Real-time monitoring dashboard for Proxmox VE, PBS, Docker, Kubernetes, TrueNAS and vSphere. Self-hosted, with alerts for failed backups, full disks, unhealthy containers and offline nodes.
Go aialertsdashboarddockerdocker-monitoringgohomelabinfrastructure-monitoringkubernetesmonitoringmspproxmoxproxmox-backup-serverproxmox-mail-gatewayproxmox-veself-hostedtruenastypescriptvspherewebhooks
#!/usr/bin/env python3
"""Keep lingering-alert help tied to live evaluation, not a retained breach."""
from pathlib import Path
import unittest
ROOT = Path(__file__).resolve().parents[2]
HEADING = '#### Usage alert stays open after the reading falls\n'
ANCHOR = '#usage-alert-stays-open-after-the-reading-falls'
class MetricAlertHelpDocsTest(unittest.TestCase):
def setUp(self):
self.source = (ROOT / 'docs/TROUBLESHOOTING.md').read_text()
self.guide = ' '.join(self.source.split(HEADING, 1)[1].split('\n#### ', 1)[0].split())
self.presentation = (ROOT / 'frontend-modern/src/features/alerts/metricAlertPresentation.ts').read_text()
def test_workflow_entry_reaches_one_section_in_the_shipped_copy(self):
self.assertEqual(self.source.count(HEADING), 1)
self.assertIn(ANCHOR, self.source.split('## ⚡ Quick Fixes', 1)[0])
self.assertEqual((ROOT / 'docs/TROUBLESHOOTING.md').read_bytes(),
(ROOT / 'frontend-modern/public/docs/TROUBLESHOOTING.md').read_bytes())
def test_named_states_and_units_follow_the_actual_card_presenter(self):
for label in ('Alert still open', 'Recovering', 'No recent reading'):
with self.subTest(label=label):
self.assertIn(f"phaseLabel = '{label}'", self.presentation)
self.assertIn(f'**{label}**', self.guide)
for label in ('averaged', 'latest', 'Last reading at or above'):
with self.subTest(label=label):
self.assertIn(label, self.presentation)
self.assertIn(f'**{label}**', self.guide)
card = (ROOT / 'frontend-modern/src/features/alerts/AlertOverviewAlertCard.tsx').read_text()
self.assertIn('getMetricAlertPresentation(props.alert', card)
self.assertIn('not current usage', self.guide)
self.assertIn('match the filesystem too', self.guide)
def test_clear_rule_example_is_not_a_universal_or_immediate_promise(self):
self.assertIn('90% trigger and 85% clear, 88% can still hold', self.guide)
self.assertIn('not the saved rule for every resource', self.guide)
self.assertIn('elapsed wall-clock time alone does not prove', self.guide)
self.assertIn('fresh eligible observations', self.guide)
anchor = 'CONFIGURATION.md#metric-thresholds-off-and-inheritance'
self.assertIn(anchor, self.guide)
self.assertIn('### Metric thresholds, Off and inheritance',
(ROOT / 'docs/CONFIGURATION.md').read_text())
# The producer retains breach fields during a hold; only live status moves.
producer = (ROOT / 'internal/alerts/canonical_metric.go').read_text()
hold = producer.split('if !triggered && primary == "" {', 1)[1].split('return true', 1)[0]
self.assertIn('existingAlert.MetricStatus = metricStatus', hold)
self.assertNotIn('existingAlert.Value =', hold)
self.assertNotIn('existingAlert.LastSeen =', hold)
def test_missing_data_attention_and_delivery_are_not_measured_recovery(self):
for boundary in (
'retained evidence, not a healthy zero',
'missing detail does not establish a current breach',
'not required for a threshold alert to recover',
'retained failed notification can outlive its incident',
'#recover-retained-delivery-failures',
'Unknown details are valid', 'Add only missing evidence',
'do not rerun a backup, create load, restart, change thresholds',
'disable monitoring or retry notifications', 'Do not delete alert or queue data',
'not proof that the workload recovered',
):
with self.subTest(boundary=boundary):
self.assertIn(boundary, self.guide)
self.assertNotIn('```', self.guide)
def test_threshold_marker_help_follows_both_current_consumers(self):
source = (ROOT / 'docs/CONFIGURATION.md').read_text()
heading = '### Read active-alert markers\n'
self.assertEqual(source.count(heading), 1)
self.assertIn('[active-alert markers](#read-active-alert-markers)', source)
self.assertEqual(source.encode(),
(ROOT / 'frontend-modern/public/docs/CONFIGURATION.md').read_bytes())
guide = ' '.join(source.split(heading, 1)[1].split('\n### ', 1)[0].split())
for file in ('AlertResourceTableRow.tsx', 'AlertResourceTableMobile.tsx'):
consumer = (ROOT / 'frontend-modern/src/components/Alerts' / file).read_text()
self.assertIn('title="Active alert"', consumer)
self.assertIn('hasActiveAlert(', consumer)
self.assertIn('current alert list contains an open alert for that row and metric', guide)
self.assertIn('not a new reading, another threshold', guide)
self.assertIn('No dot is not proof that the workload is healthy', guide)
self.assertIn('Recent delivery activity', guide)
self.assertIn('#usage-alert-stays-open-after-the-reading-falls', guide)
self.assertIn('#test-succeeds-but-real-alerts-are-missing', guide)
self.assertIn('Do not create load, change thresholds or send a Test', guide)
self.assertNotIn('```', guide)
def test_marker_attribution_distinguishes_machine_disks_and_linked_nodes(self):
source = (ROOT / 'docs/CONFIGURATION.md').read_text()
guide = ' '.join(source.split('### Read active-alert markers\n', 1)[1]
.split('\n### ', 1)[0].split())
model = (ROOT / 'frontend-modern/src/features/alerts/thresholds/thresholdsResourceModel.ts').read_text()
host = (ROOT / 'frontend-modern/src/features/alerts/thresholds/hooks/useThresholdsHostData.ts').read_text()
self.assertIn("child.startsWith('disk:') || child.startsWith('disk_temp:')", model)
self.assertIn("row.type === 'agent' && index.byMachine", model)
self.assertIn('alertResourceIds: uniqueIds(node.proxmox?.sourceId, node.id)', host)
self.assertIn('agentAlertResourceId(', host)
for boundary in ('**Disk %** or **Disk Temp**', 'exact filesystem or device',
'does not mean every disk is affected',
"agent's CPU, memory and disk alerts", 'not the node',
'Check the owning row rather than changing the node'):
with self.subTest(boundary=boundary):
self.assertIn(boundary, guide)
if __name__ == '__main__':
unittest.main()