Separate network faults from software drops and fix CPU temperature history

cpu.go

@@ -3,6 +3,7 @@ package main
 import (
 	"bufio"
 	"fmt"
+	"math"
 	"os"
 	"path/filepath"
 	"strconv"
@@ -33,15 +34,16 @@ type CPUStatic struct {
 
 type CPUMetrics struct {
 	CPUStatic
-	UsagePercent float64        `json:"usagePercent"`
-	FrequencyMHz float64        `json:"frequencyMhz"`
-	Load1        float64        `json:"load1"`
-	Load5        float64        `json:"load5"`
-	Load15       float64        `json:"load15"`
-	Uptime       uint64         `json:"uptimeSeconds"`
-	Temperatures []Temperature  `json:"temperatures"`
-	TopProcesses []AgentProcess `json:"topProcesses"`
-	CollectedAt  time.Time      `json:"collectedAt"`
+	UsagePercent       float64        `json:"usagePercent"`
+	FrequencyMHz       float64        `json:"frequencyMhz"`
+	Load1              float64        `json:"load1"`
+	Load5              float64        `json:"load5"`
+	Load15             float64        `json:"load15"`
+	Uptime             uint64         `json:"uptimeSeconds"`
+	TemperatureCelsius *float64       `json:"temperatureCelsius"`
+	Temperatures       []Temperature  `json:"temperatures"`
+	TopProcesses       []AgentProcess `json:"topProcesses"`
+	CollectedAt        time.Time      `json:"collectedAt"`
 }
 
 type Temperature struct {
@@ -90,10 +92,11 @@ func (c *cpuCollector) collect() (CPUMetrics, error) {
 	load1, load5, load15, _ := readLoadAverage()
 	uptime, _ := readUptime()
 
+	temperatures := readTemperatures()
 	return CPUMetrics{
 		CPUStatic: c.static, UsagePercent: usage, FrequencyMHz: frequency,
 		Load1: load1, Load5: load5, Load15: load15, Uptime: uptime,
-		Temperatures: readTemperatures(), TopProcesses: collectAgentProcesses(), CollectedAt: time.Now(),
+		Temperatures: temperatures, TemperatureCelsius: cpuTemperature(temperatures), TopProcesses: collectAgentProcesses(), CollectedAt: time.Now(),
 	}, nil
 }
 
@@ -285,3 +288,19 @@ func isCPUTemperatureChip(name string) bool {
 		return false
 	}
 }
+
+// cpuTemperature is the hottest CPU sensor, shared by live and historical views.
+// Do not average Tctl/Tdie with cooler cores or CCDs.
+func cpuTemperature(temperatures []Temperature) *float64 {
+	var hottest *float64
+	for _, t := range temperatures {
+		if math.IsNaN(t.Celsius) || math.IsInf(t.Celsius, 0) || t.Celsius <= 0 {
+			continue
+		}
+		if hottest == nil || t.Celsius > *hottest {
+			value := t.Celsius
+			hottest = &value
+		}
+	}
+	return hottest
+}