coding-agent/s13_background_tasks/code.py

#!/usr/bin/env python3
"""
s13: 后台任务 — 基于线程的异步执行 + 通知注入。

运行:  python s13_background_tasks/code.py
需要: pip install anthropic python-dotenv + .env 中配置 ANTHROPIC_API_KEY

相对 s12 的变化：
  - 使用 threading.Thread 做后台执行
  - background_tasks 字典跟踪生命周期（bg_id、command、status）
  - background_results 字典 + threading.Lock 实现线程安全存储
  - should_run_background：模型通过 run_in_background 参数显式请求
  - is_slow_operation：当模型未指定时使用的兜底启发式判断
  - start_background_task：分发到守护线程，返回后台任务 id
  - collect_background_results：收集已完成任务，并以通知形式返回
  - agent_loop：慢操作 → 后台执行 + 占位结果，随后注入通知
  - 通知使用 <task_notification> 格式，不复用 tool_use_id

说明：教学代码保留一个基础 Agent 循环，以便聚焦后台任务。
S11 的完整错误恢复（RecoveryState、退避、升级、reactive compact、备用模型）被省略。
"""

import os, subprocess, json, time, random, threading
from pathlib import Path
from dataclasses import dataclass, asdict

try:
    import readline
    readline.parse_and_bind('set bind-tty-special-chars 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()
MEMORY_DIR = WORKDIR / ".memory"
MEMORY_INDEX = MEMORY_DIR / "MEMORY.md"
client = Anthropic(base_url=os.getenv("ANTHROPIC_BASE_URL"))
MODEL = os.environ["MODEL_ID"]

# ── 任务系统 （来自 s12，已同步） ──

TASKS_DIR = WORKDIR / ".tasks"
TASKS_DIR.mkdir(exist_ok=True)


@dataclass
class Task:
    id: str
    subject: str
    description: str
    status: str          # pending | in_progress | completed
    owner: str | None
    blockedBy: list[str]


def _task_path(task_id: str) -> Path:
    return TASKS_DIR / f"{task_id}.json"


def create_task(subject: str, description: str = "",
                blockedBy: list[str] | None = None) -> Task:
    task = Task(
        id=f"task_{int(time.time())}_{random.randint(0, 9999):04d}",
        subject=subject, description=description,
        status="pending", owner=None,
        blockedBy=blockedBy or [],
    )
    save_task(task)
    return task


def save_task(task: Task):
    _task_path(task.id).write_text(json.dumps(asdict(task), indent=2))


def load_task(task_id: str) -> Task:
    return Task(**json.loads(_task_path(task_id).read_text()))


def list_tasks() -> list[Task]:
    return [Task(**json.loads(p.read_text()))
            for p in sorted(TASKS_DIR.glob("task_*.json"))]


def get_task(task_id: str) -> str:
    """以 JSON 返回完整任务详情。"""
    task = load_task(task_id)
    return json.dumps(asdict(task), indent=2)


def can_start(task_id: str) -> bool:
    """Check if all blockedBy dependencies are completed.
    Missing dependencies are treated as blocked."""
    task = load_task(task_id)
    for dep_id in task.blockedBy:
        if not _task_path(dep_id).exists():
            return False
        if load_task(dep_id).status != "completed":
            return False
    return True


def claim_task(task_id: str, owner: str = "agent") -> str:
    task = load_task(task_id)
    if task.status != "pending":
        return f"任务 {task_id} 当前状态为 {task.status}，无法认领"
    if not can_start(task_id):
        deps = [d for d in task.blockedBy
                if not _task_path(d).exists() or load_task(d).status != "completed"]
        return f"Blocked by: {deps}"
    task.owner = owner
    task.status = "in_progress"
    save_task(task)
    print(f"  \033[36m[claim] {task.subject} → in_progress (owner: {owner})\033[0m")
    return f"已认领 {task.id} ({task.subject})"


def complete_task(task_id: str) -> str:
    task = load_task(task_id)
    if task.status != "in_progress":
        return f"任务 {task_id} 当前状态为 {task.status}，无法完成"
    task.status = "completed"
    save_task(task)
    unblocked = [t.subject for t in list_tasks()
                 if t.status == "pending" and t.blockedBy and can_start(t.id)]
    print(f"  \033[32m[complete] {task.subject} ✓\033[0m")
    msg = f"已完成 {task.id} ({task.subject})"
    if unblocked:
        msg += f"\n已解除阻塞：{', '.join(unblocked)}"
        print(f"  \033[33m[unblocked] {', '.join(unblocked)}\033[0m")
    return msg


# ── 提示词组装 （来自 s10，已同步） ──

PROMPT_SECTIONS = {
    "identity": "你是一个编码 Agent。直接行动，不要只解释。",
    "tools": "可用工具：bash, read_file, write_file, "
             "create_task, list_tasks, get_task, claim_task, complete_task.",
    "workspace": f"工作目录：{WORKDIR}",
    "memory": "有可用的相关记忆时，会在下方注入。",
}


def assemble_system_prompt(context: dict) -> str:
    sections = [PROMPT_SECTIONS["identity"],
                PROMPT_SECTIONS["tools"],
                PROMPT_SECTIONS["workspace"]]
    memories = context.get("memories", "")
    if memories:
        sections.append(f"Relevant memories:\n{memories}")
    return "\n\n".join(sections)


