diff --git a/AppImage/components/health-status-modal.tsx b/AppImage/components/health-status-modal.tsx index 556f86dd..783f1d6d 100644 --- a/AppImage/components/health-status-modal.tsx +++ b/AppImage/components/health-status-modal.tsx @@ -38,15 +38,17 @@ interface CategoryCheck { [key: string]: any } -interface DismissedError { + interface DismissedError { error_key: string category: string severity: string reason: string dismissed: boolean + permanent?: boolean suppression_remaining_hours: number + suppression_hours?: number resolved_at: string -} + } interface HealthDetails { overall: string @@ -361,31 +363,33 @@ export function HealthStatusModal({ open, onOpenChange, getApiUrl }: HealthStatu return (
- {Object.entries(checks).map(([checkKey, checkData]) => { + {Object.entries(checks) + .filter(([, checkData]) => checkData.installed !== false) + .map(([checkKey, checkData]) => { const isDismissable = checkData.dismissable === true const checkStatus = checkData.status?.toUpperCase() || "OK" return (
-
+
{getStatusIcon(checkData.status, "sm")} {formatCheckLabel(checkKey)} {checkData.detail} {checkData.dismissed && ( - + Dismissed )}
-
+
{(checkStatus === "WARNING" || checkStatus === "CRITICAL") && isDismissable && !checkData.dismissed && ( @@ -414,21 +418,21 @@ export function HealthStatusModal({ open, onOpenChange, getApiUrl }: HealthStatu return ( - +
- - - System Health Status - {healthData &&
{getStatusBadge(healthData.overall)}
} + + + System Health Status + {healthData &&
{getStatusBadge(healthData.overall)}
}
- - Detailed health checks for all system components + + Detailed health checks for all system components {getTimeSinceCheck() && ( - Last check: {getTimeSinceCheck()} + {getTimeSinceCheck()} )} @@ -450,28 +454,28 @@ export function HealthStatusModal({ open, onOpenChange, getApiUrl }: HealthStatu {healthData && !loading && (
{/* Overall Stats Summary */} -
0 ? "grid-cols-5" : "grid-cols-4"}`}> +
0 ? "grid-cols-5" : "grid-cols-4"}`}>
-
{stats.total}
-
Total
+
{stats.total}
+
Total
-
{stats.healthy}
-
Healthy
+
{stats.healthy}
+
Healthy
{stats.info > 0 && (
-
{stats.info}
-
Info
+
{stats.info}
+
Info
)}
-
{stats.warnings}
-
Warnings
+
{stats.warnings}
+
Warn
-
{stats.critical}
-
Critical
+
{stats.critical}
+
Critical
@@ -498,32 +502,32 @@ export function HealthStatusModal({ open, onOpenChange, getApiUrl }: HealthStatu > {/* Clickable header row */}
toggleCategory(key)} > -
- +
+ {getStatusIcon(status)}
-
-

{label}

+
+

{label}

{hasChecks && ( - ({Object.keys(checks).length} checks) + ({Object.values(checks).filter(c => c.installed !== false).length}) )}
{reason && !isExpanded && ( -

{reason}

+

{reason}

)}
-
- +
+ {status} @@ -532,7 +536,7 @@ export function HealthStatusModal({ open, onOpenChange, getApiUrl }: HealthStatu {/* Expandable checks section */} {isExpanded && ( -
+
{reason && (

{reason}

)} @@ -554,41 +558,62 @@ export function HealthStatusModal({ open, onOpenChange, getApiUrl }: HealthStatu {/* Dismissed Items Section */} {dismissedItems.length > 0 && (
-
- +
+ Dismissed Items ({dismissedItems.length})
- {dismissedItems.map((item) => ( -
-
- - {getStatusIcon("INFO")} -
-
-
-

{item.reason}

-
- - Dismissed - - - was {item.severity} - -
+ {dismissedItems.map((item) => { + const catMeta = CATEGORIES.find(c => c.category === item.category || c.key === item.category) + const CatIcon = catMeta?.Icon || BellOff + const catLabel = catMeta?.label || item.category + const isPermanent = item.permanent || item.suppression_remaining_hours === -1 + + return ( +
+
+ +
+
+
+
+

