coding-agent/s04_hooks/code.py

#!/usr/bin/env python3
"""
s04: 钩子系统 — 把扩展逻辑从循环中移出，挂到钩子上。

  用户输入问题
       │
       ▼
  ┌──────────────────┐
  │ UserPromptSubmit │ ── LLM 调用前触发 trigger_hooks()
  └────────┬─────────┘
           ▼
  ┌────────────┐     ┌─────────────────────────────┐
  │  messages  │────▶│  LLM (stop_reason=tool_use?)│
  └────────────┘     │   否 ──▶ Stop hooks ──▶ 退出 │
                     │   是 ──▶ tool_use block ──┐ │
                     └────────────────────────────┘ │
                                                    ▼
                                          ┌──────────────────┐
                                          │ trigger_hooks()   │
                                          │  PreToolUse:      │
                                          │   permission_hook │
                                          │   log_hook        │
                                          └───────┬──────────┘
                                                  │ (未被拦截)
                                          ┌───────▼──────────┐
                                          │ TOOL_HANDLERS[x]  │
                                          └───────┬──────────┘
                                                  │
                                          ┌───────▼──────────┐
                                          │ trigger_hooks()   │
                                          │  PostToolUse:     │
                                          │   large_output    │
                                          └───────┬──────────┘
                                                  │
                                          results ──▶ 回到 messages
"""

import os, subprocess
from pathlib import Path

try:
    import readline
    readline.parse_and_bind('set bind-tty-special-chars off')
    readline.parse_and_bind('set input-meta on')
    readline.parse_and_bind('set output-meta on')
    readline.parse_and_bind('set convert-meta off')
except ImportError:
    pass

from anthropic import Anthropic
from dotenv import load_dotenv

load_dotenv(override=True)
if os.getenv("ANTHROPIC_BASE_URL"):
    os.environ.pop("ANTHROPIC_AUTH_TOKEN", None)

WORKDIR = Path.cwd()
client = Anthropic(base_url=os.getenv("ANTHROPIC_BASE_URL"))
MODEL = os.environ["MODEL_ID"]

SYSTEM = f"你是位于 {WORKDIR}. 使用工具解决任务。直接行动，不要只解释。"


# ═══════════════════════════════════════════════════════════
#  来自 s02-s03 : 工具实现
# ═══════════════════════════════════════════════════════════

def run_bash(command: str) -> str:
    try:
        r = subprocess.run(command, shell=True, cwd=WORKDIR,
                           capture_output=True, text=True, timeout=120)
        out = (r.stdout + r.stderr).strip()
        return out[:50000] if out else "（无输出）"
    except subprocess.TimeoutExpired:
        return "错误：执行超时（120 秒）"

def run_read(path: str, limit: int | None = None) -> str:
    try:
        file_path = (WORKDIR / path).resolve()
        lines = file_path.read_text().splitlines()
        if limit and limit < len(lines):
            lines = lines[:limit] + [f"... ({len(lines) - limit} 行更多内容）"]
        return "\n".join(lines)
    except Exception as e:
        return f"错误：{e}"

def run_write(path: str, content: str) -> str:
    try:
        file_path = (WORKDIR / path).resolve()
        file_path.parent.mkdir(parents=True, exist_ok=True)
        file_path.write_text(content)
        return f"已写入 {len(content)} 字节到 {path}"
    except Exception as e:
        return f"错误：{e}"

def run_edit(path: str, old_text: str, new_text: str) -> str:
    try:
        file_path = (WORKDIR / path).resolve()
        text = file_path.read_text()
        if old_text not in text:
            return f"错误：在文件中未找到目标文本：{path}"
        file_path.write_text(text.replace(old_text, new_text, 1))
        return f"已编辑 {path}"
    except Exception as e:
        return f"错误：{e}"

def run_glob(pattern: str) -> str:
    import glob as g
    try:
        results = []
        for match in g.glob(pattern, root_dir=WORKDIR):
            if (WORKDIR / match).resolve().is_relative_to(WORKDIR):
                results.append(match)
        return "\n".join(results) if results else "（无匹配）"
    except Exception as e:
        return f"错误：{e}"

TOOLS = [
    {"name": "bash", "description": "运行一条 shell 命令。",
     "input_schema": {"type": "object", "properties": {"command": {"type": "string"}}, "required": ["command"]}},
    {"name": "read_file", "description": "读取文件内容。",
     "input_schema": {"type": "object", "properties": {"path": {"type": "string"}, "limit": {"type": "integer"}}, "required": ["path"]}},
    {"name": "write_file", "description": "向文件写入内容。",
     "input_schema": {"type": "object", "properties": {"path": {"type": "string"}, "content": {"type": "string"}}, "required": ["path", "content"]}},
    {"name": "edit_file", "description": "在文件中替换一次完全匹配的文本。",
     "input_schema": {"type": "object", "properties": {"path": {"type": "string"}, "old_text": {"type": "string"}, "new_text": {"type": "string"}}, "required": ["path", "old_text", "new_text"]}},
    {"name": "glob", "description": "查找匹配 glob 模式的文件。",
     "input_schema": {"type": "object", "properties": {"pattern": {"type": "string"}}, "required": ["pattern"]}},
]

TOOL_HANDLERS = {
    "bash": run_bash, "read_file": run_read, "write_file": run_write,
    "edit_file": run_edit, "glob": run_glob,
}


