AIDomesticCoreAIJ/MONITORING_CONFIG.json at main · Katya-AI-Systems-LLC/AIDomesticCoreAIJ · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
{
  "monitoring_alerts": [
    {
      "name": "high_cpu_utilization",
      "description": "Alert when CPU utilization exceeds 85%",
      "metric": "system.cpu.utilization",
      "condition": "avg() > 0.85",
      "duration": "5m",
      "severity": "warning",
      "actions": [
        "send_slack_notification",
        "auto_scale_up",
        "create_incident"
      ],
      "notification": {
        "slack": "#alerts",
        "email": ["ops@company.com"],
        "pagerduty": "service-key"
      }
    },
    {
      "name": "high_memory_utilization",
      "description": "Alert when memory utilization exceeds 90%",
      "metric": "system.memory.utilization",
      "condition": "avg() > 0.90",
      "duration": "3m",
      "severity": "critical",
      "actions": [
        "send_slack_notification",
        "create_incident",
        "page_on_call"
      ]
    },
    {
      "name": "database_slow_queries",
      "description": "Alert when slow queries exceed 100 per minute",
      "metric": "db.slow_queries",
      "condition": "sum() > 100",
      "duration": "2m",
      "severity": "warning",
      "actions": [
        "send_slack_notification",
        "run_query_analysis"
      ]
    },
    {
      "name": "api_error_rate_high",
      "description": "Alert when error rate exceeds 5%",
      "metric": "http.request.error_rate",
      "condition": "avg() > 0.05",
      "duration": "1m",
      "severity": "critical",
      "actions": [
        "send_slack_notification",
        "page_on_call",
        "create_incident"
      ]
    },
    {
      "name": "redis_connection_pool_exhausted",
      "description": "Alert when Redis connection pool is nearly exhausted",
      "metric": "redis.connections.used",
      "condition": "avg() > 95",
      "duration": "1m",
      "severity": "critical",
      "actions": [
        "send_slack_notification",
        "auto_restart_service",
        "page_on_call"
      ]
    },
    {
      "name": "disk_space_low",
      "description": "Alert when disk space is below 10%",
      "metric": "system.disk.free_percent",
      "condition": "avg() < 0.10",
      "duration": "5m",
      "severity": "warning",
      "actions": [
        "send_slack_notification",
        "cleanup_logs"
      ]
    },
    {
      "name": "quantum_circuit_timeout",
      "description": "Alert when quantum circuits timeout",
      "metric": "quantum.circuit.timeout_count",
      "condition": "sum() > 5",
      "duration": "5m",
      "severity": "warning",
      "actions": [
        "send_slack_notification",
        "review_circuit_params"
      ]
    },
    {
      "name": "vision_processing_latency",
      "description": "Alert when vision processing latency exceeds 5 seconds",
      "metric": "vision.processing.latency_p99",
      "condition": "avg() > 5000",
      "duration": "3m",
      "severity": "warning",
      "actions": [
        "send_slack_notification",
        "analyze_gpu_usage"
      ]
    }
  ],
  "dashboards": [
    {
      "name": "System Overview",
      "description": "High-level system health and performance",
      "panels": [
        {
          "id": "cpu_utilization",
          "title": "CPU Utilization",
          "metric": "system.cpu.utilization",
          "type": "timeseries",
          "threshold": 0.85
        },
        {
          "id": "memory_utilization",
          "title": "Memory Utilization",
          "metric": "system.memory.utilization",
          "type": "gauge",
          "threshold": 0.90
        },
        {
          "id": "disk_utilization",
          "title": "Disk Utilization",
          "metric": "system.disk.utilization",
          "type": "timeseries"
        },
        {
          "id": "network_throughput",
          "title": "Network Throughput",
          "metric": "system.network.throughput",
          "type": "timeseries"
        }
      ]
    },
    {
      "name": "API Performance",
      "description": "API latency and error rates",
      "panels": [
        {
          "id": "request_latency",
          "title": "Request Latency (p50/p95/p99)",
          "metric": "http.request.duration",
          "type": "timeseries"
        },
        {
          "id": "error_rate",
          "title": "Error Rate",
          "metric": "http.request.error_rate",
          "type": "timeseries",
          "threshold": 0.05
        },
        {
          "id": "throughput",
          "title": "Requests per Second",
          "metric": "http.request.count",
          "type": "timeseries"
        }
      ]
    },
    {
      "name": "Database Performance",
      "description": "Database query metrics",
      "panels": [
        {
          "id": "query_latency",
          "title": "Query Latency (p50/p95/p99)",
          "metric": "db.query.duration",
          "type": "timeseries"
        },
        {
          "id": "slow_queries",
          "title": "Slow Queries",
          "metric": "db.slow_queries",
          "type": "timeseries"
        },
        {
          "id": "connection_count",
          "title": "Active Connections",
          "metric": "db.connections.active",
          "type": "gauge"
        }
      ]
    }
  ],
  "slo_targets": [
    {
      "name": "api_availability",
      "description": "API availability",
      "target": 0.9999,
      "measurement_window_days": 30,
      "alert_threshold": 0.9995
    },
    {
      "name": "api_latency_p99",
      "description": "API latency 99th percentile",
      "target": 500,
      "unit": "ms",
      "measurement_window_days": 30,
      "alert_threshold": 750
    },
    {
      "name": "data_freshness",
      "description": "Data is fresh within 5 minutes",
      "target": 0.99,
      "measurement_window_days": 30,
      "alert_threshold": 0.98
    }
  ]
}