_last_context_key, _last_prompt = None, None


def get_system_prompt(context: dict) -> str:
    global _last_context_key, _last_prompt
    key = json.dumps(context, sort_keys=True, ensure_ascii=False, default=str)
    if key == _last_context_key and _last_prompt:
        return _last_prompt
    _last_context_key = key
    _last_prompt = assemble_system_prompt(context)
    return _last_prompt


# ── 工具 ──

def safe_path(p: str) -> Path:
    path = (WORKDIR / p).resolve()
    if not path.is_relative_to(WORKDIR):
        raise ValueError(f"路径逃逸出工作区：{p}")
    return path


def run_bash(command: str, run_in_background: bool = False) -> str:
    # run_in_background 由 agent_loop 分发处理，不在这里处理
    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:
        lines = safe_path(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:
        fp = safe_path(path)
        fp.parent.mkdir(parents=True, exist_ok=True)
        fp.write_text(content)
        return f"已写入 {len(content)} 字节到 {path}"
    except Exception as e:
        return f"错误：{e}"


# 任务工具

def run_create_task(subject: str, description: str = "",
                    blockedBy: list[str] | None = None) -> str:
    task = create_task(subject, description, blockedBy)
    deps = f" (blockedBy: {', '.join(blockedBy)})" if blockedBy else ""
    print(f"  \033[34m[create] {task.subject}{deps}\033[0m")
    return f"已创建 {task.id}: {task.subject}{deps}"


def run_list_tasks() -> str:
    个任务 = list_tasks()
    if not 个任务:
        return "暂无任务。请使用 create_task 添加任务。"
    lines = []
    for t in 个任务:
        icon = {"pending": "○", "in_progress": "●",
                "completed": "✓"}.get(t.status, "?")
        deps = f" (blockedBy: {', '.join(t.blockedBy)})" if t.blockedBy else ""
        owner = f" [{t.owner}]" if t.owner else ""
        lines.append(f"  {icon} {t.id}: {t.subject} "
                     f"[{t.status}]{owner}{deps}")
    return "\n".join(lines)


def run_get_task(task_id: str) -> str:
    try:
        return get_task(task_id)
    except FileNotFoundError:
        return f"错误：任务 {task_id} 未找到"


def run_claim_task(task_id: str) -> str:
    return claim_task(task_id, owner="agent")


def run_complete_task(task_id: str) -> str:
    return complete_task(task_id)


TOOLS = [
    {"name": "bash", "description": "运行一条 shell 命令。",
     "input_schema": {"type": "object",
                      "properties": {
                          "command": {"type": "string"},
                          "run_in_background": {"type": "boolean"}},
                      "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": "create_task",
     "description": "创建一个新任务，可选 blockedBy 依赖。",
     "input_schema": {"type": "object",
                      "properties": {
                          "subject": {"type": "string"},
                          "description": {"type": "string"},
                          "blockedBy": {"type": "array",
                                        "items": {"type": "string"}}},
                      "required": ["subject"]}},
    {"name": "list_tasks",
     "description": "列出所有任务及其状态、负责人和依赖。",
     "input_schema": {"type": "object", "properties": {},
                      "required": []}},
    {"name": "get_task",
     "description": "按 ID 获取指定任务的完整详情。",
     "input_schema": {"type": "object",
                      "properties": {"task_id": {"type": "string"}},
                      "required": ["task_id"]}},
    {"name": "claim_task",
     "description": "认领一个待处理任务。设置 owner，并将状态改为 in_progress。",
     "input_schema": {"type": "object",
                      "properties": {"task_id": {"type": "string"}},
                      "required": ["task_id"]}},
    {"name": "complete_task",
     "description": "完成一个进行中的任务。报告被解除阻塞的下游任务。",
     "input_schema": {"type": "object",
                      "properties": {"task_id": {"type": "string"}},
                      "required": ["task_id"]}},
]

TOOL_HANDLERS = {
    "bash": run_bash, "read_file": run_read, "write_file": run_write,
    "create_task": run_create_task, "list_tasks": run_list_tasks,
    "get_task": run_get_task, "claim_task": run_claim_task,
    "complete_task": run_complete_task,
}


