@senad-d/observme 0.1.0

package/dashboards/observme-export-health.json

@@ -0,0 +1,1802 @@
+{
+  "__requires": [
+    {
+      "id": "grafana",
+      "name": "Grafana",
+      "type": "grafana",
+      "version": "10.0.0"
+    },
+    {
+      "id": "prometheus",
+      "name": "Prometheus",
+      "type": "datasource",
+      "version": "1.0.0"
+    },
+    {
+      "id": "loki",
+      "name": "Loki",
+      "type": "datasource",
+      "version": "1.0.0"
+    },
+    {
+      "id": "row",
+      "name": "Row",
+      "type": "panel",
+      "version": ""
+    },
+    {
+      "id": "timeseries",
+      "name": "Time series",
+      "type": "panel",
+      "version": ""
+    },
+    {
+      "id": "stat",
+      "name": "Stat",
+      "type": "panel",
+      "version": ""
+    },
+    {
+      "id": "bargauge",
+      "name": "Bar gauge",
+      "type": "panel",
+      "version": ""
+    },
+    {
+      "id": "table",
+      "name": "Table",
+      "type": "panel",
+      "version": ""
+    },
+    {
+      "id": "text",
+      "name": "Text",
+      "type": "panel",
+      "version": ""
+    }
+  ],
+  "annotations": {
+    "list": []
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [
+    {
+      "icon": "external link",
+      "includeVars": true,
+      "keepTime": true,
+      "targetBlank": false,
+      "title": "Overview",
+      "tooltip": "Open the overview with the current time range.",
+      "type": "link",
+      "url": "/d/observme-overview/observme-overview?${__url_time_range}"
+    },
+    {
+      "icon": "external link",
+      "includeVars": true,
+      "keepTime": true,
+      "targetBlank": false,
+      "title": "SLO Health",
+      "tooltip": "Open SLO scorecards, burn rates, and alert thresholds with the current time range.",
+      "type": "link",
+      "url": "/d/observme-slo-health/observme-slo-health?${__url_time_range}"
+    },
+    {
+      "icon": "external link",
+      "includeVars": true,
+      "keepTime": true,
+      "targetBlank": false,
+      "title": "Errors",
+      "tooltip": "Open parsed failure logs and trace links.",
+      "type": "link",
+      "url": "/d/observme-errors/observme-errors?${__url_time_range}"
+    },
+    {
+      "icon": "external link",
+      "includeVars": true,
+      "keepTime": true,
+      "targetBlank": false,
+      "title": "Trace Journey",
+      "tooltip": "Open trace/log drill-downs for propagation failures.",
+      "type": "link",
+      "url": "/d/observme-trace-journey/observme-trace-journey?${__url_time_range}"
+    }
+  ],
+  "liveNow": false,
+  "panels": [
+    {
+      "collapsed": false,
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 0
+      },
+      "id": 100,
+      "panels": [],
+      "title": "Health",
+      "type": "row"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "Recent ObservMe handler activity from observme_events_observed_total. A zero value means the selected range is idle or no matching events have been observed; use the adjacent failure chips to distinguish healthy idle from unhealthy export behavior.",
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "blue",
+                "value": null
+              },
+              {
+                "color": "green",
+                "value": 1e-9
+              }
+            ]
+          },
+          "unit": "ops"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 4,
+        "x": 0,
+        "y": 1
+      },
+      "id": 10,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "(sum(rate(observme_events_observed_total[$__rate_interval])) or vector(0))",
+          "legendFormat": "observed events",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Observed event liveness",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "Composite runtime export state: 1 (green) means active telemetry with no local drops, export errors, or redaction failures; 0.5 (blue) means idle or unobserved telemetry with no failures; values below 1 indicate active failures, and 0 indicates failures without observed-event liveness. Use the adjacent liveness and failure chips to distinguish idle from missing instrumentation.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "red",
+                "value": null
+              },
+              {
+                "color": "blue",
+                "value": 0.5
+              },
+              {
+                "color": "yellow",
+                "value": 0.500001
+              },
+              {
+                "color": "green",
