fix(aibox): Batch N 波次3 平台兼容（T3/T11/T25/T26/T27）
- T3 basic_tools 平台感知引用与 Windows 指引：_quote_arg 按 os.name 分支（Windows 双引号包裹，拒绝双引号/换行/%变量名% 注入形态）； ReadFile/WriteFile/ListFiles/Web 四工具 Windows 走 PowerShell/ curl.exe 等价命令（WriteFile 用 Base64 规避 cmd 换行/转义限制） - T11 executors 与 process_manager 的 _terminate_tree Windows 分支 改 taskkill /T /F 递归收割进程树，兜底单进程 kill - T25 MemoryDatabase 统一 _connect 工厂（busy_timeout=10000）， 7 处直连替换，对齐 MemoDatabase J9 - T26 SkillManager._load_skills 原子替换 self.skills（对齐 PromptManager M6），reload 期间不再读到空/半截技能表 - T27 atomic_write_text 对 PermissionError 做 3 次退避重试 测试：新增 tests/test_n_fixes.py 30 项；全量 566 passed / 1 failed （Windows 向 ping 用例，环境项），零回归。审计报告补记 §24.5/§24.6。
This commit is contained in:
qing committed
1 parent
5894e64287
commit
2dc79f0637
8 files changed
+617
-34
No files matched your search
+180
-8
@@ -15,8 +15,10 @@ tools.basic_tools - 基础工具集（A 批抽离）
|
||||
依赖方向：common <- tools.basic_tools，不反向依赖 aibox 任何符号。
|
||||
"""
|
||||
|
||||
import base64
|
||||
import os
|
||||
import queue
|
||||
import re
|
||||
import shlex
|
||||
from datetime import datetime
|
||||
from typing import Dict, Optional, Tuple
|
||||
@@ -25,6 +27,40 @@ from common import ConfigManager, constants
|
||||
from .base import Tool
|
||||
|
||||
|
||||
# T3（审计 2026-08-21）：cmd.exe 变量展开形态——%VAR% 匹配已定义环境变量时
|
||||
# 展开为变量值，值中的 & | 会成为命令分隔符（经典 cmd 注入）。URL 编码
|
||||
# （%20/%E4 等）与 PowerShell 的 %{http_code} 均不匹配该模式，不受影响。
|
||||
_WIN_VAR_PATTERN = re.compile(r"%[A-Za-z_][A-Za-z0-9_]*%")
|
||||
|
||||
|
||||
def _quote_arg(value: str) -> Tuple[str, Optional[str]]:
|
||||
"""平台感知的 shell 参数引用，返回 (quoted, error)。
|
||||
|
||||
POSIX：shlex.quote（sh 单引号语义）。
|
||||
Windows（run_command 经 cmd.exe / shell=True 执行）：
|
||||
- 双引号包裹（& | < > ( ) ^ 在双引号内为字面量）
|
||||
- 含 " → 拒绝（闭合外层双引号，其后内容暴露给 cmd 解析）
|
||||
- 匹配 %VAR% 形态 → 拒绝（cmd 变量展开注入面）
|
||||
- 含换行/控制字符 → 拒绝（cmd 命令行不可含换行）
|
||||
"""
|
||||
value = str(value)
|
||||
if os.name != "nt":
|
||||
return shlex.quote(value), None
|
||||
if '"' in value:
|
||||
return "", f"❌ 参数含双引号，无法安全生成 Windows 命令: {value[:100]}"
|
||||
if "\n" in value or "\r" in value:
|
||||
return "", f"❌ 参数含换行符，无法生成命令: {value[:100]}"
|
||||
if _WIN_VAR_PATTERN.search(value):
|
||||
return "", (f"❌ 参数疑似含 cmd 变量引用（%变量名%），已拒绝以防命令注入: "
|
||||
f"{value[:100]}")
|
||||
return f'"{value}"', None
|
||||
|
||||
|
||||
def _ps_quote(value: str) -> str:
|
||||
"""PowerShell 单引号字面量（内部单引号翻倍），用于 -Command 内层参数。"""
|
||||
return "'" + str(value).replace("'", "''") + "'"
|
||||
|
||||
|
||||
# ==================== 文件操作工具基类 ====================
|
||||
|
||||
class FileToolBase(Tool):
|
||||
@@ -106,9 +142,54 @@ class ReadFileTool(FileToolBase):
|
||||
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
|
||||
