fix(aibox): batch H audit fixes - subagent cancel propagation, scheduler timeout, exec process-group reaping

Fourth audit round (see docs/reports/aibox_audit_20260817.md §11):
- H1: shared parent cancel event no longer cleared on subagent first think
  (N5 regression); parent-already-cancelled skips subagent start
- M1: /reload_prompts moved off event loop (run_in_executor, N3 sibling)
- M2: skill --help scan prewarmed before serving connections
- M3: scheduler task-level timeout (scheduler.task_timeout, default 600s)
- M4: get_recent_memories(None) capped instead of full-table load
- M5: memo delete now physically removes rows (was complete-only)
- M6: PromptManager.reload builds new list then atomically swaps
- L1-L12: read_file arg coercion, proxy save failure reported, SSE
  utf-8 tolerance, persona realpath check, truncation char boundary,
  compressor div0, skill path quoting, ask_user required, POSIX
  process-group kill (pgid captured at Popen), web scheme whitelist,
  registry redact substring match, Bearer redaction in failover logs

aibox/aibox.py

@@ -328,14 +328,35 @@ class TaskScheduler:
             ai_thread.daemon = True
             ai_thread.start()
             
-            # 等待 AI 完成，同时处理可能的取消
+            # M3（审计 2026-08-18）：任务级超时兜底。此前 await ai_future
+            # 无任何超时/取消路径——AI think 卡死（LLM 挂起、子进程不可杀）
+            # 时该任务永不返回，调度器 run 循环顺序 await 被阻塞，后续全部
+            # 定时/即时任务不再执行且任务已 mark_as_triggered 不会重试。
+            # 到点 call_later 触发 ai.cancel()（置取消事件 + 关在途 HTTP 流），
+            # worker 线程自然收尾，调度循环继续。
+            task_timeout = float(ConfigManager().get("scheduler.task_timeout", 600))
+            timed_out = threading.Event()
+
+            def _timeout_cancel():
+                timed_out.set()
+                try:
+                    ai.cancel()
+                except Exception:
+                    pass
+
+            timeout_handle = loop.call_later(task_timeout, _timeout_cancel)
             try:
                 response = await ai_future
                 result = response or "AI无响应"
             except Exception as e:
-                self.logger.error(f"AI对话失败: {e}")
+                if timed_out.is_set():
-                result = f"任务执行但AI对话失败: {str(e)}"
+                    self.logger.error(f"任务执行超时（{task_timeout}秒），AI 已取消")
+                    result = f"任务执行超时（{task_timeout}秒），AI 已取消"
+                else:
+                    self.logger.error(f"AI对话失败: {e}")
+                    result = f"任务执行但AI对话失败: {str(e)}"
             finally:
+                timeout_handle.cancel()
                 # 确保线程结束
                 ai_thread.join(timeout=1.0)
             
@@ -534,10 +555,11 @@ class ExpressEmotionTool(Tool):
         if not name:
             return ""
         path = os.path.join(constants.SKILLS_DIR, name + ".md")
-        # N12：persona 为 LLM 可控输入，做路径边界校验——normcase 统一大小写与
+        # N12 + L4（审计 2026-08-18）：persona 为 LLM 可控输入。abspath 前缀
-        # 分隔符后要求解析结果仍在 SKILLS_DIR 内，防止 ../../ 越界读取并注入
+        # 检查拦截 ../ 越界，但符号链接可绕过（skills 目录内软链指向任意文件
+        # 即被读取注入）；realpath 解析软链后再做前缀校验。
         skills_root = os.path.normcase(os.path.abspath(constants.SKILLS_DIR))
-        resolved = os.path.normcase(os.path.abspath(path))
+        resolved = os.path.normcase(os.path.realpath(path))
         if not resolved.startswith(skills_root + os.sep):
             self.logger.warning(f"人格技能名非法（越界路径）: {name}")
             return ""
@@ -673,6 +695,14 @@ def run_full_subagent(role, task, config, logger=None, model=None,
         # 深度中断（sub_chat.cancel() 强关在途 HTTP 流并 kill 其子进程）。
         if cancel_event is not None:
             sub_chat._cancel_event = cancel_event
+            # H1（审计 2026-08-18）：共享父事件后禁止子代理首轮 clear——
+            # _think_and_respond_impl 首轮无条件 clear() 会吞掉父级已置位的
+            # 取消信号（用户中断 / --once 超时恰落在子代理生成窗口时被清掉，
+            # 观察者线程随之失效，子代理跑完全程）。置位后立即检查一次，
+            # 父级已取消则不再启动子代理。
+            sub_chat._shared_cancel_event = True
+            if cancel_event.is_set():
+                return "❌ 子代理已因父级取消而终止"
 
             def _watch_parent_cancel():
                 while not _watch_done.wait(timeout=0.2):
@@ -1456,8 +1486,9 @@ class DeepSeekChat:
     
     def _think_and_respond_impl(self, input_text: str, output_callback: Callable = None, is_continuation: bool = False) -> Optional[str]:
         """think_and_respond 的实际实现，在 _msg_lock 保护下执行。"""
-        # 首轮开始时清除取消标志
+        # 首轮开始时清除取消标志（H1：共享父事件的子代理不清除——清除会
-        if not is_continuation:
+        # 吞掉父级已置位的取消信号，使中断/--once 超时失效）
+        if not is_continuation and not getattr(self, "_shared_cancel_event", False):
             self._cancel_event.clear()
         
         # 立即检查是否已被取消
@@ -2492,10 +2523,17 @@ class WebSocketHandler:
         elif command == "/reload_prompts":
             session = self._get_session(websocket)
             ai = session.get("ai") if session else None
-            if ai:
+            # M1（审计 2026-08-18）：reload_prompts 内部同步获取 _msg_lock
-                new_count = ai.reload_prompts()
+            # （繁忙对话持锁可达数十秒），直接调用会冻结整个事件循环——
-            else:
+            # N3 只修了 /new，这里同类遗漏。移入线程池执行。
-                new_count = self.ai_manager.prompt_manager.reload()
+            loop = asyncio.get_running_loop()
+
+            def _do_reload_prompts():
+                if ai:
+                    return ai.reload_prompts()
+                return self.ai_manager.prompt_manager.reload()
+
+            new_count = await loop.run_in_executor(None, _do_reload_prompts)
             await self.send_message(websocket, {
                 "type": "command_result",
                 "content": i18n.get('prompts_reloaded', new_count)
@@ -2883,12 +2921,17 @@ class EnhancedAIManager:
         port = constants.WEBSOCKET_PORT
         
         self.ws_handler = WebSocketHandler(self)
+        # M2（审计 2026-08-18）：技能扫描对每个可执行技能串行跑 --help
+        # 子进程（各 ≤10s），懒加载于首条消息/首个任务时在事件循环线程
+        # 执行会冻结整个服务。启动前预热，把扫描成本移到连接建立之前。
+        self.ws_handler._get_shared_skill_manager()
         
