Stability hardening, build script fixes, GRUB bee logo

Stability hardening (webui/app):
- readFileLimited(): защита от OOM при чтении audit JSON (100 MB),
  component-status DB (10 MB) и лога задачи (50 MB)
- jobs.go: буферизованный лог задачи — один открытый fd на задачу
  вместо open/write/close на каждую строку (устраняет тысячи syscall/сек
  при GPU стресс-тестах)
- stability.go: экспоненциальный backoff в goRecoverLoop (2s→4s→…→60s),
  сброс при успешном прогоне >30s, счётчик перезапусков в slog
- kill_workers.go: таймаут 5s на скан /proc, warn при срабатывании
- bee-web.service: MemoryMax=3G — OOM killer защищён

Build script:
- build.sh: удалён блок генерации grub-pc/grub.cfg + live.cfg.in —
  мёртвый код с v8.25; grub-pc игнорируется live-build, а генерируемый
  live.cfg.in перезаписывал правильный статический файл устаревшей
  версией без tuning-параметров ядра и пунктов gsp-off/kms+gsp-off
- build.sh: dump_memtest_debug теперь логирует grub-efi/grub.cfg
  вместо grub-pc/grub.cfg (было всегда "missing")

GRUB:
- live-theme/bee-logo.png: логотип пчелы 400×400px на чёрном фоне
- live-theme/theme.txt: + image компонент по центру в верхней трети
  экрана; меню сдвинуто с 62% до 65%

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

audit/internal/app/app.go

@@ -304,7 +304,7 @@ func (a *App) ExportLatestAudit(target platform.RemovableTarget) (string, error)
 	}
 	filename := fmt.Sprintf("audit-%s-%s.json", sanitizeFilename(hostnameOr("unknown")), time.Now().UTC().Format("20060102-150405"))
 	tmpPath := filepath.Join(os.TempDir(), filename)
-	data, err := os.ReadFile(DefaultAuditJSONPath)
+	data, err := readFileLimited(DefaultAuditJSONPath, 100<<20)
 	if err != nil {
 		return "", err
 	}

audit/internal/app/atomic_write.go

@@ -2,10 +2,29 @@ package app
 
 import (
 	"fmt"
+	"io"
 	"os"
 	"path/filepath"
 )
 
+// readFileLimited reads path into memory, refusing files larger than maxBytes.
+// Prevents OOM on corrupted or unexpectedly large data files.
+func readFileLimited(path string, maxBytes int64) ([]byte, error) {
+	f, err := os.Open(path)
+	if err != nil {
+		return nil, err
+	}
+	defer f.Close()
+	data, err := io.ReadAll(io.LimitReader(f, maxBytes+1))
+	if err != nil {
+		return nil, err
+	}
+	if int64(len(data)) > maxBytes {
+		return nil, fmt.Errorf("file %s too large (exceeds %d bytes)", path, maxBytes)
+	}
+	return data, nil
+}
+
 func atomicWriteFile(path string, data []byte, perm os.FileMode) error {
 	if err := os.MkdirAll(filepath.Dir(path), 0755); err != nil {
 		return fmt.Errorf("mkdir %s: %w", filepath.Dir(path), err)

audit/internal/app/component_status_db.go

@@ -46,7 +46,7 @@ func OpenComponentStatusDB(path string) (*ComponentStatusDB, error) {
 	if err := os.MkdirAll(filepath.Dir(path), 0755); err != nil {
 		return nil, err
 	}
-	data, err := os.ReadFile(path)
+	data, err := readFileLimited(path, 10<<20)
 	if err != nil && !os.IsNotExist(err) {
 		return nil, err
 	}

audit/internal/platform/kill_workers.go

@@ -1,11 +1,14 @@
 package platform
 
 import (
+	"context"
 	"fmt"
+	"log/slog"
 	"os"
 	"strconv"
 	"strings"
 	"syscall"
+	"time"
 )
 
 // workerPatterns are substrings matched against /proc/<pid>/cmdline to identify
@@ -30,7 +33,12 @@ type KilledProcess struct {
 // KillTestWorkers scans /proc for running test worker processes and sends
 // SIGKILL to each one found. It returns a list of killed processes.
 // Errors for individual processes (e.g. already exited) are silently ignored.
+// The scan runs under a 5-second deadline to avoid blocking if the process
+// table is very large (e.g. after a stress test with thousands of children).
 func KillTestWorkers() []KilledProcess {
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
 	entries, err := os.ReadDir("/proc")
 	if err != nil {
 		return nil
@@ -38,6 +46,13 @@ func KillTestWorkers() []KilledProcess {
 
 	var killed []KilledProcess
 	for _, e := range entries {
+		select {
+		case <-ctx.Done():
+			slog.Warn("KillTestWorkers scan timed out", "killed_so_far", len(killed))
+			return killed
+		default:
+		}
+
 		if !e.IsDir() {
 			continue
 		}

