feat(telemetry): add per-app metrics and log telemetry to hub reports (v0.28.0)

- New internal/metrics/telemetry.go: MetricsStore.GetContainerTelemetry()
  aggregates container memory/CPU from SQLite over the last 15 min
- New internal/metrics/logscanner.go: ScanContainerLogs() scans docker logs
  for errors/warnings, deduplicates via fingerprinting (strips timestamps,
  replaces 6+ digit numbers, hex strings, UUIDs)
- New internal/report/telemetry.go: buildAppTelemetrySection() assembles
  per-stack AppTelemetry by aggregating container metrics and log summaries
- internal/report/types.go: added AppTelemetry field to Report struct plus
  AppTelemetry type with memory/CPU/log fields and LogIssue references
- internal/report/builder.go: calls buildAppTelemetrySection() in BuildReport()
- Backward-compatible: old Hub versions silently ignore app_telemetry field

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

controller/internal/report/builder.go

@@ -150,9 +150,12 @@ func BuildReport(
 	// Stacks
 	r.Stacks = buildStacksReport(stackMgr)
 
+	// App telemetry (metrics + log scan)
+	r.AppTelemetry = buildAppTelemetrySection(stackMgr, metricsStore, logger)
+
 	if debug && logger != nil {
-		logger.Printf("[DEBUG] BuildReport: complete — containers=%d, health=%s, deployed=%d, available=%d",
-			r.Containers.Total, r.Health.Status, len(r.Stacks.Deployed), len(r.Stacks.Available))
+		logger.Printf("[DEBUG] BuildReport: complete — containers=%d, health=%s, deployed=%d, available=%d, app_telemetry=%d",
+			r.Containers.Total, r.Health.Status, len(r.Stacks.Deployed), len(r.Stacks.Available), len(r.AppTelemetry))
 	}
 