         # 如果启用了任务调度器，创建并启动
         if constants.SCHEDULER_ENABLED:
             self.scheduler = TaskScheduler(asyncio.get_running_loop(), self.logger)
             self.scheduler.set_websocket_handler(self.ws_handler)
             self.scheduler.set_ai_manager(self)  # 设置AI管理器引用
+            self.scheduler._get_shared_skill_manager()
         
         async def handler(websocket):
             await self.handle_connection(websocket, None)

aibox/common/config.py

@@ -278,27 +278,32 @@ class ConfigManager:
             "password_env": password_env
         }
         if save:
-            self._save_config()
+            return self._save_config()
         return True
 
-    def _save_config(self):
+    def _save_config(self) -> bool:
-        """将当前配置保存到配置文件（覆盖）。
+        """将当前配置保存到配置文件（覆盖）。返回是否成功落盘。
 
         落盘前对代理密码做纵深防御脱敏：无论调用路径如何，明文密码一律不写入文件。
+        L2（审计 2026-08-18）：此前异常仅 print，set_proxy 无条件报"已保存"，
+        磁盘只读等场景下用户以为已持久化，重启后配置丢失。
         """
         config_path = self._config_path
-        if config_path:
+        if not config_path:
-            try:
+            return False
-                safe_config = copy.deepcopy(self._config)
+        try:
-                socks = safe_config.get("proxy", {}).get("socks5")
+            safe_config = copy.deepcopy(self._config)
-                if socks and socks.get("password"):
+            socks = safe_config.get("proxy", {}).get("socks5")
-                    socks["password"] = None
+            if socks and socks.get("password"):
-                os.makedirs(os.path.dirname(config_path), exist_ok=True)
+                socks["password"] = None
-                with open(config_path, 'w', encoding='utf-8') as f:
+            os.makedirs(os.path.dirname(config_path), exist_ok=True)
-                    json.dump(safe_config, f, ensure_ascii=False, indent=2)
+            with open(config_path, 'w', encoding='utf-8') as f:
-                print(f"✅ 配置已保存到 {config_path}")
+                json.dump(safe_config, f, ensure_ascii=False, indent=2)
-            except Exception as e:
+            print(f"✅ 配置已保存到 {config_path}")
-                print(f"⚠️ 保存配置失败: {e}")
+            return True
+        except Exception as e:
+            print(f"⚠️ 保存配置失败: {e}")
+            return False
 
     def get_proxy_info(self) -> Dict:
         """获取代理配置的详细信息（用于显示，不回传任何密码值）"""

aibox/llm_client.py

@@ -22,9 +22,21 @@ from typing import Dict, Iterator, List, Optional
 
 import json
 import os
+import re
 import time
 import requests
 
+# L12（审计 2026-08-18）：瞬时错误体可能回显网关/WAF 错误页中的
+# Authorization 头，抹掉 Bearer 令牌后再进日志，防密钥落盘
+_AUTH_HEADER_RE = re.compile(r"Bearer\s+[A-Za-z0-9._~+/=-]+")
+
+
+def _sanitize_log_msg(msg: str) -> str:
+    """日志脱敏：替换错误消息中的 Bearer 令牌。"""
+    if not msg:
+        return msg
+    return _AUTH_HEADER_RE.sub("Bearer ***", msg)
+
 
 class LLMClient(ABC):
     """大模型客户端抽象基类。子类需实现流式/非流式两种调用，并归一化为统一事件格式。"""
@@ -64,7 +76,7 @@ class LLMClient(ABC):
     def _log(self, level: str, msg: str):
         if self.logger is not None and hasattr(self.logger, level):
             try:
-                getattr(self.logger, level)(msg)
+                getattr(self.logger, level)(_sanitize_log_msg(msg))
             except Exception:
                 pass
 
@@ -219,7 +231,7 @@ class DeepSeekClient(LLMClient):
             for line in response.iter_lines():
                 if not line:
                     continue
-                line_text = line.decode("utf-8")
+                line_text = line.decode("utf-8", errors="replace")  # L3：非 UTF-8 行不中断流
                 if not line_text.startswith("data: "):
                     continue
                 data = line_text[6:]
@@ -352,7 +364,7 @@ class FailoverClient:
     def _log(self, level: str, msg: str):
         if self.logger is not None and hasattr(self.logger, level):
             try:
-                getattr(self.logger, level)(msg)
+                getattr(self.logger, level)(_sanitize_log_msg(msg))
             except Exception:
                 pass
 
@@ -382,7 +394,7 @@ class FailoverClient:
         self._stats["failovers"] += 1
         try:
             if self.on_failover is not None:
-                self.on_failover(from_name, to_name, reason)
+                self.on_failover(from_name, to_name, _sanitize_log_msg(reason))
         except Exception as e:
             self._log("warning", f"on_failover 回调异常（忽略）: {e}")
 

aibox/subsystems/conversation_compressor.py

@@ -514,7 +514,8 @@ class ConversationCompressor:
         final_tokens = self.estimate_tokens([m for m in final_messages if m.get("role") != "system"])
 
         print(f"\n✅ {i18n.get('conversation_compressed', original_count, final_count)}")
-        print(f"   Token: {original_tokens} -> {final_tokens} (压缩率: {final_tokens/original_tokens:.1%})")
+        # L6：压缩块全空时 original_tokens 可能为 0，除零防护
+        print(f"   Token: {original_tokens} -> {final_tokens} (压缩率: {final_tokens / max(original_tokens, 1):.1%})")
 
