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
This commit is contained in:
qing committed
1 parent
d1f780e381
commit
d3acccd146
14 files changed
+643
-79
No files matched your search
@@ -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.logger.info("已终止正在运行的子进程")
|
||||
self._terminate_tree(proc, force=True)
|
||||
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:
|
||||
process.kill()
|
||||
else:
|
||||
process.terminate()
|
||||
self._terminate_tree(process, force=timeout_occurred or truncated)
|
||||
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
|
||||
Reference in new issue
Block a user