- {getStatusIcon(checkData.status, "sm")}
+
+ {getStatusIcon(checkData.status, "sm")}
{formatCheckLabel(checkKey)}
- {checkData.detail}
+ {checkData.detail}
{checkData.dismissed && (
Dismissed
@@ -520,8 +520,8 @@ export function HealthStatusModal({ open, onOpenChange, getApiUrl }: HealthStatu
{healthData.summary && healthData.summary !== "All systems operational" && (
-
-
{healthData.summary}
+
)}
@@ -559,7 +559,7 @@ export function HealthStatusModal({ open, onOpenChange, getApiUrl }: HealthStatu
)}
{reason && !isExpanded && (
-
{reason}
+
{reason}
)}
@@ -578,7 +578,7 @@ export function HealthStatusModal({ open, onOpenChange, getApiUrl }: HealthStatu
{isExpanded && (
{reason && (
-
{reason}
+
{reason}
)}
{hasChecks ? (
renderChecks(checks, key)
diff --git a/AppImage/components/storage-overview.tsx b/AppImage/components/storage-overview.tsx
index a9a4cf79..648993b9 100644
--- a/AppImage/components/storage-overview.tsx
+++ b/AppImage/components/storage-overview.tsx
@@ -34,6 +34,12 @@ interface DiskInfo {
wear_leveling_count?: number // SSD: Wear Leveling Count
total_lbas_written?: number // SSD/NVMe: Total LBAs Written (GB)
ssd_life_left?: number // SSD: SSD Life Left percentage
+ io_errors?: {
+ count: number
+ severity: string
+ sample: string
+ reason: string
+ }
}
interface ZFSPool {
@@ -776,6 +782,17 @@ export function StorageOverview() {
{disk.size_formatted && (
diff --git a/AppImage/scripts/health_monitor.py b/AppImage/scripts/health_monitor.py
index 4e8a3c48..97966d5d 100644
--- a/AppImage/scripts/health_monitor.py
+++ b/AppImage/scripts/health_monitor.py
@@ -324,7 +324,8 @@ class HealthMonitor:
Returns JSON structure with ALL 10 categories always present.
Now includes persistent error tracking.
"""
- # Run cleanup on every status check to auto-resolve stale errors
+ # Run cleanup on every status check so stale errors are auto-resolved
+ # using the user-configured Suppression Duration (single source of truth).
try:
health_persistence.cleanup_old_errors()
except Exception:
@@ -2157,18 +2158,18 @@ class HealthMonitor:
# Get a representative critical error reason
representative_error = next(iter(critical_errors_found.values()))
reason = f'Critical error detected: {representative_error[:100]}'
- elif cascade_count > 0:
- status = 'WARNING'
- samples = _get_samples(cascading_errors, 3)
- reason = f'Error cascade ({cascade_count} patterns repeating):\n' + '\n'.join(f' - {s}' for s in samples)
- elif spike_count > 0:
- status = 'WARNING'
- samples = _get_samples(spike_errors, 3)
- reason = f'Error spike ({spike_count} patterns with 4x increase):\n' + '\n'.join(f' - {s}' for s in samples)
- elif persistent_count > 0:
- status = 'WARNING'
- samples = _get_samples(persistent_errors, 3)
- reason = f'Persistent errors ({persistent_count} patterns over 15+ min):\n' + '\n'.join(f' - {s}' for s in samples)
+ elif cascade_count > 0:
+ status = 'WARNING'
+ samples = _get_samples(cascading_errors, 3)
+ reason = f'Error cascade ({cascade_count} patterns repeating):\n' + '\n'.join(f' - {s}' for s in samples)
+ elif spike_count > 0:
+ status = 'WARNING'
+ samples = _get_samples(spike_errors, 3)
+ reason = f'Error spike ({spike_count} patterns with 4x increase):\n' + '\n'.join(f' - {s}' for s in samples)
+ elif persistent_count > 0:
+ status = 'WARNING'
+ samples = _get_samples(persistent_errors, 3)
+ reason = f'Persistent errors ({persistent_count} patterns over 15+ min):\n' + '\n'.join(f' - {s}' for s in samples)
else:
# No significant issues found
status = 'OK'
@@ -2189,23 +2190,23 @@ class HealthMonitor:
'log_critical_errors': {'active': unique_critical_count > 0, 'severity': 'CRITICAL',