         # 检查是否压缩到阈值以下
         if final_count >= threshold:

aibox/subsystems/db.py

@@ -232,14 +232,15 @@ class MemoryDatabase:
         return results
 
     def get_recent_memories(self, limit: int = 10) -> List[Dict]:
-        """获取最近的记忆。limit=None 时不限制返回条数（供分页使用）。"""
+        """获取最近的记忆。limit=None 时使用默认上限（M4：此前 None 无 LIMIT
+        全表加载，记忆库增长后单次调用 fetchall 全量入内存；与 search_memories
+        的 None→默认上限语义对齐）。"""
+        if limit is None:
+            limit = constants.MEMORY_MAX_SEARCH_RESULTS
         with sqlite3.connect(self.db_path) as conn:
             conn.row_factory = sqlite3.Row
             cursor = conn.cursor()
-            if limit is None:
+            cursor.execute('SELECT * FROM memories ORDER BY end_time DESC LIMIT ?', (limit,))
-                cursor.execute('SELECT * FROM memories ORDER BY end_time DESC')
-            else:
-                cursor.execute('SELECT * FROM memories ORDER BY end_time DESC LIMIT ?', (limit,))
 
             results = []
             for row in cursor.fetchall():
@@ -672,6 +673,15 @@ class MemoDatabase:
             return True
         return False
 
+    def delete_memo(self, memo_id: int) -> bool:
+        """物理删除任务（M5：delete 语义此前被 complete_memo 顶替——只标记
+        完成不删行，重复任务还会被推进而非移除，stats 计数失真）"""
+        with sqlite3.connect(self.db_path) as conn:
+            cursor = conn.cursor()
+            cursor.execute("DELETE FROM memos WHERE id = ?", (memo_id,))
+            conn.commit()
+            return cursor.rowcount > 0
+
     def get_memo_stats(self) -> Dict:
         """获取任务统计信息"""
         with sqlite3.connect(self.db_path) as conn:

aibox/subsystems/executors.py

@@ -13,6 +13,7 @@ subsystems.executors - 命令执行器
 
 import os
 import queue
+import signal
 import subprocess
 import threading
 import time
@@ -71,17 +72,44 @@ class SubprocessCommandExecutor(CommandExecutor):
     def __init__(self, logger=None):
         super().__init__(logger)
         self._current_process = None
+        self._current_pgid = None  # L9：Popen 后立即捕获，shell 死亡后 getpgid 会失败
         self._process_lock = threading.Lock()
 
+    def _terminate_tree(self, proc, force: bool = False):
+        """终止整个进程组（L9：POSIX 下 shell=True 只杀 shell 时，孙进程
+        （`(x &)` 等）仍持管道写端——reader 阻塞无 EOF、fd/线程悬挂至孙
+        进程退出，写满 64KB 管道缓冲后孙进程也卡死。start_new_session 使
+        shell 成为会话首进程，按组信号可一次覆盖整棵进程树）。
+        组 ID 在 Popen 后立即保存：shell 死亡后 os.getpgid(pid) 会抛
+        ProcessLookupError，届时无法再从进程反查组。
+        Windows 无进程组概念，退回单进程 terminate/kill。"""
+        try:
+            if os.name == "posix":
+                sig = signal.SIGKILL if force else signal.SIGTERM
+                with self._process_lock:
+                    pgid = self._current_pgid
+                if pgid is None:
+                    pgid = os.getpgid(proc.pid)
+                os.killpg(pgid, sig)
+            elif force:
+                proc.kill()
+            else:
+                proc.terminate()
+        except Exception:
+            try:
+                proc.kill()
+            except Exception:
+                pass
+
     def cancel(self):
-        """取消当前正在运行的命令（kill子进程）。线程安全。"""
+        """取消当前正在运行的命令（kill子进程组）。线程安全。"""
         with self._process_lock:
             proc = self._current_process
         if proc is not None:
             try:
                 if proc.poll() is None:
-                    proc.kill()
+                    self._terminate_tree(proc, force=True)
-                    self.logger.info("已终止正在运行的子进程")
+                    self.logger.info("已终止正在运行的子进程组")
             except Exception:
                 pass
 
@@ -117,14 +145,14 @@ class SubprocessCommandExecutor(CommandExecutor):
         while True:
             # 检查超时（readline 阻塞不再影响本判断）
             if timeout > 0 and time.time() - start_time > timeout:
-                process.terminate()
+                self._terminate_tree(process)
                 timeout_occurred = True
                 break
 
             # 检查输出大小
             if total_bytes >= self.MAX_OUTPUT_BYTES:
                 truncated = True
-                process.terminate()
+                self._terminate_tree(process)
                 break
 
             try:
@@ -140,6 +168,12 @@ class SubprocessCommandExecutor(CommandExecutor):
                     if shell_dead_since is None:
                         shell_dead_since = time.time()
                     elif time.time() - shell_dead_since > 1.0:
+                        # L9：shell 已死但孙进程仍持管道写端（`(sleep 300 &) ;
+                        # echo done` 形态）。只靠 daemon reader 兜底会悬挂线程
+                        # 与管道 fd 至孙进程退出，写满 64KB 缓冲后孙进程自身
+                        # 也卡死。此处强杀进程组收尾（nohup 重定向输出的
+                        # 真正脱离场景不持管道，不会走到这里）。
+                        self._terminate_tree(process, force=True)
                         break
                 continue
 
