qing
d3acccd146
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
487 lines
18 KiB
Python
487 lines
18 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
tools.basic_tools - 基础工具集（A 批抽离）
|
|
|
|
抽离自 aibox.py 的无外部子系统依赖工具类，仅依赖 common 与标准库。
|
|
包含：
|
|
- FileToolBase : 文件操作工具基类
|
|
- ReadFileTool : 读文件（返回命令行指引）
|
|
- WriteFileTool : 写文件（返回命令行指引）
|
|
- ListFilesTool : 列目录（返回命令行指引）
|
|
- SimpleWebCrawlerTool : 网页访问（返回 curl 指引）
|
|
- GetCurrentTimeTool : 获取当前时间
|
|
- CalculatorTool : 数学计算
|
|
|
|
依赖方向：common <- tools.basic_tools，不反向依赖 aibox 任何符号。
|
|
"""
|
|
|
|
import os
|
|
import queue
|
|
import shlex
|
|
from datetime import datetime
|
|
from typing import Dict, Optional, Tuple
|
|
|
|
from common import ConfigManager, constants
|
|
from .base import Tool
|
|
|
|
|
|
# ==================== 文件操作工具基类 ====================
|
|
|
|
class FileToolBase(Tool):
|
|
"""文件操作工具基类"""
|
|
|
|
def __init__(self, logger=None):
|
|
super().__init__(logger)
|
|
|
|
def normalize_path(self, filepath: str) -> str:
|
|
return os.path.abspath(os.path.expanduser(filepath))
|
|
|
|
def check_path_safety(self, filepath: str, check_exists: bool = False) -> Tuple[bool, str, str]:
|
|
"""检查路径安全性"""
|
|
try:
|
|
abs_path = self.normalize_path(filepath)
|
|
|
|
if check_exists and not os.path.exists(abs_path):
|
|
return False, abs_path, f"❌ 文件不存在: {abs_path}"
|
|
|
|
# 检查文件大小
|
|
if os.path.exists(abs_path) and os.path.isfile(abs_path):
|
|
file_size = os.path.getsize(abs_path)
|
|
max_size = constants.MAX_FILE_SIZE
|
|
if file_size > max_size:
|
|
return False, abs_path, f"❌ 文件太大 ({file_size/1024/1024:.1f}MB)"
|
|
|
|
return True, abs_path, ""
|
|
|
|
except Exception as e:
|
|
return False, filepath, f"❌ 路径检查错误: {str(e)}"
|
|
|
|
|
|
# ==================== 文件操作工具（修改版，支持流式输出） ====================
|
|
|
|
class ReadFileTool(FileToolBase):
|
|
"""读取文件内容工具（支持流式输出）"""
|
|
|
|
def get_name(self) -> str:
|
|
return "read_file"
|
|
|
|
def get_description(self) -> str:
|
|
return "读取文件内容，支持指定起始行和结束行，或读取开头/结尾"
|
|
|
|
def get_parameters(self) -> Dict:
|
|
return {
|
|
"type": "object",
|
|
"properties": {
|
|
"filepath": {"type": "string"},
|
|
"encoding": {"type": "string", "default": "utf-8"},
|
|
"start_line": {"type": "integer", "default": 1},
|
|
"end_line": {"type": "integer", "default": 0},
|
|
"max_lines": {"type": "integer", "default": 100},
|
|
"head": {"type": "boolean", "default": False},
|
|
"tail": {"type": "boolean", "default": False}
|
|
},
|
|
"required": ["filepath"]
|
|
}
|
|
|
|
def execute(self, filepath: str, encoding: str = "utf-8",
|
|
start_line: int = 1, end_line: int = 0,
|
|
max_lines: int = 100, head: bool = False,
|
|
tail: bool = False, **kwargs) -> str:
|
|
if error := self.validate_params(["filepath"], filepath=filepath):
|
|
return error
|
|
|
|
is_safe, abs_path, error = self.check_path_safety(filepath, check_exists=True)
|
|
if not is_safe:
|
|
return error
|
|
|
|
# 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
|
|
if head:
|
|
cmd = f"head -n {max_lines} {quoted}"
|
|
elif tail:
|
|
cmd = f"tail -n {max_lines} {quoted}"
|
|
elif end_line > 0:
|
|
cmd = f"sed -n '{start_line},{end_line}p' {quoted}"
|
|
elif max_lines > 0:
|
|
end = start_line + max_lines - 1
