refactor(platform): harden LAB evidence and telemetry

deploy/telemetry-plane/README.md

@@ -115,6 +115,12 @@ configuration and rolls back if the service does not return to `Running`. MQTT
 credentials are scoped to the service environment and must not be passed on a command
 line or stored in the repository.
 
+Both install and update configure Windows Service Control Manager recovery for
+Telegraf: restart after 5 seconds, then 30 seconds, then 60 seconds, with the failure
+counter reset after one day. The compute-contour worker network transition applies
+the same policy to already-provisioned agents and fails closed unless the worker
+confirms it.
+
 The same host service reads the existing perception worker's loopback `/health`
 contract with `Get-NdcMissionCorePipelineTelemetry.ps1` and publishes nine
 stage-keyed snapshots to the contour's `pipeline` topic. The perception container

deploy/telemetry-plane/telegraf/Install-NdcMissionCoreTelegraf.ps1

@@ -128,6 +128,15 @@ try {
         throw "Failed to apply the NDC service display name"
     }
     Set-Service -Name $serviceName -StartupType Automatic
+    & sc.exe failure $serviceName reset= 86400 `
+        actions= restart/5000/restart/30000/restart/60000 | Out-Null
+    if ($LASTEXITCODE -ne 0) {
+        throw "Failed to configure Telegraf service recovery actions"
+    }
+    & sc.exe failureflag $serviceName 1 | Out-Null
+    if ($LASTEXITCODE -ne 0) {
+        throw "Failed to enable Telegraf recovery for non-crash failures"
+    }
     Start-Service -Name $serviceName
     $service = Get-Service -Name $serviceName
     $service.WaitForStatus([ServiceProcess.ServiceControllerStatus]::Running, [TimeSpan]::FromSeconds(20))
@@ -140,6 +149,7 @@ try {
         DisplayName = $service.DisplayName
         Status = $service.Status.ToString()
         StartType = $service.StartType.ToString()
+        RecoveryConfigured = $true
         Configuration = $configurationPath
         PipelineCollector = $collectorPath
         PipelineJournal = $PipelineJournal

deploy/telemetry-plane/telegraf/Update-NdcMissionCoreTelegraf.ps1

@@ -118,8 +118,27 @@ try {
             [ServiceProcess.ServiceControllerStatus]::Running,
             [TimeSpan]::FromSeconds(20)
         )
+        & sc.exe failure $serviceName reset= 86400 `
+            actions= restart/5000/restart/30000/restart/60000 | Out-Null
+        if ($LASTEXITCODE -ne 0) {
+            throw "Failed to configure Telegraf service recovery actions"
+        }
+        & sc.exe failureflag $serviceName 1 | Out-Null
+        if ($LASTEXITCODE -ne 0) {
+            throw "Failed to enable Telegraf recovery for non-crash failures"
+        }
     }
     catch {
+        Stop-Service -Name $serviceName -Force -ErrorAction SilentlyContinue
+        $service = Get-Service -Name $serviceName
+        if ($service.Status -ne [ServiceProcess.ServiceControllerStatus]::Stopped) {
+            $service.WaitForStatus(
+                [ServiceProcess.ServiceControllerStatus]::Stopped,
+                [TimeSpan]::FromSeconds(20)
+            )
+        }
+        Set-ItemProperty -Path $serviceRegistryPath -Name Environment `
+            -Type MultiString -Value $serviceEnvironmentBefore
         Copy-Item -LiteralPath $backupPath -Destination $configurationPath
         if ($hadCollector) {
             Copy-Item -LiteralPath $backupCollectorPath -Destination $collectorPath
@@ -135,6 +154,7 @@ try {
         SchemaVersion = "missioncore.telemetry-agent-config-result/v1"
         ServiceName = $serviceName
         Status = (Get-Service -Name $serviceName).Status.ToString()
+        RecoveryConfigured = $true
         Configuration = $configurationPath
         Backup = $backupPath
         PipelineCollector = $collectorPath