只有 bash 时, 所有操作都走 shell。cat 截断不可预测, sed 遇到特殊字符就崩, 每次 bash 调用都是不受约束的安全面。专用工具 (read_file, write_file) 可以在工具层面做路径沙箱。

1
2
3
4
5
6
7
8
9
10
11
12
def safe_path(p: str) -> Path:
    path = (WORKDIR / p).resolve()
    if not path.is_relative_to(WORKDIR):
        raise ValueError(f"Path escapes workspace: {p}")
    return path

def run_read(path: str, limit: int = None) -> str:
    text = safe_path(path).read_text()
    lines = text.splitlines()
    if limit and limit < len(lines):
        lines = lines[:limit]
    return "\n".join(lines)[:50000]

看一下源码，传入的参数p类型是str，返回的值应该是path。path首先将工作目录与传入的p做了一个拼接，并用resolve函数转换成了绝对路径。如果路径不是工作区的绝对路径，就会报错，这样就解决了路径越界的问题。

第二个函数是读文件的函数，user可能会传入一个limit的参数，需要保证lines要小于用户要求的参数。（因为用户可能要求读前几行）

1
2
3
4
5
6
7
8
TOOL_HANDLERS = {
    "bash":       lambda **kw: run_bash(kw["command"]),
    "read_file":  lambda **kw: run_read(kw["path"], kw.get("limit")),
    "write_file": lambda **kw: run_write(kw["path"], kw["content"]),
    "edit_file":  lambda **kw: run_edit(kw["path"], kw["old_text"],
                                        kw["new_text"]),
}

看一下这个字典，用lambda做了几个函数。

1
2
3
4
5
6
7
8
9
10
TOOLS = [
    {"name": "bash", "description": "Run a shell command.",
     "input_schema": {"type": "object", "properties": {"command": {"type": "string"}}, "required": ["command"]}},
    {"name": "read_file", "description": "Read file contents.",
     "input_schema": {"type": "object", "properties": {"path": {"type": "string"}, "limit": {"type": "integer"}}, "required": ["path"]}},
    {"name": "write_file", "description": "Write content to file.",
     "input_schema": {"type": "object", "properties": {"path": {"type": "string"}, "content": {"type": "string"}}, "required": ["path", "content"]}},
    {"name": "edit_file", "description": "Replace exact text in file.",
     "input_schema": {"type": "object", "properties": {"path": {"type": "string"}, "old_text": {"type": "string"}, "new_text": {"type": "string"}}, "required": ["path", "old_text", "new_text"]}},
]

这个其实感觉像一个说明