|
|
cmd = f"sed -n '{start_line},{end}p' {quoted}"
|
|
else:
|
|
cmd = f"sed -n '{start_line},$p' {quoted}"
|
|
|
|
# 返回 markdown 提示词，指导智能体用命令行工具读取文件
|
|
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：
|
|
|
|
```bash
|
|
{cmd}
|
|
```
|
|
|
|
- 若需统计总行数：`wc -l {quoted}`
|
|
- 若需查看文件编码：`file -b --mime-encoding {quoted}`
|
|
- 若单行超长，可在命令后追加 `| cut -c 1-10000` 截断到 10000 字符
|
|
- 文件大小上限 {constants.MAX_FILE_SIZE} 字节，单次最多读取 500 行"""
|
|
return prompt
|
|
|
|
def execute_streaming(self, output_queue: queue.Queue, **kwargs):
|
|
"""流式执行文件读取"""
|
|
filepath = kwargs.get("filepath")
|
|
|
|
# 发送开始执行的消息
|
|
output_queue.put(("line", f"\n📄 读取文件: {filepath}\n"))
|
|
output_queue.put(("line", "-" * 50 + "\n"))
|
|
|
|
# 执行操作
|
|
result = self.execute(**kwargs)
|
|
|
|
# 发送结果
|
|
output_queue.put(("line", result + "\n"))
|
|
output_queue.put(("complete", result))
|
|
|
|
|
|
class WriteFileTool(FileToolBase):
|
|
"""写入文件工具（支持流式输出）"""
|
|
|
|
def get_name(self) -> str:
|
|
return "write_file"
|
|
|
|
def get_description(self) -> str:
|
|
return "文件写入工具 - 支持覆盖、追加"
|
|
|
|
def get_parameters(self) -> Dict:
|
|
return {
|
|
"type": "object",
|
|
"properties": {
|
|
"filepath": {"type": "string"},
|
|
"content": {"type": "string"},
|
|
"mode": {"type": "string", "enum": ["w", "a"], "default": "w"},
|
|
"encoding": {"type": "string", "default": "utf-8"}
|
|
},
|
|
"required": ["filepath", "content"]
|
|
}
|
|
|
|
def execute(self, filepath: str = None, content: str = None, mode: str = "w",
|
|
encoding: str = "utf-8", **kwargs) -> str:
|
|
if error := self.validate_params(["filepath", "content"], filepath=filepath, content=content):
|
|
return error
|
|
|
|
is_safe, abs_path, error = self.check_path_safety(filepath)
|
|
if not is_safe:
|
|
return error
|
|
|
|
quoted = shlex.quote(abs_path)
|
|
directory = os.path.dirname(abs_path)
|
|
dir_cmd = f"mkdir -p {shlex.quote(directory)}" if directory else ""
|
|
|
|
# 内容写入使用 heredoc，避免引号/特殊字符转义问题
|
|
# M1 修复（审计 2026-08-17）：定界符唯一化——若 content 中含独立行
|
|
# 与定界符相同（如 "AIBOX_EOF"），heredoc 会提前终止，其后内容被
|
|
# 当作 shell 命令执行（注入）。冲突时递增后缀直到唯一。
|
|
delimiter = "AIBOX_EOF"
|
|
content_lines = {line.strip() for line in content.split("\n")}
|
|
while delimiter in content_lines:
|
|
delimiter += "_X"
|
|
redirect = ">" if mode == "w" else ">>"
|
|
write_cmd = f"cat {redirect} {quoted} <<'{delimiter}'\n{content}\n{delimiter}"
|
|
if dir_cmd:
|
|
write_cmd = f"{dir_cmd} && {write_cmd}"
|
|
|
|
# 返回 markdown 提示词，指导智能体用命令行工具写入文件
|
|
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：
|
|
|
|
```bash
|
|
{write_cmd}
|
|
```
|
|
|
|
- 如遇 heredoc 内容含特殊字符导致解析失败，可用 `printf '%s' '内容' > {quoted}` 覆盖写入
|
|
- 若需检查文件大小：`wc -c {quoted}`
|
|
- 文件大小上限 {constants.MAX_FILE_SIZE} 字节"""
|
|
return prompt
|
|
|
|
def execute_streaming(self, output_queue: queue.Queue, **kwargs):
|
|
"""流式执行文件写入"""
|
|
filepath = kwargs.get("filepath")
|
|
|
|
# 发送开始执行的消息
|
|
output_queue.put(("line", f"\n📝 写入文件: {filepath}\n"))
|
|
output_queue.put(("line", "-" * 50 + "\n"))
|
|
|
|
# 执行操作
|
|
result = self.execute(**kwargs)
|
|
|
|
# 发送结果
|
|
output_queue.put(("line", result + "\n"))
|
|
output_queue.put(("complete", result))
|
|
|
|
|
|
class ListFilesTool(FileToolBase):
|
|
"""列出目录内容工具（支持流式输出）"""
