feat: show error reason when monitors go DOWN
CI / test (pull_request) Successful in 2m42s
CI / lint (pull_request) Successful in 1m11s
CI / vulncheck (pull_request) Successful in 51s

Propagate check failure reasons through the entire stack:
- Checker captures specific errors (DNS, timeout, HTTP status, SSL, etc.)
- Engine tracks LastError, StatusChangedAt, LastSuccessAt per monitor
- State transitions persisted to new state_changes table
- Detail panel shows error reason, HTTP code, state duration, last
  success time, and last 5 state change events
- Monitor table shows inline error preview for DOWN services
- Alert messages include error reason
- Probe nodes forward error reasons to leader

15 files changed across models, checker, engine, store, TUI, and probes.
This commit is contained in:
2026-05-27 19:32:30 -04:00
parent d8a2cab90f
commit bc3a44beac
15 changed files with 299 additions and 96 deletions
+5 -4
View File
@@ -403,9 +403,10 @@ func Start(cfg ServerConfig, s store.Store, eng *monitor.Engine) *http.Server {
var req struct {
NodeID string `json:"node_id"`
Results []struct {
SiteID int `json:"site_id"`
LatencyNs int64 `json:"latency_ns"`
IsUp bool `json:"is_up"`
SiteID int `json:"site_id"`
LatencyNs int64 `json:"latency_ns"`
IsUp bool `json:"is_up"`
ErrorReason string `json:"error_reason"`
} `json:"results"`
}
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
@@ -420,7 +421,7 @@ func Start(cfg ServerConfig, s store.Store, eng *monitor.Engine) *http.Server {
if err := s.SaveCheckFromNode(result.SiteID, req.NodeID, result.LatencyNs, result.IsUp); err != nil {
log.Printf("Failed to save probe result: %v", err)
}
eng.IngestProbeResult(req.NodeID, result.SiteID, result.LatencyNs, result.IsUp)
eng.IngestProbeResult(req.NodeID, result.SiteID, result.LatencyNs, result.IsUp, result.ErrorReason)
}
if err := s.UpdateNodeLastSeen(req.NodeID); err != nil {
log.Printf("Failed to update node last seen: %v", err)
+12 -9
View File
@@ -4,13 +4,14 @@ import (
"bytes"
"encoding/json"
"fmt"
"gitea.lerkolabs.com/lerko/uptop/internal/models"
"gitea.lerkolabs.com/lerko/uptop/internal/monitor"
"net"
"net/http"
"sync"
"testing"
"time"
"gitea.lerkolabs.com/lerko/uptop/internal/models"
"gitea.lerkolabs.com/lerko/uptop/internal/monitor"
)
// --- Mock Store ---
@@ -69,13 +70,15 @@ func (m *mockStore) LoadLogs(int) ([]string, error) { return nil, nil
func (m *mockStore) GetAllMaintenanceWindows(int) ([]models.MaintenanceWindow, error) {
return nil, nil
}
func (m *mockStore) AddMaintenanceWindow(models.MaintenanceWindow) error { return nil }
func (m *mockStore) EndMaintenanceWindow(int) error { return nil }
func (m *mockStore) DeleteMaintenanceWindow(int) error { return nil }
func (m *mockStore) IsMonitorInMaintenance(int) (bool, error) { return false, nil }
func (m *mockStore) GetPreference(string) (string, error) { return "", nil }
func (m *mockStore) SetPreference(string, string) error { return nil }
func (m *mockStore) Close() error { return nil }
func (m *mockStore) AddMaintenanceWindow(models.MaintenanceWindow) error { return nil }
func (m *mockStore) EndMaintenanceWindow(int) error { return nil }
func (m *mockStore) DeleteMaintenanceWindow(int) error { return nil }
func (m *mockStore) IsMonitorInMaintenance(int) (bool, error) { return false, nil }
func (m *mockStore) GetPreference(string) (string, error) { return "", nil }
func (m *mockStore) SetPreference(string, string) error { return nil }
func (m *mockStore) SaveStateChange(int, string, string, string) error { return nil }
func (m *mockStore) GetStateChanges(int, int) ([]models.StateChange, error) { return nil, nil }
func (m *mockStore) Close() error { return nil }
func (m *mockStore) ExportData() (models.Backup, error) {
return models.Backup{