v0.24.0 — Pre-testing observability: debug logging, diagnostic dump, startup self-test

- Add [DEBUG] logging across all modules (backup, storage, sync, selfupdate,
  monitor, notify, report, assets, setup) gated behind logging.level: "debug"
- Add /api/debug/dump endpoint returning full controller state JSON (debug only)
- Add startup self-test validating 9 subsystems (Docker, dirs, storage, hub,
  restic repos, metrics DB) with pass/warn/fail summary
- New packages: internal/selftest, internal/util
- Constructor/signature changes: debug bool params, logger params on
  RunHealthCheck and BuildReport, smart watchdog probe logging

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

controller/internal/report/builder.go

@@ -4,6 +4,7 @@ import (
 	"crypto/sha256"
 	"encoding/hex"
 	"fmt"
+	"log"
 	"os"
 	"strconv"
 	"strings"
@@ -29,7 +30,13 @@ func BuildReport(
 	metricsStore *metrics.MetricsStore,
 	version string,
 	storagePaths []settings.StoragePath,
+	logger *log.Logger,
 ) *Report {
+	debug := cfg.Logging.Level == "debug"
+	if debug && logger != nil {
+		logger.Printf("[DEBUG] BuildReport: starting — version=%s, storagePaths=%d", version, len(storagePaths))
+	}
+
 	r := &Report{
 		Version:           1,
 		CustomerID:        cfg.Customer.ID,
@@ -48,6 +55,9 @@ func BuildReport(
 		if data, err := os.ReadFile(configPath); err == nil {
 			h := sha256.Sum256(data)
 			r.ConfigHash = hex.EncodeToString(h[:])
+			if debug && logger != nil {
+				logger.Printf("[DEBUG] BuildReport: configHash=%s (%d bytes)", r.ConfigHash[:12]+"...", len(data))
+			}
 		}
 	}
 
@@ -111,6 +121,12 @@ func BuildReport(
 		})
 	}
 
+	if debug && logger != nil {
+		logger.Printf("[DEBUG] BuildReport: system info collected — cpu=%.1f%%, mem=%d/%dMB, temp=%.1fC",
+			sysInfo.CPUPercent, sysInfo.UsedMemMB, sysInfo.TotalMemMB, sysInfo.TemperatureCelsius)
+		logger.Printf("[DEBUG] BuildReport: storage entries=%d", len(r.Storage))
+	}
+
 	// Containers
 	r.Containers = buildContainerReport(stackMgr, metricsStore)
 
@@ -118,7 +134,7 @@ func BuildReport(
 	r.Backup = buildBackupReport(cfg, backupMgr)
 
 	// Health
-	healthReport := monitor.RunHealthCheck(cfg, cpuCollector, storagePaths)
+	healthReport := monitor.RunHealthCheck(cfg, cpuCollector, storagePaths, logger)
 	r.Health = HealthReport{
 		Status:   healthReport.Status,
 		Issues:   healthReport.Issues,
@@ -134,6 +150,11 @@ func BuildReport(
 	// Stacks
 	r.Stacks = buildStacksReport(stackMgr)
 
+	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))
+	}
+
 	return r
 }
 

controller/internal/report/pusher.go

@@ -35,6 +35,7 @@ type Pusher struct {
 	httpClient *http.Client
 	logger     *log.Logger
 	enabled    bool
+	debug      bool
 
 	statusMu sync.RWMutex
 	status   PushStatus
@@ -45,7 +46,7 @@ type Pusher struct {
 }
 
 // NewPusher creates a new report pusher from hub configuration.
-func NewPusher(cfg *config.HubConfig, logger *log.Logger) *Pusher {
+func NewPusher(cfg *config.HubConfig, logger *log.Logger, debug bool) *Pusher {
 	return &Pusher{
 		hubURL: strings.TrimRight(cfg.URL, "/"),
 		apiKey: cfg.APIKey,
@@ -54,6 +55,7 @@ func NewPusher(cfg *config.HubConfig, logger *log.Logger) *Pusher {
 		},
 		logger:  logger,
 		enabled: cfg.Enabled,
+		debug:   debug,
 	}
 }
 
@@ -69,6 +71,9 @@ func (p *Pusher) Push(report *Report) error {
 	}
 
 	url := p.hubURL + "/api/v1/report"
+	if p.debug {
+		p.logger.Printf("[DEBUG] Push: url=%s payload=%d bytes", url, len(data))
+	}
 
 	p.statusMu.Lock()
 	p.status.LastAttempt = time.Now()
@@ -143,6 +148,9 @@ func (p *Pusher) PushInfraBackup(data []byte) error {
 	}
 
 	url := p.hubURL + "/api/v1/infra-backup"
+	if p.debug {
+		p.logger.Printf("[DEBUG] PushInfraBackup: url=%s payload=%d bytes", url, len(data))
+	}
 
 	var lastErr error
 	for attempt := 0; attempt < 3; attempt++ {
@@ -173,6 +181,9 @@ func (p *Pusher) PushInfraBackup(data []byte) error {
 			return nil
 		}
 		lastErr = fmt.Errorf("HTTP %d", resp.StatusCode)
+		if p.debug {
+			p.logger.Printf("[DEBUG] PushInfraBackup: attempt %d failed — HTTP %d", attempt+1, resp.StatusCode)
+		}
 	}
 
 	return fmt.Errorf("infra backup push failed after 3 attempts: %w", lastErr)