 	return r

controller/internal/report/telemetry.go

@@ -0,0 +1,119 @@
+package report
+
+import (
+	"log"
+	"sort"
+	"time"
+
+	"gitea.dooplex.hu/admin/felhom-controller/internal/metrics"
+	"gitea.dooplex.hu/admin/felhom-controller/internal/stacks"
+)
+
+// buildAppTelemetrySection collects metrics telemetry and log scans for all
+// non-protected, deployed stacks and returns per-app telemetry data.
+func buildAppTelemetrySection(stackMgr *stacks.Manager, metricsStore *metrics.MetricsStore, logger *log.Logger) []AppTelemetry {
+	allStacks := stackMgr.GetStacks()
+
+	// 1. Get metrics telemetry (last 15 minutes)
+	var telemetry []metrics.ContainerTelemetry
+	if metricsStore != nil {
+		var err error
+		telemetry, err = metricsStore.GetContainerTelemetry(time.Now().Add(-15 * time.Minute))
+		if err != nil && logger != nil {
+			logger.Printf("[WARN] Telemetry metrics query failed: %v", err)
+		}
+	}
+
+	// 2. Collect non-protected container names for log scan
+	var containerNames []string
+	for _, s := range allStacks {
+		if s.Protected || !s.Deployed {
+			continue
+		}
+		for _, c := range s.Containers {
+			containerNames = append(containerNames, c.Name)
+		}
+	}
+
+	// 3. Scan logs
+	logs := metrics.ScanContainerLogs(containerNames, 15*time.Minute, logger)
+
+	// 4. Build per-app telemetry
+	return buildAppTelemetry(allStacks, telemetry, logs)
+}
+
+// buildAppTelemetry aggregates container-level telemetry and log data into per-stack AppTelemetry entries.
+func buildAppTelemetry(allStacks []stacks.Stack, telemetry []metrics.ContainerTelemetry, logs []metrics.ContainerLogSummary) []AppTelemetry {
+	// Build lookup maps
+	telemetryMap := make(map[string]metrics.ContainerTelemetry, len(telemetry))
+	for _, ct := range telemetry {
+		telemetryMap[ct.ContainerName] = ct
+	}
+
+	logMap := make(map[string]metrics.ContainerLogSummary, len(logs))
+	for _, ls := range logs {
+		logMap[ls.ContainerName] = ls
+	}
+
+	var result []AppTelemetry
+
+	for _, s := range allStacks {
+		if s.Protected || !s.Deployed {
+			continue
+		}
+
+		app := AppTelemetry{
+			AppName:         s.Name,
+			DisplayName:     s.Meta.DisplayName,
+			CatalogEstimate: s.Meta.Resources.MemRequest,
+			CatalogLimit:    s.Meta.Resources.MemLimit,
+		}
+
+		var mergedIssues []metrics.LogIssue
+
+		for _, c := range s.Containers {
+			app.Containers = append(app.Containers, c.Name)
+
+			if ct, ok := telemetryMap[c.Name]; ok {
+				app.MemoryCurrentMB += ct.MemoryCurrentMB
+				app.MemoryAvgMB += ct.MemoryAvgMB
+				app.MemoryPeakMB += ct.MemoryPeakMB
+				app.CPUAvgPercent += ct.CPUAvgPercent
+			}
+
+			if ls, ok := logMap[c.Name]; ok {
+				app.LogErrors += ls.ErrorCount
+				app.LogWarnings += ls.WarnCount
+				mergedIssues = append(mergedIssues, ls.RecentIssues...)
+			}
+		}
+
+		if app.Containers == nil {
+			app.Containers = []string{}
+		}
+
+		// Sort and cap merged issues at 10
+		sort.Slice(mergedIssues, func(i, j int) bool {
+			if mergedIssues[i].Count != mergedIssues[j].Count {
+				return mergedIssues[i].Count > mergedIssues[j].Count
+			}
+			return mergedIssues[i].LastSeen.After(mergedIssues[j].LastSeen)
+		})
+		if len(mergedIssues) > 10 {
+			mergedIssues = mergedIssues[:10]
+		}
+		app.Issues = mergedIssues
+
+		result = append(result, app)
+	}
+
+	// Sort by app name
+	sort.Slice(result, func(i, j int) bool {
+		return result[i].AppName < result[j].AppName
+	})
+
+	if result == nil {
+		result = []AppTelemetry{}
+	}
+	return result
+}

controller/internal/report/types.go

@@ -1,6 +1,10 @@
 package report
 
-import "time"
+import (
+	"time"
+
+	"gitea.dooplex.hu/admin/felhom-controller/internal/metrics"
+)
 
 // Report is the JSON payload pushed to the central hub.
 type Report struct {
@@ -18,6 +22,7 @@ type Report struct {
 	Backup            BackupReport     `json:"backup"`
 	Health            HealthReport     `json:"health"`
 	Stacks            StacksReport     `json:"stacks"`
+	AppTelemetry      []AppTelemetry   `json:"app_telemetry,omitempty"`
 }
 
 // SystemReport holds host-level system info.
@@ -91,3 +96,19 @@ type StacksReport struct {
 	Deployed  []string `json:"deployed"`
 	Available []string `json:"available"`
 }
+
+// AppTelemetry holds per-app (per-stack) resource and log telemetry.
+type AppTelemetry struct {
+	AppName         string             `json:"app_name"`
+	DisplayName     string             `json:"display_name"`
+	Containers      []string           `json:"containers"`
+	MemoryCurrentMB float64            `json:"memory_current_mb"`
+	MemoryAvgMB     float64            `json:"memory_avg_mb"`
+	MemoryPeakMB    float64            `json:"memory_peak_mb"`
+	CPUAvgPercent   float64            `json:"cpu_avg_percent"`
+	CatalogEstimate string             `json:"catalog_estimate"`
+	CatalogLimit    string             `json:"catalog_limit"`
+	LogErrors       int                `json:"log_errors"`
+	LogWarnings     int                `json:"log_warnings"`
+	Issues          []metrics.LogIssue `json:"issues,omitempty"`
+}