+                "value": 1
+              }
+            ]
+          },
+          "unit": "percentunit"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 4,
+        "x": 4,
+        "y": 1
+      },
+      "id": 5,
+      "links": [
+        {
+          "targetBlank": false,
+          "title": "Open SLO Health",
+          "url": "/d/observme-slo-health/observme-slo-health?${__url_time_range}"
+        }
+      ],
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "clamp_max(((((sum(rate(observme_events_observed_total[$__rate_interval])) or vector(0)) > bool 0) * clamp_min(1 - (((sum(rate(observme_telemetry_dropped_total[$__rate_interval])) or vector(0)) + (sum(rate(observme_export_errors_total[$__rate_interval])) or vector(0)) + (sum(rate(observme_redaction_failures_total[$__rate_interval])) or vector(0))) / clamp_min((sum(rate(observme_events_observed_total[$__rate_interval])) or vector(0)), 1e-9)), 0)) + (((sum(rate(observme_events_observed_total[$__rate_interval])) or vector(0)) == bool 0) * (((sum(rate(observme_telemetry_dropped_total[$__rate_interval])) or vector(0)) + (sum(rate(observme_export_errors_total[$__rate_interval])) or vector(0)) + (sum(rate(observme_redaction_failures_total[$__rate_interval])) or vector(0))) == bool 0) * 0.5)), 1)",
+          "legendFormat": "clean export score",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Collector/export health",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "Local telemetry drop ratio for the selected window, bounded to 100%. Zero means no drops were observed; when event liveness is also zero, treat it as idle/unmeasured rather than proof of active health.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 1e-9
+              }
+            ]
+          },
+          "unit": "percentunit"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 4,
+        "x": 8,
+        "y": 1
+      },
+      "id": 12,
+      "links": [
+        {
+          "targetBlank": false,
+          "title": "Open drop logs",
+          "url": "/d/observme-export-health/observme-export-health?${__url_time_range}&viewPanel=8"
+        }
+      ],
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "clamp_max((sum(rate(observme_telemetry_dropped_total[$__rate_interval])) or vector(0)) / clamp_min((sum(rate(observme_events_observed_total[$__rate_interval])) or vector(0)), 1e-9), 1)",
+          "legendFormat": "drop ratio",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Telemetry drop ratio",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "Exporter/backend error rate. Zero means no export errors were observed; when event liveness is also zero, treat the range as idle/unmeasured rather than proof of active health.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 1e-9
+              }
+            ]
+          },
+          "unit": "ops"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 4,
+        "x": 12,
+        "y": 1
+      },
+      "id": 13,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "(sum(rate(observme_export_errors_total[$__rate_interval])) or vector(0))",
+          "legendFormat": "export errors",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Export error rate",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "Redaction failure rate. Any non-zero value is critical when content capture is enabled. Zero means no failures were observed; when event liveness is also zero, treat the range as idle/unmeasured.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 1e-9
+              }
+            ]
+          },
+          "unit": "ops"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 4,
+        "x": 16,
+        "y": 1
+      },
+      "id": 14,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "(sum(rate(observme_redaction_failures_total[$__rate_interval])) or vector(0))",
+          "legendFormat": "redaction failures",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Redaction failure rate",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "Instrumentation overhead chip: p99 handler lifecycle latency should stay under the 10 ms SLO threshold. No histogram observations render as no data rather than a false healthy zero.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 10
+              }
+            ]
+          },
+          "unit": "ms"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 4,
+        "x": 20,
+        "y": 1
+      },
+      "id": 15,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.99, sum(rate(observme_handler_duration_ms_bucket[$__rate_interval])) by (le))",
