Autonomous Agents

s01 > s02 > s03 > s04 > s05 > s06 | s07 > s08 > s09 > s10 > [ s11 ] s12

"队友自己看看板, 有活就认领" -- 不需要领导逐个分配, 自组织。

Harness 层: 自治 -- 模型自己找活干, 无需指派。

问题

s09-s10 中, 队友只在被明确指派时才动。领导得给每个队友写 prompt, 任务看板上 10 个未认领的任务得手动分配。这扩展不了。

真正的自治: 队友自己扫描任务看板, 认领没人做的任务, 做完再找下一个。

一个细节: Context Compact (s06) 后 Agent 可能忘了自己是谁。身份重注入解决这个问题。

解决方案

Teammate lifecycle with idle cycle:

+-------+
| spawn |
+---+---+
    |
    v
+-------+   tool_use     +-------+
| WORK  | <------------- |  LLM  |
+---+---+                +-------+
    |
    | stop_reason != tool_use (or idle tool called)
    v
+--------+
|  IDLE  |  poll every 5s for up to 60s
+---+----+
    |
    +---> check inbox --> message? ----------> WORK
    |
    +---> scan .tasks/ --> unclaimed? -------> claim -> WORK
    |
    +---> 60s timeout ----------------------> SHUTDOWN

Identity re-injection after compression:
  if len(messages) <= 3:
    messages.insert(0, identity_block)

工作原理

1. 队友循环分两个阶段: WORK 和 IDLE。LLM 停止调用工具 (或调用了 idle) 时, 进入 IDLE。

def _loop(self, name, role, prompt):
    while True:
        # -- WORK PHASE --
        messages = [{"role": "user", "content": prompt}]
        for _ in range(50):
            response = client.messages.create(...)
            if response.stop_reason != "tool_use":
                break
            # execute tools...
            if idle_requested:
                break

        # -- IDLE PHASE --
        self._set_status(name, "idle")
        resume = self._idle_poll(name, messages)
        if not resume:
            self._set_status(name, "shutdown")
            return
        self._set_status(name, "working")

1. 空闲阶段循环轮询收件箱和任务看板。

def _idle_poll(self, name, messages):
    for _ in range(IDLE_TIMEOUT // POLL_INTERVAL):  # 60s / 5s = 12
        time.sleep(POLL_INTERVAL)
        inbox = BUS.read_inbox(name)
        if inbox:
            messages.append({"role": "user",
                "content": f"<inbox>{inbox}</inbox>"})
            return True
        unclaimed = scan_unclaimed_tasks()
        if unclaimed:
            claim_task(unclaimed[0]["id"], name)
            messages.append({"role": "user",
                "content": f"<auto-claimed>Task #{unclaimed[0]['id']}: "
                           f"{unclaimed[0]['subject']}</auto-claimed>"})
            return True
    return False  # timeout -> shutdown

1. 任务看板扫描: 找 pending 状态、无 owner、未被阻塞的任务。

def scan_unclaimed_tasks() -> list:
    unclaimed = []
    for f in sorted(TASKS_DIR.glob("task_*.json")):
        task = json.loads(f.read_text())
        if (task.get("status") == "pending"
                and not task.get("owner")
                and not task.get("blockedBy")):
            unclaimed.append(task)
    return unclaimed

1. 身份重注入: 上下文过短 (说明发生了压缩) 时, 在开头插入身份块。

if len(messages) <= 3:
    messages.insert(0, {"role": "user",
        "content": f"<identity>You are '{name}', role: {role}, "
                   f"team: {team_name}. Continue your work.</identity>"})
    messages.insert(1, {"role": "assistant",
        "content": f"I am {name}. Continuing."})

相对 s10 的变更

试一试

cd claude-code-for-researchers
python agents/s11_autonomous_agents.py

试试这些 prompt (英文 prompt 对 LLM 效果更好, 也可以用中文):

1. Create 13 robustness tasks (PC measure swaps, lag specs, subsample drops) on the board, then spawn 2 robust-runner teammates. Watch them auto-claim.
2. Spawn a stata-runner teammate and let it find robustness work from the task board itself
3. Create tasks with dependencies (do4 panel -> do6 baseline -> do10 robustness). Watch teammates respect the blocked order.
4. 输入 /tasks 查看带 owner 的任务看板
5. 输入 /team 监控谁在工作、谁在空闲