# ── 后台任务 （s13 新增） ──

_bg_计数器 = 0
background_tasks: dict[str, dict] = {}   # bg_id → {tool_use_id, command, status}
background_results: dict[str, str] = {}   # bg_id → output
background_lock = threading.Lock()


def is_slow_operation(tool_name: str, tool_input: dict) -> bool:
    """兜底启发式：判断命令是否可能超过 30 秒。"""
    if tool_name != "bash":
        return False
    cmd = tool_input.get("command", "").lower()
    slow_keywords = ["install", "build", "test", "deploy", "compile",
                     "docker build", "pip install", "npm install",
                     "cargo build", "pytest", "make"]
    return any(kw in cmd for kw in slow_keywords)


def should_run_background(tool_name: str, tool_input: dict) -> bool:
    """模型的显式请求优先；否则使用启发式兜底。"""
    if tool_input.get("run_in_background"):
        return True
    return is_slow_operation(tool_name, tool_input)


def execute_tool(block) -> str:
    """执行工具调用块并返回输出。"""
    handler = TOOL_HANDLERS.get(block.name)
    if handler:
        return handler(**block.input)
    return f"未知工具：{block.name}"


def start_background_task(block) -> str:
    """在守护线程中运行工具，并返回后台任务 ID。"""
    global _bg_计数器
    _bg_计数器 += 1
    bg_id = f"bg_{_bg_计数器:04d}"
    cmd = block.input.get("command", block.name)

    def worker():
        result = execute_tool(block)
        with background_lock:
            background_tasks[bg_id]["status"] = "completed"
            background_results[bg_id] = result

    with background_lock:
        background_tasks[bg_id] = {
            "tool_use_id": block.id,
            "command": cmd,
            "status": "running",
        }
    thread = threading.Thread(target=worker, daemon=True)
    thread.start()
    print(f"  \033[33m[background] dispatched {bg_id}: {cmd[:40]}\033[0m")
    return bg_id


def collect_background_results() -> list[str]:
    """将已完成的后台结果收集为 task_notification 消息。"""
    with background_lock:
        ready_ids = [bid for bid, task in background_tasks.items()
                     if task["status"] == "completed"]
    notifications = []
    for bg_id in ready_ids:
        with background_lock:
            task = background_tasks.pop(bg_id)
            output = background_results.pop(bg_id, "")
        summary = output[:200] if len(output) > 200 else output
        notifications.append(
            f"<task_notification>\n"
            f"  <task_id>{bg_id}</task_id>\n"
            f"  <status>completed</status>\n"
            f"  <command>{task['command']}</command>\n"
            f"  <summary>{summary}</summary>\n"
            f"</task_notification>")
        print(f"  \033[32m[background done] {bg_id}: "
              f"{task['command'][:40]} ({len(output)} 个字符)\033[0m")
    return notifications


# ── 上下文 ──

def update_context(context: dict, messages: list) -> dict:
    """Derive context from real state."""
    memories = ""
    if MEMORY_INDEX.exists():
        content = MEMORY_INDEX.read_text().strip()
        if content:
            memories = content
    return {
        "enabled_tools": list(TOOL_HANDLERS.keys()),
        "workspace": str(WORKDIR),
        "memories": memories,
    }


# ── Agent 循环（简化版，聚焦后台任务） ──

def agent_loop(messages: list, context: dict):
    system = get_system_prompt(context)
    while True:
        try:
            response = client.messages.create(
                model=MODEL, system=system, messages=messages,
                tools=TOOLS, max_tokens=8000)
        except Exception as e:
            messages.append({"role": "assistant", "content": [
                {"type": "text",
                 "text": f"[错误] {type(e).__name__}: {e}"}]})
            return

        messages.append({"role": "assistant", "content": response.content})
        if response.stop_reason != "tool_use":
            return

        results = []
        for block in response.content:
            if block.type != "tool_use":
                continue
            print(f"\033[36m> {block.name}\033[0m")

            if should_run_background(block.name, block.input):
                bg_id = start_background_task(block)
                results.append({"type": "tool_result",
                                "tool_use_id": block.id,
                                "content": f"[Background task {bg_id} started] "
                                           f"命令：{block.input.get('command', '')}. "
                                           f"完成后结果将可用。"})
            else:
                output = execute_tool(block)
                print(str(output)[:300])
                results.append({"type": "tool_result",
                                "tool_use_id": block.id,
                                "content": output})

        # 在一条用户消息中注入工具结果 + 后台通知
        user_content = list(results)
        bg_notifications = collect_background_results()
        if bg_notifications:
            for notif in bg_notifications:
                user_content.append({"type": "text", "text": notif})
            print(f"  \033[32m[inject] {len(bg_notifications)} background "
                  f"notification(s)\033[0m")
        messages.append({"role": "user", "content": user_content})
        context = update_context(context, messages)
        system = get_system_prompt(context)


if __name__ == "__main__":
    print("s13: background 个任务")
    print("输入问题后按回车发送。输入 q 退出。\n")
    history = []
    context = update_context({}, [])
    while True:
        try:
            query = input("\033[36ms13 >> \033[0m")
        except (EOFError, KeyboardInterrupt):
            break
        if query.strip().lower() in ("q", "exit", ""):
            break
        history.append({"role": "user", "content": query})
        agent_loop(history, context)
        context = update_context(context, history)
        for block in history[-1]["content"]:
            if getattr(block, "type", None) == "text":
                print(block.text)
            elif isinstance(block, dict) and block.get("type") == "text":
                print(block.get("text", ""))
        print()