+          "legendFormat": "handler p99",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Handler p99 latency",
+      "type": "stat"
+    },
+    {
+      "collapsed": false,
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 5
+      },
+      "id": 101,
+      "panels": [],
+      "title": "SLOs",
+      "type": "row"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "30-day Observability Export SLO aligned with observme-slos.yaml: 99% of observed events are not locally dropped. The denominator guard makes no events and no drops evaluate to 1; treat that state as idle/unmeasured and confirm liveness instead of assuming a measured healthy workload.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "red",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 0.98
+              },
+              {
+                "color": "green",
+                "value": 0.99
+              }
+            ]
+          },
+          "unit": "percentunit"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 5,
+        "w": 6,
+        "x": 0,
+        "y": 6
+      },
+      "id": 16,
+      "links": [
+        {
+          "targetBlank": false,
+          "title": "Open SLO Health",
+          "url": "/d/observme-slo-health/observme-slo-health?${__url_time_range}"
+        }
+      ],
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "clamp_max(clamp_min(1 - ((sum(rate(observme_telemetry_dropped_total[30d])) or vector(0)) / clamp_min((sum(rate(observme_events_observed_total[30d])) or vector(0)), 1e-9)), 0), 1)",
+          "instant": true,
+          "legendFormat": "export SLO",
+          "range": false,
+          "refId": "A"
+        }
+      ],
+      "title": "Observability Export SLO (30d)",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "Instrumentation Overhead SLO scorecard: p99 handler duration over 30 days should stay under 10 ms. No histogram observations render as no data rather than a false healthy zero.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 10
+              }
+            ]
+          },
+          "unit": "ms"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 5,
+        "w": 6,
+        "x": 6,
+        "y": 6
+      },
+      "id": 17,
+      "links": [
+        {
+          "targetBlank": false,
+          "title": "Open SLO Health",
+          "url": "/d/observme-slo-health/observme-slo-health?${__url_time_range}"
+        }
+      ],
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.99, sum(rate(observme_handler_duration_ms_bucket[30d])) by (le))",
+          "instant": true,
+          "legendFormat": "handler p99",
+          "range": false,
+          "refId": "A"
+        }
+      ],
+      "title": "Instrumentation Overhead SLO p99 (30d)",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "Short-window burn rates normalized by a 1% error budget. Values above 1 consume error budget faster than target.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 1
+              },
+              {
+                "color": "red",
+                "value": 2
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 5,
+        "w": 6,
+        "x": 12,
+        "y": 6
+      },
+      "id": 18,
+      "options": {
+        "displayMode": "gradient",
+        "maxVizHeight": 300,
+        "minVizHeight": 16,
+        "minVizWidth": 8,
+        "namePlacement": "auto",
+        "orientation": "horizontal",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showUnfilled": true,
+        "sizing": "auto",
+        "valueMode": "color"
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "((sum(rate(observme_telemetry_dropped_total[1h])) or vector(0)) / clamp_min((sum(rate(observme_events_observed_total[1h])) or vector(0)), 1e-9)) / 0.01",
+          "instant": true,
+          "legendFormat": "export drops",
+          "range": false,
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "clamp_max(clamp_min(((sum(rate(observme_handler_duration_ms_count[1h])) or vector(0)) - (sum(rate(observme_handler_duration_ms_bucket{le=\"10\"}[1h])) or vector(0))) / clamp_min((sum(rate(observme_handler_duration_ms_count[1h])) or vector(0)), 1e-9), 0), 1) / 0.01",
+          "instant": true,
+          "legendFormat": "handler >10ms",
+          "range": false,
+          "refId": "B"
+        }
+      ],
+      "title": "Runtime SLO burn rate (1h)",