{catLabel}

+

{item.reason}

+
+
+ {isPermanent ? ( + + Permanent + + ) : ( + + Dismissed + + )} + + was {item.severity} + +
+
+

+ + {isPermanent + ? "Permanently suppressed" + : `Suppressed for ${ + item.suppression_remaining_hours < 24 + ? `${Math.round(item.suppression_remaining_hours)}h` + : item.suppression_remaining_hours < 720 + ? `${Math.round(item.suppression_remaining_hours / 24)} days` + : `${Math.round(item.suppression_remaining_hours / 720)} month(s)` + } more` + } +

-

- - Suppressed for {item.suppression_remaining_hours < 24 - ? `${Math.round(item.suppression_remaining_hours)}h` - : `${Math.round(item.suppression_remaining_hours / 24)} days` - } more -

-
- ))} + ) + })}
)} diff --git a/AppImage/components/settings.tsx b/AppImage/components/settings.tsx index 73625767..764bfeb1 100644 --- a/AppImage/components/settings.tsx +++ b/AppImage/components/settings.tsx @@ -2,11 +2,44 @@ import { useState, useEffect } from "react" import { Card, CardContent, CardDescription, CardHeader, CardTitle } from "./ui/card" -import { Wrench, Package, Ruler } from "lucide-react" +import { Wrench, Package, Ruler, HeartPulse, Cpu, MemoryStick, HardDrive, CircleDot, Network, Server, Settings2, FileText, RefreshCw, Shield, AlertTriangle, Info, Loader2, Check } from "lucide-react" import { Select, SelectContent, SelectItem, SelectTrigger, SelectValue } from "./ui/select" +import { Input } from "./ui/input" +import { Badge } from "./ui/badge" import { getNetworkUnit } from "../lib/format-network" import { fetchApi } from "../lib/api-config" +interface SuppressionCategory { + key: string + label: string + category: string + icon: string + hours: number +} + +const SUPPRESSION_OPTIONS = [ + { value: "24", label: "24 hours" }, + { value: "72", label: "3 days" }, + { value: "168", label: "1 week" }, + { value: "720", label: "1 month" }, + { value: "8760", label: "1 year" }, + { value: "custom", label: "Custom" }, + { value: "-1", label: "Permanent" }, +] + +const CATEGORY_ICONS: Record = { + cpu: Cpu, + memory: MemoryStick, + storage: HardDrive, + disk: CircleDot, + network: Network, + vms: Server, + services: Settings2, + logs: FileText, + updates: RefreshCw, + security: Shield, +} + interface ProxMenuxTool { key: string name: string @@ -18,10 +51,18 @@ export function Settings() { const [loadingTools, setLoadingTools] = useState(true) const [networkUnitSettings, setNetworkUnitSettings] = useState<"Bytes" | "Bits">("Bytes") const [loadingUnitSettings, setLoadingUnitSettings] = useState(true) + + // Health Monitor suppression settings + const [suppressionCategories, setSuppressionCategories] = useState([]) + const [loadingHealth, setLoadingHealth] = useState(true) + const [savingHealth, setSavingHealth] = useState(null) + const [savedHealth, setSavedHealth] = useState(null) + const [customValues, setCustomValues] = useState>({}) useEffect(() => { loadProxmenuxTools() getUnitsSettings() + loadHealthSettings() }, []) const loadProxmenuxTools = async () => { @@ -57,6 +98,78 @@ export function Settings() { setLoadingUnitSettings(false) } + const loadHealthSettings = async () => { + try { + const data = await fetchApi("/api/health/settings") + if (data.categories) { + setSuppressionCategories(data.categories) + } + } catch (err) { + console.error("Failed to load health settings:", err) + } finally { + setLoadingHealth(false) + } + } + + const getSelectValue = (hours: number, key: string): string => { + if (hours === -1) return "-1" + const preset = SUPPRESSION_OPTIONS.find(o => o.value === String(hours)) + if (preset && preset.value !