Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| a8ccf1d35c |
@ -6,6 +6,9 @@ LOG_LEVEL=info
|
|||||||
# Опционально: общий секрет для вебхуков (если у источника в JSON не задан свой webhook_secret)
|
# Опционально: общий секрет для вебхуков (если у источника в JSON не задан свой webhook_secret)
|
||||||
# GRAFANA_WEBHOOK_SECRET=
|
# GRAFANA_WEBHOOK_SECRET=
|
||||||
|
|
||||||
|
# Устаревшее: автосоздание инцидента на каждый вебхук (дублирует irm_alerts). Обычно не нужно.
|
||||||
|
# AUTO_INCIDENT_FROM_ALERT=1
|
||||||
|
|
||||||
# Несколько Grafana: JSON-массив. slug — часть URL вебхука: /api/v1/ingress/grafana/{slug}
|
# Несколько Grafana: JSON-массив. slug — часть URL вебхука: /api/v1/ingress/grafana/{slug}
|
||||||
# Пример: [{"slug":"adibrov","api_url":"https://grafana-adibrov.example","api_token":"glsa_...","webhook_secret":"длинный-секрет"}]
|
# Пример: [{"slug":"adibrov","api_url":"https://grafana-adibrov.example","api_token":"glsa_...","webhook_secret":"длинный-секрет"}]
|
||||||
# Если пусто, но задан GRAFANA_URL — один источник со slug "default" (вебхук /api/v1/ingress/grafana/default)
|
# Если пусто, но задан GRAFANA_URL — один источник со slug "default" (вебхук /api/v1/ingress/grafana/default)
|
||||||
|
|||||||
17
CHANGELOG.md
17
CHANGELOG.md
@ -2,6 +2,23 @@
|
|||||||
|
|
||||||
Формат: семантическое версионирование `MAJOR.MINOR.PATCH`. Git-теги `v1.0.0`, `v1.1.0` и т.д. — см. [docs/VERSIONING.md](docs/VERSIONING.md).
|
Формат: семантическое версионирование `MAJOR.MINOR.PATCH`. Git-теги `v1.0.0`, `v1.1.0` и т.д. — см. [docs/VERSIONING.md](docs/VERSIONING.md).
|
||||||
|
|
||||||
|
## [1.9.0] — 2026-04-03
|
||||||
|
|
||||||
|
Алерты отдельно от инцидентов (модель ближе к Grafana IRM).
|
||||||
|
|
||||||
|
### Добавлено
|
||||||
|
|
||||||
|
- **Alembic `005_irm_alerts`:** таблицы `irm_alerts`, `incident_alert_links`.
|
||||||
|
- **Модуль «Алерты»:** API и UI, статусы firing → acknowledged → resolved, полный JSON вебхука, кнопка «Создать инцидент».
|
||||||
|
- **Вебхук Grafana:** в одной транзакции `ingress_events` + `irm_alerts`.
|
||||||
|
- **`extract_alert_row_from_grafana_body`** — заголовок, severity, labels, fingerprint.
|
||||||
|
- **Документация:** [docs/IRM_GRAFANA_PARITY.md](docs/IRM_GRAFANA_PARITY.md).
|
||||||
|
|
||||||
|
### Изменено
|
||||||
|
|
||||||
|
- **Инцидент из вебхука по умолчанию не создаётся**; включение старого поведения: `AUTO_INCIDENT_FROM_ALERT=1`.
|
||||||
|
- **POST /incidents:** опционально `alert_ids` для привязки к `irm_alerts`.
|
||||||
|
|
||||||
## [1.8.0] — 2026-04-03
|
## [1.8.0] — 2026-04-03
|
||||||
|
|
||||||
UI каталога Grafana и инцидентов; правки CI/CD деплоя.
|
UI каталога Grafana и инцидентов; правки CI/CD деплоя.
|
||||||
|
|||||||
74
alembic/versions/005_irm_alerts.py
Normal file
74
alembic/versions/005_irm_alerts.py
Normal file
@ -0,0 +1,74 @@
|
|||||||
|
"""IRM: алерты отдельно от инцидентов (ack/resolve), связь N:M инцидент↔алерт
|
||||||
|
|
||||||
|
Revision ID: 005_irm_alerts
|
||||||
|
Revises: 004_grafana_catalog
|
||||||
|
Create Date: 2026-04-03
|
||||||
|
|
||||||
|
"""
|
||||||
|
|
||||||
|
from typing import Sequence, Union
|
||||||
|
|
||||||
|
from alembic import op
|
||||||
|
|
||||||
|
revision: str = "005_irm_alerts"
|
||||||
|
down_revision: Union[str, None] = "004_grafana_catalog"
|
||||||
|
branch_labels: Union[str, Sequence[str], None] = None
|
||||||
|
depends_on: Union[str, Sequence[str], None] = None
|
||||||
|
|
||||||
|
|
||||||
|
def upgrade() -> None:
|
||||||
|
op.execute(
|
||||||
|
"""
|
||||||
|
CREATE TABLE IF NOT EXISTS irm_alerts (
|
||||||
|
id uuid PRIMARY KEY DEFAULT gen_random_uuid(),
|
||||||
|
ingress_event_id uuid NOT NULL UNIQUE REFERENCES ingress_events(id) ON DELETE CASCADE,
|
||||||
|
status text NOT NULL DEFAULT 'firing'
|
||||||
|
CHECK (status IN ('firing', 'acknowledged', 'resolved', 'silenced')),
|
||||||
|
title text NOT NULL DEFAULT '',
|
||||||
|
severity text NOT NULL DEFAULT 'warning',
|
||||||
|
source text NOT NULL DEFAULT 'grafana',
|
||||||
|
grafana_org_slug text,
|
||||||
|
service_name text,
|
||||||
|
labels jsonb NOT NULL DEFAULT '{}'::jsonb,
|
||||||
|
fingerprint text,
|
||||||
|
acknowledged_at timestamptz,
|
||||||
|
acknowledged_by text,
|
||||||
|
resolved_at timestamptz,
|
||||||
|
resolved_by text,
|
||||||
|
created_at timestamptz NOT NULL DEFAULT now(),
|
||||||
|
updated_at timestamptz NOT NULL DEFAULT now()
|
||||||
|
);
|
||||||
|
"""
|
||||||
|
)
|
||||||
|
op.execute(
|
||||||
|
"""
|
||||||
|
CREATE INDEX IF NOT EXISTS irm_alerts_status_created_idx
|
||||||
|
ON irm_alerts (status, created_at DESC);
|
||||||
|
"""
|
||||||
|
)
|
||||||
|
op.execute(
|
||||||
|
"""
|
||||||
|
CREATE INDEX IF NOT EXISTS irm_alerts_ingress_event_id_idx
|
||||||
|
ON irm_alerts (ingress_event_id);
|
||||||
|
"""
|
||||||
|
)
|
||||||
|
op.execute(
|
||||||
|
"""
|
||||||
|
CREATE TABLE IF NOT EXISTS incident_alert_links (
|
||||||
|
incident_id uuid NOT NULL REFERENCES incidents(id) ON DELETE CASCADE,
|
||||||
|
alert_id uuid NOT NULL REFERENCES irm_alerts(id) ON DELETE CASCADE,
|
||||||
|
PRIMARY KEY (incident_id, alert_id)
|
||||||
|
);
|
||||||
|
"""
|
||||||
|
)
|
||||||
|
op.execute(
|
||||||
|
"""
|
||||||
|
CREATE INDEX IF NOT EXISTS incident_alert_links_alert_idx
|
||||||
|
ON incident_alert_links (alert_id);
|
||||||
|
"""
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def downgrade() -> None:
|
||||||
|
op.execute("DROP TABLE IF EXISTS incident_alert_links;")
|
||||||
|
op.execute("DROP TABLE IF EXISTS irm_alerts;")
|
||||||
12
docs/IRM.md
12
docs/IRM.md
@ -6,7 +6,8 @@
|
|||||||
|
|
||||||
| Область | Назначение | onGuard24 | Grafana / внешнее |
|
| Область | Назначение | onGuard24 | Grafana / внешнее |
|
||||||
|---------|------------|-----------|-------------------|
|
|---------|------------|-----------|-------------------|
|
||||||
| **Инциденты** | Учёт сбоев, статусы (open → resolved), связь с алертом | Модуль `incidents`: таблица `incidents`, API, UI, авто-создание из `alert.received` | Contact point **Webhook** → `POST /api/v1/ingress/grafana`; правила алертинга в Grafana |
|