# T3（审计 2026-08-21）：shlex.quote 是 POSIX 单引号语义，Windows 上
|
||||
# run_command 经 cmd.exe 执行——单引号不被识别，& | % < > 仍是元字符
|
||||
# （URL 含 & 即命令被截断；%VAR% 变量展开可注入）。按平台生成指引：
|
||||
# POSIX 保持 head/tail/sed，Windows 走 PowerShell 等价命令。
|
||||
quoted, qerr = _quote_arg(abs_path)
|
||||
if qerr:
|
||||
return qerr
|
||||
|
||||
if os.name == "nt":
|
||||
# PowerShell 等价命令（经 cmd 调 powershell，-Command 整体双引号
|
||||
# 包裹，内层路径用 _ps_quote 单引号字面量）
|
||||
if head:
|
||||
cmd = (f'powershell -NoProfile -Command "Get-Content -Path '
|
||||
f'{_ps_quote(abs_path)} -TotalCount {max_lines}"')
|
||||
wc_cmd = (f'powershell -NoProfile -Command "(Get-Content '
|
||||
f'{_ps_quote(abs_path)} | Measure-Object -Line).Lines"')
|
||||
elif tail:
|
||||
cmd = (f'powershell -NoProfile -Command "Get-Content -Path '
|
||||
f'{_ps_quote(abs_path)} -Tail {max_lines}"')
|
||||
wc_cmd = (f'powershell -NoProfile -Command "(Get-Content '
|
||||
f'{_ps_quote(abs_path)} | Measure-Object -Line).Lines"')
|
||||
else:
|
||||
if end_line > 0:
|
||||
first = start_line - 1
|
||||
take = end_line - start_line + 1
|
||||
elif max_lines > 0:
|
||||
first = start_line - 1
|
||||
take = max_lines
|
||||
else:
|
||||
first = start_line - 1
|
||||
take = 10_000_000
|
||||
cmd = (f'powershell -NoProfile -Command "Get-Content -Path '
|
||||
f'{_ps_quote(abs_path)} | Select-Object -Skip {first} '
|
||||
f'-First {take}"')
|
||||
wc_cmd = (f'powershell -NoProfile -Command "(Get-Content '
|
||||
f'{_ps_quote(abs_path)} | Measure-Object -Line).Lines"')
|
||||
prompt = f"""请使用 `run_command` 工具执行以下命令来读取文件内容，不要直接返回文件内容：
|
||||
|
||||
```
|
||||
{cmd}
|
||||
```
|
||||
|
||||
- 若需统计总行数：`{wc_cmd}`
|
||||
- 文件大小上限 {constants.MAX_FILE_SIZE} 字节，单次最多读取 500 行"""
|
||||
return prompt
|
||||
|
||||
# 构造等价的命令行读取命令（POSIX）
|
||||
if head:
|
||||
cmd = f"head -n {max_lines} {quoted}"
|
||||
elif tail:
|
||||
@@ -180,7 +261,40 @@ class WriteFileTool(FileToolBase):
|
||||
if not is_safe:
|
||||
return error
|
||||
|
||||
quoted = shlex.quote(abs_path)
|
||||
quoted, qerr = _quote_arg(abs_path)
|
||||
if qerr:
|
||||
return qerr
|
||||
|
||||
if os.name == "nt":
|
||||
# T3：Windows 下 heredoc 不可用（cmd 命令行不能含换行，且引号
|
||||
# 转义跨 cmd/PowerShell 两层极易出错）。content 整体 Base64 编码
|
||||
# 后经 PowerShell 解码写入——Base64 字符集 [A-Za-z0-9+/=] 不含
|
||||
# 任何 cmd/PowerShell 元字符，多行/引号/特殊字符内容全覆盖。
|
||||
b64 = base64.b64encode(content.encode("utf-8")).decode("ascii")
|
||||
if len(b64) > 6000:
|
||||
return ("❌ 写入内容过大：Windows 命令行长度上限约 8191 字符，"
|
||||
"Base64 编码后超出。请将内容分成多次调用（每次 ≤4KB），"
|
||||
"首次 mode=w、后续 mode=a 追加写入")
|
||||
writer = "Add-Content" if mode == "a" else "Set-Content"
|
||||
write_cmd = (f'powershell -NoProfile -Command "{writer} -Path '
|
||||
f'{_ps_quote(abs_path)} -Value ([Text.Encoding]::UTF8.'
