fix: P0+P1 critical bug fixes across controller (24 files)

Concurrency fixes:
- Deep-copy stacks in GetStack/GetStacks to prevent shared state mutation (C04)
- Add per-state mutex to watchdog pathProbeState (C05)
- Guard MetricsCollector.Start() with sync.Once against double-start (C06)
- Hold diskJobMu across entire raw mount operation (C07)
- Add mutex to SetEncryptionKey (C08), MigrateEncryption write lock (H03)
- Use sync.Once for sync.Stop() channel close (H08)
- Set syncing=true before releasing lock in TriggerSync (H09)
- Deep-copy lastDBDump/lastBackup in GetFullStatus (H11)
- Add WaitGroup for stderr goroutine in MigrateDrive (H19)
- Add mutex to SetBackupRunningCheck (M18)

Security fixes:
- Validate Bearer token against Hub API key in CSRF middleware (H16)
- Validate backup paths start with expected prefix in RemoveStack (M12)
- Guard uuid[:8] slice with length check (H20)
- Parse fstab fields exactly for mount target matching (H21)

Bug fixes:
- Use decrypted env vars for compose deploy (C01)
- Log decrypt failures in DecryptMap instead of swallowing (C02)
- Move Deployed=false inside lock in runComposeDeploy (C03)
- Fix activeDrives() to skip disconnected drives (H02)
- Fix Snapshot() stderr extraction from exec.ExitError (H01)
- Check unlockCmd.Run() error in restic (H01)
- Buffer template rendering via bytes.Buffer (H07)
- Thread context.Context through cloudflare client (H10)
- Fix leaf-name collision detection in cross-drive backup (H15)
- Add nil check for crossDriveRunner (H17)
- Use strings.TrimSpace instead of slice on command output (H18)
- Make SaveAppConfig atomic with write-to-tmp+rename (H04)
- Pass encKey on deploy failure SaveAppConfig (H05)
- Fix IPv6 address format in TCP health probe

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

controller/internal/backup/backup.go

@@ -203,20 +203,22 @@ func (m *Manager) groupStacksByDrive() map[string][]StackSummary {
 }
 
 // activeDrives returns sorted list of drives that have deployed apps.
+// Disconnected and decommissioned drives are excluded.
 func (m *Manager) activeDrives() []string {
 	groups := m.groupStacksByDrive()
 	var drives []string
-	var disconnected []string
+	var skipped []string
 	for d := range groups {
 		if m.settings != nil && (m.settings.IsDisconnected(d) || m.settings.IsDecommissioned(d)) {
-			disconnected = append(disconnected, d)
+			skipped = append(skipped, d)
+			continue
 		}
 		drives = append(drives, d)
 	}
 	sort.Strings(drives)
 	if m.isDebug() {
-		m.logger.Printf("[DEBUG] activeDrives: %d total (%s), %d disconnected/decommissioned",
-			len(drives), strings.Join(drives, ", "), len(disconnected))
+		m.logger.Printf("[DEBUG] activeDrives: %d active (%s), %d skipped (disconnected/decommissioned)",
+			len(drives), strings.Join(drives, ", "), len(skipped))
 	}
 	return drives
 }
@@ -1211,11 +1213,10 @@ func (m *Manager) GetFullStatus(nextDBDump, nextBackup time.Time) *FullBackupSta
 	}
 
 	// No cache yet — return a minimal status (first page load before cache is populated)
-	return &FullBackupStatus{
+	// Deep-copy lastDBDump and lastBackup to prevent callers from mutating shared state.
+	status := &FullBackupStatus{
 		Enabled:        m.cfg.Backup.Enabled,
 		Running:        m.running,
-		LastDBDump:     m.lastDBDump,
-		LastBackup:     m.lastBackup,
 		DBDumpSchedule: m.cfg.Backup.DBDumpSchedule,
 		ResticSchedule: m.cfg.Backup.ResticSchedule,
 		PruneSchedule:  m.cfg.Backup.PruneSchedule,
@@ -1225,6 +1226,19 @@ func (m *Manager) GetFullStatus(nextDBDump, nextBackup time.Time) *FullBackupSta
 		LastCheckTime:  m.lastCheckTime,
 		LastCheckOK:    m.lastCheckOK,
 	}
+	if m.lastDBDump != nil {
+		copyDump := *m.lastDBDump
+		if len(m.lastDBDump.Results) > 0 {
+			copyDump.Results = make([]DumpResult, len(m.lastDBDump.Results))
+			copy(copyDump.Results, m.lastDBDump.Results)
+		}
+		status.LastDBDump = &copyDump
+	}
+	if m.lastBackup != nil {
+		copyBackup := *m.lastBackup
+		status.LastBackup = &copyBackup
+	}
+	return status
 }
 
 // isDebug returns true if logging level is "debug".

controller/internal/backup/crossdrive.go

@@ -372,7 +372,8 @@ func (r *CrossDriveRunner) runRsyncBackup(ctx context.Context, stackName, destBa
 		return fmt.Errorf("creating rsync dest dir: %w", err)
 	}
 
-	for i, srcMount := range mounts {
+	seen := make(map[string]bool)
+	for _, srcMount := range mounts {
 		var dstPath string
 		if len(mounts) == 1 {
 			// Single mount: rsync directly into the stack folder (no extra nesting)
@@ -380,13 +381,18 @@ func (r *CrossDriveRunner) runRsyncBackup(ctx context.Context, stackName, destBa
 		} else {
 			// Multiple mounts: use the leaf directory name as subfolder
 			leaf := filepath.Base(srcMount)
-			dstPath = filepath.Join(destDir, leaf)
-			// Disambiguate duplicate leaf names (e.g. two mounts both named "data")
-			if i > 0 {
-				if _, err := os.Stat(dstPath); err == nil {
-					dstPath = filepath.Join(destDir, fmt.Sprintf("%s_%d", leaf, i))
+			if seen[leaf] {
+				// Disambiguate duplicate leaf names (e.g. two mounts both named "data")
+				for j := 2; ; j++ {
+					candidate := fmt.Sprintf("%s_%d", leaf, j)
+					if !seen[candidate] {
+						leaf = candidate
+						break
+					}
 				}
 			}
+			seen[leaf] = true
+			dstPath = filepath.Join(destDir, leaf)
 		}
 		if err := os.MkdirAll(dstPath, 0755); err != nil {
 			return fmt.Errorf("creating rsync destination: %w", err)

controller/internal/backup/restic.go

@@ -134,12 +134,17 @@ func (r *ResticManager) Snapshot(repoPath string, paths []string, tags []string)
 	cmd := r.command(ctx, repoPath, args...)
 	out, err := cmd.Output()
 	if err != nil {
-		// Check for stale lock
+		// Check for stale lock — restic writes lock errors to stderr, not stdout
 		errStr := string(out)
+		if exitErr, ok := err.(*exec.ExitError); ok {
+			errStr += string(exitErr.Stderr)
+		}
 		if strings.Contains(errStr, "lock") || strings.Contains(errStr, "locked") {
 			r.logger.Printf("[WARN] Restic repo locked — attempting unlock")
 			unlockCmd := r.command(ctx, repoPath, "unlock")
-			unlockCmd.Run()
+			if unlockErr := unlockCmd.Run(); unlockErr != nil {
+				r.logger.Printf("[WARN] Restic unlock failed: %v", unlockErr)
+			}
 			// Retry once
 			cmd = r.command(ctx, repoPath, args...)
 			out, err = cmd.Output()