| **Инциденты** | Учёт сбоев, статусы (open → resolved), связь с алертами | Модуль `incidents`: `incidents`, `incident_alert_links`, API, UI; создание вручную или с `alert_ids` | См. **Алерты**; [IRM_GRAFANA_PARITY.md](IRM_GRAFANA_PARITY.md) |
|
||||||
|
| **Алерты (IRM)** | Приём, Ack/Resolve, не смешивать с инцидентом | Модуль `alerts`: `irm_alerts`, UI/API, вебхук пишет в одной транзакции с `ingress_events` | Grafana IRM Alert Groups; у нас без группировки/эскалации на уровне алерта |
|
||||||
| **Задачи** | Подзадачи по инциденту (разбор, фикс) | Модуль `tasks`: таблица `tasks`, привязка к `incident_id` | Опционально: ссылки из алерта; основная работа в onGuard24 |
|
| **Задачи** | Подзадачи по инциденту (разбор, фикс) | Модуль `tasks`: таблица `tasks`, привязка к `incident_id` | Опционально: ссылки из алерта; основная работа в onGuard24 |
|
||||||
| **Цепочки эскалаций** | Кого звать и в каком порядке при таймаутах | Модуль `escalations`: таблица `escalation_policies` (JSON `steps`), API/UI заготовка | Маршрутизация уведомлений может дублироваться в Grafana contact points; целевая логика — в onGuard24 |
|
| **Цепочки эскалаций** | Кого звать и в каком порядке при таймаутах | Модуль `escalations`: таблица `escalation_policies` (JSON `steps`), API/UI заготовка | Маршрутизация уведомлений может дублироваться в Grafana contact points; целевая логика — в onGuard24 |
|
||||||
| **Календарь дежурств** | Кто в смене, расписание | Модуль `schedules` (развитие) | Календари/команды — данные в onGuard24; уведомления — через интеграции |
|
| **Календарь дежурств** | Кто в смене, расписание | Модуль `schedules` (развитие) | Календари/команды — данные в onGuard24; уведомления — через интеграции |
|
||||||
@ -17,11 +18,12 @@
|
|||||||
| **Пользователи / права** | RBAC | *Пока нет* | SSO Grafana, сеть за reverse proxy |
|
| **Пользователи / права** | RBAC | *Пока нет* | SSO Grafana, сеть за reverse proxy |
|
||||||
| **SLO** | Цели по доступности | *Вне скоупа v1* | Grafana SLO / Mimir |
|
| **SLO** | Цели по доступности | *Вне скоупа v1* | Grafana SLO / Mimir |
|
||||||
|
|
||||||
## Поток данных (алерт → инцидент)
|
## Поток данных (как в Grafana IRM)
|
||||||
|
|
||||||
1. Grafana срабатывает правило → шлёт JSON на **webhook** onGuard24.
|
1. Grafana срабатывает правило → JSON на **webhook** onGuard24.
|
||||||
2. Сервис пишет строку в `ingress_events`, публикует **`alert.received`**.
|
2. В одной транзакции: **`ingress_events`** + **`irm_alerts`** (статус `firing`), публикуется **`alert.received`**.
|
||||||
3. Модуль **incidents** подписан на событие и создаёт запись в **`incidents`** с ссылкой на `ingress_event_id`.
|
3. Дежурный в модуле **Алерты** читает заголовок, лейблы, **Acknowledge** / **Resolve** — это не создание инцидента.
|
||||||
|
4. **Инцидент** создаётся отдельно (вручную или из карточки алерта), опционально с привязкой **`alert_ids`**. Авто-инцидент из вебхука только при **`AUTO_INCIDENT_FROM_ALERT=1`** (legacy).
|
||||||
|
|
||||||
## Что настроить в Grafana (обязательно для приёма алертов)
|
## Что настроить в Grafana (обязательно для приёма алертов)
|
||||||
|
|
||||||
|
|||||||
39
docs/IRM_GRAFANA_PARITY.md
Normal file
39
docs/IRM_GRAFANA_PARITY.md
Normal file
@ -0,0 +1,39 @@
|
|||||||
|
# Сравнение onGuard24 с Grafana IRM (Alerting / Incident)
|
||||||
|
|
||||||
|
Grafana Cloud / IRM даёт **группы алертов**, **Acknowledge / Resolve**, **инциденты**, **команды (teams)**, **эскалационные цепочки**, **расписания дежурств**. Ниже — что уже есть в onGuard24 и что планировать отдельно.
|
||||||
|
|
||||||
|
## Уже есть (после разделения алерт / инцидент)
|
||||||
|
|
||||||
|
| Grafana IRM (идея) | onGuard24 |
|
||||||
|
|--------------------|-----------|
|
||||||
|
| Входящие уведомления от интеграции | Webhook `POST /api/v1/ingress/grafana` → `ingress_events` + **`irm_alerts`** |
|
||||||
|
| Статусы firing / acknowledged / resolved | Поле **`irm_alerts.status`**, UI **Алерты**, API `PATCH …/acknowledge`, `…/resolve` |
|
||||||
|
| Просмотр labels / сырого payload | Карточка алерта в UI, JSON вебхука |
|
||||||
|
| Инцидент как отдельная сущность | **`incidents`**, создание вручную или кнопка «Создать инцидент» на алерте; связь **`incident_alert_links`** |
|
||||||
|
| Эскалации (JSON-шаги) | Модуль **Эскалации** (`escalation_policies`) — без автодвижка по таймерам |
|
||||||
|
| Контакты / каналы | Модуль **Контакты** |
|
||||||
|
| Расписания (заглушка) | **Календарь дежурств** — UI-задел |
|
||||||
|
|
||||||
|
## Пока нет (зрелые следующие этапы)
|
||||||
|
|
||||||
|
| Функция Grafana IRM | Заметка |
|
||||||
|
|---------------------|---------|
|
||||||
|
| **Teams** с фильтрами и привязкой маршрутов | Нет сущности `team`; алерты не маршрутизируются по команде |
|
||||||
|
| **Alert groups** (несколько алертов в одной группе с общим ID) | Сейчас **одна строка `irm_alerts` на один webhook**; группировка fingerprint / rule_uid — отдельная задача |
|
||||||
|
| **Silence / Restart** из UI | Статус `silenced` в БД зарезервирован, логика не подключена |
|
||||||
|
| **Эскалация по таймеру** (wait 15m → notify next) | Политики есть, **фонового исполнителя** нет |
|
||||||
|
| **On-call из расписания** в цепочке | Нет связи schedules → escalation executor |
|
||||||
|
| **Пользователи / «Mine» / назначение** | Нет учётных записей onGuard24 для дежурного; `acknowledged_by` — свободный текст (можно расширить) |
|
||||||
|
| **Интеграция обратно в Grafana** (resolve в Grafana из IRM) | Не делалось |
|
||||||
|
|
||||||
|
## Переменные окружения
|
||||||
|
|
||||||
|
- **`AUTO_INCIDENT_FROM_ALERT`** — если `1` / `true`, сохраняется старое поведение: **каждый** вебхук ещё и создаёт строку в **`incidents`**. По умолчанию **выключено**: только **`irm_alerts`**.
|
||||||
|
|
||||||
|
## Рекомендуемый поток
|
||||||
|
|
||||||
|
1. Grafana → webhook → **алерт** (`firing`).
|
||||||
|
2. Дежурный в **Алертах**: прочитал → **Ack** → разобрался → **Resolve** (или сразу Resolve).
|
||||||
|
3. При необходимости **Создать инцидент** (документирование, задачи, эскалация вручную).
|
||||||
|
|
||||||
|
Так модель ближе к IRM, где **алерт** и **инцидент** разведены.
|
||||||
@ -1,3 +1,3 @@
|
|||||||
"""onGuard24 — модульный монолит (ядро + модули)."""
|
"""onGuard24 — модульный монолит (ядро + модули)."""