'reason': f'{unique_critical_count} critical error(s) found', 'dismissable': False},
}
-
- # Track which sub-checks were dismissed
- dismissed_keys = set()
- for err_key, info in log_sub_checks.items():
- if info['active']:
- is_dismissable = info.get('dismissable', True)
- result = health_persistence.record_error(
- error_key=err_key,
- category='logs',
- severity=info['severity'],
- reason=info['reason'],
- details={'dismissable': is_dismissable}
- )
- if result and result.get('type') == 'skipped_acknowledged':
- dismissed_keys.add(err_key)
- elif health_persistence.is_error_active(err_key):
- health_persistence.clear_error(err_key)
+
+ # Track which sub-checks were dismissed
+ dismissed_keys = set()
+ for err_key, info in log_sub_checks.items():
+ if info['active']:
+ is_dismissable = info.get('dismissable', True)
+ result = health_persistence.record_error(
+ error_key=err_key,
+ category='logs',
+ severity=info['severity'],
+ reason=info['reason'],
+ details={'dismissable': is_dismissable}
+ )
+ if result and result.get('type') == 'skipped_acknowledged':
+ dismissed_keys.add(err_key)
+ elif health_persistence.is_error_active(err_key):
+ health_persistence.clear_error(err_key)
# Build checks dict - downgrade dismissed items to INFO
def _log_check_status(key, active, severity):
diff --git a/AppImage/scripts/health_persistence.py b/AppImage/scripts/health_persistence.py
index 53ebe257..fede9b53 100644
--- a/AppImage/scripts/health_persistence.py
+++ b/AppImage/scripts/health_persistence.py
@@ -26,7 +26,7 @@ class HealthPersistence:
"""Manages persistent health error tracking"""
# Default suppression duration when no user setting exists for a category.
- # Users can override per-category via the Suppression Duration settings.
+ # Users override per-category via the Suppression Duration settings UI.
DEFAULT_SUPPRESSION_HOURS = 24
# Mapping from error categories to settings keys
@@ -498,13 +498,16 @@ class HealthPersistence:
cutoff_resolved = (now - timedelta(days=7)).isoformat()
cursor.execute('DELETE FROM errors WHERE resolved_at < ?', (cutoff_resolved,))
- # ── Auto-resolve stale errors using user-configured Suppression Duration ──
- # Read the per-category suppression hours from user_settings.
- # If the user hasn't configured a category, fall back to DEFAULT_SUPPRESSION_HOURS.
+ # ── Auto-resolve stale errors using Suppression Duration settings ──
+ # Read per-category suppression hours from user_settings.
+ # If the user hasn't configured a value, use DEFAULT_SUPPRESSION_HOURS.
# This is the SINGLE source of truth for auto-resolution timing.
user_settings = {}
try:
- cursor.execute('SELECT setting_key, setting_value FROM user_settings WHERE setting_key LIKE ?', ('suppress_%',))
+ cursor.execute(
+ 'SELECT setting_key, setting_value FROM user_settings WHERE setting_key LIKE ?',
+ ('suppress_%',)
+ )
for row in cursor.fetchall():
user_settings[row[0]] = row[1]
except Exception:
@@ -517,6 +520,10 @@ class HealthPersistence:
except (ValueError, TypeError):
hours = self.DEFAULT_SUPPRESSION_HOURS
+ # -1 means permanently suppressed -- skip auto-resolve
+ if hours < 0:
+ continue
+
cutoff = (now - timedelta(hours=hours)).isoformat()
cursor.execute('''
UPDATE errors
@@ -527,7 +534,7 @@ class HealthPersistence:
AND acknowledged = 0
''', (now_iso, category, cutoff))
- # Catch-all: auto-resolve ANY error from an unmapped category
+ # Catch-all: auto-resolve any error from an unmapped category
# whose last_seen exceeds DEFAULT_SUPPRESSION_HOURS.
fallback_cutoff = (now - timedelta(hours=self.DEFAULT_SUPPRESSION_HOURS)).isoformat()
cursor.execute('''