== "custom") return String(hours) + return "custom" + } + + const handleSuppressionChange = async (settingKey: string, value: string) => { + if (value === "custom") { + // Show custom input -- don't save yet + const current = suppressionCategories.find(c => c.key === settingKey) + setCustomValues(prev => ({ ...prev, [settingKey]: String(current?.hours || 48) })) + // Temporarily mark as custom in state + setSuppressionCategories(prev => + prev.map(c => c.key === settingKey ? { ...c, hours: -2 } : c) + ) + return + } + + const hours = parseInt(value, 10) + if (isNaN(hours)) return + + await saveSuppression(settingKey, hours) + } + + const handleCustomSave = async (settingKey: string) => { + const raw = customValues[settingKey] + const hours = parseInt(raw, 10) + if (isNaN(hours) || hours < 1) return + await saveSuppression(settingKey, hours) + } + + const saveSuppression = async (settingKey: string, hours: number) => { + setSavingHealth(settingKey) + try { + await fetchApi("/api/health/settings", { + method: "POST", + headers: { "Content-Type": "application/json" }, + body: JSON.stringify({ [settingKey]: String(hours) }), + }) + + setSuppressionCategories(prev => + prev.map(c => c.key === settingKey ? { ...c, hours } : c) + ) + // Remove from custom values + setCustomValues(prev => { + const next = { ...prev } + delete next[settingKey] + return next + }) + setSavedHealth(settingKey) + setTimeout(() => setSavedHealth(null), 2000) + } catch (err) { + console.error("Failed to save health setting:", err) + } finally { + setSavingHealth(null) + } + } + return (
@@ -95,6 +208,143 @@ export function Settings() { + {/* Health Monitor Settings */} + + +
+ + Health Monitor +
+ + Configure how long dismissed alerts stay suppressed for each category. + When you dismiss a warning, it will not reappear until the suppression period expires. + + + + {loadingHealth ? ( +
+
+
+ ) : ( +
+ {/* Header */} +
+ Category + Suppression Duration +
+ + {/* Per-category rows */} + {suppressionCategories.map((cat) => { + const IconComp = CATEGORY_ICONS[cat.icon] || HeartPulse + const isCustomMode = cat.hours === -2 || (cat.key in customValues) + const isPermanent = cat.hours === -1 + const isLong = cat.hours >= 720 && cat.hours !== -1 + const selectVal = isCustomMode ? "custom" : getSelectValue(cat.hours, cat.key) + + return ( +
+
+
+ + {cat.label} + {savingHealth === cat.key && ( + + )} + {savedHealth === cat.key && ( + + )} +
+
+ {isCustomMode ? ( +
+ setCustomValues(prev => ({ ...prev, [cat.key]: e.target.value }))} + placeholder="Hours" + /> + h + + +
+ ) : ( + + )} +
+
+ + {/* Warning for Permanent */} + {isPermanent && ( +
+ +

