feat(monitoring): add prometheus metrics, alerts, and dashboard for taupi fan

k8s/monitoring/dashboards/grafana-dashboard-taupi-fan.yaml

@@ -0,0 +1,266 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: grafana-dashboard-taupi-fan
+  namespace: monitoring
+  labels:
+    grafana_dashboard: '1'
+  annotations:
+    grafana_dashboard_folder: 🏠 Home
+data:
+  taupi-fan.json: |
+    {
+      "uid": "taupi-fan",
+      "title": "💨 Cellar Fan (TAUPI)",
+      "tags": ["climate", "fan", "cellar", "prometheus"],
+      "timezone": "browser",
+      "schemaVersion": 39,
+      "version": 1,
+      "refresh": "30s",
+      "editable": false,
+      "graphTooltip": 1,
+      "time": {
+        "from": "now-24h",
+        "to": "now"
+      },
+      "panels": [
+        {
+          "title": "⚡ Status & Controls",
+          "type": "row",
+          "gridPos": {"h": 1, "w": 24, "x": 0, "y": 0},
+          "collapsed": false
+        },
+        {
+          "title": "Fan Power Relay",
+          "type": "stat",
+          "datasource": {"type": "prometheus", "uid": "prometheus"},
+          "gridPos": {"h": 4, "w": 6, "x": 0, "y": 1},
+          "fieldConfig": {
+            "defaults": {
+              "mappings": [
+                {"type": "value", "options": {"0": {"text": "OFF", "color": "blue"}, "1": {"text": "ON", "color": "orange"}}}
+              ],
+              "color": {"mode": "thresholds"}
+            }
+          },
+          "options": {
+            "graphMode": "none",
+            "colorMode": "background",
+            "textMode": "auto",
+            "reduceOptions": {"values": false, "calcs": ["lastNotNull"]}
+          },
+          "targets": [
+            {"expr": "taupi_relay_status", "legendFormat": "Fan Status"}
+          ]
+        },
+        {
+          "title": "Mold Danger Status",
+          "type": "stat",
+          "datasource": {"type": "prometheus", "uid": "prometheus"},
+          "gridPos": {"h": 4, "w": 6, "x": 6, "y": 1},
+          "fieldConfig": {
+            "defaults": {
+              "mappings": [
+                {"type": "value", "options": {"0": {"text": "SAFE", "color": "green"}, "1": {"text": "CRITICAL", "color": "red"}}}
+              ]
+            }
+          },
+          "options": {
+            "graphMode": "none",
+            "colorMode": "background",
+            "textMode": "auto",
+            "reduceOptions": {"values": false, "calcs": ["lastNotNull"]}
+          },
+          "targets": [
+            {"expr": "taupi_is_critical", "legendFormat": "Mold Danger"}
+          ]
+        },
+        {
+          "title": "Activation Criteria Met",
+          "type": "stat",
+          "datasource": {"type": "prometheus", "uid": "prometheus"},
+          "gridPos": {"h": 4, "w": 6, "x": 12, "y": 1},
+          "fieldConfig": {
+            "defaults": {
+              "mappings": [
+                {"type": "value", "options": {"0": {"text": "NO", "color": "gray"}, "1": {"text": "YES", "color": "green"}}}
+              ]
+            }
+          },
+          "options": {
+            "graphMode": "none",
+            "colorMode": "background",
+            "textMode": "auto",
+            "reduceOptions": {"values": false, "calcs": ["lastNotNull"]}
+          },
+          "targets": [
+            {"expr": "taupi_would_fan_activate", "legendFormat": "Dewpoint Condition"}
+          ]
+        },
+        {
+          "title": "Shelly Plug Reachability",
+          "type": "stat",
+          "datasource": {"type": "prometheus", "uid": "prometheus"},
+          "gridPos": {"h": 4, "w": 6, "x": 18, "y": 1},
+          "fieldConfig": {
+            "defaults": {
+              "mappings": [
+                {"type": "value", "options": {"0": {"text": "OFFLINE", "color": "red"}, "1": {"text": "ONLINE", "color": "green"}}}
+              ]
+            }
+          },
+          "options": {
+            "graphMode": "none",
+            "colorMode": "background",
+            "textMode": "auto",
+            "reduceOptions": {"values": false, "calcs": ["lastNotNull"]}
+          },
+          "targets": [
+            {"expr": "up{job=\"taupi-fan\"}", "legendFormat": "Connectivity"}
+          ]
+        },
+        {
+          "title": "🌡️ Climate Details",
+          "type": "row",
+          "gridPos": {"h": 1, "w": 24, "x": 0, "y": 5},
+          "collapsed": false
+        },
+        {
+          "title": "Temperatures",
+          "type": "timeseries",
+          "datasource": {"type": "prometheus", "uid": "prometheus"},
+          "gridPos": {"h": 8, "w": 12, "x": 0, "y": 6},
+          "fieldConfig": {
+            "defaults": {
+              "unit": "celsius",
+              "custom": {
+                "lineWidth": 2,
+                "fillOpacity": 5,