+      "type": "bargauge"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "Long-window burn rates normalized by a 1% error budget. Pair with the 1h view to identify sustained SLO risk.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 1
+              },
+              {
+                "color": "red",
+                "value": 2
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 5,
+        "w": 6,
+        "x": 18,
+        "y": 6
+      },
+      "id": 19,
+      "options": {
+        "displayMode": "gradient",
+        "maxVizHeight": 300,
+        "minVizHeight": 16,
+        "minVizWidth": 8,
+        "namePlacement": "auto",
+        "orientation": "horizontal",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showUnfilled": true,
+        "sizing": "auto",
+        "valueMode": "color"
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "((sum(rate(observme_telemetry_dropped_total[30d])) or vector(0)) / clamp_min((sum(rate(observme_events_observed_total[30d])) or vector(0)), 1e-9)) / 0.01",
+          "instant": true,
+          "legendFormat": "export drops",
+          "range": false,
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "clamp_max(clamp_min(((sum(rate(observme_handler_duration_ms_count[30d])) or vector(0)) - (sum(rate(observme_handler_duration_ms_bucket{le=\"10\"}[30d])) or vector(0))) / clamp_min((sum(rate(observme_handler_duration_ms_count[30d])) or vector(0)), 1e-9), 0), 1) / 0.01",
+          "instant": true,
+          "legendFormat": "handler >10ms",
+          "range": false,
+          "refId": "B"
+        }
+      ],
+      "title": "Runtime SLO burn rate (30d)",
+      "type": "bargauge"
+    },
+    {
+      "description": "Alert thresholds mirrored from dashboards/observme-alerts.yaml for quick operational context.",
+      "gridPos": {
+        "h": 6,
+        "w": 24,
+        "x": 0,
+        "y": 11
+      },
+      "id": 20,
+      "options": {
+        "code": {
+          "language": "markdown",
+          "showLineNumbers": false,
+          "showMiniMap": false
+        },
+        "content": "### Alert threshold reference\n\n- **ObservMeExportDropsDetected:** any local telemetry drops for 5m.\n- **ObservMeRedactionFailures:** any redaction failures for 5m.\n- **ObservMeTraceContextPropagationFailures:** any trace-context propagation failures for 10m.\n- **ObservMeActiveAgentsStuckHigh:** active agents > **100** for 30m.\n- Agent orchestration thresholds: p95 fan-out > **20** and p95 tree depth > **5** for 10m.",
+        "mode": "markdown"
+      },
+      "pluginVersion": "11.1.0",
+      "title": "Alert threshold reference",
+      "type": "text"
+    },
+    {
+      "collapsed": false,
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 17
+      },
+      "id": 102,
+      "panels": [],
+      "title": "Signals",
+      "type": "row"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "Sessions started and shut down in the selected time range. Zero means no matching session lifecycle samples exist for the range.",
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 0,
+        "y": 18
+      },
+      "id": 11,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "(sum(increase(observme_sessions_started_total[$__range])) or vector(0))",
+          "instant": true,
+          "legendFormat": "sessions started",
+          "range": false,
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "(sum(increase(observme_sessions_shutdown_total[$__range])) or vector(0))",
+          "instant": true,
+          "legendFormat": "sessions shutdown",
+          "range": false,
+          "refId": "B"
+        }
+      ],
+      "title": "Session lifecycle",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "Telemetry drop rate grouped by bounded drop reason. The zero fallback means no local drops were observed in the selected range.",
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 1e-9
+              }
+            ]
+          },
+          "unit": "ops"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 8,
+        "y": 18
+      },
+      "id": 1,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "(sum by (reason) (rate(observme_telemetry_dropped_total[$__rate_interval])) or on() vector(0))",
+          "legendFormat": "{{reason}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Telemetry drops",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "Exporter/backend failure rate grouped by bounded reason. The zero fallback means no export failures were observed in the selected range.",
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 1e-9
