up

deploy/telemetry/alerts/export-center-alerts.yaml

@@ -0,0 +1,164 @@
+# ExportCenter Alert Rules
+# SLO Burn-rate alerts for export service reliability
+
+groups:
+  - name: export-center-slo
+    interval: 30s
+    rules:
+      # SLO: 99.5% success rate target
+      # Error budget: 0.5% (432 errors per day at 86400 requests/day)
+
+      # Fast burn - 2% budget consumption in 1 hour (critical)
+      - alert: ExportCenterHighErrorBurnRate
+        expr: |
+          (
+            sum(rate(export_runs_failed_total[1h]))
+            /
+            sum(rate(export_runs_total[1h]))
+          ) > (14.4 * 0.005)
+        for: 2m
+        labels:
+          severity: critical
+          service: export-center
+          slo: availability
+        annotations:
+          summary: "ExportCenter high error burn rate"
+          description: "Error rate is {{ $value | humanizePercentage }} over the last hour, consuming error budget at 14.4x the sustainable rate."
+          runbook_url: "https://docs.stellaops.io/runbooks/export-center/high-error-rate"
+
+      # Slow burn - 10% budget consumption in 6 hours (warning)
+      - alert: ExportCenterElevatedErrorBurnRate
+        expr: |
+          (
+            sum(rate(export_runs_failed_total[6h]))
+            /
+            sum(rate(export_runs_total[6h]))
+          ) > (6 * 0.005)
+        for: 5m
+        labels:
+          severity: warning
+          service: export-center
+          slo: availability
+        annotations:
+          summary: "ExportCenter elevated error burn rate"
+          description: "Error rate is {{ $value | humanizePercentage }} over the last 6 hours, consuming error budget at 6x the sustainable rate."
+          runbook_url: "https://docs.stellaops.io/runbooks/export-center/elevated-error-rate"
+
+  - name: export-center-latency
+    interval: 30s
+    rules:
+      # SLO: 95% of exports complete within 120s
+      # Fast burn - p95 latency exceeding threshold
+      - alert: ExportCenterHighLatency
+        expr: |
+          histogram_quantile(0.95,
+            sum(rate(export_run_duration_seconds_bucket[5m])) by (le)
+          ) > 120
+        for: 5m
+        labels:
+          severity: warning
+          service: export-center
+          slo: latency
+        annotations:
+          summary: "ExportCenter high latency"
+          description: "95th percentile export duration is {{ $value | humanizeDuration }}, exceeding 120s SLO target."
+          runbook_url: "https://docs.stellaops.io/runbooks/export-center/high-latency"
+
+      # Critical latency - p99 exceeding 5 minutes
+      - alert: ExportCenterCriticalLatency
+        expr: |
+          histogram_quantile(0.99,
+            sum(rate(export_run_duration_seconds_bucket[5m])) by (le)
+          ) > 300
+        for: 2m
+        labels:
+          severity: critical
+          service: export-center
+          slo: latency
+        annotations:
+          summary: "ExportCenter critical latency"
+          description: "99th percentile export duration is {{ $value | humanizeDuration }}, indicating severe performance degradation."
+          runbook_url: "https://docs.stellaops.io/runbooks/export-center/critical-latency"
+
+  - name: export-center-capacity
+    interval: 60s
+    rules:
+      # Queue buildup warning
+      - alert: ExportCenterHighConcurrency
+        expr: sum(export_runs_in_progress) > 50
+        for: 5m
+        labels:
+          severity: warning
+          service: export-center
+        annotations:
+          summary: "ExportCenter high concurrency"
+          description: "{{ $value }} exports currently in progress. Consider scaling or investigating slow exports."
+          runbook_url: "https://docs.stellaops.io/runbooks/export-center/high-concurrency"
+
+      # Stuck exports - exports running longer than 30 minutes
+      - alert: ExportCenterStuckExports
+        expr: |
+          histogram_quantile(0.99,
+            sum(rate(export_run_duration_seconds_bucket{status!="completed"}[1h])) by (le)
+          ) > 1800
+        for: 10m
+        labels:
+          severity: warning
+          service: export-center
+        annotations:
+          summary: "ExportCenter potentially stuck exports"
+          description: "Some exports may be stuck - 99th percentile duration for incomplete exports exceeds 30 minutes."