|
||||||
|
|
||||||
__version__ = "1.8.0"
|
__version__ = "1.9.0"
|
||||||
|
|||||||
@ -34,6 +34,11 @@ class Settings(BaseSettings):
|
|||||||
forgejo_url: str = Field(default="", validation_alias="FORGEJO_URL")
|
forgejo_url: str = Field(default="", validation_alias="FORGEJO_URL")
|
||||||
forgejo_token: str = Field(default="", validation_alias="FORGEJO_TOKEN")
|
forgejo_token: str = Field(default="", validation_alias="FORGEJO_TOKEN")
|
||||||
log_level: str = Field(default="info", validation_alias="LOG_LEVEL")
|
log_level: str = Field(default="info", validation_alias="LOG_LEVEL")
|
||||||
|
# Устаревшее: автосоздание инцидента на каждый вебхук (без учёта irm_alerts). По умолчанию выкл.
|
||||||
|
auto_incident_from_alert: bool = Field(
|
||||||
|
default=False,
|
||||||
|
validation_alias="AUTO_INCIDENT_FROM_ALERT",
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
def get_settings() -> Settings:
|
def get_settings() -> Settings:
|
||||||
|
|||||||
@ -9,6 +9,7 @@ from starlette.responses import Response
|
|||||||
|
|
||||||
from onguard24.domain.entities import Alert, Severity
|
from onguard24.domain.entities import Alert, Severity
|
||||||
from onguard24.grafana_sources import sources_by_slug, webhook_authorized
|
from onguard24.grafana_sources import sources_by_slug, webhook_authorized
|
||||||
|
from onguard24.ingress.grafana_payload import extract_alert_row_from_grafana_body
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
router = APIRouter(tags=["ingress"])
|
router = APIRouter(tags=["ingress"])
|
||||||
@ -119,19 +120,38 @@ async def _grafana_webhook_impl(
|
|||||||
logger.warning("ingress: database not configured, event not persisted")
|
logger.warning("ingress: database not configured, event not persisted")
|
||||||
return Response(status_code=202)
|
return Response(status_code=202)
|
||||||
|
|
||||||
|
title_row, sev_row, labels_row, fp_row = extract_alert_row_from_grafana_body(body)
|
||||||
async with pool.acquire() as conn:
|
async with pool.acquire() as conn:
|
||||||
row = await conn.fetchrow(
|
async with conn.transaction():
|
||||||
"""
|
row = await conn.fetchrow(
|
||||||
INSERT INTO ingress_events (source, body, org_slug, service_name)
|
"""
|
||||||
VALUES ($1, $2::jsonb, $3, $4)
|
INSERT INTO ingress_events (source, body, org_slug, service_name)
|
||||||
RETURNING id
|
VALUES ($1, $2::jsonb, $3, $4)
|
||||||
""",
|
RETURNING id
|
||||||
"grafana",
|
""",
|
||||||
json.dumps(body),
|
"grafana",
|
||||||
stored_org_slug,
|
json.dumps(body),
|
||||||
service_name,
|
stored_org_slug,
|
||||||
)
|
service_name,
|
||||||
raw_id = row["id"] if row else None
|
)
|
||||||
|
raw_id = row["id"] if row else None
|
||||||
|
if raw_id is not None:
|
||||||
|
await conn.execute(
|
||||||
|
"""
|
||||||
|
INSERT INTO irm_alerts (
|
||||||
|
ingress_event_id, status, title, severity, source,
|
||||||
|
grafana_org_slug, service_name, labels, fingerprint
|
||||||
|
)
|
||||||
|
VALUES ($1, 'firing', $2, $3, 'grafana', $4, $5, $6::jsonb, $7)
|
||||||
|
""",
|
||||||
|
raw_id,
|
||||||
|
title_row or "—",
|
||||||
|
sev_row,
|
||||||
|
stored_org_slug,
|
||||||
|
service_name,
|
||||||
|
json.dumps(labels_row),
|
||||||
|
fp_row,
|
||||||
|
)
|
||||||
bus = getattr(request.app.state, "event_bus", None)
|
bus = getattr(request.app.state, "event_bus", None)
|
||||||
if bus and raw_id is not None:
|
if bus and raw_id is not None:
|
||||||
title = str(body.get("title") or body.get("ruleName") or "")[:500]
|
title = str(body.get("title") or body.get("ruleName") or "")[:500]
|
||||||
|
|||||||
53
onguard24/ingress/grafana_payload.py
Normal file
53
onguard24/ingress/grafana_payload.py
Normal file
@ -0,0 +1,53 @@
|
|||||||
|
"""Извлечение полей для учёта алерта из тела вебхука Grafana (Unified Alerting)."""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import json
|
||||||
|
from typing import Any
|
||||||
|
|
||||||
|
|
||||||
|
def extract_alert_row_from_grafana_body(body: dict[str, Any]) -> tuple[str, str, dict[str, Any], str | None]:
|
||||||
|
"""
|
||||||
|
Возвращает: title, severity (info|warning|critical), labels (dict), fingerprint.
|
||||||
|
"""
|
||||||
|
title = str(body.get("title") or body.get("ruleName") or "").strip()[:500]
|
||||||
|
alerts = body.get("alerts")
|
||||||
|
labels: dict[str, Any] = {}
|
||||||
|
fingerprint: str | None = None
|
||||||
|
sev = "warning"
|
||||||
|
|
||||||
|
if isinstance(alerts, list) and alerts and isinstance(alerts[0], dict):
|
||||||
|
a0 = alerts[0]
|
||||||
|
fp = a0.get("fingerprint")
|
||||||
|
if fp is not None:
|
||||||
|
fingerprint = str(fp)[:500]
|
||||||
|
if isinstance(a0.get("labels"), dict):
|
||||||
|
labels.update(a0["labels"])
|
||||||
|
ann = a0.get("annotations")
|
||||||
|
if isinstance(ann, dict) and not title:
|
||||||
|
title = str(ann.get("summary") or ann.get("description") or "").strip()[:500]
|
||||||
|
|
||||||
|
cl = body.get("commonLabels")
|
||||||
|
if isinstance(cl, dict):
|
||||||
|
for k, v in cl.items():
|
||||||
|
labels.setdefault(k, v)
|
||||||
|
|
||||||
|
if not title and isinstance(alerts, list) and alerts and isinstance(alerts[0], dict):
|
||||||
|
title = str(alerts[0].get("labels", {}).get("alertname") or "").strip()[:500]
|
||||||
|
|
||||||
|
raw_s = None
|
||||||
|
if isinstance(labels.get("severity"), str):
|
||||||
|
raw_s = labels["severity"].lower()
|
||||||
|
elif isinstance(labels.get("priority"), str):
|
||||||
|
raw_s = labels["priority"].lower()
|
||||||
|
if raw_s in ("critical", "error", "fatal"):
|
||||||
|
sev = "critical"
|
||||||
|
elif raw_s in ("warning", "warn"):
|
||||||
|
sev = "warning"
|
||||||
|
elif raw_s in ("info", "informational", "none"):
|
||||||
|
sev = "info"
|
||||||
|
|
||||||
|
# JSONB: только JSON-совместимые значения
|
||||||
|
clean_labels = {str(k): v for k, v in labels.items() if isinstance(v, (str, int, float, bool, type(None)))}
|
||||||
|
|
||||||
|
return title, sev, clean_labels, fingerprint
|
||||||
346
onguard24/modules/alerts.py
Normal file
346
onguard24/modules/alerts.py
Normal file
@ -0,0 +1,346 @@
|
|||||||
|
"""Учёт входящих алертов (отдельно от инцидентов): firing → acknowledged → resolved."""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import html
|
||||||
|
import json
|
||||||
|
import logging
|
||||||
|
