"""规则机器人玩家——"AI 也能玩"的最小可用示例。

它的意义不在于"内置了 AI"，而在于证明一件事：
**服务器把状态和合法动作都摊开了，外面是谁在决策根本不重要。**
这个机器人做决策的方式是"给候选动作打分"，而一个 LLM 做决策的方式是
"读同一份 ``/api/actions``，用语言模型选一个"。两者的接口调用序列一模一样。

所以：

* :meth:`RuleBot.choose` 里那段打分逻辑 = 可以整体替换成 LLM 的"策略函数"；
* :meth:`RuleBot.step` 的执行路径 = LLM 将来要走的那条路（读动作 → 执行 → 看回执）。

它只依赖 :mod:`farm.client`，因此既能在本机跑，也能从别处连上服务器跑——
换个 ``--url`` 就是一个独立的外挂玩家。
"""

from __future__ import annotations

import random
import threading
import time
from typing import Any, Dict, List, Optional

from .engine import GameError


class RuleBot:
    """一个会种地、会养殖、会投资的规则机器人。"""

    def __init__(self, client, verbose: bool = True, pause: float = 0.25,
                 name: str = "bot") -> None:
        self.client = client          # 任何与 RemoteFarm 接口一致的对象
        self.verbose = verbose
        self.pause = pause
        self.name = name
        self.done: List[str] = []
        self.failures = 0
        self.actions_executed = 0
        self._stop = threading.Event()

    # ------------------------------------------------------------ 输出
    def say(self, text: str) -> None:
        if self.verbose:
            print(f"[{time.strftime('%H:%M:%S')}] {text}", flush=True)

    def stop(self) -> None:
        self._stop.set()

    @property
    def stopped(self) -> bool:
        return self._stop.is_set()

    # ------------------------------------------------------------ 打分
    def score(self, action: Dict[str, Any], state: Dict[str, Any],
              catalog: Dict[str, Any]) -> float:
        """给一个候选动作打分。分数越高越先执行。

        这张表就是整个"策略"：先做免费的，再喂饱牲畜，再补水，再扩张。
        换成 LLM 时，把这里换成一次模型调用即可，其余代码不用动。
        """
        name = action.get("action")
        params = action.get("params") or {}
        gold = state.get("gold", 0)
        feed = state.get("feed", 0)
        ap = state.get("ap", 0)

        if name == "harvest":
            return 100.0
        if name == "collect":
            return 96.0
        if name == "feed":
            return 92.0
        if name == "water":
            return 84.0
        if name == "plant":
            # 优先种"每天净收益"最高的作物
            crop = params.get("crop")
            entry = next((c for c in catalog.get("crops", []) if c["key"] == crop), None)
            per_day = entry["profit_per_day"] if entry else 0.0
            return 60.0 + max(0.0, per_day)
        if name == "buy_feed":
            # 饲料快见底才补，且别把钱花光
            if feed <= 2 and gold >= 200:
                return 40.0
            return 5.0
        if name == "buy_plot":
            price = state.get("next_plot_price") or 0
            # 地太贵就别买，留下周转资金
            if price > 0 and gold >= price * 3:
                return 34.0
            return 4.0
        if name == "buy_animal":
            info = next((a for a in catalog.get("animals", [])
                         if a["key"] == params.get("kind")), None)
            cost = info["cost"] if info else 0
            if cost and gold >= cost * 3 and ap >= 1:
                return 30.0 + (info.get("profit_per_day", 0) if info else 0)
            return 3.0
        return 1.0

    def choose(self) -> Optional[Dict[str, Any]]:
        """在服务器给出的合法动作里挑一个最优的。"""
        actions = self.client.available_actions()
        if not actions:
            return None
        state = self.client.snapshot()
        catalog = self.client.catalog()
        best = max(actions, key=lambda item: self.score(item, state, catalog))
        if self.score(best, state, catalog) <= 1.0:
            return None
        return best

    # ------------------------------------------------------------ 单步
    def step(self) -> Optional[str]:
        """执行一个动作，返回动作名；没得做或做不了返回 None。"""
        action = self.choose()
        if action is None:
            return None
        name = action["action"]
        params = action.get("params") or {}
        try:
            result = self.client._action(name, params)   # 走通用动作入口
        except GameError as exc:
            self.failures += 1
            if exc.code == "cooldown":
                # 休息有冷却；这是正常节奏，不该记成失败
                self.failures -= 1
                self.say(f"冷却中… {exc.message}")
                time.sleep(1.0)
                return None
            self.say(f"✗ {name} 失败（{exc.code}）：{exc.message}")
            return None
        self.actions_executed += 1
        self.done.append(name)
        self.say(f"✓ {name} {params} → {result.get('message', '')}")
        if self.pause:
            time.sleep(self.pause)
        return name

    def rest(self) -> bool:
        """行动点用完时推进一天。"""
        try:
            result = self.client.sleep()
        except GameError as exc:
            if exc.code == "cooldown":
                time.sleep(1.0)
                return True
            self.say(f"✗ sleep 失败：{exc.message}")
            return False
        self.say(f"— {result.get('message', '进入下一天')}")
        return True

    # ------------------------------------------------------------ 主循环
    def run(self, rounds: int = 0, max_minutes: float = 0.0,
            idle_limit: int = 8) -> Dict[str, Any]:
        """跑机器人。

        ``rounds`` 为 0 表示不限轮数；``max_minutes`` 为 0 表示不限时间。
        """
        deadline = (time.time() + max_minutes * 60) if max_minutes > 0 else None
        start_day = self.client.snapshot().get("day", 1)
        idle = 0
        round_no = 0
        self.say(f"机器人 {self.name} 上线（第 {start_day} 天，"
                 f"{self.client.transport_label()}）")

        while not self._stop.is_set():
            round_no += 1
            if rounds and round_no > rounds:
                break
            if deadline and time.time() > deadline:
                self.say("到时间了，收工。")
                break

            state = self.client.snapshot()
            if state.get("ap", 0) <= 0:
                # 行动点用完：休息推进一天，顺便等冷却
                self.rest()
                continue

            did = self.step()
            if did is None:
                idle += 1
                if idle >= idle_limit:
                    self.say("暂时没有可做的事，休息一天再看。")
                    self.rest()
                    idle = 0
                else:
                    time.sleep(0.4)
            else:
                idle = 0

        end_day = self.client.snapshot().get("day", start_day)
        summary = {
            "name": self.name,
            "days": end_day - start_day,
            "actions": self.actions_executed,
            "failures": self.failures,
            "net_worth": self.client.snapshot().get("net_worth"),
            "gold": self.client.snapshot().get("gold"),
        }
        self.say(f"机器人 {self.name} 下线：跑了 {summary['days']} 天、"
                 f"执行 {summary['actions']} 个动作、净资产 {summary['net_worth']}")
        return summary


def random_bot(client, **kwargs) -> RuleBot:
    """随机策略机器人：用来做对照实验（证明"有策略"确实比乱按强）。"""
    bot = RuleBot(client, **kwargs)
    original = bot.choose

    def choose() -> Optional[Dict[str, Any]]:
        actions = client.available_actions()
        if not actions:
            return None
        return random.choice(actions)

    bot.choose = choose          # type: ignore[assignment]
    bot.name = kwargs.get("name", "random")
    del original
    return bot