+              }
+            ]
+          },
+          "unit": "ops"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 16,
+        "y": 18
+      },
+      "id": 3,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "(sum by (reason) (rate(observme_export_errors_total[$__rate_interval])) or on() vector(0))",
+          "legendFormat": "{{reason}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Export failures",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "Redaction failure rate. The zero fallback means no redaction failures were observed in the selected range.",
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 1e-9
+              }
+            ]
+          },
+          "unit": "ops"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 0,
+        "y": 26
+      },
+      "id": 2,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "(sum(rate(observme_redaction_failures_total[$__rate_interval])) or vector(0))",
+          "legendFormat": "redaction failures",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Redaction failures",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "Active spans by bounded operation as an SDK pressure signal. Zero means no active spans are exposed or the gauge series is absent; consult observed-event liveness before interpreting it as healthy idle.",
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 8,
+        "y": 26
+      },
+      "id": 4,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "(sum by (operation) (observme_active_spans) or on() vector(0))",
+          "legendFormat": "{{operation}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Active spans by operation",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "description": "Handler error rate grouped by operation and error class. The zero fallback means no handler errors were observed; if event liveness is also zero, the range is idle/unmeasured rather than confirmed healthy.",
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 1e-9
+              }
+            ]
+          },
+          "unit": "ops"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 16,
+        "y": 26
+      },
+      "id": 6,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "(sum by (operation, error_class) (rate(observme_handler_errors_total[$__rate_interval])) or on() vector(0))",
+          "legendFormat": "{{operation}} / {{error_class}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Handler error pressure",
+      "type": "timeseries"
+    },
+    {
+      "collapsed": false,
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 34
+      },
+      "id": 103,
+      "panels": [],
+      "title": "Logs",
+      "type": "row"
+    },
+    {
+      "datasource": {
+        "type": "loki",
+        "uid": "loki"
+      },
+      "description": "Latest redaction.failed events first. Safe deterministic fields expose event, category, execution context, error type, trace, and span while raw lines are hidden. trace_id opens Tempo. Empty means no matching failure logs in the selected time range; this is healthy when no redaction failures occurred.",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": [
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "trace_id"
+            },
+            "properties": [
+              {
+                "id": "links",
+                "value": [
+                  {
+                    "targetBlank": false,
+                    "title": "Open Tempo trace",
+                    "url": "/explore?left=%7B%22datasource%22:%22tempo%22,%22queries%22:%5B%7B%22query%22:%22${__value.raw}%22%7D%5D,%22range%22:%7B%22from%22:%22${__from}%22,%22to%22:%22${__to}%22%7D%7D"
+                  }
+                ]
+              }
+            ]
+          }
+        ]
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 0,
+        "y": 35
+      },
+      "id": 7,
+      "links": [
+        {
+          "targetBlank": false,
+          "title": "Open Errors",
+          "url": "/d/observme-errors/observme-errors?${__url_time_range}"
+        }
+      ],
+      "options": {
+        "cellHeight": "sm",
+        "footer": {
+          "countRows": false,
+          "fields": "",
+          "reducer": [
+            "sum"
+          ],
+          "show": false
+        },
+        "showHeader": true,
+        "sortBy": [
+          {
+            "desc": true,
+            "displayName": "Time"
+          }
+        ]
+      },
+      "pluginVersion": "11.1.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "loki",