|
|
|
|
def get_name(self) -> str:
|
|
return "list_files"
|
|
|
|
def get_description(self) -> str:
|
|
return "列出指定目录下的文件和子目录"
|
|
|
|
def get_parameters(self) -> Dict:
|
|
return {
|
|
"type": "object",
|
|
"properties": {
|
|
"directory": {"type": "string", "default": "."},
|
|
"show_hidden": {"type": "boolean", "default": False}
|
|
}
|
|
}
|
|
|
|
def execute(self, directory: str = ".", show_hidden: bool = False, **kwargs) -> str:
|
|
is_safe, abs_path, error = self.check_path_safety(directory)
|
|
if not is_safe:
|
|
return error
|
|
|
|
if not os.path.exists(abs_path):
|
|
return f"❌ 目录不存在: {abs_path}"
|
|
|
|
if not os.path.isdir(abs_path):
|
|
return f"❌ 路径不是目录: {abs_path}"
|
|
|
|
quoted = shlex.quote(abs_path)
|
|
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
|
|
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：
|
|
|
|
```bash
|
|
ls {flag} {quoted}
|
|
```
|
|
|
|
- 若需区分目录/文件并显示大小：`ls -lhF {quoted}`
|
|
- 若需统计目录总大小：`du -sh {quoted}`
|
|
- 若需递归列出：`find {quoted} -maxdepth 2`
|
|
- 若需了解文件类型：`file {quoted}/*`"""
|
|
return prompt
|
|
|
|
def execute_streaming(self, output_queue: queue.Queue, **kwargs):
|
|
"""流式执行列出目录"""
|
|
directory = kwargs.get("directory", ".")
|
|
|
|
# 发送开始执行的消息
|
|
output_queue.put(("line", f"\n📁 列出目录: {directory}\n"))
|
|
output_queue.put(("line", "-" * 50 + "\n"))
|
|
|
|
# 执行操作
|
|
result = self.execute(**kwargs)
|
|
|
|
# 发送结果
|
|
output_queue.put(("line", result + "\n"))
|
|
output_queue.put(("complete", result))
|
|
|
|
|
|
# ==================== 网页访问工具 ====================
|
|
|
|
class SimpleWebCrawlerTool(Tool):
|
|
"""简化版网页爬虫工具（返回 markdown 提示词，指导改用 curl 命令行）"""
|
|
|
|
def __init__(self, logger=None):
|
|
super().__init__(logger)
|
|
|
|
def get_name(self) -> str:
|
|
return "web"
|
|
|
|
def get_description(self) -> str:
|
|
return """简单易用的网页访问工具 - 一句话搞定！
|
|
支持：获取网页、提取内容、搜索关键词、下载文件"""
|
|
|
|
def get_parameters(self) -> Dict:
|
|
return {
|
|
"type": "object",
|
|
"properties": {
|
|
"action": {
|
|
"type": "string",
|
|
"enum": ["get", "text", "title", "links", "search"]
|
|
},
|
|
"url": {"type": "string"},
|
|
"keyword": {"type": "string"}
|
|
},
|
|
"required": ["action", "url"]
|
|
}
|
|
|
|
def _proxy_curl_args(self) -> str:
|
|
"""根据当前代理配置构造 curl --socks5 参数"""
|
|
proxies = ConfigManager().get_proxy()
|
|
if not proxies:
|
|
return ""
|
|
proxy_url = proxies.get("https") or proxies.get("http") or ""
|
|
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)}"
|
|
|
|
def execute(self, action: str, url: str, **kwargs) -> str:
|
|
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)
|
|
proxy = self._proxy_curl_args()
|
|
base = f"curl -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 -sIL ...`；如需保存到文件：`curl -sL ... -o 文件名`"
|
|
elif action == "text":
|
|
cmd = f"{base} {quoted_url} | sed -r 's/<[^>]+>//g'"
|
|
extra = "若系统装有 lynx，可用 `lynx -dump -stdin` 提取纯文本更准确"
|
|
elif action == "title":
|
|
cmd = f"{base} {quoted_url} | grep -oP '<title>\\K[^<]+'"
|
|
extra = "无输出则表示未找到标题"
|
|
elif action == "links":
|
|
cmd = f"{base} {quoted_url} | grep -oP 'href=\"\\K[^\"]+'"
|
|
extra = "输出所有链接 URL，可配合 `head` 限制数量"
|
|
else: # search
|
|
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)}"
|
|