+          runbook_url: "https://docs.stellaops.io/runbooks/export-center/stuck-exports"
+
+  - name: export-center-errors
+    interval: 30s
+    rules:
+      # Specific error code spike
+      - alert: ExportCenterErrorCodeSpike
+        expr: |
+          sum by (error_code) (
+            rate(export_runs_failed_total[5m])
+          ) > 0.1
+        for: 5m
+        labels:
+          severity: warning
+          service: export-center
+        annotations:
+          summary: "ExportCenter error code spike: {{ $labels.error_code }}"
+          description: "Error code {{ $labels.error_code }} is occurring at {{ $value | humanize }}/s rate."
+          runbook_url: "https://docs.stellaops.io/runbooks/export-center/error-codes"
+
+      # No successful exports in 15 minutes (when there is traffic)
+      - alert: ExportCenterNoSuccessfulExports
+        expr: |
+          (
+            sum(rate(export_runs_total[15m])) > 0
+          )
+          and
+          (
+            sum(rate(export_runs_success_total[15m])) == 0
+          )
+        for: 10m
+        labels:
+          severity: critical
+          service: export-center
+        annotations:
+          summary: "ExportCenter no successful exports"
+          description: "No exports have completed successfully in the last 15 minutes despite ongoing attempts."
+          runbook_url: "https://docs.stellaops.io/runbooks/export-center/no-successful-exports"
+
+  - name: export-center-deprecation
+    interval: 5m
+    rules:
+      # Deprecated endpoint usage
+      - alert: ExportCenterDeprecatedEndpointUsage
+        expr: |
+          sum(rate(export_center_deprecated_endpoint_access_total[1h])) > 0
+        for: 1h
+        labels:
+          severity: info
+          service: export-center
+        annotations:
+          summary: "Deprecated export endpoints still in use"
+          description: "Legacy /exports endpoints are still being accessed at {{ $value | humanize }}/s. Migration to v1 API recommended."
+          runbook_url: "https://docs.stellaops.io/api/export-center/migration"

deploy/telemetry/dashboards/export-center.json

@@ -0,0 +1,638 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": { "type": "grafana", "uid": "-- Grafana --" },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "description": "ExportCenter service observability dashboard",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "liveNow": false,
+  "panels": [
+    {
+      "collapsed": false,
+      "gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
+      "id": 1,
+      "panels": [],
+      "title": "Export Runs Overview",
+      "type": "row"
+    },
+    {
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "thresholds" },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              { "color": "green", "value": null }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": { "h": 4, "w": 4, "x": 0, "y": 1 },
+      "id": 2,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": ["lastNotNull"],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "pluginVersion": "10.0.0",
+      "targets": [
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "editorMode": "code",
+          "expr": "sum(increase(export_runs_total{tenant=~\"$tenant\"}[$__range]))",
+          "legendFormat": "Total Runs",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Total Export Runs",
+      "type": "stat"
+    },
+    {
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "thresholds" },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              { "color": "green", "value": null }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": { "h": 4, "w": 4, "x": 4, "y": 1 },
+      "id": 3,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": ["lastNotNull"],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "pluginVersion": "10.0.0",
+      "targets": [
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "editorMode": "code",
+          "expr": "sum(increase(export_runs_success_total{tenant=~\"$tenant\"}[$__range]))",
+          "legendFormat": "Successful",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Successful Runs",
+      "type": "stat"
+    },
+    {
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "thresholds" },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "yellow", "value": 1 },
+              { "color": "red", "value": 5 }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": { "h": 4, "w": 4, "x": 8, "y": 1 },
+      "id": 4,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": ["lastNotNull"],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "pluginVersion": "10.0.0",
+      "targets": [
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "editorMode": "code",
+          "expr": "sum(increase(export_runs_failed_total{tenant=~\"$tenant\"}[$__range]))",
+          "legendFormat": "Failed",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Failed Runs",
+      "type": "stat"
+    },
+    {
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "thresholds" },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              { "color": "red", "value": null },
+              { "color": "yellow", "value": 95 },