+            "uid": "loki"
+          },
+          "editorMode": "code",
+          "expr": "{service_name=\"observme-pi-extension\", event_name=\"redaction.failed\"} | line_format `{\"event\":{{ printf \"%q\" .event_name }},\"category\":{{ printf \"%q\" .event_category }},\"session\":{{ printf \"%q\" .pi_session_id }},\"workflow\":{{ printf \"%q\" .pi_workflow_id }},\"agent\":{{ printf \"%q\" .pi_agent_id }},\"parent_agent\":{{ printf \"%q\" .pi_agent_parent_id }},\"agent_run\":{{ printf \"%q\" .pi_agent_run_id }},\"error_type\":{{ printf \"%q\" .error_type }},\"trace_id\":{{ printf \"%q\" .trace_id }},\"span_id\":{{ printf \"%q\" .span_id }}}`",
+          "maxLines": 500,
+          "queryType": "range",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Redaction failure logs",
+      "transformations": [
+        {
+          "id": "labelsToFields",
+          "options": {
+            "mode": "columns"
+          }
+        },
+        {
+          "id": "extractFields",
+          "options": {
+            "format": "json",
+            "keepTime": true,
+            "replace": false,
+            "source": "Line"
+          }
+        },
+        {
+          "id": "organize",
+          "options": {
+            "excludeByName": {
+              "Line": true,
+              "id": true,
+              "labels": true,
+              "service_name": true,
+              "telemetry_source": true,
+              "tsNs": true
+            },
+            "renameByName": {
+              "event_category": "category",
+              "event_name": "event",
+              "pi_agent_id": "agent",
+              "pi_agent_parent_id": "parent_agent",
+              "pi_agent_run_id": "agent_run",
+              "pi_session_id": "session",
+              "pi_workflow_id": "workflow"
+            }
+          }
+        }
+      ],
+      "type": "table"
+    },
+    {
+      "datasource": {
+        "type": "loki",
+        "uid": "loki"
+      },
+      "description": "Latest telemetry.dropped events first. Safe deterministic fields expose event, category, execution context, error type, trace, and span while raw lines are hidden. trace_id opens Tempo. Empty means no matching failure logs in the selected time range; this is healthy when no local telemetry drops occurred.",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": [
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "trace_id"
+            },
+            "properties": [
+              {
+                "id": "links",
+                "value": [
+                  {
+                    "targetBlank": false,
+                    "title": "Open Tempo trace",
+                    "url": "/explore?left=%7B%22datasource%22:%22tempo%22,%22queries%22:%5B%7B%22query%22:%22${__value.raw}%22%7D%5D,%22range%22:%7B%22from%22:%22${__from}%22,%22to%22:%22${__to}%22%7D%7D"
+                  }
+                ]
+              }
+            ]
+          }
+        ]
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 12,
+        "y": 35
+      },
+      "id": 8,
+      "links": [
+        {
+          "targetBlank": false,
+          "title": "Open Errors",
+          "url": "/d/observme-errors/observme-errors?${__url_time_range}"
+        }
+      ],
+      "options": {
+        "cellHeight": "sm",
+        "footer": {
+          "countRows": false,
+          "fields": "",
+          "reducer": [
+            "sum"
+          ],
+          "show": false
+        },
+        "showHeader": true,
+        "sortBy": [
+          {
+            "desc": true,
+            "displayName": "Time"
+          }
+        ]
+      },
+      "pluginVersion": "11.1.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "loki",
+            "uid": "loki"
+          },
+          "editorMode": "code",
+          "expr": "{service_name=\"observme-pi-extension\", event_name=\"telemetry.dropped\"} | line_format `{\"event\":{{ printf \"%q\" .event_name }},\"category\":{{ printf \"%q\" .event_category }},\"session\":{{ printf \"%q\" .pi_session_id }},\"workflow\":{{ printf \"%q\" .pi_workflow_id }},\"agent\":{{ printf \"%q\" .pi_agent_id }},\"parent_agent\":{{ printf \"%q\" .pi_agent_parent_id }},\"agent_run\":{{ printf \"%q\" .pi_agent_run_id }},\"error_type\":{{ printf \"%q\" .error_type }},\"trace_id\":{{ printf \"%q\" .trace_id }},\"span_id\":{{ printf \"%q\" .span_id }}}`",
+          "maxLines": 500,
+          "queryType": "range",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Telemetry drop logs",
