMA busy_timeout=5000`,
 		`CREATE TABLE IF NOT EXISTS settings (key TEXT PRIMARY KEY, value TEXT NOT NULL)`,
@@ -126,6 +139,11 @@ func openStore(path string) (*Store, error) {
 		`CREATE INDEX IF NOT EXISTS service_checks_service_ts_idx ON service_checks(service_id,ts)`,
 		`CREATE TABLE IF NOT EXISTS entity_history (kind TEXT NOT NULL,name TEXT NOT NULL,ts INTEGER NOT NULL,value1 REAL,value2 REAL,PRIMARY KEY(kind,name,ts))`,
 		`CREATE INDEX IF NOT EXISTS entity_history_kind_ts_idx ON entity_history(kind,ts)`,
+		`CREATE TABLE IF NOT EXISTS agent_enrollment_tokens (token_hash TEXT PRIMARY KEY, created_at INTEGER NOT NULL, expires_at INTEGER NOT NULL, used_at INTEGER)`,
+		`CREATE TABLE IF NOT EXISTS agents (id TEXT PRIMARY KEY, name TEXT NOT NULL, vmid INTEGER NOT NULL DEFAULT 0, hostname TEXT NOT NULL DEFAULT '', machine_id TEXT NOT NULL DEFAULT '', secret_hash TEXT NOT NULL, enrolled_at INTEGER NOT NULL, last_seen INTEGER NOT NULL, version TEXT NOT NULL DEFAULT '', report_json TEXT NOT NULL DEFAULT '{}', remote_address TEXT NOT NULL DEFAULT '')`,
+		`CREATE TABLE IF NOT EXISTS agent_actions (id INTEGER PRIMARY KEY AUTOINCREMENT, agent_id TEXT NOT NULL, action TEXT NOT NULL, target TEXT NOT NULL DEFAULT '', requested_at INTEGER NOT NULL, started_at INTEGER, completed_at INTEGER, status TEXT NOT NULL DEFAULT 'queued', result TEXT NOT NULL DEFAULT '', FOREIGN KEY(agent_id) REFERENCES agents(id) ON DELETE CASCADE)`,
+		`CREATE INDEX IF NOT EXISTS agent_actions_agent_status_idx ON agent_actions(agent_id,status)`,
+		`CREATE TABLE IF NOT EXISTS service_links (service_id INTEGER PRIMARY KEY, agent_id TEXT NOT NULL DEFAULT '', vmid INTEGER NOT NULL DEFAULT 0, component_type TEXT NOT NULL DEFAULT '', component_name TEXT NOT NULL DEFAULT '', port INTEGER NOT NULL DEFAULT 0, FOREIGN KEY(service_id) REFERENCES services(id) ON DELETE CASCADE)`,
 	}
 	for _, statement := range statements {
 		if _, err := db.Exec(statement); err != nil {
@@ -135,6 +153,9 @@ func openStore(path string) (*Store, error) {
 	}
 	// Older databases get this column without requiring a separate migration tool.
 	_, _ = db.Exec(`ALTER TABLE alert_events ADD COLUMN recovery_sent_at INTEGER`)
+	_, _ = db.Exec(`ALTER TABLE alert_events ADD COLUMN planned INTEGER NOT NULL DEFAULT 0`)
+	_, _ = db.Exec(`ALTER TABLE alert_events ADD COLUMN maintenance_reason TEXT NOT NULL DEFAULT ''`)
+	_, _ = db.Exec(`DELETE FROM alert_events WHERE alert_key='monitor-slow'`)
 	_, _ = db.Exec(`ALTER TABLE service_checks ADD COLUMN endpoint TEXT NOT NULL DEFAULT 'public'`)
 	_, _ = db.Exec(`PRAGMA foreign_keys=ON`)
 	return &Store{db: db, path: path}, nil
@@ -218,7 +239,7 @@ func (s *Store) SaveThresholds(value AlertThresholds) error {
 }
 
 func defaultEmailSettings() EmailSettings {
-	return EmailSettings{Port: 587, IntervalMinutes: 60, Severities: []string{"critical", "warning"}, Sources: []string{"CPU", "Память", "Storage", "Диски", "ZFS", "UPS", "VM/LXC", "Proxmox", "Dashboard", "Сервисы", "Система", "Сеть"}}
+	return EmailSettings{Port: 587, IntervalMinutes: 60, Severities: []string{"critical", "warning"}, Sources: []string{"CPU", "Память", "Storage", "Диски", "ZFS", "UPS", "VM/LXC", "Proxmox", "Dashboard", "Сервисы", "Система", "Сеть", "Агенты", "Docker"}}
 }
 
 func (s *Store) EmailSettings(includePassword bool) EmailSettings {
@@ -285,6 +306,19 @@ func validateThresholds(t AlertThresholds) error {
 	if t.BackupMaxAgeHours < 1 || t.BackupMaxAgeHours > 24*365 {
 		return fmt.Errorf("возраст backup должен быть от 1 до 8760 часов")
 	}
+	for _, value := range []float64{t.DiskHDDUtil, t.DiskSSDUtil, t.DiskNVMeUtil} {
+		if value < 1 || value > 100 {
+			return fmt.Errorf("пороги utilization должны быть от 1 до 100")
+		}
+	}
+	for _, value := range []float64{t.DiskHDDLatency, t.DiskSSDLatency, t.DiskNVMeLatency, t.DiskHDDQueue, t.DiskSSDQueue, t.DiskNVMeQueue} {
+		if value < 0 {
+			return fmt.Errorf("пороги latency и очереди не могут быть отрицательными")
+		}
+	}
+	if t.DiskIODuration < 5 || t.DiskIODuration > 3600 {
+		return fmt.Errorf("длительность I/O-проблемы должна быть от 5 до 3600 секунд")
+	}
 	return nil
 }
 