+ Dismissed alerts for {cat.label} will never reappear. + {cat.category === "temperature" && ( + + Note: Critical CPU temperature alerts will still trigger for hardware safety. + + )} +

+
+ )} + + {/* Warning for long custom duration (> 1 month) */} + {isLong && !isPermanent && ( +
+ +

+ Long suppression period. Dismissed alerts for this category will not reappear for an extended time. +

+
+ )} +
+ ) + })} + + {/* Info footer */} +
+ +

+ These settings apply when you dismiss a warning from the Health Monitor. + Critical CPU temperature alerts always trigger regardless of settings to protect your hardware. +

+
+
+ )} + + + {/* ProxMenux Optimizations */} diff --git a/AppImage/scripts/flask_health_routes.py b/AppImage/scripts/flask_health_routes.py index 34f1021b..81910850 100644 --- a/AppImage/scripts/flask_health_routes.py +++ b/AppImage/scripts/flask_health_routes.py @@ -89,14 +89,20 @@ def acknowledge_error(): health_monitor.last_check_times.pop('overall_health', None) health_monitor.cached_results.pop('overall_health', None) - # Determine suppression period for the response - category = result.get('category', '') - if category == 'updates': - suppression_hours = 180 * 24 # 180 days in hours - suppression_label = '6 months' + # Use the per-record suppression hours from acknowledge_error() + sup_hours = result.get('suppression_hours', 24) + if sup_hours == -1: + suppression_label = 'permanently' + elif sup_hours >= 8760: + suppression_label = f'{sup_hours // 8760} year(s)' + elif sup_hours >= 720: + suppression_label = f'{sup_hours // 720} month(s)' + elif sup_hours >= 168: + suppression_label = f'{sup_hours // 168} week(s)' + elif sup_hours >= 72: + suppression_label = f'{sup_hours // 24} day(s)' else: - suppression_hours = 24 - suppression_label = '24 hours' + suppression_label = f'{sup_hours} hours' return jsonify({ 'success': True, @@ -104,7 +110,7 @@ def acknowledge_error(): 'error_key': error_key, 'original_severity': result.get('original_severity', 'WARNING'), 'category': category, - 'suppression_hours': suppression_hours, + 'suppression_hours': sup_hours, 'suppression_label': suppression_label, 'acknowledged_at': result.get('acknowledged_at') }) @@ -190,3 +196,54 @@ def mark_events_notified(): return jsonify({'success': True, 'marked_count': len(event_ids)}) except Exception as e: return jsonify({'error': str(e)}), 500 + + +@health_bp.route('/api/health/settings', methods=['GET']) +def get_health_settings(): + """ + Get per-category suppression duration settings. + Returns all health categories with their current configured hours. + """ + try: + categories = health_persistence.get_suppression_categories() + return jsonify({'categories': categories}) + except Exception as e: + return jsonify({'error': str(e)}), 500 + + +@health_bp.route('/api/health/settings', methods=['POST']) +def save_health_settings(): + """ + Save per-category suppression duration settings. + Expects JSON body with key-value pairs like: {"suppress_cpu": "168", "suppress_memory": "-1"} + Valid values: 24, 72, 168, 720, 8760, -1 (permanent), or any positive integer for custom. + """ + try: + data = request.get_json() + if not data: + return jsonify({'error': 'No settings provided'}), 400 + + valid_keys = set(health_persistence.CATEGORY_SETTING_MAP.values()) + updated = [] + + for key, value in data.items(): + if key not in valid_keys: + continue + + try: + hours = int(value) + # Validate: must be -1 (permanent) or positive + if hours != -1 and hours < 1: + continue + health_persistence.set_setting(key, str(hours)) + updated.append(key) + except (ValueError, TypeError): + continue + + return jsonify({ + 'success': True, + 'updated': updated, + 'count': len(updated) + }) + except Exception as e: + return jsonify({'error': str(e)}), 500 diff --git a/AppImage/scripts/health_monitor.py b/AppImage/scripts/health_monitor.py index 0334cdd9..c90be6c4 100644 --- a/AppImage/scripts/health_monitor.py +++ b/AppImage/scripts/health_monitor.py @@ -2258,10 +2258,9 @@ class HealthMonitor: try: issues = [] checks = { - 'uptime': {'status': 'OK', 'detail': ''}, - 'certificates': {'status': 'OK', 'detail': ''}, - 'login_attempts': {'status': 'OK', 'detail': ''}, - 'fail2ban': {'status': 'OK', 'detail': 'Not installed'} + 'uptime': {'status': 'OK', 'detail': ''}, + 'certificates': {'status': 'OK', 'detail': ''}, + 'login_attempts': {'status': 'OK', 'detail': ''}, } # Sub-check 1: Uptime for potential kernel vulnerabilities @@ -2322,21 +2321,23 @@ class HealthMonitor: except Exception: checks['login_attempts'] = {'status': 'OK', 'detail': 'Unable to check login attempts'} - # Sub-check 4: Fail2Ban ban detection + # Sub-check 4: Fail2Ban ban detection (only show if installed) try: f2b = self._check_fail2ban_bans() - f2b_status = f2b.get('status', 'OK') - checks['fail2ban'] = { - 'status': f2b_status, - 'dismissable': True if f2b_status not in ['OK'] else False, - 'detail': f2b.get('detail', ''), - 'installed': f2b.get('installed', False), - 'banned_count': f2b.get('banned_count', 0) - } - if f2b.get('status') == 'WARNING': - issues.append(f2b.get('detail', 'Fail2Ban bans detected')) + if f2b.get('installed', False): + f2b_status = f2b.get('status', 'OK') + checks['fail2ban'] = { + 'status': f2b_status, + 'dismissable': True if f2b_status not in ['OK'] else False, + 'detail': f2b.get('detail', ''), + 'installed': True, + 'banned_count': f2b.get('banned_count', 0) + } + if f2b.get('status') == 'WARNING': + issues.append(f2b.get('detail', 'Fail2Ban bans detected')) + # If not installed, simply don't add it to checks except Exception: - checks['fail2ban'] = {'status': 'OK', 'detail': 'Unable to check Fail2Ban'} + pass # Determine overall security status if issues: diff --git a/AppImage/scripts/health_persistence.py b/AppImage/scripts/health_persistence.py index 259bb046..ba97f1fa 100644 --- a/AppImage/scripts/health_persistence.py +++ b/AppImage/scripts/health_persistence.py @@ -28,7 +28,23 @@ class HealthPersistence: VM_ERROR_RETENTION = 48 * 3600 # 48 hours LOG_ERROR_RETENTION = 24 * 3600 # 24 hours DISK_ERROR_RETENTION = 48 * 3600 # 48 hours - UPDATES_SUPPRESSION = 180 * 24 * 3600 # 180 days (6 months) + + # Default suppression: 24 hours (user can change per-category in settings) + DEFAULT_SUPPRESSION_HOURS = 24 + + # Mapping from error categories to settings keys + CATEGORY_SETTING_MAP = { + 'temperature': 'suppress_cpu', + 'memory': 'suppress_memory', + 'storage': 'suppress_storage', + 'disks': 'suppress_disks', + 'network': 'suppress_network', + 'vms': 'suppress_vms', + 'pve_services': 'suppress_pve_services', + 'logs': 'suppress_logs', + 'updates': 'suppress_updates', + 'security': 'suppress_security', + } def __init__(self): """Initialize persistence with database in shared ProxMenux data directory""" @@ -80,6 +96,21 @@ class HealthPersistence: ) ''') + # User settings table (per-category suppression durations, etc.) + cursor.execute(''' + CREATE TABLE IF NOT EXISTS user_settings ( + setting_key TEXT PRIMARY KEY, + setting_value TEXT NOT NULL, + updated_at TEXT NOT NULL + ) + ''') + + # Migration: add suppression_hours column to errors if not present + cursor.execute("PRAGMA table_info(errors)") + columns = [col[1] for col in cursor.fetchall()] + if 'suppression_hours' not in columns: + cursor.execute('ALTER TABLE errors ADD COLUMN suppression_hours INTEGER DEFAULT 24') + # Indexes for performance cursor.execute('CREATE INDEX IF NOT EXISTS idx_error_key ON errors(error_key)') cursor.execute('CREATE INDEX IF NOT EXISTS idx_category ON errors(category)') @@ -102,33 +133,8 @@ class HealthPersistence: details_json = json.dumps(details) if details else None cursor.execute(''' - SELECT acknowledged, resolved_at - FROM errors - WHERE error_key = ? AND acknowledged = 1 - ''', (error_key,)) - ack_check = cursor.fetchone() - - if ack_check and ack_check[1]: # Has resolved_at timestamp - try: - resolved_dt = datetime.fromisoformat(ack_check[1]) - hours_since_ack = (datetime.now() - resolved_dt).total_seconds() / 3600 - - if category == 'updates': - # Updates: suppress for 180 days (6 months) - suppression_hours = self.UPDATES_SUPPRESSION / 3600 - else: - # Other errors: suppress for 24 hours - suppression_hours = 24 - - if hours_since_ack < suppression_hours: - # Skip re-adding recently acknowledged errors - conn.close() - return {'type': 'skipped_acknowledged', 'needs_notification': False} - except Exception: - pass - - cursor.execute(''' - SELECT id, first_seen, notification_sent, acknowledged, resolved_at + SELECT id, acknowledged, resolved_at, category, severity, first_seen, + notification_sent, suppression_hours FROM errors WHERE error_key = ? ''', (error_key,)) existing = cursor.fetchone() @@ -136,13 +142,64 @@ class HealthPersistence: event_info = {'type': 'updated', 'needs_notification': False} if existing: - error_id, first_seen, notif_sent, acknowledged, resolved_at = existing + err_id, ack, resolved_at, old_cat, old_severity, first_seen, notif_sent, stored_suppression = existing - if acknowledged == 1: - conn.close() - return {'type': 'skipped_acknowledged', 'needs_notification': False} + if ack == 1: + # SAFETY OVERRIDE: Critical CPU temperature ALWAYS re-triggers + # regardless of any dismiss/permanent setting (hardware protection) + if error_key == 'cpu_temperature' and severity == 'CRITICAL': + cursor.execute('DELETE FROM errors WHERE error_key = ?', (error_key,)) + cursor.execute(''' + INSERT INTO errors + (error_key, category, severity, reason, details, first_seen, last_seen) + VALUES (?, ?, ?, ?, ?, ?, ?) + ''', (error_key, category, severity, reason, details_json, now, now)) + event_info = {'type': 'new', 'needs_notification': True} + self._record_event(cursor, 'new', error_key, + {'severity': severity, 'reason': reason, + 'note': 'CRITICAL temperature override - safety alert'}) + conn.commit() + conn.close() + return event_info + + # Check suppression: use per-record stored hours (set at dismiss time) + sup_hours = stored_suppression if stored_suppression is not None else self.DEFAULT_SUPPRESSION_HOURS + + # Permanent dismiss (sup_hours == -1): always suppress + if sup_hours == -1: + conn.close() + return {'type': 'skipped_acknowledged', 'needs_notification': False} + + # Time-limited suppression + still_suppressed = False + if resolved_at: + try: + resolved_dt = datetime.fromisoformat(resolved_at) + elapsed_hours = (datetime.now() - resolved_dt).total_seconds() / 3600 + still_suppressed = elapsed_hours < sup_hours + except Exception: + pass + + if still_suppressed: + conn.close() + return {'type': 'skipped_acknowledged', 'needs_notification': False} + else: + # Suppression expired - reset as a NEW event + cursor.execute('DELETE FROM errors WHERE error_key = ?', (error_key,)) + cursor.execute(''' + INSERT INTO errors + (error_key, category, severity, reason, details, first_seen, last_seen) + VALUES (?, ?, ?, ?, ?, ?, ?) + ''', (error_key, category, severity, reason, details_json, now, now)) + event_info = {'type': 'new', 'needs_notification': True} + self._record_event(cursor, 'new', error_key, + {'severity': severity, 'reason': reason, + 'note': 'Re-triggered after suppression expired'}) + conn.commit() + conn.close() + return event_info - # Update existing error (only if NOT acknowledged) + # Not acknowledged - update existing active error cursor.execute(''' UPDATE errors SET last_seen = ?, severity = ?, reason = ?, details = ? @@ -150,13 +207,9 @@ class HealthPersistence: ''', (now, severity, reason, details_json, error_key)) # Check if severity escalated - cursor.execute('SELECT severity FROM errors WHERE error_key = ?', (error_key,)) - old_severity_row = cursor.fetchone() - if old_severity_row: - old_severity = old_severity_row[0] - if old_severity == 'WARNING' and severity == 'CRITICAL': - event_info['type'] = 'escalated' - event_info['needs_notification'] = True + if old_severity == 'WARNING' and