gsadmin/sencho
1
0
Fork 0
mirror of https://github.com/Studio-Saelix/sencho.git synced 2026-08-19 23:06:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(dashboard): harden real-time dashboard with bug fixes and design compliance (#517)

Browse Source 
* fix(dashboard): harden real-time dashboard with bug fixes and design compliance

- Fix host alert spam: add 5-minute cooldown for CPU/RAM/disk threshold
  alerts, preventing duplicate notifications every 30s during sustained
  breaches. Extract shared dispatchWithCooldown helper (also used by
  Docker janitor alerts).
- Fix memory metric inflation: subtract filesystem cache from stored
  memory_mb values, matching the existing calculateMemoryPercent logic.
- Fix crash detection reliability: replace fragile 'seconds ago' string
  matching with a tracked Set of alerted container IDs. Containers are
  only alerted once per crash event, with automatic cleanup when they
  start running again or after a 1-hour TTL.
- Fix health status bar: exited containers now trigger 'degraded' state
  independently of unread error notifications.
- Fix CPU chart Y-axis: auto-scale when aggregate container CPU exceeds
  100% instead of silently clipping at the hardcoded domain ceiling.
- Fix grammar: 'actives' to 'active' in container count label.
- Add shadow-card-bevel to all dashboard cards per design system.
- Update dashboard docs to reflect revised health status thresholds.

* test(dashboard): update monitor service tests for new alert signatures

- Add container Id fields to crash detection test fixtures
- Update host alert assertions to match dispatchWithCooldown 3-arg call
- Fix unhealthy container test to use State: 'unhealthy' instead of
  State: 'running' (running containers are now skipped in crash detect)
This commit is contained in:
Anso
2026-04-12 04:25:41 -04:00
committed by GitHub
parent c7f041957c
commit 9db97107aa
9 changed files with 98 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/src/__tests__/monitor-service.test.ts
+10 -7
View File
@@ -251,7 +251,7 @@ describe('MonitorService - evaluateGlobalSettings', () => {
const svc = MonitorService.getInstance();
await (svc as any).evaluateGlobalSettings({ host_cpu_limit: '50' });
expect(mockDispatchAlert).toHaveBeenCalledWith('warning', expect.stringContaining('CPU'));
expect(mockDispatchAlert).toHaveBeenCalledWith('warning', expect.stringContaining('CPU'), undefined);
});
it('does not dispatch when CPU below threshold', async () => {
@@ -260,7 +260,7 @@ describe('MonitorService - evaluateGlobalSettings', () => {
const svc = MonitorService.getInstance();
await (svc as any).evaluateGlobalSettings({ host_cpu_limit: '50' });
expect(mockDispatchAlert).not.toHaveBeenCalledWith('warning', expect.stringContaining('CPU'));
expect(mockDispatchAlert).not.toHaveBeenCalledWith('warning', expect.stringContaining('CPU'), undefined);
});
it('dispatches RAM warning when over threshold', async () => {
@@ -269,7 +269,7 @@ describe('MonitorService - evaluateGlobalSettings', () => {
const svc = MonitorService.getInstance();
await (svc as any).evaluateGlobalSettings({ host_ram_limit: '80' });
expect(mockDispatchAlert).toHaveBeenCalledWith('warning', expect.stringContaining('Memory'));
expect(mockDispatchAlert).toHaveBeenCalledWith('warning', expect.stringContaining('Memory'), undefined);
});
it('dispatches disk warning when over threshold', async () => {
@@ -278,7 +278,7 @@ describe('MonitorService - evaluateGlobalSettings', () => {
const svc = MonitorService.getInstance();
await (svc as any).evaluateGlobalSettings({ host_disk_limit: '90' });
expect(mockDispatchAlert).toHaveBeenCalledWith('warning', expect.stringContaining('Disk'));
expect(mockDispatchAlert).toHaveBeenCalledWith('warning', expect.stringContaining('Disk'), undefined);
});
it('skips host limits when threshold is 0 or NaN', async () => {
@@ -286,10 +286,10 @@ describe('MonitorService - evaluateGlobalSettings', () => {
const svc = MonitorService.getInstance();
await (svc as any).evaluateGlobalSettings({ host_cpu_limit: '0' });
expect(mockDispatchAlert).not.toHaveBeenCalledWith('warning', expect.stringContaining('CPU'));
expect(mockDispatchAlert).not.toHaveBeenCalledWith('warning', expect.stringContaining('CPU'), undefined);
await (svc as any).evaluateGlobalSettings({ host_cpu_limit: 'abc' });
expect(mockDispatchAlert).not.toHaveBeenCalledWith('warning', expect.stringContaining('CPU'));
expect(mockDispatchAlert).not.toHaveBeenCalledWith('warning', expect.stringContaining('CPU'), undefined);
});
});
@@ -299,6 +299,7 @@ describe('MonitorService - global crash detection', () => {
it('detects exited containers with non-intentional exit codes', async () => {
mockGetNodes.mockReturnValue([{ id: 1, name: 'local', type: 'local' }]);
mockGetAllContainers.mockResolvedValue([{
Id: 'crash-1',
State: 'exited',
Status: 'Exited (1) 5 seconds ago',
Names: ['/my-container'],
@@ -317,6 +318,7 @@ describe('MonitorService - global crash detection', () => {
for (const code of intentionalExits) {
mockDispatchAlert.mockClear();
mockGetAllContainers.mockResolvedValue([{
Id: `safe-${code}`,
State: 'exited',
Status: `Exited (${code}) 5 seconds ago`,
Names: ['/safe-container'],
@@ -332,7 +334,8 @@ describe('MonitorService - global crash detection', () => {
it('detects unhealthy containers', async () => {
mockGetNodes.mockReturnValue([{ id: 1, name: 'local', type: 'local' }]);
mockGetAllContainers.mockResolvedValue([{
State: 'running',
Id: 'sick-1',
State: 'unhealthy',
Status: 'Up 2 hours (unhealthy)',
Names: ['/sick-container'],
}]);