traffic.go

@@ -0,0 +1,355 @@
+package main
+
+import (
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net"
+	"net/http"
+	"strings"
+	"time"
+)
+
+type TrafficEvent struct {
+	City       string `json:"city,omitempty"`
+	Region     string `json:"region,omitempty"`
+	Monitoring bool   `json:"monitoring"`
+	ID         string `json:"id"`
+	Sequence   int64  `json:"sequence,omitempty"`
+	Time       int64  `json:"time"`
+	Kind       string `json:"kind"`
+	IP         string `json:"ip"`
+	Domain     string `json:"domain,omitempty"`
+	Method     string `json:"method,omitempty"`
+	Path       string `json:"path,omitempty"`
+	Status     int    `json:"status,omitempty"`
+	Reason     string `json:"reason,omitempty"`
+	Country    string `json:"country,omitempty"`
+	Agent      string `json:"agent,omitempty"`
+}
+
+type TrafficBatch struct {
+	Events          []TrafficEvent `json:"events"`
+	Files           int            `json:"files"`
+	BacklogBytes    int64          `json:"backlogBytes"`
+	CrowdSecLimited bool           `json:"crowdsecLimited"`
+	ParseErrors     uint64         `json:"parseErrors"`
+	LogError        string         `json:"logError,omitempty"`
+	CrowdSecError   string         `json:"crowdsecError,omitempty"`
+	CrowdSecAt      int64          `json:"crowdsecAt"`
+	StartedAt       int64          `json:"startedAt"`
+}
+
+type TrafficSource struct {
+	Agent    string       `json:"agent"`
+	Name     string       `json:"name"`
+	LastSeen int64        `json:"lastSeen"`
+	Status   TrafficBatch `json:"status"`
+}
+
+type TrafficCount struct {
+	Name  string `json:"name"`
+	Count int64  `json:"count"`
+}
+
+type TrafficCountryDetail struct {
+	Country   string `json:"country"`
+	Requests  int64  `json:"requests"`
+	UniqueIPs int64  `json:"uniqueIps"`
+	Alerts    int64  `json:"alerts"`
+	Decisions int64  `json:"decisions"`
+	LastSeen  int64  `json:"lastSeen"`
+}
+type TrafficView struct {
+	MaxSequence    int64                  `json:"maxSequence"`
+	CountryDetails []TrafficCountryDetail `json:"countryDetails"`
+
+	Network   *NetworkMapView `json:"network,omitempty"`
+	Events    []TrafficEvent  `json:"events"`
+	Sources   []TrafficSource `json:"sources"`
+	Countries []TrafficCount  `json:"countries"`
+	Domains   []TrafficCount  `json:"domains"`
+	IPs       []TrafficCount  `json:"ips"`
+	Requests  int64           `json:"requests"`
+	UniqueIPs int64           `json:"uniqueIps"`
+	Alerts    int64           `json:"alerts"`
+	Decisions int64           `json:"decisions"`
+	QPS       float64         `json:"qps"`
+	Series    []TrafficCount  `json:"series"`
+	GeoReady  bool            `json:"geoReady"`
+	GeoDate   string          `json:"geoDate"`
+	Now       int64           `json:"now"`
+	Settings  TrafficSettings `json:"settings"`
+	Limited   bool            `json:"limited"`
+}
+
+const trafficSchema = `CREATE TABLE IF NOT EXISTS traffic_events (
+ seq INTEGER PRIMARY KEY AUTOINCREMENT, agent TEXT NOT NULL, event_id TEXT NOT NULL,
+ ts INTEGER NOT NULL, kind TEXT NOT NULL, ip TEXT NOT NULL, domain TEXT NOT NULL,
+ method TEXT NOT NULL, path TEXT NOT NULL, status INTEGER NOT NULL, reason TEXT NOT NULL,
+ country TEXT NOT NULL, UNIQUE(agent,event_id));
+ CREATE INDEX IF NOT EXISTS traffic_ts ON traffic_events(ts);
+ CREATE INDEX IF NOT EXISTS traffic_filter ON traffic_events(domain,kind,ts);
+ CREATE TABLE IF NOT EXISTS network_sources(agent TEXT PRIMARY KEY, snapshot TEXT NOT NULL);
+ CREATE TABLE IF NOT EXISTS traffic_sources(agent TEXT PRIMARY KEY, last_seen INTEGER NOT NULL, status_json TEXT NOT NULL);`
+
+func (s *Store) SaveTraffic(agent string, batch TrafficBatch) error {
+	if len(batch.Events) > 500 {
+		return errors.New("too many traffic events")
+	}
+	now := time.Now().Unix()
+	tx, err := s.db.Begin()
+	if err != nil {
+		return err
+	}
+	defer tx.Rollback()
+	stmt, err := tx.Prepare(`INSERT OR IGNORE INTO traffic_events(agent,event_id,ts,kind,ip,domain,method,path,status,reason,country) VALUES(?,?,?,?,?,?,?,?,?,?,?)`)
+	if err != nil {
+		return err
+	}
+	defer stmt.Close()
+	for _, e := range batch.Events {
+		if e.Kind != "request" && e.Kind != "alert" && e.Kind != "decision" {
+			return errors.New("invalid traffic kind")
+		}
+		if net.ParseIP(e.IP) == nil || len(e.ID) == 0 || len(e.ID) > 160 {
+			return errors.New("invalid traffic event")
+		}
+		if e.Time < now-86400 || e.Time > now+300 {
+			continue
+		}
+		e.IP = net.ParseIP(e.IP).String()
+		country := lookupTrafficCountry(e.IP)
+		_, err = stmt.Exec(agent, e.ID, e.Time, e.Kind, e.IP, trafficText(e.Domain, 253), trafficText(e.Method, 16), trafficPath(e.Path), e.Status, trafficText(e.Reason, 256), country)
+		if err != nil {
+			return err
+		}
+	}
+	batch.Events = nil
+	raw, err := json.Marshal(batch)
+	if err != nil {
+		return err
+	}
+	if _, err = tx.Exec(`INSERT INTO traffic_sources(agent,last_seen,status_json) VALUES(?,?,?) ON CONFLICT(agent) DO UPDATE SET last_seen=excluded.last_seen,status_json=excluded.status_json`, agent, now, string(raw)); err != nil {
+		return err
+	}
+	// Bound both age and total rows, including a high-traffic installation.
+	if _, err = tx.Exec(`DELETE FROM traffic_events WHERE ts<? OR seq <= COALESCE((SELECT seq FROM traffic_events ORDER BY seq DESC LIMIT 1 OFFSET 200000),0)`, now-86400); err != nil {
+		return err
+	}
+	return tx.Commit()
+}
+
+func trafficText(s string, max int) string {
+	s = strings.Map(func(r rune) rune {
+		if r < 32 || r == 127 {
+			return -1
+		}
+		return r
+	}, s)
+	r := []rune(s)
+	if len(r) > max {
+		return string(r[:max])
+	}
+	return s
+}
+func trafficPath(s string) string {
+	s = strings.SplitN(s, "?", 2)[0]
+	s = strings.SplitN(s, "#", 2)[0]
+	return trafficText(s, 256)
+}
+
+func (s *Store) TrafficView(domain, kind string, external bool, hideMonitoring ...bool) (TrafficView, error) {
+	now := time.Now().Unix()
+	v := TrafficView{Events: []TrafficEvent{}, Sources: []TrafficSource{}, Countries: []TrafficCount{}, Domains: []TrafficCount{}, IPs: []TrafficCount{}, Series: []TrafficCount{}, Now: now, GeoReady: trafficGeoReady(), GeoDate: trafficGeoDate}
+	v.Settings = s.TrafficSettings()
+	hide := len(hideMonitoring) > 0 && hideMonitoring[0]
+	if v.Settings.NetworkEnabled {
+		snapshot, err := s.ReadNetworkSnapshot(v.Settings.AgentID, v.Settings.MonitoringRules, hide)
+		if err != nil {
+			snapshot.Error = "Не удалось прочитать сетевой снимок"
+		}
+		network := makeNetworkMap(snapshot, external)
+		v.Network = &network
+	}
+	if err := s.db.QueryRow(`SELECT COALESCE(MAX(seq),0) FROM traffic_events WHERE agent=?`, v.Settings.AgentID).Scan(&v.MaxSequence); err != nil {
+		return v, err
+	}
+	where := ` WHERE ts>=? AND agent=? AND ts<=? AND seq<=?`
+	args := []any{now - 86400, v.Settings.AgentID, now, v.MaxSequence}
+	if hide {
+		clause, params := monitoringSQL(v.Settings.MonitoringRules)
+		where += clause
+		args = append(args, params...)
+	}
+	if external {
+		where += ` AND country!='LAN'`
+	}
+	if domain != "" {
+		where += ` AND domain=?`
+		args = append(args, domain)
+	}
+	if kind != "" {
+		where += ` AND kind=?`
+		args = append(args, kind)
+	}
+	err := s.db.QueryRow(`SELECT COALESCE(SUM(kind='request'),0),COUNT(DISTINCT CASE WHEN kind='request' THEN ip END),COALESCE(SUM(kind='alert'),0),COALESCE(SUM(kind='decision'),0),COALESCE(SUM(kind='request' AND ts>=?),0)/60.0 FROM traffic_events`+where, append([]any{now - 60}, args...)...).Scan(&v.Requests, &v.UniqueIPs, &v.Alerts, &v.Decisions, &v.QPS)
+	if err != nil {
+		return v, err
+	}
+	rows, err := s.db.Query(`SELECT seq,event_id,ts,kind,ip,domain,method,path,status,reason,country,agent FROM traffic_events`+where+` ORDER BY ts DESC,seq DESC LIMIT 100`, args...)
+	if err != nil {
+		return v, err
+	}
+	for rows.Next() {
+		var e TrafficEvent
+		if err = rows.Scan(&e.Sequence, &e.ID, &e.Time, &e.Kind, &e.IP, &e.Domain, &e.Method, &e.Path, &e.Status, &e.Reason, &e.Country, &e.Agent); err != nil {
+			rows.Close()
+			return v, err
+		}
+		e.Monitoring = isMonitoringRequest(e, v.Settings.MonitoringRules)
+		e.City, e.Region = lookupTrafficCity(e.IP)
+		v.Events = append(v.Events, e)
+	}
+	err = rows.Err()
+	rows.Close()
+	if err != nil {
+		return v, err
+	}
+	for _, q := range []struct {
+		column string
+		out    *[]TrafficCount
+	}{{"country", &v.Countries}, {"domain", &v.Domains}, {"ip", &v.IPs}} {
+		r, e := s.db.Query(`SELECT `+q.column+`,COUNT(*) FROM traffic_events`+where+` GROUP BY `+q.column+` ORDER BY COUNT(*) DESC LIMIT 50`, args...)
+		if e != nil {
+			return v, e
+		}
+		for r.Next() {
+			var c TrafficCount
+			if e = r.Scan(&c.Name, &c.Count); e != nil {
+				r.Close()
+				return v, e
+			}
+			*q.out = append(*q.out, c)
+		}
+		e = r.Err()
+		r.Close()
+		if e != nil {
+			return v, e
+		}
+	}
+	detailRows, detailErr := s.db.Query(`SELECT country,SUM(kind='request'),COUNT(DISTINCT CASE WHEN kind='request' THEN ip END),SUM(kind='alert'),SUM(kind='decision'),MAX(ts) FROM traffic_events`+where+` GROUP BY country`, args...)
+	if detailErr != nil {
+		return v, detailErr
+	}
+	v.CountryDetails = []TrafficCountryDetail{}
+	for detailRows.Next() {
+		var d TrafficCountryDetail
+		if err = detailRows.Scan(&d.Country, &d.Requests, &d.UniqueIPs, &d.Alerts, &d.Decisions, &d.LastSeen); err != nil {
+			detailRows.Close()
+			return v, err
+		}
+		v.CountryDetails = append(v.CountryDetails, d)
+	}
+	detailErr = detailRows.Err()
+	detailRows.Close()
+	if detailErr != nil {
+		return v, detailErr
+	}
+	r, err := s.db.Query(`SELECT CAST((ts/60)*60 AS TEXT),COUNT(*) FROM traffic_events`+where+` AND kind='request' AND ts>=? GROUP BY ts/60 ORDER BY ts/60`, append(args, now-3600)...)
+	if err != nil {
+		return v, err
+	}
+	for r.Next() {
+		var c TrafficCount
+		if err = r.Scan(&c.Name, &c.Count); err != nil {
+			r.Close()
+			return v, err
+		}
+		v.Series = append(v.Series, c)
+	}
+	err = r.Err()
+	r.Close()
+	if err != nil {
+		return v, err
+	}
+	r, err = s.db.Query(`SELECT t.agent,COALESCE(a.name,t.agent),t.last_seen,t.status_json FROM traffic_sources t LEFT JOIN agents a ON a.id=t.agent WHERE t.agent=? ORDER BY t.last_seen DESC`, v.Settings.AgentID)
+	if err != nil {
+		return v, err
+	}
+	for r.Next() {
+		var src TrafficSource
+		var raw string
+		if err = r.Scan(&src.Agent, &src.Name, &src.LastSeen, &raw); err != nil {
+			r.Close()
+			return v, err
+		}
+		json.Unmarshal([]byte(raw), &src.Status)
+		v.Sources = append(v.Sources, src)
+	}
+	err = r.Err()
+	r.Close()
+	var count int64
+	s.db.QueryRow(`SELECT COUNT(*) FROM traffic_events`).Scan(&count)
+	v.Limited = count >= 200000
+	return v, err
+}
+
+func trafficRoutes(mux *http.ServeMux, s *Store) {
+	trafficSettingsRoute(mux, s)
+	s.trafficHistoryRoute(mux)
+	trafficCityRoutes(mux)
+	networkRoutes(mux, s)
+	mux.HandleFunc("/traffic", func(w http.ResponseWriter, r *http.Request) {
+		if !s.TrafficSettings().Enabled {
+			http.Error(w, "Карта трафика отключена. Включите её в настройках Dashboard.", 404)
+			return
+		}
+		w.Header().Set("Content-Type", "text/html; charset=utf-8")
+		w.Write([]byte(trafficHTML))
+	})
+	mux.HandleFunc("/api/traffic", func(w http.ResponseWriter, r *http.Request) {
+		if r.Method != "GET" {
+			w.WriteHeader(405)
+			return
+		}
+		if !s.TrafficSettings().Enabled {
+			http.Error(w, "Карта отключена", 404)
+			return
+		}
+		view, err := s.TrafficView(r.URL.Query().Get("domain"), r.URL.Query().Get("kind"), r.URL.Query().Get("external") == "1", r.URL.Query().Get("hideMonitoring") == "1")
+		writeJSON(w, view, err)
+	})
+	mux.HandleFunc("/api/traffic/world", func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		w.Header().Set("Cache-Control", "public, max-age=86400")
+		w.Write(trafficWorld)
+	})
+	mux.HandleFunc("/api/agent/traffic", func(w http.ResponseWriter, r *http.Request) {
+		if r.Method != "POST" {
+			w.WriteHeader(405)
+			return
+		}
+		id, secret, ok := agentCredentials(r)
+		if !ok || !s.AuthenticateAgent(id, secret) {
+			http.Error(w, "Unauthorized", 401)
+			return
+		}
+		settings := s.TrafficSettings()
+		if !settings.Enabled || settings.AgentID != id {
+			http.Error(w, "Источник отключён", 403)
+			return
+		}
+		var batch TrafficBatch
+		if json.NewDecoder(io.LimitReader(r.Body, 1<<20)).Decode(&batch) != nil {
+			http.Error(w, "Invalid traffic batch", 400)
+			return
+		}
+		if err := s.SaveTraffic(id, batch); err != nil {
+			http.Error(w, fmt.Sprint(err), 500)
+			return
+		}
+		writeJSON(w, map[string]bool{"accepted": true}, nil)
+	})
+}