audit/internal/webui/jobs.go

@@ -1,6 +1,9 @@
 package webui
 
 import (
+	"bufio"
+	"fmt"
+	"io"
 	"os"
 	"strings"
 	"sync"
@@ -17,6 +20,25 @@ type jobState struct {
 	cancel       func() // optional cancel function; nil if job is not cancellable
 	logPath      string
 	serialPrefix string
+	logFile      *os.File    // kept open for the task lifetime to avoid per-line open/close
+	logBuf       *bufio.Writer
+}
+
+// readTaskLogFile reads a task log, refusing files over 50 MB.
+func readTaskLogFile(path string) ([]byte, error) {
+	f, err := os.Open(path)
+	if err != nil {
+		return nil, err
+	}
+	defer f.Close()
+	data, err := io.ReadAll(io.LimitReader(f, 50<<20+1))
+	if err != nil {
+		return nil, err
+	}
+	if int64(len(data)) > 50<<20 {
+		return nil, fmt.Errorf("task log %s too large (exceeds 50 MB)", path)
+	}
+	return data, nil
 }
 
 // abort cancels the job if it has a cancel function and is not yet done.
@@ -35,7 +57,7 @@ func (j *jobState) append(line string) {
 	defer j.mu.Unlock()
 	j.lines = append(j.lines, line)
 	if j.logPath != "" {
-		appendJobLog(j.logPath, line)
+		j.writeLogLineLocked(line)
 	}
 	if j.serialPrefix != "" {
 		taskSerialWriteLine(j.serialPrefix + line)
@@ -48,6 +70,35 @@ func (j *jobState) append(line string) {
 	}
 }
 
+// writeLogLineLocked writes a line to the persistent log file, opening it lazily.
+// Must be called with j.mu held. Uses a buffered writer kept open for the task
+// lifetime — avoids thousands of open/close syscalls during high-frequency logs.
+func (j *jobState) writeLogLineLocked(line string) {
+	if j.logFile == nil {
+		f, err := os.OpenFile(j.logPath, os.O_CREATE|os.O_APPEND|os.O_WRONLY, 0644)
+		if err != nil {
+			return
+		}
+		j.logFile = f
+		j.logBuf = bufio.NewWriterSize(f, 64*1024)
+	}
+	_, _ = j.logBuf.WriteString(line + "\n")
+}
+
+// closeLog flushes and closes the log file. Called after all task output is done.
+func (j *jobState) closeLog() {
+	j.mu.Lock()
+	defer j.mu.Unlock()
+	if j.logBuf != nil {
+		_ = j.logBuf.Flush()
+	}
+	if j.logFile != nil {
+		_ = j.logFile.Close()
+		j.logFile = nil
+		j.logBuf = nil
+	}
+}
+
 func (j *jobState) finish(errMsg string) {
 	j.mu.Lock()
 	defer j.mu.Unlock()
@@ -119,7 +170,7 @@ func newTaskJobState(logPath string, serialPrefix ...string) *jobState {
 	if logPath == "" {
 		return j
 	}
-	data, err := os.ReadFile(logPath)
+	data, err := readTaskLogFile(logPath)
 	if err != nil || len(data) == 0 {
 		return j
 	}

audit/internal/webui/stability.go

@@ -7,14 +7,43 @@ import (
 	"time"
 )
 
+const (
+	recoverLoopMaxDelay   = 60 * time.Second
+	recoverLoopResetAfter = 30 * time.Second
+)
+
+// goRecoverLoop starts fn in a goroutine, restarting after panics.
+// restartDelay is the initial delay; successive panics double it up to
+// recoverLoopMaxDelay. The delay resets to restartDelay once fn runs
+// successfully for recoverLoopResetAfter without panicking.
 func goRecoverLoop(name string, restartDelay time.Duration, fn func()) {
 	go func() {
+		delay := restartDelay
+		consecutive := 0
 		for {
-			if !runRecoverable(name, fn) {
+			start := time.Now()
+			panicked := runRecoverable(name, fn)
+			if !panicked {
 				return
 			}
-			if restartDelay > 0 {
-				time.Sleep(restartDelay)
+			consecutive++
+			if time.Since(start) >= recoverLoopResetAfter {
+				delay = restartDelay
+				consecutive = 1
+			}
+			slog.Warn("goroutine restarting after panic",
+				"component", name,
+				"consecutive_panics", consecutive,
+				"next_delay", delay,
+			)
+			if delay > 0 {
+				time.Sleep(delay)
+			}
+			if delay < recoverLoopMaxDelay {
+				delay *= 2
+				if delay > recoverLoopMaxDelay {
+					delay = recoverLoopMaxDelay
+				}
 			}
 		}
 	}()

audit/internal/webui/tasks.go

@@ -585,6 +585,7 @@ func (q *taskQueue) finalizeTaskRun(t *Task, j *jobState) {
 	if err := writeTaskReportArtifacts(t); err != nil {
 		appendJobLog(t.LogPath, "WARN: task report generation failed: "+err.Error())
 	}
+	j.closeLog()
 	if t.ErrMsg != "" {
 		taskSerialEvent(t, "finished with status="+t.Status+" error="+t.ErrMsg)
 		return