+              { "color": "green", "value": 99 }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": { "h": 4, "w": 4, "x": 12, "y": 1 },
+      "id": 5,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": ["lastNotNull"],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "pluginVersion": "10.0.0",
+      "targets": [
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "editorMode": "code",
+          "expr": "100 * sum(increase(export_runs_success_total{tenant=~\"$tenant\"}[$__range])) / sum(increase(export_runs_total{tenant=~\"$tenant\"}[$__range]))",
+          "legendFormat": "Success Rate",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Success Rate",
+      "type": "stat"
+    },
+    {
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "thresholds" },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              { "color": "green", "value": null }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": { "h": 4, "w": 4, "x": 16, "y": 1 },
+      "id": 6,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": ["lastNotNull"],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "pluginVersion": "10.0.0",
+      "targets": [
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "editorMode": "code",
+          "expr": "sum(export_runs_in_progress{tenant=~\"$tenant\"})",
+          "legendFormat": "In Progress",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Runs In Progress",
+      "type": "stat"
+    },
+    {
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "palette-classic" },
+          "custom": {
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": { "legend": false, "tooltip": false, "viz": false },
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": { "type": "linear" },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": { "group": "A", "mode": "none" },
+            "thresholdsStyle": { "mode": "off" }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [{ "color": "green", "value": null }]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 5 },
+      "id": 7,
+      "options": {
+        "legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "bottom", "showLegend": true },
+        "tooltip": { "mode": "multi", "sort": "desc" }
+      },
+      "targets": [
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "editorMode": "code",
+          "expr": "sum by (export_type) (rate(export_runs_total{tenant=~\"$tenant\"}[5m]))",
+          "legendFormat": "{{export_type}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Export Runs by Type (rate/5m)",
+      "type": "timeseries"
+    },
+    {
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "palette-classic" },
+          "custom": {
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": { "legend": false, "tooltip": false, "viz": false },
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": { "type": "linear" },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": { "group": "A", "mode": "none" },
+            "thresholdsStyle": { "mode": "off" }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [{ "color": "green", "value": null }]
+          },
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 5 },
+      "id": 8,
+      "options": {
+        "legend": { "calcs": ["mean", "max", "p95"], "displayMode": "table", "placement": "bottom", "showLegend": true },
+        "tooltip": { "mode": "multi", "sort": "desc" }
+      },
+      "targets": [
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.50, sum by (le) (rate(export_run_duration_seconds_bucket{tenant=~\"$tenant\"}[5m])))",
+          "legendFormat": "p50",
+          "range": true,
+          "refId": "A"
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(export_run_duration_seconds_bucket{tenant=~\"$tenant\"}[5m])))",
+          "legendFormat": "p95",
+          "range": true,
+          "refId": "B"
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.99, sum by (le) (rate(export_run_duration_seconds_bucket{tenant=~\"$tenant\"}[5m])))",
+          "legendFormat": "p99",
+          "range": true,
+          "refId": "C"
+        }
+      ],
+      "title": "Export Run Duration (latency percentiles)",
+      "type": "timeseries"
+    },
+    {
+      "collapsed": false,
+      "gridPos": { "h": 1, "w": 24, "x": 0, "y": 13 },
+      "id": 9,
+      "panels": [],
+      "title": "Artifacts & Bundle Sizes",
+      "type": "row"
+    },
+    {
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "palette-classic" },
+          "custom": {
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "bars",
+            "fillOpacity": 50,
+            "gradientMode": "none",
+            "hideFrom": { "legend": false, "tooltip": false, "viz": false },
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "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": 14 },
+      "id": 10,
+      "options": {
+        "legend": { "calcs": ["sum"], "displayMode": "table", "placement": "bottom", "showLegend": true },
+        "tooltip": { "mode": "multi", "sort": "desc" }
+      },
+      "targets": [
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "editorMode": "code",
+          "expr": "sum by (artifact_type) (increase(export_artifacts_total{tenant=~\"$tenant\"}[1h]))",
+          "legendFormat": "{{artifact_type}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Artifacts Exported by Type (per hour)",
+      "type": "timeseries"
+    },
+    {
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "palette-classic" },
+          "custom": {
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": { "legend": false, "tooltip": false, "viz": false },
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": { "type": "linear" },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": { "group": "A", "mode": "none" },
+            "thresholdsStyle": { "mode": "off" }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [{ "color": "green", "value": null }]
+          },
+          "unit": "bytes"
+        },
+        "overrides": []
+      },
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 14 },
+      "id": 11,
+      "options": {
+        "legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "bottom", "showLegend": true },
+        "tooltip": { "mode": "multi", "sort": "desc" }
+      },
+      "targets": [
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.50, sum by (le, export_type) (rate(export_bundle_size_bytes_bucket{tenant=~\"$tenant\"}[5m])))",
+          "legendFormat": "{{export_type}} p50",
+          "range": true,
+          "refId": "A"
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.95, sum by (le, export_type) (rate(export_bundle_size_bytes_bucket{tenant=~\"$tenant\"}[5m])))",
+          "legendFormat": "{{export_type}} p95",
+          "range": true,
+          "refId": "B"
+        }
+      ],
+      "title": "Bundle Size Distribution by Type",
+      "type": "timeseries"
+    },
+    {
+      "collapsed": false,
+      "gridPos": { "h": 1, "w": 24, "x": 0, "y": 22 },
+      "id": 12,
+      "panels": [],
+      "title": "Error Analysis",
+      "type": "row"
+    },
+    {
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "palette-classic" },
+          "custom": {
+            "hideFrom": { "legend": false, "tooltip": false, "viz": false }
+          },
+          "mappings": [],
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": { "h": 8, "w": 8, "x": 0, "y": 23 },
+      "id": 13,
+      "options": {
+        "legend": { "displayMode": "table", "placement": "right", "showLegend": true },
+        "pieType": "pie",
+        "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
+        "tooltip": { "mode": "single", "sort": "none" }
+      },
+      "targets": [
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "editorMode": "code",
+          "expr": "sum by (error_code) (increase(export_runs_failed_total{tenant=~\"$tenant\"}[$__range]))",
+          "legendFormat": "{{error_code}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Failures by Error Code",
+      "type": "piechart"
+    },
+    {
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "palette-classic" },
+          "custom": {
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": { "legend": false, "tooltip": false, "viz": false },
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": { "type": "linear" },
+            "showPoints": "never",
+            "spanNulls": false,
+            "stacking": { "group": "A", "mode": "none" },
+            "thresholdsStyle": { "mode": "line" }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "red", "value": 0.01 }
+            ]
+          },
+          "unit": "percentunit"
+        },
+        "overrides": []
+      },
+      "gridPos": { "h": 8, "w": 16, "x": 8, "y": 23 },
+      "id": 14,
+      "options": {
+        "legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "bottom", "showLegend": true },
+        "tooltip": { "mode": "multi", "sort": "desc" }
+      },
+      "targets": [
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "editorMode": "code",
+          "expr": "sum(rate(export_runs_failed_total{tenant=~\"$tenant\"}[5m])) / sum(rate(export_runs_total{tenant=~\"$tenant\"}[5m]))",
+          "legendFormat": "Error Rate",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Error Rate (5m window)",
+      "type": "timeseries"
+    }
+  ],
+  "refresh": "30s",
+  "schemaVersion": 38,
+  "style": "dark",
+  "tags": ["export-center", "stellaops"],
+  "templating": {
+    "list": [
+      {
+        "current": {},
+        "hide": 0,
+        "includeAll": false,
+        "multi": false,
+        "name": "datasource",
+        "options": [],
+        "query": "prometheus",
+        "refresh": 1,
+        "regex": "",
+        "skipUrlSync": false,
+        "type": "datasource"
+      },
+      {
+        "allValue": ".*",
+        "current": {},
+        "datasource": { "type": "prometheus", "uid": "${datasource}" },
+        "definition": "label_values(export_runs_total, tenant)",
+        "hide": 0,
+        "includeAll": true,
+        "multi": true,
+        "name": "tenant",
+        "options": [],
+        "query": { "query": "label_values(export_runs_total, tenant)", "refId": "StandardVariableQuery" },
+        "refresh": 2,
+        "regex": "",
+        "skipUrlSync": false,
+        "sort": 1,
+        "type": "query"
+      }
+    ]
+  },
+  "time": { "from": "now-6h", "to": "now" },
+  "timepicker": {},
+  "timezone": "utc",
+  "title": "ExportCenter Service",
+  "uid": "export-center-overview",
+  "version": 1,
+  "weekStart": ""
+}