# ═══════════════════════════════════════════════════════════
#  新增于 s04: 钩子系统（s03 权限逻辑现在通过钩子实现）
# ═══════════════════════════════════════════════════════════

HOOKS = {"UserPromptSubmit": [], "PreToolUse": [], "PostToolUse": [], "Stop": []}

def register_hook(event: str, callback):
    HOOKS[event].append(callback)

def trigger_hooks(event: str, *args):
    for callback in HOOKS[event]:
        result = callback(*args)
        if result is not None:  # 教学快捷方式：拦截这个工具调用
            return result
    return None


# s03 权限检查逻辑，现在封装成钩子
DENY_LIST = ["rm -rf /", "sudo", "shutdown", "reboot", "mkfs", "dd if="]
DESTRUCTIVE = ["rm ", "> /etc/", "chmod 777"]

def permission_hook(block):
    """PreToolUse：这里承载从 s03 迁移过来的 check_permission() 逻辑。"""
    if block.name == "bash":
        for pattern in DENY_LIST:
            if pattern in block.input.get("command", ""):
                print(f"\n\033[31m⛔ 已拦截：'{pattern}'\033[0m")
                return "被拒绝列表拒绝授权"
        for kw in DESTRUCTIVE:
            if kw in block.input.get("command", ""):
                print(f"\n\033[33m⚠  可能具有破坏性的命令\033[0m")
                print(f"   工具：{block.name}({block.input})")
                choice = input("   是否允许？[y/N] ").strip().lower()
                if choice not in ("y", "yes"):
                    return "用户拒绝授权"
    if block.name in ("read_file", "write_file", "edit_file"):
        path = block.input.get("path", "")
        if not (WORKDIR / path).resolve().is_relative_to(WORKDIR):
            print(f"\n\033[33m⚠  访问工作区外部路径\033[0m")
            print(f"   工具：{block.name}({block.input})")
            choice = input("   是否允许？[y/N] ").strip().lower()
            if choice not in ("y", "yes"):
                return "用户拒绝授权"
    return None

def log_hook(block):
    """PreToolUse：记录每一次工具调用。"""
    args_preview = str(list(block.input.values())[:2])[:60]
    print(f"\033[90m[钩子] {block.name}({args_preview})\033[0m")
    return None

def large_output_hook(block, output):
    """PostToolUse：对大型输出给出提醒。"""
    if len(str(output)) > 100000:
        print(f"\033[33m[钩子] ⚠ 来自以下工具的大输出：{block.name}: {len(str(output))} 个字符\033[0m")
    return None

# 用户提交提示词钩子：在用户输入到达 LLM 前记录它
def context_inject_hook(query: str):
    print(f"\033[90m[钩子] UserPromptSubmit: 工作目录：{WORKDIR}\033[0m")
    return None

# 停止钩子：在循环即将退出时打印摘要
def summary_hook(messages: list):
    tool_count = sum(1 for m in messages
                     for b in (m.get("content") if isinstance(m.get("content"), list) else [])
                     if isinstance(b, dict) and b.get("type") == "tool_result")
    print(f"\033[90m[钩子] Stop：会话使用了 {tool_count} 次工具调用\033[0m")
    return None

register_hook("UserPromptSubmit", context_inject_hook)
register_hook("PreToolUse", permission_hook)
register_hook("PreToolUse", log_hook)
register_hook("PostToolUse", large_output_hook)
register_hook("Stop", summary_hook)


# ═══════════════════════════════════════════════════════════
#  agent_loop — 与 s03 结构相同，但没有硬编码检查
#  s03: if not check_permission(block): ...
#  s04: if trigger_hooks("PreToolUse", block): ...
# ═══════════════════════════════════════════════════════════

def agent_loop(messages: list):
    while True:
        response = client.messages.create(
            model=MODEL, system=SYSTEM, messages=messages,
            tools=TOOLS, max_tokens=8000,
        )
        messages.append({"role": "assistant", "content": response.content})

        if response.stop_reason != "tool_use":
            force = trigger_hooks("Stop", messages)
            if force:
                messages.append({"role": "user", "content": force})
                continue
            return

        results = []
        for block in response.content:
            if block.type != "tool_use":
                continue

            # s04 变化： Hook 替代硬编码的 check_permission()
            blocked = trigger_hooks("PreToolUse", block)
            if blocked:
                results.append({"type": "tool_result", "tool_use_id": block.id,
                                "content": str(blocked)})
                continue

            handler = TOOL_HANDLERS.get(block.name)
            output = handler(**block.input) if handler else f"未知工具：{block.name}"

            trigger_hooks("PostToolUse", block, output)  # s04: 后置钩子

            results.append({"type": "tool_result", "tool_use_id": block.id, "content": output})

        messages.append({"role": "user", "content": results})


if __name__ == "__main__":
    print("s04: 钩子系统 — 扩展逻辑挂到钩子上，循环保持干净")
    print("输入问题后按回车。输入 q 退出。\n")

    history = []
    while True:
        try:
            query = input("\033[36ms04 >> \033[0m")
        except (EOFError, KeyboardInterrupt):
            break
        if query.strip().lower() in ("q", "exit", ""):
            break
        trigger_hooks("UserPromptSubmit", query)
        history.append({"role": "user", "content": query})
        agent_loop(history)
        for block in history[-1]["content"]:
            if getattr(block, "type", None) == "text":
                print(block.text)
        print()