@@ -147,10 +181,12 @@ class SubprocessCommandExecutor(CommandExecutor):
             if total_bytes + line_bytes > self.MAX_OUTPUT_BYTES and not truncated:
                 allowed = self.MAX_OUTPUT_BYTES - total_bytes
                 if allowed > 0:
-                    output_chunks.append(line.encode('utf-8', errors='replace')[:allowed].decode('utf-8', errors='replace'))
+                    # L5：decode 用 errors='ignore'——按字节截断可能落在多字节
+                    # 字符中间，errors='replace' 会在行尾留下半个字符（�）
+                    output_chunks.append(line.encode('utf-8', errors='replace')[:allowed].decode('utf-8', errors='ignore'))
                     total_bytes = self.MAX_OUTPUT_BYTES
                 truncated = True
-                process.terminate()
+                self._terminate_tree(process)
                 break
 
             output_chunks.append(line)
@@ -209,25 +245,30 @@ class SubprocessCommandExecutor(CommandExecutor):
                 bufsize=1,
                 universal_newlines=True,
                 env=exec_env,
-                cwd=os.path.expanduser(work_dir)
+                cwd=os.path.expanduser(work_dir),
+                # L9：POSIX 下 shell 成为会话首进程，超时/取消可按进程组
+                # 一次终止整棵进程树（含 & 后台孙进程），消除管道悬挂
+                start_new_session=(os.name == "posix")
             )
             # 保存进程引用以便cancel()可以kill它
             with self._process_lock:
                 self._current_process = process
+                if os.name == "posix":
+                    try:
+                        self._current_pgid = os.getpgid(process.pid)
+                    except Exception:
+                        self._current_pgid = None
 
             start_time = time.time()
             output_str, timeout_occurred, truncated = self._read_with_limit(process, timeout, start_time)
 
             # 确保进程终止
             if process.poll() is None:
-                if timeout_occurred or truncated:
+                self._terminate_tree(process, force=timeout_occurred or truncated)
-                    process.kill()
-                else:
-                    process.terminate()
                 try:
                     process.wait(timeout=2)
                 except:
-                    process.kill()
+                    self._terminate_tree(process, force=True)
 
             return_code = process.returncode if process.returncode is not None else -1
 
@@ -255,10 +296,11 @@ class SubprocessCommandExecutor(CommandExecutor):
             return f"❌ 执行错误: {str(e)}"
         finally:
             if process and process.poll() is None:
-                process.kill()
+                self._terminate_tree(process, force=True)
             # 清除当前进程引用
             with self._process_lock:
                 self._current_process = None
+                self._current_pgid = None
 
     def execute_streaming(self, command: str, output_queue: queue.Queue, timeout: int = 30,
                           work_dir: str = None, env: Dict = None, **kwargs):
@@ -296,12 +338,20 @@ class SubprocessCommandExecutor(CommandExecutor):
                 bufsize=1,
                 universal_newlines=True,
                 env=exec_env,
-                cwd=os.path.expanduser(work_dir)
+                cwd=os.path.expanduser(work_dir),
+                # L9：POSIX 下 shell 成为会话首进程，超时/取消可按进程组
+                # 一次终止整棵进程树（含 & 后台孙进程），消除管道悬挂
+                start_new_session=(os.name == "posix")
             )
             self.process = process
             # 保存进程引用以便cancel()可以kill它
             with self._process_lock:
                 self._current_process = process
+                if os.name == "posix":
+                    try:
+                        self._current_pgid = os.getpgid(process.pid)
+                    except Exception:
+                        self._current_pgid = None
 
             start_time = time.time()
             # H2 修复：复用线程化读取（reader 线程 + 超时轮询），行经 output_queue 流式转发
@@ -315,7 +365,7 @@ class SubprocessCommandExecutor(CommandExecutor):
 
             # 如果超时或截断，确保进程被终止
             if (timeout_occurred or truncated) and process.poll() is None:
-                process.kill()
+                self._terminate_tree(process, force=True)
                 try:
                     process.wait(timeout=2)
                 except:
@@ -352,11 +402,12 @@ class SubprocessCommandExecutor(CommandExecutor):
             output_queue.put(("complete", f"❌ 执行错误: {str(e)}"))
         finally:
             if process and process.poll() is None:
-                process.terminate()
+                self._terminate_tree(process)
                 try:
                     process.wait(timeout=2)
                 except:
-                    process.kill()
+                    self._terminate_tree(process, force=True)
             self.process = None
             with self._process_lock:
                 self._current_process = None
+                self._current_pgid = None

aibox/subsystems/prompt_manager.py

@@ -60,10 +60,16 @@ class PromptManager:
         prompts_dir = config.get("system.prompts_dir", "~/.aibox/prompts")
         return os.path.expanduser(prompts_dir)
 
-    def _load_prompts(self):
+    def _load_prompts(self, target: Optional[List[Dict]] = None):
+        """加载提示词到 target 列表（缺省 self._prompts）。
+
+        M6：reload 传入新列表本地构建，完成后由 reload 原子替换——
+        此前先清空 self._prompts 再逐文件重读，并发读者（其他连接构建
+        system 消息）会读到空/半截提示词列表。
+        """
+        prompts = target if target is not None else self._prompts
         self._prompts_dir = self._get_prompts_dir()
         os.makedirs(self._prompts_dir, exist_ok=True)
-        self._prompts = []
 
         # 确保核心文件存在
         self._ensure_identity_file()
@@ -86,17 +92,14 @@ class PromptManager:
                     with open(filepath, 'r', encoding='utf-8') as f:
                         content = f.read().strip()
                         if content:
-                            self._prompts.append({
+                            prompts.append({
                                 'file': filename,
                                 'content': content
                             })
                 except Exception as e:
                     print(f"⚠️ 读取提示词文件 {filename} 失败: {e}")
 
-        essential_files = [self.IDENTITY_FILE, self.STATUS_FILE, self.SOUL_FILE]
+        if not prompts:
-        other_files = [f for f in prompt_files if f not in essential_files] if prompt_files else []
-
-        if not self._prompts:
             self._create_default_prompts()
 
     def _get_template_dir(self) -> str:
@@ -240,10 +243,6 @@ class PromptManager:
         return """我是DeepSeek，一个智能AI助手。
 请创建 99_SOUL.md 文件来定义我的完整身份、角色、性格和能力边界。"""
 
