fix(aibox): Batch N 波次4+5 LLM 健壮性与权限隔离,Batch N 收束

波次 4 LLM 健壮性(T10/T19/T20/T21/T23 + T14 复现证伪):
- T10 调度器 await 改 wait_for 硬超时兜底(task_timeout+30s 宽限),
  软取消够不到的卡死路径不再永久停摆调度循环
- T19 FailoverClient 异常收窄为瞬时白名单(Connection/Timeout/
  ChunkedEncoding),MissingSchema 等永久配置错误不再污染冷却表
- T20 流式未收到 [DONE] 抛 TransientLLMError,回答无声截断可感知
- T21 env 覆盖黑名单 filter_env_overrides(LD_*/DYLD_*/PATH 等),
  executors 两处 + process_manager 接入
- T23 压缩后 tool 配对双向修复(失配 tool_calls 剥离防 API 400)
- T14 FTS5 复现证伪:JOIN 别名场景表名 MATCH 正常,无需修复

波次 5 权限隔离(T22/T-L17/T-L18;T1/T2 产品决策:仅告警/维持现状):
- T22a TOOL_PROFILE_TASK 定时任务精简工具面(无 update_identity/
  update_soul/set_proxy)
- T22b ProcessManager owner 隔离:bg_write/bg_kill 属主校验,
  观察面共享;DeepSeekChat 新增 owner_id 传导
- T1 绑定非回环地址时启动显著告警
- T-L17 model_config env 名按域名推荐(防跨厂商凭据外发)
- T-L18 list_profiles 过滤控制字符(防 ANSI 注入)

测试:test_n_fixes.py 增至 62 项;全量 598 passed / 1 failed
(Windows 向 ping 用例,环境项),零回归。审计报告补记 §24.7~24.11,
README 同步 owner 隔离语义。八轮审计 T 系列 28 项全部处置完毕。
This commit is contained in:
qing committed 2026-08-21 14:53:42 +00:00
1 parent 7e44025671
commit 67acae708c
10 files changed
+824 -107

No files matched your search

+39 -5
View File
@@ -35,6 +35,7 @@ import time
from typing import Dict, List, Optional
from common import ConfigManager, constants, Logger
from subsystems.executors import filter_env_overrides
# 单行输出最大字节数,超出截断(防超长单行撑爆环形缓冲内存预算)
MAX_LINE_BYTES = 16 * 1024
@@ -162,7 +163,11 @@ class ProcessManager:
exec_env = os.environ.copy()
if env:
exec_env.update(env)
# T21:黑名单键拒绝(对齐 executors,防 LD_PRELOAD/PYTHONPATH 劫持)
safe_env, rejected_keys = filter_env_overrides(env)
if rejected_keys:
self.logger.warning(f"env 覆盖被黑名单拒绝(T21): {rejected_keys}")
exec_env.update(safe_env)
try:
popen = subprocess.Popen(
@@ -322,7 +327,7 @@ class ProcessManager:
def write(self, handle, text: str, append_newline: bool = True,
wait_lines: int = 0, wait_timeout: float = 5.0,
write_timeout: float = 5.0) -> Dict:
write_timeout: float = 5.0, owner: str = None) -> Dict:
"""向后台进程 stdin 写入一行(交互式问答)。
返回 {ok, handle, watermark, sent_bytes[, wait]}:
@@ -330,10 +335,16 @@ class ProcessManager:
watermark) 得到的必然且仅是本条输入引发的响应(写读对齐)
- wait_lines>0 时同步等待 N 行响应(wait 子 dict 含 output/
timed_out),expect 式一步问答
失败返回 {ok: False, error}(进程已退出/写入超时/超长等)。"""
失败返回 {ok: False, error}(进程已退出/写入超时/超长等)。
T22 属主隔离:条目与调用方都携带 owner 且不一致时拒绝——他人
stdin 不容注入。任一侧未标识(None,如测试/管理面直调)不隔离。"""
entry = self._lookup(handle)
if entry is None:
return {"ok": False, "error": f"句柄 #{handle} 不存在"}
denial = self._check_owner(entry, owner, "写入")
if denial:
return denial
if not isinstance(text, str) or text == "":
return {"ok": False, "error": "缺少或空的 text"}
data = text if (not append_newline or text.endswith("\n")) else text + "\n"
@@ -467,12 +478,20 @@ class ProcessManager:
key=lambda e: (e.status != "running", e.handle))
return [self._entry_info(e) for e in entries]
def kill(self, handle, force: bool = False, grace: float = 3.0) -> Dict:
def kill(self, handle, force: bool = False, grace: float = 3.0,
owner: str = None) -> Dict:
"""终止后台进程。SIGTERM → 宽限轮询 → SIGKILL;force=True 直接 SIGKILL。
对已退出条目幂等,返回当前状态。"""
对已退出条目幂等,返回当前状态。
T22 属主隔离:条目与调用方都携带 owner 且不一致时拒绝——防止
提示注入的会话/任务跨属主杀掉他人的 dev server。shutdown/TTL
清理属管理器特权,不走本校验。"""
entry = self._lookup(handle)
if entry is None:
return {"ok": False, "error": f"句柄 #{handle} 不存在"}
denial = self._check_owner(entry, owner, "终止")
if denial:
return denial
with self._lock:
self._update_status_locked(entry)
@@ -562,6 +581,20 @@ class ProcessManager:
# 内部实现
# ------------------------------------------------------------------
def _check_owner(self, entry: _ProcEntry, caller_owner: Optional[str],
action: str) -> Optional[Dict]:
"""T22:属主校验——条目与调用方都携带 owner 且不一致时返回拒绝
dict(写/杀权限隔离);任一侧未标识(None,如测试/管理面直调)
不隔离,保持向后兼容。观察面(list/get_output)不经过本校验。"""
if (entry.owner is not None and caller_owner is not None
and entry.owner != caller_owner):
self.logger.warning(
f"属主校验拒绝:owner={caller_owner} 尝试{action} "
f"#{entry.handle}(属主 {entry.owner})")
return {"ok": False,
"error": f"进程 #{entry.handle} 属于其他会话(属主不匹配),无权{action}"}
return None
def _lookup(self, handle) -> Optional[_ProcEntry]:
try:
handle = int(handle)
@@ -699,6 +732,7 @@ class ProcessManager:
"buffered_lines": len(entry.lines),
"evicted_lines": entry.evicted,
"command": entry.command,
"owner": entry.owner, # T22:属主标识(观察面可见,写/杀需匹配)
}