新增 AI 自動化 Grafana 儀表板
Some checks failed
CD Pipeline / deploy (push) Has been cancelled

This commit is contained in:
OoO
2026-04-30 00:06:24 +08:00
parent d5f4fd7198
commit 5a61c020e3
13 changed files with 866 additions and 15 deletions

View File

@@ -0,0 +1,779 @@
{
"annotations": {
"list": []
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": null,
"links": [
{
"icon": "external link",
"tags": [],
"targetBlank": true,
"title": "AI Automation Smoke Dashboard",
"tooltip": "App read-only smoke dashboard",
"type": "link",
"url": "/ai_automation_smoke"
}
],
"liveNow": false,
"panels": [
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 100,
"panels": [],
"title": "AI 自動化總覽",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"description": "最近 1 小時 EventRouter 接收並處理的事件量。",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 6,
"x": 0,
"y": 1
},
"id": 1,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"targets": [
{
"expr": "sum(increase(momo_ai_event_router_dispatch_total[1h]))",
"legendFormat": "dispatch / 1h",
"refId": "A"
}
],
"title": "EventRouter 1h 事件量",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"description": "最近 24 小時 L2 SAFE_ACTIONS 執行量,依 action/status 分組。",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 6,
"x": 6,
"y": 1
},
"id": 2,
"options": {
"displayMode": "gradient",
"maxVizHeight": 300,
"minVizHeight": 16,
"minVizWidth": 8,
"namePlacement": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showUnfilled": true,
"valueMode": "color"
},
"targets": [
{
"expr": "sum by (action, status) (increase(momo_ai_event_router_safe_action_total[24h]))",
"legendFormat": "{{action}} / {{status}}",
"refId": "A"
}
],
"title": "L2 Safe Action 24h",
"type": "bargauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"description": "最近 24 小時 Telegram queue replay 狀態。",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 6,
"x": 12,
"y": 1
},
"id": 3,
"options": {
"displayMode": "gradient",
"maxVizHeight": 300,
"minVizHeight": 16,
"minVizWidth": 8,
"namePlacement": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showUnfilled": true,
"valueMode": "color"
},
"targets": [
{
"expr": "sum by (status) (increase(momo_ai_event_router_replay_total[24h]))",
"legendFormat": "{{status}}",
"refId": "A"
}
],
"title": "Telegram Replay 24h",
"type": "bargauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"description": "最近 24 小時 AutoHeal 動作結果,依 action/error_type/result 分組。",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 6,
"x": 18,
"y": 1
},
"id": 4,
"options": {
"displayMode": "gradient",
"maxVizHeight": 300,
"minVizHeight": 16,
"minVizWidth": 8,
"namePlacement": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showUnfilled": true,
"valueMode": "color"
},
"targets": [
{
"expr": "sum by (action, error_type, result) (increase(momo_ai_autoheal_action_total[24h]))",
"legendFormat": "{{action}} / {{error_type}} / {{result}}",
"refId": "A"
}
],
"title": "AutoHeal Action 24h",
"type": "bargauge"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 6
},
"id": 101,
"panels": [],
"title": "EventRouter 路由與延遲",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"description": "EventRouter 每 5 分鐘新增 dispatch 數,依 outcome 分組。",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 15,
"gradientMode": "opacity",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "smooth",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 7
},
"id": 5,
"options": {
"legend": {
"calcs": [
"lastNotNull",
"sum"
],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"expr": "sum by (outcome) (increase(momo_ai_event_router_dispatch_total[5m]))",
"legendFormat": "{{outcome}}",
"refId": "A"
}
],
"title": "EventRouter Dispatch by Outcome",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"description": "EventRouter 平均延遲與最大延遲,依 tier/event_type 分組。",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "smooth",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 3000
},
{
"color": "red",
"value": 10000
}
]
},
"unit": "ms"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 7
},
"id": 6,
"options": {
"legend": {
"calcs": [
"mean",
"max"
],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"expr": "sum by (tier, event_type) (increase(momo_ai_event_router_latency_ms_sum[5m])) / clamp_min(sum by (tier, event_type) (increase(momo_ai_event_router_latency_ms_count[5m])), 1)",