traffic_city.go

@@ -0,0 +1,166 @@
+package main
+
+import (
+	"compress/gzip"
+	"crypto/sha1"
+	"encoding/hex"
+	"fmt"
+	"io"
+	"net"
+	"net/http"
+	"os"
+	"path/filepath"
+	"strings"
+	"sync"
+	"time"
+
+	"github.com/oschwald/maxminddb-golang"
+)
+
+const cityDownloadURL = "https://download.db-ip.com/free/dbip-city-lite-2026-10.mmdb.gz"
+const cityDatabaseSHA1 = "df17bd24390108ed1d24dcb7718dc60f6b9abd4f"
+
+var trafficCity struct {
+	sync.Mutex
+	once    sync.Once
+	db      *maxminddb.Reader
+	running bool
+	message string
+}
+
+func trafficCityPath() string {
+	db := os.Getenv("DASHBOARD_DB_PATH")
+	if db == "" {
+		db = defaultDatabasePath
+	}
+	return filepath.Join(filepath.Dir(db), "dbip-city.mmdb")
+}
+func trafficCityReady() bool {
+	trafficCity.once.Do(func() {
+		trafficCity.Lock()
+		defer trafficCity.Unlock()
+		trafficCity.db, _ = maxminddb.Open(trafficCityPath())
+		if trafficCity.db != nil && !strings.Contains(strings.ToLower(trafficCity.db.Metadata.DatabaseType), "city") {
+			trafficCity.db.Close()
+			trafficCity.db = nil
+		}
+	})
+	trafficCity.Lock()
+	defer trafficCity.Unlock()
+	return trafficCity.db != nil
+}
+func lookupTrafficCity(text string) (string, string) {
+	ip := net.ParseIP(text)
+	if ip == nil || ip.IsPrivate() || ip.IsLoopback() || ip.IsLinkLocalUnicast() || !ip.IsGlobalUnicast() || !trafficCityReady() {
+		return "", ""
+	}
+	trafficCity.Lock()
+	defer trafficCity.Unlock()
+	var r struct {
+		City struct {
+			Names map[string]string `maxminddb:"names"`
+		} `maxminddb:"city"`
+		Subdivisions []struct {
+			Names map[string]string `maxminddb:"names"`
+		} `maxminddb:"subdivisions"`
+	}
+	if trafficCity.db.Lookup(ip, &r) != nil {
+		return "", ""
+	}
+	region := ""
+	if len(r.Subdivisions) > 0 {
+		region = cityName(r.Subdivisions[0].Names)
+	}
+	return cityName(r.City.Names), region
+}
+func trafficCityRoutes(mux *http.ServeMux) {
+	mux.HandleFunc("/api/settings/traffic/city-database", func(w http.ResponseWriter, r *http.Request) {
+		if r.Method != "GET" && r.Method != "POST" {
+			w.WriteHeader(405)
+			return
+		}
+		trafficCityReady()
+		trafficCity.Lock()
+		if r.Method == "POST" && !trafficCity.running && trafficCity.db == nil {
+			trafficCity.running = true
+			trafficCity.message = "Загрузка базы городов (около 58 МБ)…"
+			go func() {
+				err := installTrafficCity()
+				trafficCity.Lock()
+				defer trafficCity.Unlock()
+				trafficCity.running = false
+				if err != nil {
+					trafficCity.message = "Не удалось установить базу: " + err.Error()
+				} else {
+					trafficCity.message = "База городов DB-IP City Lite 2026-10 установлена"
+				}
+			}()
+		}
+		status := map[string]any{"ready": trafficCity.db != nil, "running": trafficCity.running, "message": trafficCity.message, "date": "2026-10"}
+		trafficCity.Unlock()
+		writeJSON(w, status, nil)
+	})
+}
+func installTrafficCity() error { return installTrafficCityFrom(cityDownloadURL, cityDatabaseSHA1) }
+func installTrafficCityFrom(source, expectedHash string) error {
+	client := &http.Client{Timeout: 15 * time.Minute}
+	response, err := client.Get(source)
+	if err != nil {
+		return err
+	}
+	defer response.Body.Close()
+	if response.StatusCode != 200 {
+		return fmt.Errorf("HTTP %d", response.StatusCode)
+	}
+	reader, err := gzip.NewReader(io.LimitReader(response.Body, 70<<20))
+	if err != nil {
+		return err
+	}
+	defer reader.Close()
+	path := trafficCityPath()
+	if err = os.MkdirAll(filepath.Dir(path), 0750); err != nil {
+		return err
+	}
+	file, err := os.CreateTemp(filepath.Dir(path), ".city-*.mmdb")
+	if err != nil {
+		return err
+	}
+	defer os.Remove(file.Name())
+	defer file.Close()
+	hash := sha1.New()
+	n, err := io.Copy(io.MultiWriter(file, hash), io.LimitReader(reader, (160<<20)+1))
+	if err != nil {
+		return err
+	}
+	if n > 160<<20 {
+		return fmt.Errorf("база превышает лимит размера")
+	}
+	if hex.EncodeToString(hash.Sum(nil)) != expectedHash {
+		return fmt.Errorf("контрольная сумма базы не совпала")
+	}
+	if err = file.Sync(); err != nil {
+		return err
+	}
+	if err = file.Close(); err != nil {
+		return err
+	}
+	db, err := maxminddb.Open(file.Name())
+	if err != nil {
+		return err
+	}
+	if !strings.Contains(strings.ToLower(db.Metadata.DatabaseType), "city") {
+		db.Close()
+		return fmt.Errorf("неверный тип GeoIP-базы")
+	}
+	if err = os.Rename(file.Name(), path); err != nil {
+		db.Close()
+		return err
+	}
+	trafficCity.Lock()
+	defer trafficCity.Unlock()
+	if trafficCity.db != nil {
+		trafficCity.db.Close()
+	}
+	trafficCity.db = db
+	return nil
+}

traffic_city_test.go

@@ -0,0 +1,54 @@
+package main
+
+import (
+	"compress/gzip"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+func TestCityInstallRejectsBadDownload(t *testing.T) {
+	dir := t.TempDir()
+	t.Setenv("DASHBOARD_DB_PATH", filepath.Join(dir, "dashboard.db"))
+	existing := []byte("existing database")
+	if err := os.WriteFile(trafficCityPath(), existing, 0600); err != nil {
+		t.Fatal(err)
+	}
+	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		g := gzip.NewWriter(w)
+		g.Write([]byte("corrupt database"))
+		g.Close()
+	}))
+	defer server.Close()
+	if err := installTrafficCityFrom(server.URL, cityDatabaseSHA1); err == nil {
+		t.Fatal("bad checksum accepted")
+	}
+	got, err := os.ReadFile(trafficCityPath())
+	if err != nil || string(got) != string(existing) {
+		t.Fatal("existing database replaced on failure")
+	}
+	files, _ := filepath.Glob(filepath.Join(dir, ".city-*"))
+	if len(files) != 0 {
+		t.Fatal("partial file left behind")
+	}
+}
+func TestCityDatabaseDownloaded(t *testing.T) {
+	source := os.Getenv("DASHBOARD_CITY_TEST_GZIP")
+	if source == "" {
+		t.Skip("optional official database integration test")
+	}
+	t.Setenv("DASHBOARD_DB_PATH", filepath.Join(t.TempDir(), "dashboard.db"))
+	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { http.ServeFile(w, r, source) }))
+	defer server.Close()
+	trafficCityReady()
+	if err := installTrafficCityFrom(server.URL, cityDatabaseSHA1); err != nil {
+		t.Fatal(err)
+	}
+	city, region := lookupTrafficCity("20.194.96.114")
+	t.Logf("city=%q region=%q", city, region)
+	if city == "" {
+		t.Fatal("public IP city not decoded")
+	}
+}

traffic_country_test.go

@@ -0,0 +1,44 @@
+package main
+
+import (
+	"fmt"
+	"testing"
+	"time"
+)
+
+func TestTrafficCountryDetailsUseHistoryAndFilters(t *testing.T) {
+	s, a := trafficFixture(t)
+	if _, err := s.SaveTrafficSettings(TrafficSettings{Enabled: true, AgentID: a.ID, MonitoringRules: []MonitoringRule{{IP: "8.8.8.8"}}}); err != nil {
+		t.Fatal(err)
+	}
+	events := []TrafficEvent{}
+	for i := 0; i < 120; i++ {
+		events = append(events, TrafficEvent{ID: fmt.Sprint("http-", i), Time: time.Now().Unix(), Kind: "request", IP: "8.8.8.8", Domain: "example.test", Path: "/", Status: 200})
+	}
+	events = append(events, TrafficEvent{ID: "alert", Time: time.Now().Unix(), Kind: "alert", IP: "8.8.8.8", Domain: "example.test", Reason: "test"})
+	if err := s.SaveTraffic(a.ID, TrafficBatch{Events: events}); err != nil {
+		t.Fatal(err)
+	}
+	v, err := s.TrafficView("", "", false)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(v.Events) != 100 || len(v.CountryDetails) != 1 {
+		t.Fatalf("events=%d countries=%+v", len(v.Events), v.CountryDetails)
+	}
+	d := v.CountryDetails[0]
+	if d.Requests != 120 || d.UniqueIPs != 1 || d.Alerts != 1 || d.LastSeen == 0 {
+		t.Fatalf("%+v", d)
+	}
+	v, err = s.TrafficView("example.test", "", false, true)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(v.CountryDetails) != 1 || v.CountryDetails[0].Requests != 0 || v.CountryDetails[0].Alerts != 1 {
+		t.Fatalf("filter: %+v", v.CountryDetails)
+	}
+	v, err = s.TrafficView("other.test", "", false)
+	if err != nil || len(v.CountryDetails) != 0 {
+		t.Fatalf("domain: %+v %v", v.CountryDetails, err)
+	}
+}

traffic_geo.go

@@ -0,0 +1,65 @@
+package main
+
+import (
+	"bytes"
+	"compress/gzip"
+	_ "embed"
+	"io"
+	"net"
+	"sync"
+
+	"github.com/oschwald/maxminddb-golang"
+)
+
+//go:embed assets/world.json
+var trafficWorld []byte
+
+//go:embed assets/dbip-country-lite-2026-10.mmdb.gz
+var trafficGeoCompressed []byte
+
+const trafficGeoDate = "2026-10"
+
+var trafficGeo struct {
+	sync.Once
+	db *maxminddb.Reader
+}
+
+func trafficGeoReady() bool {
+	trafficGeo.Do(func() {
+		r, err := gzip.NewReader(bytes.NewReader(trafficGeoCompressed))
+		if err != nil {
+			return
+		}
+		defer r.Close()
+		data, err := io.ReadAll(io.LimitReader(r, 32<<20))
+		if err != nil {
+			return
+		}
+		trafficGeo.db, _ = maxminddb.FromBytes(data)
+	})
+	return trafficGeo.db != nil
+}
+func lookupTrafficCountry(ipText string) string {
+	ip := net.ParseIP(ipText)
+	if ip == nil {
+		return ""
+	}
+	if ip.IsPrivate() || ip.IsLoopback() || ip.IsLinkLocalUnicast() {
+		return "LAN"
+	}
+	if !ip.IsGlobalUnicast() {
+		return ""
+	}
+	if !trafficGeoReady() {
+		return ""
+	}
+	var record struct {
+		Country struct {
+			Code string `maxminddb:"iso_code"`
+		} `maxminddb:"country"`
+	}
+	if trafficGeo.db.Lookup(ip, &record) != nil {
+		return ""
+	}
+	return record.Country.Code
+}

traffic_history.go

@@ -0,0 +1,144 @@
+package main
+
+import (
+	"net/http"
+	"strconv"
+	"strings"
+	"time"
+)
+
+type TrafficIPDetail struct {
+	IP       string `json:"ip"`
+	Country  string `json:"country"`
+	Requests int64  `json:"requests"`
+	LastSeen int64  `json:"lastSeen"`
+	City     string `json:"city,omitempty"`
+	Region   string `json:"region,omitempty"`
+}
+type TrafficHistory struct {
+	Events      []TrafficEvent    `json:"events"`
+	IPs         []TrafficIPDetail `json:"ips"`
+	Total       int64             `json:"total"`
+	Page        int               `json:"page"`
+	PageSize    int               `json:"pageSize"`
+	Snapshot    int64             `json:"snapshot"`
+	MaxSequence int64             `json:"maxSequence"`
+	CityReady   bool              `json:"cityReady"`
+}
+
+func (s *Store) trafficHistoryRoute(mux *http.ServeMux) {
+	mux.HandleFunc("/api/traffic/history", func(w http.ResponseWriter, r *http.Request) {
+		if r.Method != "GET" {
+			w.WriteHeader(405)
+			return
+		}
+		if !s.TrafficSettings().Enabled {
+			http.Error(w, "Карта отключена", 404)
+			return
+		}
+		q := r.URL.Query()
+		page, _ := strconv.Atoi(q.Get("page"))
+		snapshot, _ := strconv.ParseInt(q.Get("snapshot"), 10, 64)
+		maxSeq, _ := strconv.ParseInt(q.Get("maxSequence"), 10, 64)
+		if q.Get("maxSequence") == "0" {
+			maxSeq = -1
+		}
+		if page < 0 || page > 10000 {
+			http.Error(w, "Invalid page", 400)
+			return
+		}
+		kind := q.Get("kind")
+		metricType := q.Get("type")
+		if metricType != "" && metricType != "request" && metricType != "alert" && metricType != "decision" {
+			http.Error(w, "Invalid type", 400)
+			return
+		}
+		if kind != "" && kind != "request" && kind != "alert" && kind != "decision" {
+			http.Error(w, "Invalid kind", 400)
+			return
+		}
+		result, err := s.TrafficHistory(q.Get("domain"), kind, q.Get("country"), q.Get("ip"), q.Get("type"), q.Get("external") == "1", q.Get("hideMonitoring") == "1", q.Get("group") == "ip", page, snapshot, maxSeq)
+		writeJSON(w, result, err)
+	})
+}
+func (s *Store) TrafficHistory(domain, kind, country, ip, metricType string, external, hide, group bool, page int, snapshot, maxSeq int64) (TrafficHistory, error) {
+	now := time.Now().Unix()
+	if snapshot <= 0 || snapshot > now {
+		snapshot = now
+	}
+	if snapshot < now-86400 {
+		snapshot = now
+	}
+	settings := s.TrafficSettings()
+	v := TrafficHistory{Events: []TrafficEvent{}, IPs: []TrafficIPDetail{}, Page: page, PageSize: 50, Snapshot: snapshot, CityReady: trafficCityReady()}
+	if maxSeq == 0 {
+		if err := s.db.QueryRow(`SELECT COALESCE(MAX(seq),0) FROM traffic_events WHERE agent=?`, settings.AgentID).Scan(&maxSeq); err != nil {
+			return v, err
+		}
+	}
+	v.MaxSequence = maxSeq
+	where := ` WHERE agent=? AND ts>=? AND ts<=? AND seq<=?`
+	args := []any{settings.AgentID, snapshot - 86400, snapshot, maxSeq}
+	if hide {
+		clause, values := monitoringSQL(settings.MonitoringRules)
+		where += clause
+		args = append(args, values...)
+	}
+	if external {
+		where += ` AND country!='LAN'`
+	}
+	for _, filter := range []struct{ column, value string }{{"domain", domain}, {"kind", kind}, {"kind", metricType}, {"country", country}, {"ip", ip}} {
+		if filter.value != "" {
+			where += " AND " + filter.column + "=?"
+			args = append(args, filter.value)
+		}
+	}
+	count := "COUNT(*)"
+	if group {
+		where += ` AND kind='request'`
+		count = "COUNT(DISTINCT ip)"
+	}
+	if err := s.db.QueryRow("SELECT "+count+" FROM traffic_events"+where, args...).Scan(&v.Total); err != nil {
+		return v, err
+	}
+	paged := append(append([]any{}, args...), v.PageSize, page*v.PageSize)
+	if group {
+		rows, err := s.db.Query(`SELECT ip,MIN(country),COUNT(*),MAX(ts) FROM traffic_events`+where+` GROUP BY ip ORDER BY COUNT(*) DESC,ip LIMIT ? OFFSET ?`, paged...)
+		if err != nil {
+			return v, err
+		}
+		defer rows.Close()
+		for rows.Next() {
+			var item TrafficIPDetail
+			if err = rows.Scan(&item.IP, &item.Country, &item.Requests, &item.LastSeen); err != nil {
+				return v, err
+			}
+			item.City, item.Region = lookupTrafficCity(item.IP)
+			v.IPs = append(v.IPs, item)
+		}
+		return v, rows.Err()
+	}
+	rows, err := s.db.Query(`SELECT seq,event_id,ts,kind,ip,domain,method,path,status,reason,country,agent FROM traffic_events`+where+` ORDER BY ts DESC,seq DESC LIMIT ? OFFSET ?`, paged...)
+	if err != nil {
+		return v, err
+	}
+	defer rows.Close()
+	for rows.Next() {
+		var e TrafficEvent
+		if err = rows.Scan(&e.Sequence, &e.ID, &e.Time, &e.Kind, &e.IP, &e.Domain, &e.Method, &e.Path, &e.Status, &e.Reason, &e.Country, &e.Agent); err != nil {
+			return v, err
+		}
+		e.Monitoring = isMonitoringRequest(e, settings.MonitoringRules)
+		e.City, e.Region = lookupTrafficCity(e.IP)
+		v.Events = append(v.Events, e)
+	}
+	return v, rows.Err()
+}
+func cityName(names map[string]string) string {
+	for _, lang := range []string{"ru", "en"} {
+		if s := strings.TrimSpace(names[lang]); s != "" {
+			return s
+		}
+	}
+	return ""
+}