from uuid import UUID
|
||||||
|
|
||||||
|
import asyncpg
|
||||||
|
from fastapi import APIRouter, Depends, HTTPException, Request
|
||||||
|
from fastapi.responses import HTMLResponse
|
||||||
|
from pydantic import BaseModel, Field
|
||||||
|
|
||||||
|
from onguard24.deps import get_pool
|
||||||
|
from onguard24.domain.events import EventBus
|
||||||
|
from onguard24.modules.ui_support import wrap_module_html_page
|
||||||
|
|
||||||
|
log = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
router = APIRouter(tags=["module-alerts"])
|
||||||
|
ui_router = APIRouter(tags=["web-alerts"], include_in_schema=False)
|
||||||
|
|
||||||
|
_VALID_STATUS = frozenset({"firing", "acknowledged", "resolved", "silenced"})
|
||||||
|
|
||||||
|
|
||||||
|
def register_events(_bus: EventBus, _pool: asyncpg.Pool | None = None) -> None:
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
class AckBody(BaseModel):
|
||||||
|
by_user: str | None = Field(default=None, max_length=200, description="Кто подтвердил")
|
||||||
|
|
||||||
|
|
||||||
|
class ResolveBody(BaseModel):
|
||||||
|
by_user: str | None = Field(default=None, max_length=200)
|
||||||
|
|
||||||
|
|
||||||
|
def _row_to_item(r: asyncpg.Record) -> dict:
|
||||||
|
return {
|
||||||
|
"id": str(r["id"]),
|
||||||
|
"ingress_event_id": str(r["ingress_event_id"]),
|
||||||
|
"status": r["status"],
|
||||||
|
"title": r["title"],
|
||||||
|
"severity": r["severity"],
|
||||||
|
"source": r["source"],
|
||||||
|
"grafana_org_slug": r["grafana_org_slug"],
|
||||||
|
"service_name": r["service_name"],
|
||||||
|
"labels": r["labels"] if isinstance(r["labels"], dict) else {},
|
||||||
|
"fingerprint": r["fingerprint"],
|
||||||
|
"acknowledged_at": r["acknowledged_at"].isoformat() if r["acknowledged_at"] else None,
|
||||||
|
"acknowledged_by": r["acknowledged_by"],
|
||||||
|
"resolved_at": r["resolved_at"].isoformat() if r["resolved_at"] else None,
|
||||||
|
"resolved_by": r["resolved_by"],
|
||||||
|
"created_at": r["created_at"].isoformat() if r["created_at"] else None,
|
||||||
|
"updated_at": r["updated_at"].isoformat() if r["updated_at"] else None,
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
@router.get("/")
|
||||||
|
async def list_alerts_api(
|
||||||
|
pool: asyncpg.Pool | None = Depends(get_pool),
|
||||||
|
status: str | None = None,
|
||||||
|
limit: int = 100,
|
||||||
|
):
|
||||||
|
if pool is None:
|
||||||
|
return {"items": [], "database": "disabled"}
|
||||||
|
limit = min(max(limit, 1), 200)
|
||||||
|
st = (status or "").strip().lower()
|
||||||
|
if st and st not in _VALID_STATUS:
|
||||||
|
raise HTTPException(status_code=400, detail="invalid status filter")
|
||||||
|
async with pool.acquire() as conn:
|
||||||
|
if st:
|
||||||
|
rows = await conn.fetch(
|
||||||
|
"""
|
||||||
|
SELECT * FROM irm_alerts WHERE status = $1
|
||||||
|
ORDER BY created_at DESC LIMIT $2
|
||||||
|
""",
|
||||||
|
st,
|
||||||
|
limit,
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
rows = await conn.fetch(
|
||||||
|
"""
|
||||||
|
SELECT * FROM irm_alerts
|
||||||
|
ORDER BY created_at DESC LIMIT $1
|
||||||
|
""",
|
||||||
|
limit,
|
||||||
|
)
|
||||||
|
return {"items": [_row_to_item(r) for r in rows]}
|
||||||
|
|
||||||
|
|
||||||
|
@router.get("/{alert_id}")
|
||||||
|
async def get_alert_api(alert_id: UUID, pool: asyncpg.Pool | None = Depends(get_pool)):
|
||||||
|
if pool is None:
|
||||||
|
raise HTTPException(status_code=503, detail="database disabled")
|
||||||
|
async with pool.acquire() as conn:
|
||||||
|
row = await conn.fetchrow("SELECT * FROM irm_alerts WHERE id = $1::uuid", alert_id)
|
||||||
|
raw = None
|
||||||
|
if row and row.get("ingress_event_id"):
|
||||||
|
raw = await conn.fetchrow(
|
||||||
|
"SELECT id, body, received_at FROM ingress_events WHERE id = $1::uuid",
|
||||||
|
row["ingress_event_id"],
|
||||||
|
)
|
||||||
|
if not row:
|
||||||
|
raise HTTPException(status_code=404, detail="not found")
|
||||||
|
out = _row_to_item(row)
|
||||||
|
if raw:
|
||||||
|
out["raw_received_at"] = raw["received_at"].isoformat() if raw["received_at"] else None
|
||||||
|
body = raw["body"]
|
||||||
|
out["raw_body"] = dict(body) if hasattr(body, "keys") else body
|
||||||
|
else:
|
||||||
|
out["raw_received_at"] = None
|
||||||
|
out["raw_body"] = None
|
||||||
|
return out
|
||||||
|
|
||||||
|
|
||||||
|
@router.patch("/{alert_id}/acknowledge", status_code=200)
|
||||||
|
async def acknowledge_alert_api(
|
||||||
|
alert_id: UUID,
|
||||||
|
body: AckBody,
|
||||||
|
pool: asyncpg.Pool | None = Depends(get_pool),
|
||||||
|
):
|
||||||
|
if pool is None:
|
||||||
|
raise HTTPException(status_code=503, detail="database disabled")
|
||||||
|
who = (body.by_user or "").strip() or None
|
||||||
|
async with pool.acquire() as conn:
|
||||||
|
row = await conn.fetchrow(
|
||||||
|
"""
|
||||||
|
UPDATE irm_alerts SET
|
||||||
|
status = 'acknowledged',
|
||||||
|
acknowledged_at = now(),
|
||||||
|
acknowledged_by = COALESCE($2, acknowledged_by),
|
||||||
|
updated_at = now()
|
||||||
|
WHERE id = $1::uuid AND status = 'firing'
|
||||||
|
RETURNING *
|
||||||
|
""",
|
||||||
|
alert_id,
|
||||||
|
who,
|
||||||
|
)
|
||||||
|
if not row:
|
||||||
|
raise HTTPException(status_code=409, detail="alert not in firing state or not found")
|
||||||
|
return _row_to_item(row)
|
||||||
|
|
||||||
|
|
||||||
|
@router.patch("/{alert_id}/resolve", status_code=200)
|
||||||
|
async def resolve_alert_api(
|
||||||
|
alert_id: UUID,
|
||||||
|
body: ResolveBody,
|
||||||
|
pool: asyncpg.Pool | None = Depends(get_pool),
|
||||||
|
):
|
||||||
|
if pool is None:
|
||||||
|
raise HTTPException(status_code=503, detail="database disabled")
|
||||||
|
who = (body.by_user or "").strip() or None
|
||||||
|
async with pool.acquire() as conn:
|
||||||
|
row = await conn.fetchrow(
|
||||||
|
"""
|
||||||
|
UPDATE irm_alerts SET
|
||||||
|
status = 'resolved',
|
||||||
|
resolved_at = now(),
|
||||||
|
resolved_by = COALESCE($2, resolved_by),
|
||||||
|
updated_at = now()
|
||||||
|
WHERE id = $1::uuid AND status IN ('firing', 'acknowledged')
|
||||||
|
RETURNING *
|
||||||
|
""",
|
||||||
|
alert_id,
|
||||||
|
who,
|
||||||
|
)
|
||||||
|
if not row:
|
||||||
|
raise HTTPException(
|
||||||
|
status_code=409,
|
||||||