|
||||
f'GetString([Convert]::FromBase64String(\'{b64}\')))"')
|
||||
directory = os.path.dirname(abs_path)
|
||||
if directory:
|
||||
write_cmd = (f'powershell -NoProfile -Command "New-Item '
|
||||
f'-ItemType Directory -Force -Path '
|
||||
f'{_ps_quote(directory)}" & {write_cmd}')
|
||||
prompt = f"""请使用 `run_command` 工具执行以下命令来写入文件，不要在此工具中直接写入：
|
||||
|
||||
```
|
||||
{write_cmd}
|
||||
```
|
||||
|
||||
- 写入内容已编码为 Base64（避免换行/引号/特殊字符的跨 cmd+PowerShell 转义问题），命令会自动解码并以 UTF-8 写入
|
||||
- 若需检查文件大小：`powershell -NoProfile -Command "(Get-Item {_ps_quote(abs_path)}).Length"`
|
||||
- 文件大小上限 {constants.MAX_FILE_SIZE} 字节"""
|
||||
return prompt
|
||||
|
||||
directory = os.path.dirname(abs_path)
|
||||
dir_cmd = f"mkdir -p {shlex.quote(directory)}" if directory else ""
|
||||
|
||||
@@ -254,7 +368,26 @@ class ListFilesTool(FileToolBase):
|
||||
if not os.path.isdir(abs_path):
|
||||
return f"❌ 路径不是目录: {abs_path}"
|
||||
|
||||
quoted = shlex.quote(abs_path)
|
||||
quoted, qerr = _quote_arg(abs_path)
|
||||
if qerr:
|
||||
return qerr
|
||||
|
||||
if os.name == "nt":
|
||||
# T3：Windows 走 PowerShell 等价命令（ls/du/find/file 无原生等价物）
|
||||
force_flag = " -Force" if show_hidden else ""
|
||||
cmd = (f'powershell -NoProfile -Command "Get-ChildItem{force_flag} '
|
||||
f'{_ps_quote(abs_path)} | Select-Object '
|
||||
f'Mode,LastWriteTime,Length,Name"')
|
||||
prompt = f"""请使用 `run_command` 工具执行以下命令来列出目录内容，不要直接在此工具中列出：
|
||||
|
||||
```
|
||||
{cmd}
|
||||
```
|
||||
|
||||
- 若需统计目录总大小：`powershell -NoProfile -Command "(Get-ChildItem -Recurse {_ps_quote(abs_path)} | Measure-Object Length -Sum).Sum"`
|
||||
- 若需递归列出：`powershell -NoProfile -Command "Get-ChildItem -Recurse -Depth 2 {_ps_quote(abs_path)} | Select-Object FullName"`"""
|
||||
return prompt
|
||||
|
||||
flag = "-la" if show_hidden else "-l"
|
||||
|
||||
# 返回 markdown 提示词，指导智能体用命令行工具列目录
|
||||
@@ -324,7 +457,9 @@ class SimpleWebCrawlerTool(Tool):
|
||||
host_port = proxy_url.split("://", 1)[-1]
|
||||
if "@" in host_port:
|
||||
host_port = host_port.split("@", 1)[-1]
|
||||
return f"--socks5 {shlex.quote(host_port)}"
|
||||
# T3：平台感知引用（原 shlex.quote 在 Windows cmd.exe 下无效）
|
||||
quoted, _err = _quote_arg(host_port)
|
||||
return f"--socks5 {quoted}" if quoted else ""
|
||||
|
||||
def execute(self, action: str, url: str, **kwargs) -> str:
|
||||