-    def get_skill_prompts(self) -> List[Dict]:
-        """获取所有基础技能提示词（以1_开头的文件）"""
-        return [p for p in self._prompts if p['file'].startswith(self.SKILL_PREFIX)]
-
     def get_soul_prompt(self) -> Optional[Dict]:
         """获取灵魂提示词（99_SOUL.md）"""
         for p in self._prompts:
@@ -296,9 +295,10 @@ class PromptManager:
         return [p for p in self._prompts if self._skill_sort_key(p['file']) is not None]
 
     def reload(self):
-        """重新加载所有提示词"""
+        """重新加载所有提示词（M6：构建新列表后原子替换，并发读者始终读到完整列表）"""
-        self._prompts = []
+        new_prompts: List[Dict] = []
-        self._load_prompts()
+        self._load_prompts(new_prompts)
+        self._prompts = new_prompts
         return len(self._prompts)
 
     def get_prompt_count(self) -> int:

aibox/tests/test_h_fixes.py

@@ -0,0 +1,408 @@
+"""aibox 第四轮审计 Batch H 修复回归测试（2026-08-18，审计报告 §十一）
+
+覆盖：
+  - H1：子代理共享父取消事件后首轮 think 不再清除父事件（N5 回归）+ 父已取消时跳过启动
+  - M3：调度器任务级超时兜底（AI think 卡死不再停摆调度循环）
+  - M4：get_recent_memories(limit=None) 使用默认上限（不再全表加载）
+  - M5：memo delete 物理删除（此前只标记完成）
+  - M6：PromptManager.reload 原子替换（并发读者不再读到空/半截列表）
+  - L1：read_file 的 sed 参数强转 int（防引号注入）
+  - L2：set_proxy 落盘失败如实报告（不再静默报"已保存"）
+  - L3：SSE 非 UTF-8 行不中断流（errors=replace）
+  - L4：persona 路径校验解析符号链接（软链越界拒绝）
+  - L5：1MB 截断不再产生半个字符（�）
+  - L6：compressor 空内容压缩不再除零
+  - L7：InstallSkillTool 指引命令路径引用（防拆词/注入）
+  - L8：ask_user 缺参返回明确错误（不再 TypeError）
+  - L10：web 工具仅允许 http/https（file:// 等拒绝）
+  - L11：registry 日志打码改包含匹配（apiKey/access_token 等变体）
+  - L12：FailoverClient 日志 Bearer 令牌脱敏
+
+M1（/reload_prompts 移线程池）/M2（技能扫描启动前预热）为 async WebSocket /
+启动路径，依赖事件循环与真实连接对象，由既有 WebSocket 测试面与启动逻辑回归。
+"""
+
+import asyncio
+import os
+import queue
+import sys
+import threading
+import types
+from unittest import mock
+
+import pytest
+
+# ---- 环境桩：websockets 未安装时保证 import aibox.py 不失败 ----
+if "websockets" not in sys.modules:
+    sys.modules["websockets"] = types.ModuleType("websockets")
+
+import aibox  # noqa: E402
+from aibox import DeepSeekChat, TaskScheduler, run_full_subagent  # noqa: E402
+
+from llm_client import DeepSeekClient, FailoverClient, _sanitize_log_msg  # noqa: E402
+from subsystems.db import MemoryDatabase, MemoDatabase  # noqa: E402
+from subsystems.prompt_manager import PromptManager  # noqa: E402
+from subsystems.conversation_compressor import ConversationCompressor  # noqa: E402
+from common import constants  # noqa: E402
+
+from test_conversation_compressor import FakeLLMClient  # noqa: E402
+from test_once_mode import _make_ai  # noqa: E402
+
+
+def _fake_sub_chat():
+    fake = mock.MagicMock()
+    fake.think_and_respond = mock.MagicMock(return_value="任务完成报告")
+    fake.stats = {}
+    fake.messages = []
+    fake._cancel_event = threading.Event()
+    return fake
+
+
+# ==================== H1：子代理取消事件清除回归 ====================
+
+class TestH1SubagentCancelClear:
+    def test_shared_event_not_cleared_on_first_think(self):
+        """共享父事件后首轮 think 不清除事件——父级已置位的取消信号不被吞掉"""
+        ai = _make_ai()
+        parent_event = threading.Event()
+        parent_event.set()
+        ai._cancel_event = parent_event
+        ai._shared_cancel_event = True
+        with pytest.raises(InterruptedError):
+            ai._think_and_respond_impl("hi")
+        assert parent_event.is_set()
+
+    def test_own_event_still_cleared_on_first_think(self):
+        """未共享（普通会话）时首轮仍清除自身事件——原语义不回归"""
+        import contextlib
+        ai = _make_ai()
+        ai._cancel_event.set()
+        with contextlib.suppress(Exception):
+            ai._think_and_respond_impl("hi")
+        assert not ai._cancel_event.is_set()
+
+    def test_subagent_not_started_when_parent_already_cancelled(self):
+        """父事件已置位 → 直接返回取消提示，不启动子代理"""
+        fake = _fake_sub_chat()
+        parent_event = threading.Event()
+        parent_event.set()
+        with mock.patch("aibox.DeepSeekChat", return_value=fake), \
+             mock.patch("aibox.create_llm_client"), \
+             mock.patch("aibox.SubprocessCommandExecutor"):
+            result = run_full_subagent("r", "t", None, cancel_event=parent_event)
+        assert "取消" in result
+        fake.think_and_respond.assert_not_called()
+
+
+# ==================== M3：调度器任务超时 ====================
+
+class _BlockingAI:
+    """think 卡死直到被 cancel 的伪 AI（模拟 LLM 挂起）"""
+
+    def __init__(self):
+        self.cancelled = threading.Event()
+        self.cancel_called = 0
+
+    def cancel(self):
+        self.cancel_called += 1
+        self.cancelled.set()
+
+    def think_and_respond(self, input_text, output_callback=None,
+                          is_continuation=False):
+        self.cancelled.wait(timeout=15)
+        raise InterruptedError("用户中断")
+
+
+class _FakeMemoDB:
+    def get_memo(self, memo_id):
+        return None
+
+
+class TestM3SchedulerTimeout:
+    def test_stuck_task_times_out_and_scheduler_continues(self):
+        from aibox import ConfigManager
+        loop = asyncio.new_event_loop()
+        try:
+            scheduler = TaskScheduler(loop=loop, logger=None)
+            fake_ai = _BlockingAI()
+            memo = {"id": 7, "title": "卡死任务", "content": "内容", "trigger_count": 0}
+            orig_get = ConfigManager.get
+
+            def fake_get(self, key, default=None):
+                # 只把任务超时压到 0.3s，其余配置读取走原实现（防止
+                # DATETIME_FORMAT 等属性读到错误类型）
+                if key == "scheduler.task_timeout":
+                    return 0.3