+      "transformations": [
+        {
+          "id": "labelsToFields",
+          "options": {
+            "mode": "columns"
+          }
+        },
+        {
+          "id": "extractFields",
+          "options": {
+            "format": "json",
+            "keepTime": true,
+            "replace": false,
+            "source": "Line"
+          }
+        },
+        {
+          "id": "organize",
+          "options": {
+            "excludeByName": {
+              "Line": true,
+              "id": true,
+              "labels": true,
+              "service_name": true,
+              "telemetry_source": true,
+              "tsNs": true
+            },
+            "renameByName": {
+              "event_category": "category",
+              "event_name": "event",
+              "pi_agent_id": "agent",
+              "pi_agent_parent_id": "parent_agent",
+              "pi_agent_run_id": "agent_run",
+              "pi_session_id": "session",
+              "pi_workflow_id": "workflow"
+            }
+          }
+        }
+      ],
+      "type": "table"
+    },
+    {
+      "datasource": {
+        "type": "loki",
+        "uid": "loki"
+      },
+      "description": "Latest export.failed events first. Safe deterministic fields expose event, category, execution context, error type, trace, and span while raw lines are hidden. trace_id opens Tempo. Empty means no matching failure logs in the selected time range; this is healthy when no exporter/backend failures occurred.",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": [
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "trace_id"
+            },
+            "properties": [
+              {
+                "id": "links",
+                "value": [
+                  {
+                    "targetBlank": false,
+                    "title": "Open Tempo trace",
+                    "url": "/explore?left=%7B%22datasource%22:%22tempo%22,%22queries%22:%5B%7B%22query%22:%22${__value.raw}%22%7D%5D,%22range%22:%7B%22from%22:%22${__from}%22,%22to%22:%22${__to}%22%7D%7D"
+                  }
+                ]
+              }
+            ]
+          }
+        ]
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 0,
+        "y": 44
+      },
+      "id": 21,
+      "links": [
+        {
+          "targetBlank": false,
+          "title": "Open Errors",
+          "url": "/d/observme-errors/observme-errors?${__url_time_range}"
+        }
+      ],
+      "options": {
+        "cellHeight": "sm",
+        "footer": {
+          "countRows": false,
+          "fields": "",
+          "reducer": [
+            "sum"
+          ],
+          "show": false
+        },
+        "showHeader": true,
+        "sortBy": [
+          {
+            "desc": true,
+            "displayName": "Time"
+          }
+        ]
+      },
+      "pluginVersion": "11.1.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "loki",
+            "uid": "loki"
+          },
+          "editorMode": "code",
+          "expr": "{service_name=\"observme-pi-extension\", event_name=\"export.failed\"} | line_format `{\"event\":{{ printf \"%q\" .event_name }},\"category\":{{ printf \"%q\" .event_category }},\"session\":{{ printf \"%q\" .pi_session_id }},\"workflow\":{{ printf \"%q\" .pi_workflow_id }},\"agent\":{{ printf \"%q\" .pi_agent_id }},\"parent_agent\":{{ printf \"%q\" .pi_agent_parent_id }},\"agent_run\":{{ printf \"%q\" .pi_agent_run_id }},\"error_type\":{{ printf \"%q\" .error_type }},\"trace_id\":{{ printf \"%q\" .trace_id }},\"span_id\":{{ printf \"%q\" .span_id }}}`",
+          "maxLines": 500,
+          "queryType": "range",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Export failure logs",
+      "transformations": [
+        {
+          "id": "labelsToFields",
+          "options": {
+            "mode": "columns"
+          }
+        },
+        {
+          "id": "extractFields",
+          "options": {
+            "format": "json",
+            "keepTime": true,
+            "replace": false,
+            "source": "Line"
+          }
+        },
+        {
+          "id": "organize",
+          "options": {
+            "excludeByName": {
+              "Line": true,
+              "id": true,
+              "labels": true,
+              "service_name": true,
+              "telemetry_source": true,
+              "tsNs": true
+            },
+            "renameByName": {
+              "event_category": "category",