traffic_history_test.go

@@ -0,0 +1,109 @@
+package main
+
+import (
+	"fmt"
+	"testing"
+	"time"
+)
+
+func TestTrafficHistoryFullPaginationAndSnapshot(t *testing.T) {
+	s, a := trafficFixture(t)
+	if _, err := s.SaveTrafficSettings(TrafficSettings{Enabled: true, AgentID: a.ID}); err != nil {
+		t.Fatal(err)
+	}
+	now := time.Now().Unix()
+	batch := TrafficBatch{}
+	for i := 0; i < 137; i++ {
+		batch.Events = append(batch.Events, TrafficEvent{ID: fmt.Sprint(i), Time: now - 60, Kind: "request", IP: "8.8.8.8", Domain: "example.test"})
+	}
+	batch.Events = append(batch.Events, TrafficEvent{ID: "old-alert", Time: now - 3600, Kind: "alert", IP: "1.1.1.1", Domain: "other.test"})
+	if err := s.SaveTraffic(a.ID, batch); err != nil {
+		t.Fatal(err)
+	}
+	first, err := s.TrafficHistory("", "request", "", "", "", false, false, false, 0, now, 0)
+	if err != nil || first.Total != 137 || len(first.Events) != 50 {
+		t.Fatalf("first: %+v %v", first, err)
+	}
+	if err := s.SaveTraffic(a.ID, TrafficBatch{Events: []TrafficEvent{{ID: "new", Time: now - 60, Kind: "request", IP: "8.8.8.8"}}}); err != nil {
+		t.Fatal(err)
+	}
+	seen := map[int64]bool{}
+	for page := 0; page < 3; page++ {
+		h, err := s.TrafficHistory("", "request", "", "", "", false, false, false, page, first.Snapshot, first.MaxSequence)
+		if err != nil || h.Total != 137 {
+			t.Fatalf("page %d: %v total %d", page, err, h.Total)
+		}
+		for _, e := range h.Events {
+			if seen[e.Sequence] {
+				t.Fatal("duplicate page event")
+			}
+			seen[e.Sequence] = true
+		}
+	}
+	if len(seen) != 137 {
+		t.Fatalf("missing history: %d", len(seen))
+	}
+	h, err := s.TrafficHistory("other.test", "alert", "", "", "", false, false, false, 0, now, 0)
+	if err != nil || h.Total != 1 || h.Events[0].ID != "old-alert" {
+		t.Fatalf("old alert missing: %+v %v", h, err)
+	}
+	h, err = s.TrafficHistory("", "alert", "", "", "request", false, false, false, 0, now, 0)
+	if err != nil || h.Total != 0 {
+		t.Fatal("metric must respect global kind filter")
+	}
+	h, err = s.TrafficHistory("example.test", "", "", "", "", false, false, true, 0, now, 0)
+	if err != nil || h.Total != 1 || len(h.IPs) != 1 || h.IPs[0].Requests != 137 {
+		t.Fatalf("IP summary %+v %v", h, err)
+	}
+	h, err = s.TrafficHistory("", "", "ZZ", "", "", false, false, false, 0, now, 0)
+	if err != nil || h.Total != 0 {
+		t.Fatal("country filter ignored")
+	}
+	h, err = s.TrafficHistory("", "", "", "1.1.1.1", "", false, false, false, 0, now, 0)
+	if err != nil || h.Total != 1 {
+		t.Fatal("IP filter ignored")
+	}
+}
+func TestCityNamesAndLocalAddresses(t *testing.T) {
+	if cityName(map[string]string{"ru": "Москва", "en": "Moscow"}) != "Москва" || cityName(map[string]string{"en": "Amsterdam"}) != "Amsterdam" {
+		t.Fatal("city localization")
+	}
+	for _, ip := range []string{"192.168.0.10", "127.0.0.1", "::1", "fe80::1", "invalid"} {
+		c, r := lookupTrafficCity(ip)
+		if c != "" || r != "" {
+			t.Fatal("local IP geolocated")
+		}
+	}
+}
+
+func TestTrafficHistoryMonitoringAndAgentIsolation(t *testing.T) {
+	s, a := trafficFixture(t)
+	s.SaveTrafficSettings(TrafficSettings{Enabled: true, AgentID: a.ID, MonitoringRules: []MonitoringRule{{IP: "192.168.0.10"}}})
+	now := time.Now().Unix()
+	batch := TrafficBatch{Events: []TrafficEvent{{ID: "check", Time: now, Kind: "request", IP: "192.168.0.10"}, {ID: "alert", Time: now, Kind: "alert", IP: "192.168.0.10"}, {ID: "public", Time: now, Kind: "request", IP: "8.8.8.8"}}}
+	if err := s.SaveTraffic(a.ID, batch); err != nil {
+		t.Fatal(err)
+	}
+	token, _ := s.CreateAgentEnrollmentToken()
+	other, err := s.EnrollAgent(agentEnrollmentRequest{Token: token, Name: "other", VMID: 103})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if err = s.SaveTraffic(other.ID, batch); err != nil {
+		t.Fatal(err)
+	}
+	for _, tc := range []struct {
+		external, hide bool
+		want           int64
+	}{{false, false, 3}, {false, true, 2}, {true, false, 1}, {true, true, 1}} {
+		h, err := s.TrafficHistory("", "", "", "", "", tc.external, tc.hide, false, 0, now, 0)
+		if err != nil || h.Total != tc.want {
+			t.Fatalf("filters %+v total=%d err=%v", tc, h.Total, err)
+		}
+		for _, e := range h.Events {
+			if e.Agent != a.ID {
+				t.Fatal("foreign agent leaked")
+			}
+		}
+	}
+}

traffic_monitoring.go

@@ -0,0 +1,76 @@
+package main
+
+import (
+	"fmt"
+	"net"
+	"strings"
+)
+
+// Domain/path restrictions describe HTTP probes only. An IP-only rule also
+// matches conntrack initiators; a destination match never hides other clients.
+type MonitoringRule struct {
+	IP         string `json:"ip"`
+	Domain     string `json:"domain,omitempty"`
+	PathPrefix string `json:"pathPrefix,omitempty"`
+}
+
+func validateMonitoringRules(rules []MonitoringRule) ([]MonitoringRule, error) {
+	if len(rules) > 32 {
+		return nil, fmt.Errorf("Не более 32 правил мониторинга")
+	}
+	result := make([]MonitoringRule, 0, len(rules))
+	for i, r := range rules {
+		ip := net.ParseIP(strings.TrimSpace(r.IP))
+		if ip == nil {
+			return nil, fmt.Errorf("Правило %d: нужен точный IPv4/IPv6-адрес", i+1)
+		}
+		r.IP = ip.String()
+		r.Domain = strings.ToLower(strings.TrimSpace(r.Domain))
+		r.PathPrefix = strings.TrimSpace(r.PathPrefix)
+		if len(r.Domain) > 253 || strings.ContainsAny(r.Domain, " /|\t\r\n") || len(r.PathPrefix) > 256 || strings.ContainsAny(r.PathPrefix, "|\r\n") || (r.PathPrefix != "" && !strings.HasPrefix(r.PathPrefix, "/")) {
+			return nil, fmt.Errorf("Правило %d: проверьте домен и префикс пути (начинается с /)", i+1)
+		}
+		result = append(result, r)
+	}
+	return result, nil
+}
+func isMonitoringRequest(e TrafficEvent, rules []MonitoringRule) bool {
+	if e.Kind != "request" {
+		return false
+	}
+	for _, r := range rules {
+		if e.IP == r.IP && (r.Domain == "" || strings.EqualFold(e.Domain, r.Domain)) && strings.HasPrefix(e.Path, r.PathPrefix) {
+			return true
+		}
+	}
+	return false
+}
+func isMonitoringFlow(f NetworkFlow, rules []MonitoringRule) bool {
+	for _, r := range rules {
+		if net.ParseIP(f.Source).Equal(net.ParseIP(r.IP)) && r.Domain == "" && r.PathPrefix == "" {
+			return true
+		}
+	}
+	return false
+}
+func monitoringSQL(rules []MonitoringRule) (string, []any) {
+	var parts []string
+	var args []any
+	for _, r := range rules {
+		p := "(ip=?"
+		args = append(args, r.IP)
+		if r.Domain != "" {
+			p += " AND lower(domain)=?"
+			args = append(args, r.Domain)
+		}
+		if r.PathPrefix != "" {
+			p += " AND substr(path,1,length(?))=?"
+			args = append(args, r.PathPrefix, r.PathPrefix)
+		}
+		parts = append(parts, p+")")
+	}
+	if len(parts) == 0 {
+		return "", nil
+	}
+	return " AND NOT (kind='request' AND (" + strings.Join(parts, " OR ") + "))", args
+}

traffic_monitoring_test.go

@@ -0,0 +1,140 @@
+package main
+
+import (
+	"encoding/json"
+	"testing"
+	"time"
+)
+
+func TestMonitoringRulesValidation(t *testing.T) {
+	rules, err := validateMonitoringRules([]MonitoringRule{{IP: "2001:db8:0:0::1", Domain: "EXAMPLE.org", PathPrefix: "/health"}})
+	if err != nil || rules[0].IP != "2001:db8::1" || rules[0].Domain != "example.org" {
+		t.Fatalf("normalization: %+v %v", rules, err)
+	}
+	for _, r := range []MonitoringRule{{IP: "192.168.0.0/24"}, {IP: "8.8.8.8", Domain: "https://example.org"}, {IP: "8.8.8.8", PathPrefix: "health"}} {
+		if _, err := validateMonitoringRules([]MonitoringRule{r}); err == nil {
+			t.Fatalf("bad rule accepted: %+v", r)
+		}
+	}
+	if _, err := validateMonitoringRules(make([]MonitoringRule, 33)); err == nil {
+		t.Fatal("unbounded rules")
+	}
+}
+func TestMonitoringFiltersKeepHistoryAndSecurityEvents(t *testing.T) {
+	s, a := trafficFixture(t)
+	rules := []MonitoringRule{{IP: "192.168.0.10"}, {IP: "8.8.8.8", Domain: "example.org", PathPrefix: "/health"}}
+	s.SaveTrafficSettings(TrafficSettings{Enabled: true, AgentID: a.ID, MonitoringRules: rules})
+	now := time.Now().Unix()
+	batch := TrafficBatch{Events: []TrafficEvent{
+		{ID: "probe", Time: now, Kind: "request", IP: "192.168.0.10", Domain: "other.org", Path: "/"},
+		{ID: "health", Time: now, Kind: "request", IP: "8.8.8.8", Domain: "EXAMPLE.org", Path: "/health/live"},
+		{ID: "visitor", Time: now, Kind: "request", IP: "8.8.8.8", Domain: "example.org", Path: "/login"},
+		{ID: "other-domain", Time: now, Kind: "request", IP: "8.8.8.8", Domain: "other.org", Path: "/health"},
+		{ID: "alert", Time: now, Kind: "alert", IP: "192.168.0.10"},
+		{ID: "ban", Time: now, Kind: "decision", IP: "192.168.0.10"},
+	}}
+	if err := s.SaveTraffic(a.ID, batch); err != nil {
+		t.Fatal(err)
+	}
+	all, err := s.TrafficView("", "", false)
+	if err != nil || all.Requests != 4 {
+		t.Fatalf("all: %+v %v", all, err)
+	}
+	tagged := 0
+	for _, e := range all.Events {
+		if e.Monitoring {
+			tagged++
+		}
+	}
+	if tagged != 2 {
+		t.Fatalf("tags %d", tagged)
+	}
+	filtered, err := s.TrafficView("", "", false, true)
+	if err != nil || filtered.Requests != 2 || filtered.Alerts != 1 || filtered.Decisions != 1 || len(filtered.Events) != 4 {
+		t.Fatalf("filter: %+v %v", filtered, err)
+	}
+	if len(filtered.Series) != 1 || filtered.Series[0].Count != 2 {
+		t.Fatalf("graph leaks probes: %+v", filtered.Series)
+	}
+	var count int
+	s.db.QueryRow("SELECT COUNT(*) FROM traffic_events").Scan(&count)
+	if count != 6 {
+		t.Fatal("history deleted")
+	}
+	s.SaveTrafficSettings(TrafficSettings{Enabled: true, AgentID: a.ID, MonitoringRules: []MonitoringRule{}})
+	filtered, err = s.TrafficView("", "", false, true)
+	if err != nil || filtered.Requests != 4 {
+		t.Fatal("cleared rules not applied retroactively")
+	}
+}
+func TestMonitoringPrefixIsLiteralAndDefaultCanBeCleared(t *testing.T) {
+	s, a := trafficFixture(t)
+	if len(s.TrafficSettings().MonitoringRules) != 1 {
+		t.Fatal("missing suggested rule")
+	}
+	rules := []MonitoringRule{{IP: "8.8.8.8", PathPrefix: "/health_%"}}
+	s.SaveTrafficSettings(TrafficSettings{Enabled: true, AgentID: a.ID, MonitoringRules: rules})
+	s.SaveTraffic(a.ID, TrafficBatch{Events: []TrafficEvent{{ID: "x", Time: time.Now().Unix(), Kind: "request", IP: "8.8.8.8", Path: "/health_ok"}}})
+	v, err := s.TrafficView("", "", false, true)
+	if err != nil || v.Requests != 1 {
+		t.Fatal("prefix used as wildcard")
+	}
+	s.SaveTrafficSettings(TrafficSettings{Enabled: true, AgentID: a.ID})
+	if len(s.TrafficSettings().MonitoringRules) != 0 {
+		t.Fatal("cannot clear default")
+	}
+}
+func TestNetworkMapAndMonitoringSourceOnly(t *testing.T) {
+	s, a := trafficFixture(t)
+	rules := []MonitoringRule{{IP: "192.168.0.10"}, {IP: "8.8.8.8", Domain: "example.org"}}
+	s.SaveTrafficSettings(TrafficSettings{Enabled: true, NetworkEnabled: true, AgentID: a.ID, MonitoringRules: rules})
+	incoming, _ := parseNetworkFlow(networkNATLine)
+	probe := incoming
+	probe.Source = "192.168.0.10"
+	outgoing := incoming
+	outgoing.Source = "192.168.0.12"
+	outgoing.Destination = "1.1.1.1"
+	outgoing.Protocol = "udp"
+	local := incoming
+	local.Source = "192.168.0.15"
+	local.Destination = "192.168.0.10"
+	local.Protocol = "icmpv6"
+	s.SaveNetwork(a.ID, NetworkSnapshot{At: time.Now().Unix(), Flows: []NetworkFlow{incoming, probe, outgoing, local}})
+	snapshot, err := s.ReadNetworkSnapshot(a.ID, rules, true)
+	if err != nil || len(snapshot.Flows) != 3 || snapshot.MonitoringHidden != 1 {
+		t.Fatalf("source-only: %+v %v", snapshot, err)
+	}
+	mapped := makeNetworkMap(snapshot, false)
+	if mapped.TCP != 1 || mapped.UDP != 1 || mapped.ICMP != 1 || mapped.Unmapped != 1 || len(mapped.Points) != 2 {
+		t.Fatalf("map: %+v", mapped)
+	}
+	for _, p := range mapped.Points {
+		if p.Protocol == "udp" && p.Direction != "out" {
+			t.Fatal("outbound direction lost")
+		}
+		if p.Protocol == "tcp" && p.Direction != "in" {
+			t.Fatal("inbound direction lost")
+		}
+	}
+	mapped = makeNetworkMap(snapshot, true)
+	if mapped.ICMP != 0 {
+		t.Fatal("LAN flow leaked")
+	}
+	view, err := s.TrafficView("example.org", "alert", false, true)
+	if err != nil || view.Network == nil || view.Network.TCP != 1 {
+		t.Fatal("HTTP filters incorrectly hide network layer")
+	}
+	encoded, _ := json.Marshal(view)
+	if len(encoded) == 0 {
+		t.Fatal("map not serializable")
+	}
+	s.SaveTrafficSettings(TrafficSettings{Enabled: true, AgentID: a.ID})
+	view, _ = s.TrafficView("", "", false)
+	if view.Network != nil {
+		t.Fatal("disabled network leaked")
+	}
+	v6 := NetworkFlow{Source: "2001:db8:0:0::1"}
+	if !isMonitoringFlow(v6, []MonitoringRule{{IP: "2001:db8::1"}}) {
+		t.Fatal("IPv6 representation mismatch")
+	}
+}