|
detail="alert cannot be resolved from current state or not found",
|
||||||
|
)
|
||||||
|
return _row_to_item(row)
|
||||||
|
|
||||||
|
|
||||||
|
_SYNC_BTN_STYLE = """
|
||||||
|
<script>
|
||||||
|
function ogAck(aid){fetch('/api/v1/modules/alerts/'+aid+'/acknowledge',{method:'PATCH',headers:{'Content-Type':'application/json'},body:JSON.stringify({})}).then(r=>{if(r.ok)location.reload();else r.text().then(t=>alert('Ошибка '+r.status+': '+t.slice(0,200)));});}
|
||||||
|
function ogRes(aid){fetch('/api/v1/modules/alerts/'+aid+'/resolve',{method:'PATCH',headers:{'Content-Type':'application/json'},body:JSON.stringify({})}).then(r=>{if(r.ok)location.reload();else r.text().then(t=>alert('Ошибка '+r.status+': '+t.slice(0,200)));});}
|
||||||
|
function ogInc(aid,title){var t=prompt('Заголовок инцидента',title||'');if(t===null)return;fetch('/api/v1/modules/incidents/',{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify({title:t,alert_ids:[aid]})}).then(r=>{if(r.ok)r.json().then(j=>location.href='/ui/modules/incidents/'+j.id);else r.text().then(x=>alert('Ошибка '+r.status+': '+x.slice(0,200)));});}
|
||||||
|
</script>
|
||||||
|
"""
|
||||||
|
|
||||||
|
|
||||||
|
@ui_router.get("/", response_class=HTMLResponse)
|
||||||
|
async def alerts_ui_list(request: Request):
|
||||||
|
pool = get_pool(request)
|
||||||
|
body = ""
|
||||||
|
if pool is None:
|
||||||
|
body = "<p>База не настроена.</p>"
|
||||||
|
else:
|
||||||
|
try:
|
||||||
|
async with pool.acquire() as conn:
|
||||||
|
rows = await conn.fetch(
|
||||||
|
"""
|
||||||
|
SELECT id, status, title, severity, grafana_org_slug, service_name, created_at, fingerprint
|
||||||
|
FROM irm_alerts
|
||||||
|
ORDER BY created_at DESC
|
||||||
|
LIMIT 150
|
||||||
|
"""
|
||||||
|
)
|
||||||
|
if not rows:
|
||||||
|
body = "<p>Пока нет алертов. События появляются после вебхука Grafana.</p>"
|
||||||
|
else:
|
||||||
|
trs = []
|
||||||
|
for r in rows:
|
||||||
|
aid = str(r["id"])
|
||||||
|
trs.append(
|
||||||
|
"<tr>"
|
||||||
|
f"<td>{html.escape(r['status'])}</td>"
|
||||||
|
f"<td><a href=\"/ui/modules/alerts/{html.escape(aid, quote=True)}\">"
|
||||||
|
f"{html.escape(aid[:8])}…</a></td>"
|
||||||
|
f"<td>{html.escape((r['title'] or '—')[:200])}</td>"
|
||||||
|
f"<td>{html.escape(r['severity'])}</td>"
|
||||||
|
f"<td>{html.escape(str(r['grafana_org_slug'] or '—'))}</td>"
|
||||||
|
f"<td>{html.escape(str(r['service_name'] or '—'))}</td>"
|
||||||
|
f"<td>{html.escape(r['created_at'].isoformat() if r['created_at'] else '—')}</td>"
|
||||||
|
"</tr>"
|
||||||
|
)
|
||||||
|
body = (
|
||||||
|
"<p class='gc-muted'>Алерт — запись о входящем уведомлении. "
|
||||||
|
"<strong>Инцидент</strong> создаётся вручную (из карточки алерта или раздела «Инциденты») "
|
||||||
|
"и может ссылаться на один или несколько алертов.</p>"
|
||||||
|
"<table class='irm-table'><thead><tr><th>Статус</th><th>ID</th><th>Заголовок</th>"
|
||||||
|
"<th>Важность</th><th>Grafana slug</th><th>Сервис</th><th>Создан</th></tr></thead><tbody>"
|
||||||
|
+ "".join(trs)
|
||||||
|
+ "</tbody></table>"
|
||||||
|
)
|
||||||
|
except Exception as e:
|
||||||
|
body = f"<p class='module-err'>{html.escape(str(e))}</p>"
|
||||||
|
page = f"<h1>Алерты</h1>{body}{_SYNC_BTN_STYLE}"
|
||||||
|
return HTMLResponse(
|
||||||
|
wrap_module_html_page(
|
||||||
|
document_title="Алерты — onGuard24",
|
||||||
|
current_slug="alerts",
|
||||||
|
main_inner_html=page,
|
||||||
|
)
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
@ui_router.get("/{alert_id:uuid}", response_class=HTMLResponse)
|
||||||
|
async def alerts_ui_detail(request: Request, alert_id: UUID):
|
||||||
|
pool = get_pool(request)
|
||||||
|
if pool is None:
|
||||||
|
return HTMLResponse(
|
||||||
|
wrap_module_html_page(
|
||||||
|
document_title="Алерт — onGuard24",
|
||||||
|
current_slug="alerts",
|
||||||
|
main_inner_html="<h1>Алерт</h1><p>База не настроена.</p>",
|
||||||
|
)
|
||||||
|
)
|
||||||
|
try:
|
||||||
|
async with pool.acquire() as conn:
|
||||||
|
row = await conn.fetchrow("SELECT * FROM irm_alerts WHERE id = $1::uuid", alert_id)
|
||||||
|
raw = None
|
||||||
|
if row and row.get("ingress_event_id"):
|
||||||
|
raw = await conn.fetchrow(
|
||||||
|
"SELECT body, received_at FROM ingress_events WHERE id = $1::uuid",
|
||||||
|
row["ingress_event_id"],
|
||||||
|
)
|
||||||
|
except Exception as e:
|
||||||
|
return HTMLResponse(
|
||||||
|
wrap_module_html_page(
|
||||||
|
document_title="Алерт — onGuard24",
|
||||||
|
current_slug="alerts",
|
||||||
|
main_inner_html=f"<h1>Алерт</h1><p class='module-err'>{html.escape(str(e))}</p>",
|
||||||
|
)
|
||||||
|
)
|
||||||
|
if not row:
|
||||||
|
inner = "<p>Не найдено.</p>"
|
||||||
|
else:
|
||||||
|
aid = str(row["id"])
|
||||||
|
st = row["status"]
|
||||||
|
title_js = json.dumps(row["title"] or "")
|
||||||
|
btns = []
|
||||||
|
if st == "firing":
|
||||||
|
btns.append(
|
||||||
|
f"<button type='button' class='og-btn og-btn-primary' "
|
||||||
|
f"onclick=\"ogAck('{html.escape(aid, quote=True)}')\">Подтвердить (Ack)</button>"
|
||||||
|
)
|
||||||
|
if st in ("firing", "acknowledged"):
|
||||||
|
btns.append(
|
||||||
|
f"<button type='button' class='og-btn' "
|
||||||
|
f"onclick=\"ogRes('{html.escape(aid, quote=True)}')\">Resolve</button>"
|
||||||
|
)
|
||||||
|
btns.append(
|
||||||
|
f"<button type='button' class='og-btn' "
|
||||||
|
f"onclick=\"ogInc('{html.escape(aid, quote=True)}',{title_js})\">"
|
||||||
|
"Создать инцидент</button>"
|
||||||
|
)
|
||||||
|
lab = row["labels"]
|
||||||
|
lab_s = json.dumps(dict(lab), ensure_ascii=False, indent=2) if isinstance(lab, dict) else "{}"
|
||||||
|
raw_pre = ""
|
||||||
|
if raw:
|
||||||
|
b = raw["body"]
|
||||||
|
pretty = json.dumps(dict(b), ensure_ascii=False, indent=2) if hasattr(b, "keys") else str(b)
|
||||||
|
if len(pretty) > 14000:
|
||||||
|
pretty = pretty[:14000] + "\n…"
|
||||||
|
raw_pre = (
|
||||||
|
"<h2 style='font-size:1.05rem;margin-top:1rem'>Полное тело вебхука</h2>"
|
||||||
|
f"<pre style='overflow:auto;max-height:26rem;font-size:0.78rem;"
|
||||||
|
f"background:#18181b;color:#e4e4e7;padding:0.75rem;border-radius:8px'>"
|
||||||
|
f"{html.escape(pretty)}</pre>"
|
||||||
|
)
|
||||||
|
inner = (
|
||||||
|