severity == 'CRITICAL': + event_info['type'] = 'escalated' + event_info['needs_notification'] = True else: # Insert new error cursor.execute(''' @@ -225,21 +278,40 @@ class HealthPersistence: """ Remove/resolve a specific error immediately. Used when the condition that caused the error no longer exists - (e.g., storage became available again). + (e.g., storage became available again, CPU temp recovered). + + For acknowledged errors: if the condition resolved on its own, + we delete the record entirely so it can re-trigger as a fresh + event if the condition returns later. """ conn = sqlite3.connect(str(self.db_path)) cursor = conn.cursor() now = datetime.now().isoformat() + # Check if this error was acknowledged (dismissed) cursor.execute(''' - UPDATE errors - SET resolved_at = ? - WHERE error_key = ? AND resolved_at IS NULL - ''', (now, error_key)) + SELECT acknowledged FROM errors WHERE error_key = ? + ''', (error_key,)) + row = cursor.fetchone() - if cursor.rowcount > 0: - self._record_event(cursor, 'cleared', error_key, {'reason': 'condition_resolved'}) + if row and row[0] == 1: + # Dismissed error that naturally resolved - delete entirely + # so it can re-trigger as a new event if it happens again + cursor.execute('DELETE FROM errors WHERE error_key = ?', (error_key,)) + if cursor.rowcount > 0: + self._record_event(cursor, 'cleared', error_key, + {'reason': 'condition_resolved_after_dismiss'}) + else: + # Normal active error - mark as resolved + cursor.execute(''' + UPDATE errors + SET resolved_at = ? + WHERE error_key = ? AND resolved_at IS NULL + ''', (now, error_key)) + + if cursor.rowcount > 0: + self._record_event(cursor, 'cleared', error_key, {'reason': 'condition_resolved'}) conn.commit() conn.close() @@ -247,13 +319,9 @@ class HealthPersistence: def acknowledge_error(self, error_key: str) -> Dict[str, Any]: """ Manually acknowledge an error (dismiss). + - Looks up the category's configured suppression duration from user settings + - Stores suppression_hours on the error record (snapshot at dismiss time) - Marks as acknowledged so it won't re-appear during the suppression period - - Stores the original severity for reference - - Returns info about the acknowledged error - - Suppression periods: - - updates category: 180 days (6 months) - - other categories: 24 hours """ conn = sqlite3.connect(str(self.db_path)) conn.row_factory = sqlite3.Row @@ -272,15 +340,27 @@ class HealthPersistence: original_severity = error_dict.get('severity', 'WARNING') category = error_dict.get('category', '') + # Look up the user's configured suppression for this category + setting_key = self.CATEGORY_SETTING_MAP.get(category, '') + sup_hours = self.DEFAULT_SUPPRESSION_HOURS + if setting_key: + stored = self.get_setting(setting_key) + if stored is not None: + try: + sup_hours = int(stored) + except (ValueError, TypeError): + pass + cursor.execute(''' UPDATE errors - SET acknowledged = 1, resolved_at = ? + SET acknowledged = 1, resolved_at = ?, suppression_hours = ? WHERE error_key = ? - ''', (now, error_key)) + ''', (now, sup_hours, error_key)) self._record_event(cursor, 'acknowledged', error_key, { 'original_severity': original_severity, - 'category': category + 'category': category, + 'suppression_hours': sup_hours }) result = { @@ -288,7 +368,8 @@ class HealthPersistence: 'error_key': error_key, 'original_severity': original_severity, 'category': category, - 'acknowledged_at': now + 'acknowledged_at': now, + 'suppression_hours': sup_hours } conn.commit() @@ -432,22 +513,30 @@ class HealthPersistence: except (json.JSONDecodeError, TypeError): pass - # Check if still within suppression period + # Check if still within suppression period using per-record hours try: resolved_dt = datetime.fromisoformat(error_dict['resolved_at']) - elapsed_seconds = (now - resolved_dt).total_seconds() + sup_hours = error_dict.get('suppression_hours') + if sup_hours is None: + sup_hours = self.DEFAULT_SUPPRESSION_HOURS - if