+                return orig_get(self, key, default)
+
+            with mock.patch.object(ConfigManager, "get", fake_get), \
+                 mock.patch.object(scheduler, "_create_task_ai", return_value=fake_ai):
+                result = loop.run_until_complete(
+                    scheduler.execute_task_as_conversation(memo, _FakeMemoDB()))
+            assert "超时" in result
+            assert fake_ai.cancel_called >= 1
+        finally:
+            loop.close()
+
+
+# ==================== M4/M5：记忆上限与任务删除 ====================
+
+class TestM4M5Db:
+    def test_recent_memories_none_capped(self, tmp_path, monkeypatch):
+        """limit=None 不再全表加载，使用默认上限（对齐 search_memories）"""
+        from test_conversation_compressor import patch_const
+        db = MemoryDatabase(db_path=str(tmp_path / "m.db"))
+        for i in range(7):
+            db.add_memory(topic=f"t{i}", summary=f"s{i}", content="c",
+                          start_time="2026-08-18 00:00:00",
+                          end_time="2026-08-18 00:00:01", importance=1)
+        patch_const(monkeypatch, "MEMORY_MAX_SEARCH_RESULTS", 5)
+        res = db.get_recent_memories(limit=None)
+        assert len(res) == 5
+
+    def test_delete_memo_physically_removes(self, tmp_path):
+        """delete_memo 真实删除行（此前 complete_memo 只标记完成）"""
+        db = MemoDatabase(db_path=str(tmp_path / "m.db"))
+        mid = db.add_memo(title="待删任务", content="内容")
+        assert db.get_memo(mid) is not None
+        assert db.delete_memo(mid) is True
+        assert db.get_memo(mid) is None
+        assert db.delete_memo(mid) is False  # 已不存在
+
+    def test_memo_tool_delete_uses_physical_delete(self, tmp_path):
+        """MemoTool delete 走 delete_memo：行消失而非仅标记完成"""
+        from tools import MemoTool
+        db = MemoDatabase(db_path=str(tmp_path / "m.db"))
+        mid = db.add_memo(title="重复任务", content="内容", repeat_type="daily")
+        tool = MemoTool(db, None)
+        result = tool.execute(action="delete", memo_id=mid, confirm=True)
+        assert "已删除" in result
+        assert db.get_memo(mid) is None
+        stats = db.get_memo_stats()
+        assert stats["total"] == 0
+
+
+# ==================== M6：PromptManager 原子 reload ====================
+
+class TestM6PromptReloadAtomic:
+    def test_reload_builds_new_list_then_swaps(self):
+        """reload 在本地新列表构建完成后才原子替换——读者始终看到完整列表"""
+        pm = PromptManager()
+        old_list = pm._prompts
+        seen = []
+
+        def fake_load(target):
+            seen.append(target)
+            target.append({"file": "X_test.md", "content": "y"})
+
+        with mock.patch.object(pm, "_load_prompts", side_effect=fake_load):
+            n = pm.reload()
+        assert len(seen) == 1
+        assert seen[0] is not old_list          # 构建用的是新列表
+        assert pm._prompts is seen[0]           # 完成后才替换
+        assert n == 1
+
+
+# ==================== L1：read_file 参数强转 ====================
+
+class TestL1ReadFileCoercion:
+    def test_non_integer_lines_rejected(self, tmp_path):
+        from tools import ReadFileTool
+        f = tmp_path / "f.txt"
+        f.write_text("line1\nline2\n", encoding="utf-8")
+        tool = ReadFileTool()
+        r = tool.execute(filepath=str(f), start_line="1'; rm -rf /; echo '",
+                         end_line=5)
+        assert "参数错误" in r
+
+    def test_valid_integers_still_work(self, tmp_path):
+        from tools import ReadFileTool
+        f = tmp_path / "f.txt"
+        f.write_text("line1\nline2\n", encoding="utf-8")
+        tool = ReadFileTool()
+        r = tool.execute(filepath=str(f), start_line=1, end_line=2)
+        assert "sed -n" in r and "参数错误" not in r
+
+
+# ==================== L2：set_proxy 落盘失败如实报告 ====================
+
+class TestL2ProxySaveFailure:
+    def test_set_proxy_returns_false_on_save_failure(self, tmp_path):
+        from common import ConfigManager
+        cm = ConfigManager()
+        cm._config_path = str(tmp_path / "config.json")
+        with mock.patch("builtins.open", side_effect=PermissionError("disk ro")):
+            ok = cm.set_proxy("127.0.0.1", 1080, save=True)
+        assert ok is False
+
+    def test_proxy_tool_reports_save_failure(self, tmp_path):
+        from tools import SetProxyTool
+        tool = SetProxyTool(None)
+        with mock.patch("builtins.open", side_effect=PermissionError("disk ro")):
+            r = tool.execute(host="127.0.0.1", port=1080, save=True,
+                             skip_check=True, enabled=True)
+        assert "保存失败" in r
+
+
+# ==================== L3：SSE 非 UTF-8 行不中断流 ====================
+
+class TestL3SseDecode:
+    def test_non_utf8_line_does_not_break_stream(self):
+        c = DeepSeekClient(api_key="k", model="m", base_url="https://x")
+        resp = mock.MagicMock()
+        resp.status_code = 200
+        resp.iter_lines.return_value = [
+            b"data: \xff\xfe",
+            b'data: {"choices":[{"delta":{"content":"ok"}}]}',
+            b"data: [DONE]",
+        ]
+        with mock.patch("llm_client.requests.post", return_value=resp):
+            events = list(c.stream_chat([{"role": "user", "content": "hi"}]))
+        assert any(e.get("type") == "content" and e.get("text") == "ok"
+                   for e in events)
+
+
+# ==================== L4：persona 软链越界 ====================
+
+class TestL4PersonaSymlink:
+    def test_symlink_outside_skills_dir_rejected(self, tmp_path, monkeypatch):
+        from test_conversation_compressor import patch_const