+                "spanNulls": true,
+                "showPoints": "never"
+              }
+            }
+          },
+          "options": {
+            "legend": {"displayMode": "table", "placement": "bottom", "calcs": ["min", "max", "mean"]},
+            "tooltip": {"mode": "multi", "sort": "desc"}
+          },
+          "targets": [
+            {"expr": "taupi_temperature_celsius_innen", "legendFormat": "Indoor Temperature"},
+            {"expr": "taupi_temperature_celsius_aussen", "legendFormat": "Outdoor Temperature"}
+          ]
+        },
+        {
+          "title": "Dew Points",
+          "type": "timeseries",
+          "datasource": {"type": "prometheus", "uid": "prometheus"},
+          "gridPos": {"h": 8, "w": 12, "x": 12, "y": 6},
+          "fieldConfig": {
+            "defaults": {
+              "unit": "celsius",
+              "custom": {
+                "lineWidth": 2,
+                "fillOpacity": 5,
+                "spanNulls": true,
+                "showPoints": "never"
+              }
+            }
+          },
+          "options": {
+            "legend": {"displayMode": "table", "placement": "bottom", "calcs": ["min", "max", "mean"]},
+            "tooltip": {"mode": "multi", "sort": "desc"}
+          },
+          "targets": [
+            {"expr": "taupi_dewpoint_celsius_innen", "legendFormat": "Indoor Dewpoint"},
+            {"expr": "taupi_dewpoint_celsius_aussen", "legendFormat": "Outdoor Dewpoint"}
+          ]
+        },
+        {
+          "title": "Relative Humidity vs. Mold Threshold",
+          "type": "timeseries",
+          "datasource": {"type": "prometheus", "uid": "prometheus"},
+          "gridPos": {"h": 8, "w": 24, "x": 0, "y": 14},
+          "fieldConfig": {
+            "defaults": {
+              "unit": "percent",
+              "custom": {
+                "lineWidth": 2,
+                "fillOpacity": 5,
+                "spanNulls": true,
+                "showPoints": "never"
+              }
+            }
+          },
+          "options": {
+            "legend": {"displayMode": "table", "placement": "bottom", "calcs": ["min", "max", "mean"]},
+            "tooltip": {"mode": "multi", "sort": "desc"}
+          },
+          "targets": [
+            {"expr": "taupi_humidity_percent_innen", "legendFormat": "Indoor Humidity"},
+            {"expr": "taupi_humidity_percent_aussen", "legendFormat": "Outdoor Humidity"},
+            {"expr": "taupi_critical_humidity_threshold_percent", "legendFormat": "Mold Danger Threshold"}
+          ]
+        },
+        {
+          "title": "🔋 BLE Sensors Diagnostic",
+          "type": "row",
+          "gridPos": {"h": 1, "w": 24, "x": 0, "y": 22},
+          "collapsed": false
+        },
+        {
+          "title": "Sensor Batteries",
+          "type": "gauge",
+          "datasource": {"type": "prometheus", "uid": "prometheus"},
+          "gridPos": {"h": 6, "w": 12, "x": 0, "y": 23},
+          "fieldConfig": {
+            "defaults": {
+              "unit": "percent",
+              "min": 0,
+              "max": 100,
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {"color": "red", "value": null},
+                  {"color": "orange", "value": 20},
+                  {"color": "green", "value": 50}
+                ]
+              }
+            }
+          },
+          "options": {
+            "reduceOptions": {"values": false, "calcs": ["lastNotNull"]},
+            "showThresholdLabels": false,
+            "showThresholdMarkers": true
+          },
+          "targets": [
+            {"expr": "taupi_battery_percent_innen", "legendFormat": "Indoor Sensor Battery"},
+            {"expr": "taupi_battery_percent_aussen", "legendFormat": "Outdoor Sensor Battery"}
+          ]
+        },
+        {
+          "title": "Sensor Connection Age (Staleness)",
+          "type": "timeseries",
+          "datasource": {"type": "prometheus", "uid": "prometheus"},
+          "gridPos": {"h": 6, "w": 12, "x": 12, "y": 23},
+          "fieldConfig": {
+            "defaults": {
+              "unit": "s",
+              "custom": {
+                "lineWidth": 2,
+                "fillOpacity": 5,
+                "spanNulls": true,
+                "showPoints": "never"
+              }
+            }
+          },
+          "options": {
+            "legend": {"displayMode": "table", "placement": "bottom", "calcs": ["lastNotNull"]},
+            "tooltip": {"mode": "multi", "sort": "desc"}
+          },
+          "targets": [
+            {"expr": "taupi_lost_connection_seconds_innen", "legendFormat": "Indoor Connection Stale Time"},
+            {"expr": "taupi_lost_connection_seconds_aussen", "legendFormat": "Outdoor Connection Stale Time"}
+          ]
+        }
+      ]
+    }