traffic_network_map.go

@@ -0,0 +1,107 @@
+package main
+
+import (
+	"database/sql"
+	"encoding/json"
+	"fmt"
+	"sort"
+)
+
+type NetworkMapPoint struct {
+	Country   string `json:"country"`
+	Protocol  string `json:"protocol"`
+	Direction string `json:"direction"`
+	Count     int    `json:"count"`
+}
+type NetworkMapView struct {
+	At               int64             `json:"at"`
+	ReceivedAt       int64             `json:"receivedAt"`
+	TCP              int               `json:"tcp"`
+	UDP              int               `json:"udp"`
+	ICMP             int               `json:"icmp"`
+	Unmapped         int               `json:"unmapped"`
+	MonitoringHidden int               `json:"monitoringHidden"`
+	Limited          bool              `json:"limited"`
+	Error            string            `json:"error,omitempty"`
+	Points           []NetworkMapPoint `json:"points"`
+}
+
+func (s *Store) ReadNetworkSnapshot(agent string, rules []MonitoringRule, hide bool) (NetworkSnapshot, error) {
+	var raw, name string
+	err := s.db.QueryRow(`SELECT n.snapshot,a.name FROM network_sources n JOIN agents a ON a.id=n.agent WHERE n.agent=?`, agent).Scan(&raw, &name)
+	if err == sql.ErrNoRows {
+		return NetworkSnapshot{Flows: []NetworkFlow{}, Error: "Ожидание агента v0.21.0 или новее"}, nil
+	}
+	if err != nil {
+		return NetworkSnapshot{}, err
+	}
+	var snapshot NetworkSnapshot
+	if err = json.Unmarshal([]byte(raw), &snapshot); err != nil {
+		return snapshot, err
+	}
+	snapshot.AgentName = name
+	flows := make([]NetworkFlow, 0, len(snapshot.Flows))
+	for _, f := range snapshot.Flows {
+		f.Monitoring = isMonitoringFlow(f, rules)
+		if hide && f.Monitoring {
+			snapshot.MonitoringHidden++
+			continue
+		}
+		flows = append(flows, f)
+	}
+	snapshot.Flows = flows
+	return snapshot, nil
+}
+func makeNetworkMap(snapshot NetworkSnapshot, external bool) NetworkMapView {
+	v := NetworkMapView{At: snapshot.At, ReceivedAt: snapshot.ReceivedAt, Limited: snapshot.Limited, Error: snapshot.Error, MonitoringHidden: snapshot.MonitoringHidden, Points: []NetworkMapPoint{}}
+	if snapshot.ParseErrors > 0 {
+		v.Error += fmt.Sprintf(" Нераспознанных строк: %d", snapshot.ParseErrors)
+	}
+	points := map[string]*NetworkMapPoint{}
+	for _, f := range snapshot.Flows {
+		if external && !f.External {
+			continue
+		}
+		protocol := f.Protocol
+		if protocol == "icmpv6" {
+			protocol = "icmp"
+		}
+		switch protocol {
+		case "tcp":
+			v.TCP++
+		case "udp":
+			v.UDP++
+		case "icmp":
+			v.ICMP++
+		}
+		country, direction := f.Country, "in"
+		if !networkExternalIP(f.Source) {
+			if networkExternalIP(f.Destination) {
+				country, direction = f.DestinationCountry, "out"
+			} else {
+				v.Unmapped++
+				continue
+			}
+		}
+		if country == "" || country == "LAN" {
+			v.Unmapped++
+			continue
+		}
+		key := country + "/" + protocol + "/" + direction
+		if points[key] == nil {
+			points[key] = &NetworkMapPoint{Country: country, Protocol: protocol, Direction: direction}
+		}
+		points[key].Count++
+	}
+	for _, p := range points {
+		v.Points = append(v.Points, *p)
+	}
+	sort.Slice(v.Points, func(i, j int) bool {
+		a, b := v.Points[i], v.Points[j]
+		if a.Count != b.Count {
+			return a.Count > b.Count
+		}
+		return a.Country+a.Protocol+a.Direction < b.Country+b.Protocol+b.Direction
+	})
+	return v
+}

traffic_preview_test.go

@@ -0,0 +1,92 @@
+package main
+
+import (
+	"fmt"
+	"net/http"
+	"os"
+	"strings"
+	"testing"
+	"time"
+)
+
+// Opt-in local visual fixture; never included in production binaries.
+func TestTrafficPreview(t *testing.T) {
+	if os.Getenv("DASHBOARD_TRAFFIC_PREVIEW") != "1" {
+		t.Skip("manual visual preview")
+	}
+	s, a := trafficFixture(t)
+	s.SaveTrafficSettings(TrafficSettings{Enabled: true, NetworkEnabled: true, MonitoringRules: []MonitoringRule{{IP: "192.168.0.10"}}, AgentID: a.ID, ServerCountry: "RU"})
+	mux := http.NewServeMux()
+	trafficRoutes(mux, s)
+	mux.HandleFunc("/", func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "text/html; charset=utf-8")
+		w.Write([]byte(dashboardHTML))
+	})
+	mux.HandleFunc("/api/agents", func(w http.ResponseWriter, r *http.Request) { items, _ := s.Agents(); writeJSON(w, items, nil) })
+	go func() {
+		i := 0
+		for {
+			i++
+			events := []TrafficEvent{}
+			for j, ip := range []string{"8.8.8.8", "1.1.1.1", "20.194.96.114", "192.168.0.10", "77.83.39.94", "51.158.145.102", "123.56.127.23"} {
+				kind := "request"
+				if j == 4 {
+					kind = "alert"
+				}
+				if j == 5 {
+					kind = "decision"
+				}
+				events = append(events, TrafficEvent{ID: fmt.Sprintf("preview-%d-%d", i, j), Time: time.Now().Unix(), Kind: kind, IP: ip, Domain: "demo.example", Method: "GET", Path: "/demo", Status: 200, Reason: "ДЕМО · crowdsecurity/http-probing"})
+			}
+			flows := []NetworkFlow{}
+			for k := 0; k < 32; k++ {
+				f, _ := parseNetworkFlow(networkNATLine)
+				f.SourcePort = 51000 + k
+				f.ReplyDestinationPort = f.SourcePort
+				f.Source = []string{"8.8.8.8", "1.1.1.1", "20.194.96.114", "192.168.0.10", "51.158.145.102", "2001:4860:4860::8888"}[k%6]
+				f.ReplyDestination = f.Source
+				if k%3 == 0 {
+					f.Protocol = "udp"
+					f.State = "ASSURED"
+					f.DestinationPort = 53
+					f.ReplySourcePort = 53
+				}
+				if k%5 == 0 && f.Protocol == "tcp" {
+					f.State = "SYN_SENT"
+				}
+				if k%7 == 0 {
+					f.Protocol = "icmp"
+					f.State = "TRACKED"
+					f.SourcePort = 0
+					f.DestinationPort = 0
+					f.ReplySourcePort = 0
+					f.ReplyDestinationPort = 0
+				}
+				if k == 11 {
+					f.Source = "192.168.0.12"
+					f.Destination = "1.1.1.1"
+					f.ReplySource = "1.1.1.1"
+					f.ReplyDestination = "192.168.0.12"
+				}
+				flows = append(flows, f)
+			}
+			s.SaveNetwork(a.ID, NetworkSnapshot{At: time.Now().Unix(), Flows: flows, FirewallAt: time.Now().Unix(), Firewall: []FirewallCounter{{Name: "DEMO ip/crowdsec/drop #3", Packets: 12345, Bytes: 654321}}})
+			s.SaveTraffic(a.ID, TrafficBatch{Events: events, Files: 22, StartedAt: time.Now().Add(-time.Hour).Unix(), CrowdSecAt: time.Now().Unix()})
+			time.Sleep(3 * time.Second)
+		}
+	}()
+	handler := http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Path == "/network" {
+			w.Header().Set("Content-Type", "text/html; charset=utf-8")
+			w.Write([]byte(strings.Replace(networkHTML, "PROXMOX / NETWORK OBSERVATORY", "ДЕМО / ИСКУССТВЕННЫЕ ДАННЫЕ", 1)))
+			return
+		}
+		if r.URL.Path == "/traffic" {
+			w.Header().Set("Content-Type", "text/html; charset=utf-8")
+			w.Write([]byte(strings.Replace(trafficHTML, "PROXMOX / LIVE OBSERVATORY", "ДЕМО / ИСКУССТВЕННЫЕ ДАННЫЕ", 1)))
+			return
+		}
+		mux.ServeHTTP(w, r)
+	})
+	t.Fatal(http.ListenAndServe("127.0.0.1:19105", handler))
+}