if action not in ("get", "text", "title", "links", "search"):
|
||||
@@ -336,10 +471,44 @@ class SimpleWebCrawlerTool(Tool):
|
||||
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)
|
||||
quoted_url, qerr = _quote_arg(url)
|
||||
if qerr:
|
||||
return qerr
|
||||
timeout = constants.WEB_TIMEOUT
|
||||
user_agent = shlex.quote(constants.WEB_USER_AGENT)
|
||||
user_agent, ua_err = _quote_arg(constants.WEB_USER_AGENT)
|
||||
if ua_err:
|
||||
return ua_err
|
||||
proxy = self._proxy_curl_args()
|
||||
|
||||
if os.name == "nt":
|
||||
# T3：Windows 用系统内置 curl.exe（Win10 1803+）；sed/grep 等
|
||||
# POSIX 管道无原生等价，分析类动作（text/title/links/search）
|
||||
# 指引先取原始 HTML 再由 AI 自行解析。URL 含 & 时靠双引号
|
||||
# 保护（cmd 双引号内为字面量），%VAR% 形态已在 _quote_arg 拒绝。
|
||||
base = f"curl.exe -sL --max-time {timeout} -A {user_agent} {proxy}".strip()
|
||||
if action == "get":
|
||||
cmd = f'{base} -w "\\nHTTP_CODE:%{{http_code}}" {quoted_url}'
|
||||
extra = "如需查看响应头：`curl.exe -sIL ...`；如需保存到文件：`curl.exe -sL ... -o 文件名`"
|
||||
elif action == "text":
|
||||
cmd = (f'{base} {quoted_url} | powershell -NoProfile -Command '
|
||||
f'"$input -replace \'<[^>]+>\',\'\'"')
|
||||
extra = "去除 HTML 标签提取纯文本"
|
||||
else:
|
||||
cmd = f"{base} {quoted_url}"
|
||||
extra = ("Windows 下无 grep/sed 管道，请取回原始 HTML 后自行分析"
|
||||
"（提取标题/链接/检索关键词）")
|
||||
prompt = f"""请使用 `run_command` 工具执行以下命令来完成网页操作，不要直接返回网页内容：
|
||||
|
||||
```
|
||||
{cmd}
|
||||
```
|
||||
|
||||
{extra}
|
||||
- 下载大小限制 {constants.WEB_MAX_DOWNLOAD_SIZE} 字节，可在命令后追加 `| powershell -NoProfile -Command "$input | Select-Object -First 100"` 限制
|
||||
- 当前已按配置自动附带代理：{proxy or '无（如需代理请先调用 set_proxy 工具）'}"""
|
||||
return prompt
|
||||
|
||||
# POSIX 分支：_quote_arg 在 POSIX 下即 shlex.quote，直接沿用
|
||||
base = f"curl -sL --max-time {timeout} -A {user_agent} {proxy}".strip()
|
||||
|
||||
if action == "get":
|
||||
@@ -358,7 +527,10 @@ class SimpleWebCrawlerTool(Tool):
|
||||
keyword = kwargs.get("keyword")
|
||||
if not keyword:
|
||||
return "❌ 需要提供 keyword 参数"
|
||||
cmd = f"{base} {quoted_url} | grep -c {shlex.quote(keyword)}"
|
||||
quoted_kw, kw_err = _quote_arg(keyword)
|
||||
if kw_err:
|
||||
return kw_err
|
||||
cmd = f"{base} {quoted_url} | grep -c {quoted_kw}"
|
||||
extra = f"返回匹配行数，大于 0 即表示找到关键词 '{keyword}'"
|
||||
|
||||
# 返回 markdown 提示词，指导智能体用 curl 完成网页访问
|
||||
|
||||
Reference in new issue
Block a user