error_dict.get('category') == 'updates': - suppression = self.UPDATES_SUPPRESSION - else: - suppression = 24 * 3600 # 24 hours + error_dict['dismissed'] = True - if elapsed_seconds < suppression: - error_dict['dismissed'] = True - error_dict['suppression_remaining_hours'] = round( - (suppression - elapsed_seconds) / 3600, 1 - ) + if sup_hours == -1: + # Permanent dismiss + error_dict['suppression_remaining_hours'] = -1 + error_dict['permanent'] = True dismissed.append(error_dict) + else: + elapsed_seconds = (now - resolved_dt).total_seconds() + suppression_seconds = sup_hours * 3600 + + if elapsed_seconds < suppression_seconds: + error_dict['suppression_remaining_hours'] = round( + (suppression_seconds - elapsed_seconds) / 3600, 1 + ) + error_dict['permanent'] = False + dismissed.append(error_dict) except (ValueError, TypeError): pass @@ -623,6 +712,79 @@ class HealthPersistence: # from Proxmox storage types in health_monitor.get_detailed_status() # This avoids redundant subprocess calls and ensures immediate detection # when the user adds new ZFS/LVM storage via Proxmox. + + # ─── User Settings ────────────────────────────────────────── + + def get_setting(self, key: str, default: Optional[str] = None) -> Optional[str]: + """Get a user setting value by key.""" + conn = sqlite3.connect(str(self.db_path)) + cursor = conn.cursor() + cursor.execute( + 'SELECT setting_value FROM user_settings WHERE setting_key = ?', (key,) + ) + row = cursor.fetchone() + conn.close() + return row[0] if row else default + + def set_setting(self, key: str, value: str): + """Store a user setting value.""" + conn = sqlite3.connect(str(self.db_path)) + cursor = conn.cursor() + cursor.execute(''' + INSERT OR REPLACE INTO user_settings (setting_key, setting_value, updated_at) + VALUES (?, ?, ?) + ''', (key, value, datetime.now().isoformat())) + conn.commit() + conn.close() + + def get_all_settings(self, prefix: Optional[str] = None) -> Dict[str, str]: + """Get all user settings, optionally filtered by key prefix.""" + conn = sqlite3.connect(str(self.db_path)) + cursor = conn.cursor() + if prefix: + cursor.execute( + 'SELECT setting_key, setting_value FROM user_settings WHERE setting_key LIKE ?', + (f'{prefix}%',) + ) + else: + cursor.execute('SELECT setting_key, setting_value FROM user_settings') + rows = cursor.fetchall() + conn.close() + return {row[0]: row[1] for row in rows} + + def get_suppression_categories(self) -> List[Dict[str, Any]]: + """ + Get all health categories with their current suppression settings. + Used by the settings page to render the per-category configuration. + """ + category_labels = { + 'suppress_cpu': {'label': 'CPU Usage & Temperature', 'category': 'temperature', 'icon': 'cpu'}, + 'suppress_memory': {'label': 'Memory & Swap', 'category': 'memory', 'icon': 'memory'}, + 'suppress_storage': {'label': 'Storage Mounts & Space', 'category': 'storage', 'icon': 'storage'}, + 'suppress_disks': {'label': 'Disk I/O & Errors', 'category': 'disks', 'icon': 'disk'}, + 'suppress_network': {'label': 'Network Interfaces', 'category': 'network', 'icon': 'network'}, + 'suppress_vms': {'label': 'VMs & Containers', 'category': 'vms', 'icon': 'vms'}, + 'suppress_pve_services': {'label': 'PVE Services', 'category': 'pve_services', 'icon': 'services'}, + 'suppress_logs': {'label': 'System Logs', 'category': 'logs', 'icon': 'logs'}, + 'suppress_updates': {'label': 'System Updates', 'category': 'updates', 'icon': 'updates'}, + 'suppress_security': {'label': 'Security & Certificates', 'category': 'security', 'icon': 'security'}, + } + + current_settings = self.get_all_settings('suppress_') + + result = [] + for key, meta in category_labels.items(): + stored = current_settings.get(key) + hours = int(stored) if stored else self.DEFAULT_SUPPRESSION_HOURS + result.append({ + 'key': key, + 'label': meta['label'], + 'category': meta['category'], + 'icon': meta['icon'], + 'hours': hours, + }) + + return result # Global instance