traffic_settings.go

@@ -0,0 +1,80 @@
+package main
+
+import (
+	"encoding/json"
+	"errors"
+	"io"
+	"net/http"
+	"strings"
+)
+
+type TrafficSettings struct {
+	MonitoringRules []MonitoringRule `json:"monitoringRules"`
+	NetworkEnabled  bool             `json:"networkEnabled"`
+	Enabled         bool             `json:"enabled"`
+	AgentID         string           `json:"agentId"`
+	ServerCountry   string           `json:"serverCountry"`
+}
+
+func (s *Store) TrafficSettings() TrafficSettings {
+	var c TrafficSettings
+	s.loadJSONSetting("traffic", &c)
+	if c.MonitoringRules == nil {
+		c.MonitoringRules = []MonitoringRule{{IP: "192.168.0.10"}}
+	}
+	return c
+}
+func (s *Store) SaveTrafficSettings(c TrafficSettings) (TrafficSettings, error) {
+	rules, err := validateMonitoringRules(c.MonitoringRules)
+	if err != nil {
+		return c, err
+	}
+	c.MonitoringRules = rules
+	c.AgentID = strings.TrimSpace(c.AgentID)
+	c.ServerCountry = strings.ToUpper(strings.TrimSpace(c.ServerCountry))
+	if c.Enabled {
+		var count int
+		if s.db.QueryRow(`SELECT COUNT(*) FROM agents WHERE id=?`, c.AgentID).Scan(&count) != nil || count != 1 {
+			return c, errors.New("Выберите зарегистрированный агент")
+		}
+	}
+	if c.ServerCountry != "" {
+		var countries []struct {
+			Code string `json:"code"`
+		}
+		json.Unmarshal(trafficWorld, &countries)
+		found := false
+		for _, country := range countries {
+			if country.Code == c.ServerCountry {
+				found = true
+				break
+			}
+		}
+		if !found {
+			return c, errors.New("Неизвестная страна сервера")
+		}
+	}
+	return c, s.saveJSONSetting("traffic", c)
+}
+func trafficSettingsRoute(mux *http.ServeMux, s *Store) {
+	mux.HandleFunc("/api/settings/traffic", func(w http.ResponseWriter, r *http.Request) {
+		switch r.Method {
+		case "GET":
+			writeJSON(w, s.TrafficSettings(), nil)
+		case "PUT":
+			var c TrafficSettings
+			if json.NewDecoder(io.LimitReader(r.Body, 32<<10)).Decode(&c) != nil {
+				http.Error(w, "Некорректные настройки", 400)
+				return
+			}
+			value, err := s.SaveTrafficSettings(c)
+			if err != nil {
+				http.Error(w, err.Error(), 400)
+				return
+			}
+			writeJSON(w, value, nil)
+		default:
+			w.WriteHeader(405)
+		}
+	})
+}

traffic_test.go

@@ -0,0 +1,217 @@
+package main
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+)
+
+func trafficFixture(t *testing.T) (*Store, agentConfig) {
+	t.Helper()
+	s, err := openStore(":memory:")
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(func() { s.Close() })
+	token, err := s.CreateAgentEnrollmentToken()
+	if err != nil {
+		t.Fatal(err)
+	}
+	a, err := s.EnrollAgent(agentEnrollmentRequest{Token: token, Name: "NPM test", VMID: 102})
+	if err != nil {
+		t.Fatal(err)
+	}
+	return s, a
+}
+func npmTestLine(ip, path string) string {
+	return fmt.Sprintf("[%s] - - 301 - GET https example.test \"%s\" [Client %s] [Length 166] [Gzip -] [Sent-to 192.168.0.9] \"-\" \"-\"\n", time.Now().UTC().Format("02/Jan/2006:15:04:05 -0700"), path, ip)
+}
+func TestNPMTrafficFormats(t *testing.T) {
+	for _, status := range []string{"- 200 200", "- - 301", "- 502 502", "- - 401"} {
+		line := strings.Replace(npmTestLine("2001:4860:4860::8888", "/login?token=secret#fragment"), "- - 301", status, 1)
+		e, ok := parseNPMTraffic(line)
+		if !ok || e.Kind != "request" || e.Path != "/login" || e.Domain != "example.test" || e.IP != "2001:4860:4860::8888" {
+			t.Fatalf("bad parse: %+v %v", e, ok)
+		}
+	}
+	if _, ok := parseNPMTraffic("broken"); ok {
+		t.Fatal("accepted invalid log")
+	}
+}
+func TestCrowdTrafficDoesNotInventBlockedRequests(t *testing.T) {
+	raw := `[{"id":12,"uuid":"alert-uuid","created_at":"2026-10-09T16:16:43Z","source":{"ip":"20.194.96.114"},"scenario":"crowdsecurity/http-admin-interface-probing","events":[{"meta":[{"key":"target_fqdn","value":"example.test"}]}],"decisions":[{"id":42,"value":"20.194.96.114","type":"ban","simulated":false},{"id":43,"value":"1.1.1.1","type":"ban","simulated":true}]}]`
+	events, err := parseCrowdTraffic([]byte(raw))
+	if err != nil || len(events) != 2 {
+		t.Fatalf("%+v %v", events, err)
+	}
+	if events[0].Kind != "alert" || events[1].Kind != "decision" || events[1].Domain != "example.test" {
+		t.Fatalf("bad categories %+v", events)
+	}
+	simulated := strings.Replace(raw, `"id":12`, `"simulated":true,"id":12`, 1)
+	events, err = parseCrowdTraffic([]byte(simulated))
+	if err != nil || len(events) != 0 {
+		t.Fatal("simulation counted as live")
+	}
+}
+func TestTrafficLogCheckpointRotationAndPartialLines(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "proxy-host-1_access.log")
+	os.WriteFile(path, []byte(npmTestLine("1.1.1.1", "/old")), 0600)
+	state := trafficAgentState{Cursors: map[string]trafficCursor{}}
+	if _, err := state.readLogs(dir); err != nil {
+		t.Fatal(err)
+	}
+	if len(state.Pending) != 0 {
+		t.Fatal("imported old logs on first activation")
+	}
+	appendFile := func(path, s string) {
+		f, err := os.OpenFile(path, os.O_APPEND|os.O_WRONLY, 0600)
+		if err != nil {
+			t.Fatal(err)
+		}
+		f.WriteString(s)
+		f.Close()
+	}
+	line := npmTestLine("8.8.8.8", "/new")
+	appendFile(path, line[:len(line)/2])
+	state.readLogs(dir)
+	if len(state.Pending) != 0 {
+		t.Fatal("partial line emitted")
+	}
+	appendFile(path, line[len(line)/2:])
+	state.readLogs(dir)
+	if len(state.Pending) != 1 {
+		t.Fatal("complete line missing")
+	}
+	id := state.Pending[0].ID
+	state.Pending = nil
+	checkpoint := filepath.Join(dir, "state.json")
+	if err := saveTrafficAgentState(checkpoint, state); err != nil {
+		t.Fatal(err)
+	}
+	raw, _ := os.ReadFile(checkpoint)
+	var restored trafficAgentState
+	json.Unmarshal(raw, &restored)
+	os.Rename(path, path+".1")
+	appendFile(path+".1", npmTestLine("9.9.9.9", "/rotated"))
+	os.WriteFile(path, []byte(npmTestLine("1.0.0.1", "/fresh")), 0600)
+	restored.readLogs(dir)
+	if len(restored.Pending) != 2 {
+		t.Fatalf("rotation lost events %+v", restored)
+	}
+	for _, e := range restored.Pending {
+		if e.ID == id {
+			t.Fatal("duplicate id")
+		}
+	}
+	restored.Pending = nil
+	restored.readLogs(dir)
+	if len(restored.Pending) != 0 {
+		t.Fatal("re-read same lines")
+	}
+}
+func TestTrafficStoreDedupFiltersAndSanitization(t *testing.T) {
+	s, a := trafficFixture(t)
+	if s.TrafficSettings().Enabled {
+		t.Fatal("enabled by default")
+	}
+	if _, err := s.SaveTrafficSettings(TrafficSettings{Enabled: true, AgentID: a.ID}); err != nil {
+		t.Fatal(err)
+	}
+	now := time.Now().Unix()
+	batch := TrafficBatch{Files: 22, Events: []TrafficEvent{{ID: "1", Time: now, Kind: "request", IP: "1.1.1.1", Domain: "example.test", Path: "/login?secret=x", Status: 502}, {ID: "2", Time: now, Kind: "request", IP: "192.168.0.10", Domain: "example.test", Status: 200}, {ID: "3", Time: now, Kind: "alert", IP: "1.1.1.1", Reason: "probe"}, {ID: "4", Time: now, Kind: "decision", IP: "1.1.1.1", Reason: "ban"}}}
+	for i := 0; i < 2; i++ {
+		if err := s.SaveTraffic(a.ID, batch); err != nil {
+			t.Fatal(err)
+		}
+	}
+	v, err := s.TrafficView("", "", false)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if v.Requests != 2 || v.UniqueIPs != 2 || v.Alerts != 1 || v.Decisions != 1 || len(v.Events) != 4 {
+		t.Fatalf("wrong counts: %+v", v)
+	}
+	for _, e := range v.Events {
+		if strings.Contains(e.Path, "secret") {
+			t.Fatal("secret saved")
+		}
+	}
+	v, err = s.TrafficView("example.test", "request", true)
+	if err != nil || v.Requests != 1 {
+		t.Fatalf("bad filter %+v %v", v, err)
+	}
+	batch.Events = []TrafficEvent{{ID: "invalid", Kind: "blocked", IP: "1.1.1.1", Time: now}}
+	if s.SaveTraffic(a.ID, batch) == nil {
+		t.Fatal("accepted invented block event")
+	}
+}
+func TestTrafficAPIOptInAndSourceAuthorization(t *testing.T) {
+	s, a := trafficFixture(t)
+	mux := http.NewServeMux()
+	trafficRoutes(mux, s)
+	get := func(path string) int {
+		r := httptest.NewRecorder()
+		mux.ServeHTTP(r, httptest.NewRequest("GET", path, nil))
+		return r.Code
+	}
+	if get("/traffic") != 404 || get("/api/traffic") != 404 {
+		t.Fatal("disabled page exposed")
+	}
+	send := func(secret string) int {
+		r := httptest.NewRecorder()
+		req := httptest.NewRequest("POST", "/api/agent/traffic", strings.NewReader(`{"events":[]}`))
+		req.Header.Set("Authorization", "Bearer "+a.ID+"."+secret)
+		mux.ServeHTTP(r, req)
+		return r.Code
+	}
+	if send("wrong") != 401 || send(a.Secret) != 403 {
+		t.Fatal("disabled/unauthorized ingestion accepted")
+	}
+	if _, err := s.SaveTrafficSettings(TrafficSettings{Enabled: true, AgentID: "missing"}); err == nil {
+		t.Fatal("unknown agent accepted")
+	}
+	s.SaveTrafficSettings(TrafficSettings{Enabled: true, AgentID: a.ID, ServerCountry: "RU"})
+	if send(a.Secret) != 200 || get("/traffic") != 200 {
+		t.Fatal("selected agent not working")
+	}
+	token, _ := s.CreateAgentEnrollmentToken()
+	other, _ := s.EnrollAgent(agentEnrollmentRequest{Token: token, Name: "Other"})
+	s.SaveTrafficSettings(TrafficSettings{Enabled: true, AgentID: other.ID})
+	if send(a.Secret) != 403 {
+		t.Fatal("old source still accepted")
+	}
+	s.SaveTrafficSettings(TrafficSettings{Enabled: false, AgentID: other.ID})
+	if get("/api/traffic") != 404 {
+		t.Fatal("disable failed")
+	}
+}
+func TestTrafficGeoDatabase(t *testing.T) {
+	if !trafficGeoReady() {
+		t.Fatal("embedded database invalid")
+	}
+	if lookupTrafficCountry("192.168.0.10") != "LAN" {
+		t.Fatal("LAN mapped to country")
+	}
+	if c := lookupTrafficCountry("8.8.8.8"); len(c) != 2 {
+		t.Fatalf("bad public IP geo: %q", c)
+	}
+}
+func TestTrafficCheckpointKeepsPendingUntilAcknowledged(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "state.json")
+	s := trafficAgentState{Pending: []TrafficEvent{{ID: "retry-me", IP: "1.1.1.1"}}, Cursors: map[string]trafficCursor{"file": {Offset: 100}}}
+	if err := saveTrafficAgentState(path, s); err != nil {
+		t.Fatal(err)
+	}
+	raw, _ := os.ReadFile(path)
+	if !bytes.Contains(raw, []byte("retry-me")) {
+		t.Fatal("pending batch lost")
+	}
+}