k8s/monitoring/taupi-fan.yml

@@ -0,0 +1,83 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: taupi-fan
+  namespace: monitoring
+  labels:
+    app: taupi-fan
+spec:
+  ports:
+    - name: http-metrics
+      port: 80
+      targetPort: 80
+---
+apiVersion: v1
+kind: Endpoints
+metadata:
+  name: taupi-fan
+  namespace: monitoring
+  labels:
+    app: taupi-fan
+subsets:
+  - addresses:
+      - ip: 192.168.10.168
+    ports:
+      - name: http-metrics
+        port: 80
+---
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: taupi-fan
+  namespace: monitoring
+  labels:
+    app: taupi-fan
+    release: prometheus-operator
+spec:
+  selector:
+    matchLabels:
+      app: taupi-fan
+  namespaceSelector:
+    matchNames:
+      - monitoring
+  endpoints:
+    - port: http-metrics
+      path: /script/1/prometheus
+      interval: 30s
+      scrapeTimeout: 10s
+---
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: taupi-fan-alerts
+  namespace: monitoring
+  labels:
+    release: prometheus-operator
+spec:
+  groups:
+    - name: taupi-fan.rules
+      rules:
+        - alert: TaupiFanOffline
+          expr: up{job="taupi-fan"} == 0
+          for: 5m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Id: {{ $labels.instance }} - TAUPI Fan Plug is unreachable"
+            description: "The Shelly plug at 192.168.10.168 is unreachable by Prometheus. Check Wi-Fi connection or power status."
+        - alert: TaupiFanSensorsStale
+          expr: taupi_lost_connection_seconds_innen > 600 or taupi_lost_connection_seconds_aussen > 600
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "TAUPI Fan BLE sensors stale"
+            description: "The BLE sensors for temperature and humidity inside or outside have not sent new data for over 10 minutes."
+        - alert: TaupiFanMoldDanger
+          expr: taupi_is_critical == 1
+          for: 30m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Cellar mold risk detected"
+            description: "The cellar relative humidity has exceeded the critical mold threshold (inside humidity is high enough that mold can grow on cold wall surfaces)."

terraform_shelly/scripts/Taupi-4.0.js

@@ -170,46 +170,20 @@ const uint8 = 0;
 const int8 = 1;
 const uint16 = 2;
 const int16 = 3;
-const uint24 = 4;
-const int24 = 5;
-const dimmert = 6; // special data type for dimmer event
-const uint32 = 7;
-const int32 = 8;
 