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
|
|
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：
|
|
|
|
```bash
|
|
{cmd}
|
|
```
|
|
|
|
{extra}
|
|
- 下载大小限制 {constants.WEB_MAX_DOWNLOAD_SIZE} 字节，可在命令后追加 `| head -c {constants.WEB_MAX_DOWNLOAD_SIZE}` 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
|
|
|
|
def execute_streaming(self, output_queue: queue.Queue, **kwargs):
|
|
"""流式执行网页操作"""
|
|
action = kwargs.get("action")
|
|
url = kwargs.get("url")
|
|
|
|
# 发送开始执行的消息
|
|
output_queue.put(("line", f"\n🌐 执行网页操作: {action} - {url}\n"))
|
|
output_queue.put(("line", "-" * 50 + "\n"))
|
|
|
|
# 执行操作
|
|
result = self.execute(**kwargs)
|
|
|
|
# 发送结果
|
|
output_queue.put(("line", result + "\n"))
|
|
output_queue.put(("complete", result))
|
|
|
|
|
|
# ==================== 系统工具（修改版，支持流式输出） ====================
|
|
|
|
class GetCurrentTimeTool(Tool):
|
|
"""获取当前时间工具（支持流式输出）"""
|
|
|
|
def get_name(self) -> str:
|
|
return "get_current_time"
|
|
|
|
def get_description(self) -> str:
|
|
return "获取当前日期和时间"
|
|
|
|
def get_parameters(self) -> Dict:
|
|
return {
|
|
"type": "object",
|
|
"properties": {
|
|
"format": {"type": "string", "enum": ["full", "date", "time"], "default": "full"}
|
|
}
|
|
}
|
|
|
|
def execute(self, format: str = "full", **kwargs) -> str:
|
|
now = datetime.now()
|
|
|
|
if format == "date":
|
|
result = now.strftime("%Y-%m-%d")
|
|
elif format == "time":
|
|
result = now.strftime("%H:%M:%S")
|
|
else:
|
|
result = now.strftime(constants.DATETIME_FORMAT)
|
|
|
|
return self.format_result(True, "当前时间", {"时间": result})
|
|
|
|
def execute_streaming(self, output_queue: queue.Queue, **kwargs):
|
|
"""流式执行获取时间"""
|
|
output_queue.put(("line", "\n🕐 获取当前时间\n"))
|
|
output_queue.put(("line", "-" * 50 + "\n"))
|
|
|
|
result = self.execute(**kwargs)
|
|
|
|
output_queue.put(("line", result + "\n"))
|
|
output_queue.put(("complete", result))
|
|
|
|
|
|
class CalculatorTool(Tool):
|
|
"""计算器工具（支持流式输出）"""
|
|
|
|
def get_name(self) -> str:
|
|
return "calculator"
|
|
|
|
def get_description(self) -> str:
|
|
return "执行数学计算"
|
|
|
|
def get_parameters(self) -> Dict:
|
|
return {
|
|
"type": "object",
|
|
"properties": {
|
|
"a": {"type": "number"},
|
|
"b": {"type": "number"},
|
|
"operation": {"type": "string", "enum": ["add", "subtract", "multiply", "divide"]}
|
|
},
|
|
"required": ["a", "b", "operation"]
|
|
}
|
|
|
|
def execute(self, a: float, b: float, operation: str, **kwargs) -> str:
|
|
operations = {
|
|
"add": ("+", a + b),
|
|
"subtract": ("-", a - b),
|
|
"multiply": ("*", a * b),
|
|
"divide": ("/", a / b if b != 0 else None)
|
|
}
|
|
|
|
if operation not in operations:
|
|
return f"❌ 未知运算: {operation}"
|
|
|
|
op_symbol, result = operations[operation]
|
|
|
|
if result is None:
|
|
return "❌ 错误：除数不能为0"
|
|
|
|
data = {
|
|
"表达式": f"{a} {op_symbol} {b}",
|
|
"结果": result
|
|
}
|
|
|
|
return self.format_result(True, "计算成功", data)
|
|
|
|
def execute_streaming(self, output_queue: queue.Queue, **kwargs):
|
|
"""流式执行计算"""
|
|
output_queue.put(("line", "\n🧮 执行计算\n"))
|
|
output_queue.put(("line", "-" * 50 + "\n"))
|
|
|
|
result = self.execute(**kwargs)
|
|
|
|
output_queue.put(("line", result + "\n"))
|
|
output_queue.put(("complete", result))
|