f"<p><a href=\"/ui/modules/alerts/\">← К списку алертов</a></p>"
|
||||||
|
f"<h1>Алерт</h1><div class='og-sync-bar'>{''.join(btns)}</div>"
|
||||||
|
f"<dl style='display:grid;grid-template-columns:11rem 1fr;gap:0.35rem 1rem;font-size:0.9rem'>"
|
||||||
|
f"<dt>ID</dt><dd><code>{html.escape(aid)}</code></dd>"
|
||||||
|
f"<dt>Статус</dt><dd>{html.escape(st)}</dd>"
|
||||||
|
f"<dt>Заголовок</dt><dd>{html.escape(row['title'] or '—')}</dd>"
|
||||||
|
f"<dt>Важность</dt><dd>{html.escape(row['severity'])}</dd>"
|
||||||
|
f"<dt>Grafana slug</dt><dd>{html.escape(str(row['grafana_org_slug'] or '—'))}</dd>"
|
||||||
|
f"<dt>Сервис</dt><dd>{html.escape(str(row['service_name'] or '—'))}</dd>"
|
||||||
|
f"<dt>Fingerprint</dt><dd><code>{html.escape(str(row['fingerprint'] or '—'))}</code></dd>"
|
||||||
|
f"<dt>Labels</dt><dd><pre style='margin:0;font-size:0.8rem'>{html.escape(lab_s)}</pre></dd>"
|
||||||
|
f"</dl>{raw_pre}"
|
||||||
|
)
|
||||||
|
page = f"{inner}{_SYNC_BTN_STYLE}"
|
||||||
|
return HTMLResponse(
|
||||||
|
wrap_module_html_page(
|
||||||
|
document_title="Алерт — onGuard24",
|
||||||
|
current_slug="alerts",
|
||||||
|
main_inner_html=page,
|
||||||
|
)
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
async def render_home_fragment(request: Request) -> str:
|
||||||
|
pool = get_pool(request)
|
||||||
|
if pool is None:
|
||||||
|
return '<p class="module-note">Нужна БД для учёта алертов.</p>'
|
||||||
|
try:
|
||||||
|
async with pool.acquire() as conn:
|
||||||
|
n = await conn.fetchval("SELECT count(*)::int FROM irm_alerts")
|
||||||
|
nf = await conn.fetchval(
|
||||||
|
"SELECT count(*)::int FROM irm_alerts WHERE status = 'firing'"
|
||||||
|
)
|
||||||
|
except Exception:
|
||||||
|
return '<p class="module-note">Таблица алертов недоступна (миграция 005?).</p>'
|
||||||
|
return (
|
||||||
|
f'<div class="module-fragment"><p>Алертов в учёте: <strong>{int(n)}</strong> '
|
||||||
|
f'(<strong>{int(nf)}</strong> firing). '
|
||||||
|
f'<a href="/ui/modules/alerts/">Открыть</a></p></div>'
|
||||||
|
)
|
||||||
@ -12,6 +12,7 @@ from fastapi import APIRouter, Depends, HTTPException, Request
|
|||||||
from fastapi.responses import HTMLResponse
|
from fastapi.responses import HTMLResponse
|
||||||
from pydantic import BaseModel, Field
|
from pydantic import BaseModel, Field
|
||||||
|
|
||||||
|
from onguard24.config import get_settings
|
||||||
from onguard24.deps import get_pool
|
from onguard24.deps import get_pool
|
||||||
from onguard24.domain.events import AlertReceived, DomainEvent, EventBus
|
from onguard24.domain.events import AlertReceived, DomainEvent, EventBus
|
||||||
from onguard24.modules.ui_support import wrap_module_html_page
|
from onguard24.modules.ui_support import wrap_module_html_page
|
||||||
@ -26,6 +27,7 @@ class IncidentCreate(BaseModel):
|
|||||||
title: str = Field(..., min_length=1, max_length=500)
|
title: str = Field(..., min_length=1, max_length=500)
|
||||||
status: str = Field(default="open", max_length=64)
|
status: str = Field(default="open", max_length=64)
|
||||||
severity: str = Field(default="warning", max_length=32)
|
severity: str = Field(default="warning", max_length=32)
|
||||||
|
alert_ids: list[UUID] = Field(default_factory=list, description="Привязка к irm_alerts")
|
||||||
|
|
||||||
|
|
||||||
class IncidentPatch(BaseModel):
|
class IncidentPatch(BaseModel):
|
||||||
@ -39,6 +41,8 @@ def register_events(bus: EventBus, pool: asyncpg.Pool | None = None) -> None:
|
|||||||
return
|
return
|
||||||
|
|
||||||
async def on_alert(ev: DomainEvent) -> None:
|
async def on_alert(ev: DomainEvent) -> None:
|
||||||
|
if not get_settings().auto_incident_from_alert:
|
||||||
|
return
|
||||||
if not isinstance(ev, AlertReceived) or ev.raw_payload_ref is None:
|
if not isinstance(ev, AlertReceived) or ev.raw_payload_ref is None:
|
||||||
return
|
return
|
||||||
a = ev.alert
|
a = ev.alert
|
||||||
@ -136,17 +140,29 @@ async def create_incident_api(
|
|||||||
if pool is None:
|
if pool is None:
|
||||||
raise HTTPException(status_code=503, detail="database disabled")
|
raise HTTPException(status_code=503, detail="database disabled")
|
||||||
async with pool.acquire() as conn:
|
async with pool.acquire() as conn:
|
||||||
row = await conn.fetchrow(
|
async with conn.transaction():
|
||||||
"""
|
row = await conn.fetchrow(
|
||||||
INSERT INTO incidents (title, status, severity, source, grafana_org_slug, service_name)
|
"""
|
||||||
VALUES ($1, $2, $3, 'manual', NULL, NULL)
|
INSERT INTO incidents (title, status, severity, source, grafana_org_slug, service_name)
|
||||||
RETURNING id, title, status, severity, source, ingress_event_id, created_at, updated_at,
|
VALUES ($1, $2, $3, 'manual', NULL, NULL)
|
||||||
grafana_org_slug, service_name
|
RETURNING id, title, status, severity, source, ingress_event_id, created_at, updated_at,
|
||||||
""",
|
grafana_org_slug, service_name
|
||||||
body.title.strip(),
|
""",
|
||||||
body.status,
|
body.title.strip(),
|
||||||
body.severity,
|
body.status,
|
||||||
)
|
body.severity,
|
||||||
|
)
|
||||||
|
iid = row["id"]
|
||||||
|
for aid in body.alert_ids[:50]:
|
||||||
|
await conn.execute(
|
||||||
|
"""
|
||||||
|
INSERT INTO incident_alert_links (incident_id, alert_id)
|
||||||
|
VALUES ($1::uuid, $2::uuid)
|
||||||
|
ON CONFLICT DO NOTHING
|
||||||
|
""",
|
||||||
|
iid,
|
||||||
|
aid,
|
||||||
|
)
|
||||||
return {
|
return {
|
||||||
"id": str(row["id"]),
|
"id": str(row["id"]),
|
||||||
"title": row["title"],
|
"title": row["title"],
|
||||||
@ -312,7 +328,7 @@ async def incidents_ui_home(request: Request):
|
|||||||
<thead><tr><th>ID</th><th>Заголовок</th><th>Статус</th><th>Важность</th><th>Источник</th><th>Grafana slug</th><th>Сервис</th><th>Создан</th></tr></thead>
|
<thead><tr><th>ID</th><th>Заголовок</th><th>Статус</th><th>Важность</th><th>Источник</th><th>Grafana slug</th><th>Сервис</th><th>Создан</th></tr></thead>
|
||||||
<tbody>{rows_html or '<tr><td colspan="8">Пока нет записей</td></tr>'}</tbody>
|
<tbody>{rows_html or '<tr><td colspan="8">Пока нет записей</td></tr>'}</tbody>
|
||||||
</table>
|
</table>
|
||||||
<p><small>Создание из Grafana: webhook → <code>ingress_events</code> → событие → строка здесь. Пустой заголовок бывает при тестовом JSON без полей алерта.</small></p>"""
|