+              "event_name": "event",
+              "pi_agent_id": "agent",
+              "pi_agent_parent_id": "parent_agent",
+              "pi_agent_run_id": "agent_run",
+              "pi_session_id": "session",
+              "pi_workflow_id": "workflow"
+            }
+          }
+        }
+      ],
+      "type": "table"
+    },
+    {
+      "datasource": {
+        "type": "loki",
+        "uid": "loki"
+      },
+      "description": "Latest trace_context.propagation_failed events first. Safe deterministic fields expose event, category, execution context, error type, trace, and span while raw lines are hidden. trace_id opens Tempo and the panel links to Trace Journey. Empty means no matching failure logs in the selected time range; this is healthy when trace context propagated successfully.",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": [
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "trace_id"
+            },
+            "properties": [
+              {
+                "id": "links",
+                "value": [
+                  {
+                    "targetBlank": false,
+                    "title": "Open Tempo trace",
+                    "url": "/explore?left=%7B%22datasource%22:%22tempo%22,%22queries%22:%5B%7B%22query%22:%22${__value.raw}%22%7D%5D,%22range%22:%7B%22from%22:%22${__from}%22,%22to%22:%22${__to}%22%7D%7D"
+                  }
+                ]
+              }
+            ]
+          }
+        ]
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 12,
+        "y": 44
+      },
+      "id": 9,
+      "links": [
+        {
+          "targetBlank": false,
+          "title": "Open Trace Journey",
+          "url": "/d/observme-trace-journey/observme-trace-journey?${__url_time_range}"
+        }
+      ],
+      "options": {
+        "cellHeight": "sm",
+        "footer": {
+          "countRows": false,
+          "fields": "",
+          "reducer": [
+            "sum"
+          ],
+          "show": false
+        },
+        "showHeader": true,
+        "sortBy": [
+          {
+            "desc": true,
+            "displayName": "Time"
+          }
+        ]
+      },
+      "pluginVersion": "11.1.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "loki",
+            "uid": "loki"
+          },
+          "editorMode": "code",
+          "expr": "{service_name=\"observme-pi-extension\", event_name=\"trace_context.propagation_failed\"} | line_format `{\"event\":{{ printf \"%q\" .event_name }},\"category\":{{ printf \"%q\" .event_category }},\"session\":{{ printf \"%q\" .pi_session_id }},\"workflow\":{{ printf \"%q\" .pi_workflow_id }},\"agent\":{{ printf \"%q\" .pi_agent_id }},\"parent_agent\":{{ printf \"%q\" .pi_agent_parent_id }},\"agent_run\":{{ printf \"%q\" .pi_agent_run_id }},\"error_type\":{{ printf \"%q\" .error_type }},\"trace_id\":{{ printf \"%q\" .trace_id }},\"span_id\":{{ printf \"%q\" .span_id }}}`",
+          "maxLines": 500,
+          "queryType": "range",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Trace-context propagation failure logs",
+      "transformations": [
+        {
+          "id": "labelsToFields",
+          "options": {
+            "mode": "columns"
+          }
+        },
+        {
+          "id": "extractFields",
+          "options": {
+            "format": "json",
+            "keepTime": true,
+            "replace": false,
+            "source": "Line"
+          }
+        },
+        {
+          "id": "organize",
+          "options": {
+            "excludeByName": {
+              "Line": true,
+              "id": true,
+              "labels": true,
+              "service_name": true,
+              "telemetry_source": true,
+              "tsNs": true
+            },
+            "renameByName": {
+              "event_category": "category",
+              "event_name": "event",
+              "pi_agent_id": "agent",
+              "pi_agent_parent_id": "parent_agent",
+              "pi_agent_run_id": "agent_run",
+              "pi_session_id": "session",
+              "pi_workflow_id": "workflow"
+            }
+          }
+        }
+      ],
+      "type": "table"
+    }
+  ],
+  "refresh": "30s",
+  "schemaVersion": 39,
+  "style": "dark",
+  "tags": [
+    "observme",
+    "export-health"
+  ],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-6h",
+    "to": "now"
+  },
+  "timezone": "browser",
+  "title": "ObservMe Export Health",
+  "uid": "observme-export-health",
+  "version": 4,
+  "weekStart": ""
+}