+        from aibox import ExpressEmotionTool
+        skills_dir = tmp_path / "skills"
+        skills_dir.mkdir()
+        outside = tmp_path / "outside.md"
+        outside.write_text("秘密内容", encoding="utf-8")
+        (skills_dir / "evil.md").symlink_to(outside)
+        tool = ExpressEmotionTool()
+        patch_const(monkeypatch, "SKILLS_DIR", str(skills_dir))
+        content = tool._load_persona("evil", "")
+        assert content == ""
+
+    def test_normal_persona_still_loads(self, tmp_path, monkeypatch):
+        from test_conversation_compressor import patch_const
+        from aibox import ExpressEmotionTool
+        skills_dir = tmp_path / "skills"
+        skills_dir.mkdir()
+        (skills_dir / "happy.md").write_text("快乐人格", encoding="utf-8")
+        tool = ExpressEmotionTool()
+        patch_const(monkeypatch, "SKILLS_DIR", str(skills_dir))
+        content = tool._load_persona("happy", "")
+        assert content == "快乐人格"
+
+
+# ==================== L5：截断无半个字符 ====================
+
+class TestL5NoPartialChar:
+    def test_truncated_output_has_no_replacement_char(self):
+        from subsystems.executors import SubprocessCommandExecutor
+        ex = SubprocessCommandExecutor()
+        r = ex.execute("python3 -c \"print('中' * 600000)\"", timeout=60)
+        assert "截断" in r
+        assert "\ufffd" not in r
+
+    @pytest.mark.skipif(os.name != "posix", reason="Linux 进程组语义")
+    def test_grandchild_holding_pipe_is_reaped(self):
+        """`(sleep N &) ; echo done` 形态：shell 退出后孙进程持管道写端，
+        宽限窗口到期强杀进程组——不悬挂 reader、孙进程被清理"""
+        import subprocess as sp
+        from subsystems.executors import SubprocessCommandExecutor
+        marker = f"sleep {12340}"
+        ex = SubprocessCommandExecutor()
+        r = ex.execute(f"({marker} &) ; echo done", timeout=8)
+        assert "done" in r
+        leftover = sp.run(["pgrep", "-f", marker],
+                          capture_output=True, text=True).stdout.strip()
+        assert leftover == ""
+
+
+# ==================== L6：compressor 除零 ====================
+
+class TestL6CompressorDivZero:
+    def test_empty_content_compress_no_div0(self, monkeypatch):
+        comp = ConversationCompressor(llm_client=FakeLLMClient(),
+                                      logger=None)
+        from test_conversation_compressor import patch_const
+        patch_const(monkeypatch, "COMPRESS_MESSAGE_THRESHOLD", 10)
+        messages = [{"role": "system", "content": "SYS"}] + [
+            {"role": "user" if i % 2 == 0 else "assistant", "content": ""}
+            for i in range(15)
+        ]
+        result = comp.compress_conversation(messages)
+        assert isinstance(result, list)
+
+
+# ==================== L7：InstallSkillTool 路径引用 ====================
+
+class TestL7SkillPathQuoting:
+    def test_guide_commands_quote_paths(self):
+        from tools import InstallSkillTool
+        tool = InstallSkillTool()
+        r = tool.execute(skill_path="/tmp/a b; rm -rf /")
+        assert "ls -l '/tmp/a b; rm -rf /'" in r
+        assert "cp '/tmp/a b; rm -rf /' " in r
+
+
+# ==================== L8：ask_user 缺参 ====================
+
+class TestL8AskUser:
+    def test_missing_question_returns_error(self):
+        from tools import AskUserTool
+        tool = AskUserTool()
+        assert "需要提供问题" in tool.execute()
+
+    def test_question_passed_through(self):
+        from tools import AskUserTool
+        tool = AskUserTool()
+        assert "测试问题" in tool.execute(question="测试问题")
+
+
+# ==================== L10：web 工具 scheme 白名单 ====================
+
+class TestL10WebScheme:
+    def test_file_url_rejected(self):
+        from tools import SimpleWebCrawlerTool
+        tool = SimpleWebCrawlerTool()
+        r = tool.execute(action="get", url="file:///etc/shadow")
+        assert "仅支持 http/https" in r
+
+    def test_http_url_accepted(self):
+        from tools import SimpleWebCrawlerTool
+        tool = SimpleWebCrawlerTool()
+        r = tool.execute(action="get", url="https://example.com")
+        assert "curl" in r and "仅支持" not in r
+
+
+# ==================== L11：registry 打码包含匹配 ====================
+
+class TestL11SanitizeSubstring:
+    def test_variant_keys_redacted(self):
+        from tools.registry import _sanitize_kwargs
+        out = _sanitize_kwargs({
+            "apiKey": "x", "access_token": "y", "passwd": "z",
+            "url": "https://ok",
+        })
+        assert out == {"apiKey": "***", "access_token": "***",
+                       "passwd": "***", "url": "https://ok"}
+
+    def test_normal_keys_untouched(self):
+        from tools.registry import _sanitize_kwargs
+        out = _sanitize_kwargs({"filepath": "/tmp/a", "question": "hi"})
+        assert out == {"filepath": "/tmp/a", "question": "hi"}
+
+
+# ==================== L12：failover 日志 Bearer 脱敏 ====================
+
+class TestL12LogSanitize:
+    def test_sanitize_msg_redacts_bearer(self):
+        msg = "瞬时故障: HTTP 401: Bearer sk-abc123xyz"
+        out = _sanitize_log_msg(msg)
+        assert "sk-abc123xyz" not in out
+        assert "Bearer ***" in out
+
+    def test_failover_log_redacts_bearer(self):
+        logger = mock.MagicMock()
+        c = FailoverClient([], logger=logger)
+        c._log("warning", "瞬时故障（Bearer sk-secret456）")
+        logged = logger.warning.call_args[0][0]
+        assert "sk-secret456" not in logged
+        assert "Bearer ***" in logged