-// The BTH object defines the structure of the BTHome data
+// The BTH object defines the structure of the BTHome data (trimmed to temperature/humidity/battery)
 const BTH = {
   0x00: { n: "pid", t: uint8 },
-  0x01: { n: "battery", t: uint8, u: "%" },
-  0x02: { n: "temperature", t: int16, f: 0.01, u: "tC" },
-  0x04: { n: "atm. pressure", t: int24, f: 0.01, u: "hPa" },
-  0x03: { n: "humidity", t: uint16, f: 0.01, u: "%" },
-  0x05: { n: "illuminance", t: uint24, f: 0.01 },
-  0x08: { n: "dew point", t: uint16, f: 0.01, u: "tC" },
-  0x0C: { n: "capacitor voltage", t: uint16, f: 0.001, u: "V" },
-  0x1e: { n: "light", t: uint8 },
-  0x20: { n: "raining", t: uint8},
-  0x21: { n: "motion", t: uint8 },
-  0x2d: { n: "window", t: uint8 },
-  0x2e: { n: "humidity", t: uint8, u: "%" },
-  0x3a: { n: "button", t: uint8 },
-  0x3c: { n: "dimmer", t: dimmert },
-  0x3f: { n: "rotation", t: int16, f: 0.1 },
-  0x44: { n: "wind speed", t: int16, f: 0.01, u: "m/s" },
-  0x45: { n: "temperature", t: int16, f: 0.1, u: "tC" },
-  0x46: { n: "UV index", t: int8, f: 0.1 },
-  0x5E: { n: "wind direction", t: int16, f: 0.01 },
-  0x5F: { n: "precipitation", t: int16, f: 0.1, u: "mm" },
-  0x60: { n: "channel", t: uint8 },
-  0xf0: { n: "dev_type", t: uint16 },
-  0xf1: { n: "fw_version", t: uint32 },
-  0xf2: { n: "fw_version_short", t: uint24 },
+  0x01: { n: "battery", t: uint8 },
+  0x02: { n: "temperature", t: int16, f: 0.01 },
+  0x03: { n: "humidity", t: uint16, f: 0.01 },
+  0x2e: { n: "humidity", t: uint8 },
+  0x45: { n: "temperature", t: int16, f: 0.1 }
 };
 
 function getByteSize(type) {
   if (type === uint8 || type === int8) return 1;
-  if (type === uint16 || type === int16 || type === dimmert) return 2;
-  if (type === uint24 || type === int24) return 3;
-  if (type === uint32 || type === int32) return 4;
+  if (type === uint16 || type === int16) return 2;
   return 255;
 }
 
@@ -222,9 +196,6 @@ const BTHomeDecoder = {
   getUInt8: function (buffer) {
     return buffer.at(0);
   },
-  getDimmer: function (buffer) {
-    return {"dimmer": buffer.at(0), "dimmersteps": buffer.at(1)};
-  },
   getInt8: function (buffer) {
     return this.utoi(this.getUInt8(buffer), 8);
   },
@@ -234,33 +205,13 @@ const BTHomeDecoder = {
   getInt16LE: function (buffer) {
     return this.utoi(this.getUInt16LE(buffer), 16);
   },
-  getUInt24LE: function (buffer) {
-    return (
-      0x00ffffff & ((buffer.at(2) << 16) | (buffer.at(1) << 8) | buffer.at(0))
-    );
-  },
-  getInt24LE: function (buffer) {
-    return this.utoi(this.getUInt24LE(buffer), 24);
-  },
-  getUInt32LE: function (buffer) {
-    return 0xffffffff & ((buffer.at(3) << 24) | (buffer.at(2) << 16) | (buffer.at(1) << 8) | buffer.at(0));
-  },
-  getInt32LE: function (buffer) {
-    return this.utoi(this.getUInt32LE(buffer), 32);
-  },
   getBufValue: function (type, buffer) {
     if (buffer.length < getByteSize(type)) return null;
-    let res = null;
-    if (type === uint8) res = this.getUInt8(buffer);
-    if (type === int8) res = this.getInt8(buffer);
-    if (type === uint16) res = this.getUInt16LE(buffer);
-    if (type === int16) res = this.getInt16LE(buffer);
-    if (type === uint24) res = this.getUInt24LE(buffer);
-    if (type === int24) res = this.getInt24LE(buffer);
-    if (type === uint32) res = this.getUInt32LE(buffer);
-    if (type === int32) res = this.getInt32LE(buffer);
-    if (type === dimmert) res = this.getDimmer(buffer);
-    return res;
+    if (type === uint8) return this.getUInt8(buffer);
+    if (type === int8) return this.getInt8(buffer);
+    if (type === uint16) return this.getUInt16LE(buffer);
+    if (type === int16) return this.getInt16LE(buffer);
+    return null;
   },
 
   unpack: function (buffer) {
@@ -278,18 +229,11 @@ const BTHomeDecoder = {
     while (buffer.length > 0) {
       _bth = BTH[buffer.at(0)];
       if (typeof _bth === "undefined") {
-        print("BTH: Unknown type: ", buffer.at(0));
         break;
       }
       buffer = buffer.slice(1);
       _value = this.getBufValue(_bth.t, buffer);
 