<p><small>Сначала вебхук создаёт <a href="/ui/modules/alerts/">алерт</a> (учёт, Ack/Resolve). Инцидент — отдельная сущность: создаётся вручную или из карточки алерта, к нему можно привязать один или несколько алертов. Пустой заголовок в списке — часто тестовый JSON без полей правила.</small></p>"""
|
||||||
return HTMLResponse(
|
return HTMLResponse(
|
||||||
wrap_module_html_page(
|
wrap_module_html_page(
|
||||||
document_title="Инциденты — onGuard24",
|
document_title="Инциденты — onGuard24",
|
||||||
|
|||||||
@ -14,6 +14,7 @@ from starlette.requests import Request
|
|||||||
|
|
||||||
from onguard24.domain.events import EventBus
|
from onguard24.domain.events import EventBus
|
||||||
from onguard24.modules import (
|
from onguard24.modules import (
|
||||||
|
alerts,
|
||||||
contacts,
|
contacts,
|
||||||
escalations,
|
escalations,
|
||||||
grafana_catalog,
|
grafana_catalog,
|
||||||
@ -52,6 +53,15 @@ def _mounts() -> list[ModuleMount]:
|
|||||||
ui_router=grafana_catalog.ui_router,
|
ui_router=grafana_catalog.ui_router,
|
||||||
render_home_fragment=grafana_catalog.render_home_fragment,
|
render_home_fragment=grafana_catalog.render_home_fragment,
|
||||||
),
|
),
|
||||||
|
ModuleMount(
|
||||||
|
router=alerts.router,
|
||||||
|
url_prefix="/api/v1/modules/alerts",
|
||||||
|
register_events=alerts.register_events,
|
||||||
|
slug="alerts",
|
||||||
|
title="Алерты",
|
||||||
|
ui_router=alerts.ui_router,
|
||||||
|
render_home_fragment=alerts.render_home_fragment,
|
||||||
|
),
|
||||||
ModuleMount(
|
ModuleMount(
|
||||||
router=incidents.router,
|
router=incidents.router,
|
||||||
url_prefix="/api/v1/modules/incidents",
|
url_prefix="/api/v1/modules/incidents",
|
||||||
|
|||||||
@ -1,6 +1,6 @@
|
|||||||
[project]
|
[project]
|
||||||
name = "onguard24"
|
name = "onguard24"
|
||||||
version = "1.8.0"
|
version = "1.9.0"
|
||||||
description = "onGuard24 — модульный сервис (аналог IRM)"
|
description = "onGuard24 — модульный сервис (аналог IRM)"
|
||||||
readme = "README.md"
|
readme = "README.md"
|
||||||
requires-python = ">=3.11"
|
requires-python = ">=3.11"
|
||||||
|
|||||||
@ -25,15 +25,28 @@ class Row:
|
|||||||
return self._data.get(key, default)
|
return self._data.get(key, default)
|
||||||
|
|
||||||
|
|
||||||
|
class _FakeTxn:
|
||||||
|
async def __aenter__(self) -> None:
|
||||||
|
return None
|
||||||
|
|
||||||
|
async def __aexit__(self, *args: Any) -> None:
|
||||||
|
return None
|
||||||
|
|
||||||
|
|
||||||
class IrmFakeConn:
|
class IrmFakeConn:
|
||||||
def __init__(self, store: IrmFakeStore) -> None:
|
def __init__(self, store: IrmFakeStore) -> None:
|
||||||
self.store = store
|
self.store = store
|
||||||
|
|
||||||
|
def transaction(self) -> _FakeTxn:
|
||||||
|
return _FakeTxn()
|
||||||
|
|
||||||
def _q(self, query: str) -> str:
|
def _q(self, query: str) -> str:
|
||||||
return " ".join(query.split())
|
return " ".join(query.split())
|
||||||
|
|
||||||
async def execute(self, query: str, *args: Any) -> str:
|
async def execute(self, query: str, *args: Any) -> str:
|
||||||
q = self._q(query)
|
q = self._q(query)
|
||||||
|
if "INSERT INTO incident_alert_links" in q:
|
||||||
|
return "INSERT 0 1"
|
||||||
if "INSERT INTO incidents" in q and "ingress_event_id" in q:
|
if "INSERT INTO incidents" in q and "ingress_event_id" in q:
|
||||||
self.store.insert_incident_alert(
|
self.store.insert_incident_alert(
|
||||||
args[0], args[1], args[2], args[3], args[4]
|
args[0], args[1], args[2], args[3], args[4]
|
||||||
|
|||||||
9
tests/test_alerts_api.py
Normal file
9
tests/test_alerts_api.py
Normal file
@ -0,0 +1,9 @@
|
|||||||
|
"""API модуля алертов без БД."""
|
||||||
|
|
||||||
|
from fastapi.testclient import TestClient
|
||||||
|
|
||||||
|
|
||||||
|
def test_alerts_list_no_db(client: TestClient) -> None:
|
||||||
|
r = client.get("/api/v1/modules/alerts/")
|
||||||
|
assert r.status_code == 200
|
||||||
|
assert r.json() == {"items": [], "database": "disabled"}
|
||||||
26
tests/test_grafana_payload.py
Normal file
26
tests/test_grafana_payload.py
Normal file
@ -0,0 +1,26 @@
|
|||||||
|
"""Парсинг полей из тела вебхука Grafana."""
|
||||||
|
|
||||||
|
from onguard24.ingress.grafana_payload import extract_alert_row_from_grafana_body
|
||||||
|
|
||||||
|
|
||||||
|
def test_extract_title_and_severity_from_unified() -> None:
|
||||||
|
body = {
|
||||||
|
"title": "RuleName",
|
||||||
|
"alerts": [
|
||||||
|
{
|
||||||
|
"labels": {"severity": "critical", "alertname": "X"},
|
||||||
|
"fingerprint": "abc",
|
||||||
|
}
|
||||||
|
],
|
||||||
|
}
|
||||||
|
title, sev, labels, fp = extract_alert_row_from_grafana_body(body)
|
||||||
|
assert title == "RuleName"
|
||||||
|
assert sev == "critical"
|
||||||
|
assert labels.get("alertname") == "X"
|
||||||
|
assert fp == "abc"
|
||||||
|
|
||||||
|
|
||||||
|
def test_extract_empty_title_uses_alertname() -> None:
|
||||||
|
body = {"alerts": [{"labels": {"alertname": "HostDown"}}]}
|
||||||
|
title, _, _, _ = extract_alert_row_from_grafana_body(body)
|
||||||
|
assert title == "HostDown"
|
||||||
@ -1,9 +1,23 @@
|
|||||||
import json
|
import json
|
||||||
from unittest.mock import AsyncMock, MagicMock, patch
|
from unittest.mock import AsyncMock, MagicMock, patch
|
||||||
|
|
||||||
from fastapi.testclient import TestClient
|
from fastapi.testclient import TestClient
|
||||||
|
|
||||||
|
|
||||||
|
def _webhook_mock_pool(mock_conn: AsyncMock) -> MagicMock:
|
||||||
|
"""Пул с транзакцией и execute — как после вставки ingress + irm_alerts."""
|
||||||
|
tx = AsyncMock()
|
||||||
|
tx.__aenter__ = AsyncMock(return_value=None)
|
||||||
|
tx.__aexit__ = AsyncMock(return_value=None)
|
||||||
|
mock_conn.transaction = MagicMock(return_value=tx)
|
||||||
|
mock_conn.execute = AsyncMock()
|
||||||
|
mock_cm = AsyncMock()
|
||||||
|
mock_cm.__aenter__ = AsyncMock(return_value=mock_conn)
|
||||||
|
mock_cm.__aexit__ = AsyncMock(return_value=None)
|
||||||
|
mock_pool = MagicMock()
|
||||||
|
mock_pool.acquire = MagicMock(return_value=mock_cm)
|
||||||
|
return mock_pool
|
||||||
|
|
||||||
|
|
||||||
def test_grafana_webhook_no_db(client: TestClient) -> None:
|
def test_grafana_webhook_no_db(client: TestClient) -> None:
|
||||||
"""Без пула БД — 202, запись не падает."""
|
"""Без пула БД — 202, запись не падает."""