aibox/tools/basic_tools.py

@@ -96,6 +96,16 @@ class ReadFileTool(FileToolBase):
 
         # 限制max_lines上限，防止请求超大范围
         max_lines = min(max_lines, 500)
+        # L1（审计 2026-08-18）：start/end_line 为 LLM 可控参数，此前未强转
+        # 直拼 sed 单引号模板——LLM 传含引号的字符串可闭合引号注入命令。
+        # 强转 int（非法输入在此拦截）并夹取合理范围。
+        try:
+            start_line = int(start_line)
+            end_line = int(end_line)
+        except (TypeError, ValueError):
+            return "❌ 参数错误: start_line/end_line 必须为整数"
+        start_line = max(1, start_line)
+        end_line = max(0, min(end_line, 10_000_000))
         quoted = shlex.quote(abs_path)
 
         # 构造等价的命令行读取命令
@@ -320,6 +330,12 @@ class SimpleWebCrawlerTool(Tool):
         if action not in ("get", "text", "title", "links", "search"):
             return f"❌ 未知操作: {action}"
 
+        # L10（审计 2026-08-18）：url 为 LLM 可控输入（可被网页内容诱导），
+        # 此前不限 scheme——file:// 可经生成的 curl 指引读取本地文件（SSRF）。
+        # 白名单 http/https 后其余协议直接拒绝。
+        if not url or not str(url).strip().lower().startswith(("http://", "https://")):
+            return "❌ 仅支持 http/https 协议地址（已拦截 file:// 等非网络协议）"
+
         quoted_url = shlex.quote(url)
         timeout = constants.WEB_TIMEOUT
         user_agent = shlex.quote(constants.WEB_USER_AGENT)

aibox/tools/db_tools.py

@@ -752,7 +752,9 @@ class MemoTool(Tool):
 
         memo_id = kwargs.get("memo_id")
         if memo_id:
-            if self.memo_db.complete_memo(memo_id, force_complete=True):
+            # M5：真实物理删除（此前调 complete_memo 只标记完成，行不删除，
+            # 重复任务被推进而非移除，stats 计数失真）
+            if self.memo_db.delete_memo(memo_id):
                 return self.format_result(True, f"任务 #{memo_id} 已删除")
             else:
                 return f"❌ 无法删除任务 #{memo_id}"

aibox/tools/misc_tools.py

@@ -39,10 +39,13 @@ class AskUserTool(Tool):
                     )
                 }
             },
-            "required": []
+            # L8：此前 required 为空，LLM 不传 question 时 str + None 抛 TypeError
+            "required": ["question"]
         }
 
-    def execute(self, question: str, **kwargs) -> str:
+    def execute(self, question: str = None, **kwargs) -> str:
+        if not question:
+            return "❌ 需要提供问题内容（question 参数）"
         return (
                 "你遇到了想搞清楚的事情: " + question + "\n你现在可以询问用户。"
         )

aibox/tools/proxy_tools.py

@@ -146,7 +146,7 @@ class SetProxyTool(Tool):
             check_detail = detail
 
         config = ConfigManager()
-        config.set_proxy(host, port, username, password, password_env, enabled, save)
+        saved = config.set_proxy(host, port, username, password, password_env, enabled, save)
         proxy_info = config.get_proxy_info()
         if proxy_info.get("password_env"):
             pw_source = "环境变量 " + proxy_info["password_env"]
@@ -159,10 +159,13 @@ class SetProxyTool(Tool):
             "服务器": f"{proxy_info['host']}:{proxy_info['port']}",
             "认证": "有" if proxy_info.get("username") else "无",
             "密码来源": pw_source,
-            "持久化": "已保存" if save else "仅内存"
+            "持久化": "已保存" if saved else "保存失败（仅本次会话有效，重启后丢失）"
         }
         if check_detail:
             data["连通性"] = check_detail
+        # L2：落盘失败（磁盘只读等）如实报告，不再静默报"已保存"
+        if save and not saved:
+            return self.format_result(False, "代理已配置但保存失败（仅本次会话有效，重启后丢失）", data)
         return self.format_result(True, "代理设置成功", data)
 
 

aibox/tools/registry.py

@@ -16,13 +16,18 @@ from common import Logger, constants, i18n
 from .base import Tool
 
 # 工具参数名命中这些关键词时，debug 日志里打码（防密码/密钥进日志文件）
-_SENSITIVE_PARAM_KEYS = {"password", "api_key", "token", "secret", "authorization"}
+# L11（审计 2026-08-18）：精确匹配漏掉 apiKey/access_token/passwd 等变体，
+# 改包含匹配——日志场景下过度打码可接受，漏打码才是问题。
+_SENSITIVE_PARAM_KEYS = (
+    "password", "passwd", "api_key", "apikey", "token", "secret",
+    "authorization", "credential",
+)
 
 
 def _sanitize_kwargs(kwargs: Dict) -> Dict:
     """复制一份参数并把敏感键的值替换为 ***（仅用于日志输出）"""
     return {
-        k: ("***" if str(k).lower() in _SENSITIVE_PARAM_KEYS else v)
+        k: ("***" if any(s in str(k).lower() for s in _SENSITIVE_PARAM_KEYS) else v)
         for k, v in kwargs.items()
     }
 

aibox/tools/skill_tools.py

@@ -16,6 +16,7 @@ tools.skill_tools - 技能相关工具
 import os
 import queue
 import re
+import shlex
 from typing import Dict, Optional
 
 from common import constants, i18n, Logger
@@ -253,10 +254,14 @@ class InstallSkillTool(Tool):
         skills_dir = constants.SKILLS_DIR
 
         # 如果给了具体路径，在说明里带入，否则用占位符
-        src = skill_path.strip() if skill_path else "/path/to/your_skill.md"
+        raw_src = skill_path.strip() if skill_path else ""
         # 去掉扩展名作为技能名称，再统一补 .md 作为目标文件名
-        base = os.path.splitext(os.path.basename(src))[0] if src else "your_skill"
+        base = os.path.splitext(os.path.basename(raw_src))[0] if raw_src else "your_skill"
         dst = os.path.join(skills_dir, base + ".md")
+        # L7（审计 2026-08-18）：src 为 LLM 可控输入，含空格/元字符时
+        # 未经引用的命令会被 shell 拆词/注入（指引由子代理经 run_command 执行）
+        src = shlex.quote(raw_src) if raw_src else "/path/to/your_skill.md"
+        dst_q = shlex.quote(dst)
 
         guide = f"""📦 扩展技能安装指引
 {"=" * 55}
@@ -282,7 +287,7 @@ class InstallSkillTool(Tool):
 
 调用 create_subagent 派生子代理执行复制命令（目标文件名统一补 .md 扩展名）：
 
-  cp {src} {dst}
+  cp {src} {dst_q}
 
 ⚠️  注意：目标文件名必须带 .md 扩展名，
     系统以 .md 文件作为技能加载，且技能名称取文件名（不含 .md）。