-      // handle dimmer special case
-      if (typeof _value === "object" && _bth.t === dimmert) {
-        result["dimmersteps"] = _value["dimmersteps"];
-        _value = _value["dimmer"];
-      }
-
       if (_value === null) break;
       if (typeof _bth.f !== "undefined") _value = _value * _bth.f;
 
@@ -378,3 +322,62 @@ function initBLE() {
 }
 
 initBLE();
+
+// Expose metrics for Prometheus
+if (typeof HTTPServer !== "undefined" && typeof HTTPServer.registerEndpoint === "function") {
+  HTTPServer.registerEndpoint("prometheus", function(req, res) {
+    var body = "";
+    
+    function addGauge(name, val, help) {
+      if ((typeof val === "number" && !isNaN(val)) || typeof val === "boolean") {
+        var numVal = (typeof val === "boolean") ? (val ? 1 : 0) : val;
+        if (help) {
+          body += "# HELP " + name + " " + help + "\n";
+        }
+        body += "# TYPE " + name + " gauge\n";
+        body += name + " " + numVal + "\n";
+      }
+    }
+
+    // Calculate helper values
+    var rh_crit = (typeof temperatur_innen !== "undefined" && !isNaN(temperatur_innen)) ? (critical_humi_base - critical_humi_temp_coeff * (temperatur_innen - critical_humi_ref_temp)) : undefined;
+    var rh_activation = (typeof rh_crit !== "undefined" && !isNaN(rh_crit)) ? (rh_crit - critical_humi_buffer) : undefined;
+    var is_critical_val = (typeof humidity_innen !== "undefined" && !isNaN(humidity_innen) && typeof rh_activation !== "undefined" && !isNaN(rh_activation)) ? (humidity_innen >= rh_activation) : undefined;
+
+    var would_fan_activate = false;
+    if (typeof is_critical_val !== "undefined" && is_critical_val !== null &&
+        typeof temperatur_innen !== "undefined" && !isNaN(temperatur_innen) &&
+        typeof humidity_innen !== "undefined" && !isNaN(humidity_innen) &&
+        typeof taupunkt_innen !== "undefined" && !isNaN(taupunkt_innen) &&
+        typeof taupunkt_aussen !== "undefined" && !isNaN(taupunkt_aussen)) {
+      would_fan_activate = is_critical_val &&
+                           (temperatur_innen > mindesttemperatur) &&
+                           (humidity_innen > mindesthumi) &&
+                           (taupunkt_innen > taupunkt_aussen + taupunktschwelle);
+    }
+
+    addGauge("taupi_temperature_celsius_innen", temperatur_innen, "Indoor temperature in Celsius");
+    addGauge("taupi_temperature_celsius_aussen", temperatur_aussen, "Outdoor temperature in Celsius");
+    addGauge("taupi_humidity_percent_innen", humidity_innen, "Indoor relative humidity in percent");
+    addGauge("taupi_humidity_percent_aussen", humidity_aussen, "Outdoor relative humidity in percent");
+    addGauge("taupi_dewpoint_celsius_innen", taupunkt_innen, "Indoor dew point in Celsius");
+    addGauge("taupi_dewpoint_celsius_aussen", taupunkt_aussen, "Outdoor dew point in Celsius");
+    addGauge("taupi_battery_percent_innen", battery_innen, "Indoor sensor battery percentage");
+    addGauge("taupi_battery_percent_aussen", battery_aussen, "Outdoor sensor battery percentage");
+    addGauge("taupi_lost_connection_seconds_innen", lost_connection_innen, "Seconds since last contact with indoor sensor");
+    addGauge("taupi_lost_connection_seconds_aussen", lost_connection_aussen, "Seconds since last contact with outdoor sensor");
+    addGauge("taupi_critical_humidity_threshold_percent", rh_activation, "Calculated relative humidity threshold above which it is critical");
+    addGauge("taupi_is_critical", is_critical_val, "Flag indicating mold danger inside (humidity exceeds threshold)");
+    addGauge("taupi_would_fan_activate", would_fan_activate, "Flag indicating if all fan activation criteria are met");
+    
+    var relay_status = Shelly.getComponentStatus("switch", 0);
+    if (relay_status && typeof relay_status.output !== "undefined") {
+      addGauge("taupi_relay_status", relay_status.output, "Physical switch status (1 = on, 0 = off)");
+    }
+
+    res.body = body;
+    res.headers = [["Content-Type", "text/plain; version=0.0.4"]];
+    res.code = 200;
+    res.send();
+  });
+}