traffic_web.go

@@ -0,0 +1,6 @@
+package main
+
+import _ "embed"
+
+//go:embed assets/traffic.html
+var trafficHTML string

trends.go

@@ -0,0 +1,107 @@
+package main
+
+import (
+	"database/sql"
+	"fmt"
+	"sync"
+	"time"
+)
+
+type entityAverage struct {
+	Value1, Value2 float64
+	Count          int
+}
+type TrendAnomaly struct {
+	ID       string `json:"id"`
+	Severity string `json:"severity"`
+	Source   string `json:"source"`
+	Title    string `json:"title"`
+	Message  string `json:"message"`
+}
+type trendCollector struct {
+	mu        sync.Mutex
+	updatedAt time.Time
+	cached    []TrendAnomaly
+}
+
+func (s *Store) entityAverages(kind string) map[string]entityAverage {
+	return s.entityAveragesSince(kind, 7*24*time.Hour)
+}
+func (s *Store) entityAveragesSince(kind string, duration time.Duration) map[string]entityAverage {
+	rows, err := s.db.Query(`SELECT name,AVG(value1),AVG(value2),COUNT(*) FROM entity_history WHERE kind=? AND ts>=? GROUP BY name`, kind, time.Now().Add(-duration).Unix())
+	if err != nil {
+		return nil
+	}
+	defer rows.Close()
+	result := map[string]entityAverage{}
+	for rows.Next() {
+		var name string
+		var v1, v2 sql.NullFloat64
+		var count int
+		if rows.Scan(&name, &v1, &v2, &count) == nil {
+			result[name] = entityAverage{Value1: v1.Float64, Value2: v2.Float64, Count: count}
+		}
+	}
+	return result
+}
+
+func (c *trendCollector) collect(metrics dashboardMetrics, store *Store) []TrendAnomaly {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+	if time.Since(c.updatedAt) < time.Minute {
+		return c.cached
+	}
+	var out []TrendAnomaly
+	iops := store.entityAverages("disk-io")
+	latency := store.entityAverages("disk-latency")
+	latencyDay := store.entityAveragesSince("disk-latency", 24*time.Hour)
+	temps := store.entityAverages("disk")
+	for _, d := range metrics.Disks {
+		name := d.Name + " · " + d.Model
+		currentIOPS := d.ReadIOPS + d.WriteIOPS
+		if base := iops[name]; base.Count >= 30 && base.Value1 >= 1 && currentIOPS >= base.Value1*5 {
+			out = append(out, TrendAnomaly{"disk-iops-" + d.Name, "warning", "Аномалии", d.Model + ": IOPS резко выше обычного", fmt.Sprintf("Сейчас %.0f IOPS, недельный baseline %.0f — рост в %.1f раза.", currentIOPS, base.Value1, currentIOPS/base.Value1)})
+		}
+		if base := latency[name]; base.Count >= 30 && base.Value1 > 0 && d.LatencyMs >= base.Value1*2 && d.LatencyMs-base.Value1 >= 10 {
+			out = append(out, TrendAnomaly{"disk-latency-" + d.Name, "warning", "Аномалии", d.Model + ": latency ухудшилась", fmt.Sprintf("Сейчас %.1f ms при baseline %.1f ms.", d.LatencyMs, base.Value1)})
+		}
+		if week, day := latency[name], latencyDay[name]; week.Count >= 100 && day.Count >= 30 && week.Value1 > 0 && day.Value1 >= week.Value1*1.5 && day.Value1-week.Value1 >= 5 {
+			out = append(out, TrendAnomaly{"disk-latency-degrading-" + d.Name, "warning", "Аномалии", d.Model + ": latency постепенно ухудшается", fmt.Sprintf("Среднее за сутки %.1f ms против недельного %.1f ms.", day.Value1, week.Value1)})
+		}
+		if d.Temperature != nil {
+			if base := temps[name]; base.Count >= 30 && *d.Temperature >= base.Value1+10 {
+				out = append(out, TrendAnomaly{"disk-temp-trend-" + d.Name, "warning", "Аномалии", d.Model + ": температура выше обычной", fmt.Sprintf("Сейчас %.1f °C, baseline %.1f °C.", *d.Temperature, base.Value1)})
+			}
+		}
+	}
+	guestAvg := store.entityAverages("guest")
+	for _, g := range metrics.Guests.Guests {
+		if g.MaxMemory == 0 {
+			continue
+		}
+		name := fmt.Sprintf("%d · %s", g.VMID, g.Name)
+		current := float64(g.MemoryBytes) / float64(g.MaxMemory) * 100
+		if base := guestAvg[name]; base.Count >= 30 && current >= base.Value2*1.5 && current-base.Value2 >= 15 {
+			out = append(out, TrendAnomaly{fmt.Sprintf("guest-memory-%d", g.VMID), "warning", "Аномалии", g.Name + ": память выше обычной", fmt.Sprintf("Сейчас %.1f%%, baseline %.1f%%.", current, base.Value2)})
+		}
+	}
+	zfsAverage := store.entityAverages("zfs")
+	for _, pool := range metrics.ZFS.Pools {
+		if base := zfsAverage[pool.Name]; base.Count >= 30 && pool.CapacityPercent-base.Value1 >= 5 {
+			out = append(out, TrendAnomaly{"zfs-growth-" + pool.Name, "warning", "Аномалии", pool.Name + ": заполнение выше недельного уровня", fmt.Sprintf("Сейчас %.1f%%, недельный baseline %.1f%%.", pool.CapacityPercent, base.Value1)})
+		}
+	}
+	backupAverage := store.entityAverages("backup-duration")
+	for _, task := range metrics.Activity.Tasks {
+		if task.Type != "vzdump" || task.Duration <= 0 {
+			continue
+		}
+		name := "VMID " + task.ID
+		if base := backupAverage[name]; base.Count >= 3 && float64(task.Duration) >= base.Value1*1.5 && float64(task.Duration)-base.Value1 >= 60 {
+			out = append(out, TrendAnomaly{"backup-duration-" + task.ID, "warning", "Аномалии", "Backup " + name + " выполнялся дольше обычного", fmt.Sprintf("Последняя длительность %s, baseline %s.", time.Duration(task.Duration)*time.Second, time.Duration(base.Value1)*time.Second)})
+		}
+	}
+	c.cached = out
+	c.updatedAt = time.Now()
+	return out
+}