|
||||||
r = client.post(
|
r = client.post(
|
||||||
@ -41,12 +55,7 @@ def test_grafana_webhook_inserts_with_mock_pool(client: TestClient) -> None:
|
|||||||
mock_conn = AsyncMock()
|
mock_conn = AsyncMock()
|
||||||
uid = uuid4()
|
uid = uuid4()
|
||||||
mock_conn.fetchrow = AsyncMock(return_value={"id": uid})
|
mock_conn.fetchrow = AsyncMock(return_value={"id": uid})
|
||||||
mock_cm = AsyncMock()
|
mock_pool = _webhook_mock_pool(mock_conn)
|
||||||
mock_cm.__aenter__ = AsyncMock(return_value=mock_conn)
|
|
||||||
mock_cm.__aexit__ = AsyncMock(return_value=None)
|
|
||||||
|
|
||||||
mock_pool = MagicMock()
|
|
||||||
mock_pool.acquire = MagicMock(return_value=mock_cm)
|
|
||||||
|
|
||||||
app = client.app
|
app = client.app
|
||||||
real_pool = app.state.pool
|
real_pool = app.state.pool
|
||||||
@ -59,6 +68,7 @@ def test_grafana_webhook_inserts_with_mock_pool(client: TestClient) -> None:
|
|||||||
)
|
)
|
||||||
assert r.status_code == 202
|
assert r.status_code == 202
|
||||||
mock_conn.fetchrow.assert_called_once()
|
mock_conn.fetchrow.assert_called_once()
|
||||||
|
mock_conn.execute.assert_called_once()
|
||||||
finally:
|
finally:
|
||||||
app.state.pool = real_pool
|
app.state.pool = real_pool
|
||||||
|
|
||||||
@ -69,11 +79,7 @@ def test_grafana_webhook_auto_org_from_external_url(client: TestClient) -> None:
|
|||||||
mock_conn = AsyncMock()
|
mock_conn = AsyncMock()
|
||||||
uid = uuid4()
|
uid = uuid4()
|
||||||
mock_conn.fetchrow = AsyncMock(return_value={"id": uid})
|
mock_conn.fetchrow = AsyncMock(return_value={"id": uid})
|
||||||
mock_cm = AsyncMock()
|
mock_pool = _webhook_mock_pool(mock_conn)
|
||||||
mock_cm.__aenter__ = AsyncMock(return_value=mock_conn)
|
|
||||||
mock_cm.__aexit__ = AsyncMock(return_value=None)
|
|
||||||
mock_pool = MagicMock()
|
|
||||||
mock_pool.acquire = MagicMock(return_value=mock_cm)
|
|
||||||
|
|
||||||
app = client.app
|
app = client.app
|
||||||
real_pool = app.state.pool
|
real_pool = app.state.pool
|
||||||
@ -99,11 +105,7 @@ def test_grafana_webhook_publishes_alert_received(client: TestClient) -> None:
|
|||||||
mock_conn = AsyncMock()
|
mock_conn = AsyncMock()
|
||||||
uid = uuid4()
|
uid = uuid4()
|
||||||
mock_conn.fetchrow = AsyncMock(return_value={"id": uid})
|
mock_conn.fetchrow = AsyncMock(return_value={"id": uid})
|
||||||
mock_cm = AsyncMock()
|
mock_pool = _webhook_mock_pool(mock_conn)
|
||||||
mock_cm.__aenter__ = AsyncMock(return_value=mock_conn)
|
|
||||||
mock_cm.__aexit__ = AsyncMock(return_value=None)
|
|
||||||
mock_pool = MagicMock()
|
|
||||||
mock_pool.acquire = MagicMock(return_value=mock_cm)
|
|
||||||
|
|
||||||
app = client.app
|
app = client.app
|
||||||
bus = app.state.event_bus
|
bus = app.state.event_bus
|
||||||
@ -130,11 +132,7 @@ def test_grafana_webhook_org_any_slug_without_json_config(client: TestClient) ->
|
|||||||
mock_conn = AsyncMock()
|
mock_conn = AsyncMock()
|
||||||
uid = uuid4()
|
uid = uuid4()
|
||||||
mock_conn.fetchrow = AsyncMock(return_value={"id": uid})
|
mock_conn.fetchrow = AsyncMock(return_value={"id": uid})
|
||||||
mock_cm = AsyncMock()
|
mock_pool = _webhook_mock_pool(mock_conn)
|
||||||
mock_cm.__aenter__ = AsyncMock(return_value=mock_conn)
|
|
||||||
mock_cm.__aexit__ = AsyncMock(return_value=None)
|
|
||||||
mock_pool = MagicMock()
|
|
||||||
mock_pool.acquire = MagicMock(return_value=mock_cm)
|
|
||||||
|
|
||||||
app = client.app
|
app = client.app
|
||||||
real_pool = app.state.pool
|
real_pool = app.state.pool
|
||||||
@ -157,11 +155,7 @@ def test_grafana_webhook_org_ok(client: TestClient) -> None:
|
|||||||
mock_conn = AsyncMock()
|
mock_conn = AsyncMock()
|
||||||
uid = uuid4()
|
uid = uuid4()
|
||||||
mock_conn.fetchrow = AsyncMock(return_value={"id": uid})
|
mock_conn.fetchrow = AsyncMock(return_value={"id": uid})
|
||||||
mock_cm = AsyncMock()
|
mock_pool = _webhook_mock_pool(mock_conn)
|
||||||
mock_cm.__aenter__ = AsyncMock(return_value=mock_conn)
|
|
||||||
mock_cm.__aexit__ = AsyncMock(return_value=None)
|
|
||||||
mock_pool = MagicMock()
|
|
||||||
mock_pool.acquire = MagicMock(return_value=mock_cm)
|
|
||||||
|
|
||||||
app = client.app
|
app = client.app
|
||||||
real_json = app.state.settings.grafana_sources_json
|
real_json = app.state.settings.grafana_sources_json
|
||||||
|
|||||||
@ -29,8 +29,41 @@ def test_escalations_api_list_no_db(client: TestClient) -> None:
|
|||||||
|
|
||||||
|
|
||||||
@pytest.mark.asyncio
|
@pytest.mark.asyncio
|
||||||
async def test_incident_inserted_on_alert_received() -> None:
|
async def test_incident_not_created_from_alert_by_default() -> None:
|
||||||
"""При пуле БД подписка создаёт инцидент (INSERT)."""
|
"""По умолчанию AUTO_INCIDENT_FROM_ALERT выкл — инцидент из вебхука не создаётся."""
|
||||||
|
calls: list = []
|
||||||
|
|
||||||
|
async def fake_execute(_query, *args):
|
||||||
|
calls.append(args)
|
||||||
|
return "INSERT 0 1"
|
||||||
|
|
||||||
|
mock_conn = AsyncMock()
|
||||||
|
mock_conn.execute = fake_execute
|
||||||
|
mock_cm = AsyncMock()
|
||||||
|
mock_cm.__aenter__ = AsyncMock(return_value=mock_conn)
|
||||||
|
mock_cm.__aexit__ = AsyncMock(return_value=None)
|
||||||
|
mock_pool = MagicMock()
|
||||||
|
mock_pool.acquire = MagicMock(return_value=mock_cm)
|
||||||
|
|
||||||
|
from onguard24.domain.events import InMemoryEventBus
|
||||||
|
from onguard24.modules import incidents as inc_mod
|
||||||
|
|
||||||
|
bus = InMemoryEventBus()
|
||||||
|
inc_mod.register_events(bus, mock_pool)
|
||||||
|
|
||||||
|
uid = uuid4()
|
||||||
|
ev = AlertReceived(
|
||||||
|
alert=Alert(source="grafana", title="CPU high", severity=Severity.WARNING),
|
||||||
|
raw_payload_ref=uid,
|
||||||
|
)
|
||||||
|
await bus.publish(ev)
|
||||||
|
assert calls == []
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.asyncio
|
||||||
|
async def test_incident_inserted_on_alert_when_auto_enabled(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||||
|
"""При AUTO_INCIDENT_FROM_ALERT=1 подписка снова создаёт инцидент (legacy)."""
|
||||||
|
monkeypatch.setenv("AUTO_INCIDENT_FROM_ALERT", "1")
|
||||||
inserted: dict = {}
|
inserted: dict = {}
|
||||||
|
|
||||||
async def fake_execute(_query, *args):
|
async def fake_execute(_query, *args):
|
||||||
|
|||||||
@ -33,6 +33,7 @@ def test_rail_lists_all_registered_ui_modules(client: TestClient) -> None:
|
|||||||
t = r.text
|
t = r.text
|
||||||
expected = (
|
expected = (
|
||||||
("grafana-catalog", "Каталог Grafana"),
|
("grafana-catalog", "Каталог Grafana"),
|
||||||
|
("alerts", "Алерты"),
|
||||||
("incidents", "Инциденты"),
|
("incidents", "Инциденты"),
|
||||||
("tasks", "Задачи"),
|
("tasks", "Задачи"),
|
||||||
("escalations", "Эскалации"),
|
("escalations", "Эскалации"),
|
||||||
@ -49,6 +50,7 @@ def test_each_module_page_single_active_nav_item(client: TestClient) -> None:
|
|||||||
"""На странице модуля ровно один пункт с aria-current (текущий раздел)."""
|
"""На странице модуля ровно один пункт с aria-current (текущий раздел)."""
|
||||||
for slug in (
|
for slug in (
|
||||||
"grafana-catalog",
|
"grafana-catalog",
|
||||||
|
"alerts",
|
||||||
"incidents",
|
"incidents",
|
||||||
"tasks",
|
"tasks",
|
||||||
"escalations",
|
"escalations",
|
||||||
|
|||||||
Reference in New Issue
Block a user