"legendFormat": "avg {{tier}} / {{event_type}}",
"refId": "A"
},
{
"expr": "max by (tier, event_type) (momo_ai_event_router_latency_ms_max)",
"legendFormat": "max {{tier}} / {{event_type}}",
"refId": "B"
}
],
"title": "EventRouter Latency",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"description": "最近 1 小時 dispatch 明細表,方便追 L1/L2/L3 與事件類型。",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {
"align": "auto",
"cellOptions": {
"type": "auto"
},
"inspect": false
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 15
},
"id": 7,
"options": {
"cellHeight": "sm",
"footer": {
"countRows": false,
"enablePagination": true,
"fields": "",
"reducer": [
"sum"
],
"show": false
},
"showHeader": true
},
"targets": [
{
"expr": "sum by (tier, event_type, outcome) (increase(momo_ai_event_router_dispatch_total[1h]))",
"format": "table",
"instant": true,
"legendFormat": "{{tier}} / {{event_type}} / {{outcome}}",
"refId": "A"
}
],
"title": "EventRouter 1h 明細",
"type": "table"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 23
},
"id": 102,
"panels": [],
"title": "AutoHeal 自癒觀測",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"description": "AutoHeal 每 5 分鐘平均耗時與最大耗時。",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "smooth",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 3000
},
{
"color": "red",
"value": 10000
}
]
},
"unit": "ms"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 24
},
"id": 8,
"options": {
"legend": {
"calcs": [
"mean",
"max"
],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"expr": "sum by (action, error_type) (increase(momo_ai_autoheal_duration_ms_sum[5m])) / clamp_min(sum by (action, error_type) (increase(momo_ai_autoheal_duration_ms_count[5m])), 1)",
"legendFormat": "avg {{action}} / {{error_type}}",
"refId": "A"
},
{
"expr": "max by (action, error_type) (momo_ai_autoheal_duration_ms_max)",
"legendFormat": "max {{action}} / {{error_type}}",
"refId": "B"
}
],
"title": "AutoHeal Duration",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"description": "AutoHeal 最近 24 小時 action 明細表,確認是否有高風險類型集中。",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {
"align": "auto",
"cellOptions": {
"type": "auto"
},
"inspect": false
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 24
},
"id": 9,
"options": {
"cellHeight": "sm",
"footer": {
"countRows": false,
"enablePagination": true,
"fields": "",
"reducer": [
"sum"
],
"show": false
},
"showHeader": true
},
"targets": [
{
"expr": "sum by (action, error_type, result) (increase(momo_ai_autoheal_action_total[24h]))",
"format": "table",
"instant": true,
"legendFormat": "{{action}} / {{error_type}} / {{result}}",
"refId": "A"
}
],
"title": "AutoHeal 24h 明細",
"type": "table"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 32
},
"id": 103,
"panels": [],
"title": "操作說明",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 24,
"x": 0,
"y": 33
},
"id": 10,
"options": {
"code": {
"language": "plaintext",
"showLineNumbers": false,
"showMiniMap": false
},
"content": "資料來源momo-app /metrics。此 dashboard 只讀 Prometheus不觸發 AutoHeal、不清理 queue、不碰 momo-db。Smoke 狀態仍以 /ai_automation_smoke 與 /api/ai-automation/smoke 為準Grafana 用來觀察 dispatch、latency、safe action、replay、AutoHeal 趨勢。",
"mode": "markdown"
},
"pluginVersion": "10.0.0",
"title": "AI 自動化觀測邊界",
"type": "text"
}
],
"refresh": "30s",
"schemaVersion": 38,
"tags": [
"momo",
"ai-automation",
"event-router",
"autoheal"
],
"templating": {
"list": []
},
"time": {
"from": "now-6h",
"to": "now"
},
"timepicker": {},
"timezone": "Asia/Taipei",
"title": "MOMO AI Automation Overview",
"uid": "momo-ai-automation-overview",
"version": 1,
"weekStart": ""
}

View File

@@ -71,9 +71,7 @@ scrape_configs:
# ===========================================================================
# ---------------------------------------------------------------------------
# Momo Flask 應用 - 資料庫應用指標
# ---------------------------------------------------------------------------
# Momo Flask 應用 - 健康檢查 (應用未提供 /metrics改用 /health)
# Momo Flask 應用 - 資料庫應用與 AI 自動化指標
# ---------------------------------------------------------------------------
- job_name: 'momo-app'
static_configs: