#!/usr/bin/env python3
"""handle.py —— 消费飞书群消息事件，调 /kb-ask 回答，回复到群。

轮询 events/ 目录（subscribe.sh 落的事件文件）：
  过滤 @机器人 的消息 → 抽问题 → CC headless 跑 /kb-ask → lark-cli 回复。

用法:
    python3 tools/kb-bot/handle.py            # 轮询一轮已有事件后退出
    python3 tools/kb-bot/handle.py --watch    # 常驻轮询

铁律：只读知识库、答案带溯源、无据报 Gap、绝不编造（由 /kb-ask 保证）。
凭据由 lark-cli 自管，不在本脚本。
"""
import sys
import os
import re
import json
import time
import subprocess

BOT_DIR = os.path.dirname(os.path.abspath(__file__))
ROOT = os.path.abspath(os.path.join(BOT_DIR, "..", ".."))
EVENTS_DIR = os.path.join(BOT_DIR, "events")
DONE_DIR = os.path.join(BOT_DIR, "events", ".done")
SEEN_FILE = os.path.join(BOT_DIR, ".seen-msg-ids")

os.environ["PATH"] = os.path.expanduser("~/.npm-global/bin") + ":" + os.environ.get("PATH", "")


def load_seen():
    if os.path.isfile(SEEN_FILE):
        return set(open(SEEN_FILE, encoding="utf-8").read().split())
    return set()


def mark_seen(mid):
    with open(SEEN_FILE, "a", encoding="utf-8") as f:
        f.write(mid + "\n")


def extract(event):
    """从事件里取 (message_id, chat_id, 纯文本问题)；非群 @ 消息返回 None。"""
    # --compact 扁平结构；兼容原始嵌套结构
    mid = event.get("message_id") or event.get("event", {}).get("message", {}).get("message_id")
    chat_id = event.get("chat_id") or event.get("event", {}).get("message", {}).get("chat_id")
    text = event.get("text") or ""
    if not text:
        content = event.get("content") or event.get("event", {}).get("message", {}).get("content", "")
        if isinstance(content, str) and content:
            try:
                text = json.loads(content).get("text", "")
            except json.JSONDecodeError:
                text = content
    if not (mid and chat_id and text):
        return None
    # 剥离 @_user_1 等 @ 标记
    q = re.sub(r"@_?\w+", "", text).strip()
    if not q:
        return None
    return mid, chat_id, q


def ask_kb(question):
    """调 CC headless 跑 /kb-ask，返回答案文本。"""
    try:
        r = subprocess.run(
            ["claude", "-p", f"/kb-ask {question}"],
            cwd=ROOT, capture_output=True, text=True, timeout=180,
        )
        return (r.stdout or "").strip() or "（知识库查询无输出，请稍后重试）"
    except FileNotFoundError:
        return "（CC 未安装，无法查询）"
    except subprocess.TimeoutExpired:
        return "（查询超时，请缩小问题范围）"


def reply(chat_id, mid, answer):
    subprocess.run(
        ["lark-cli", "im", "+messages-reply",
         "--message-id", mid, "--markdown", answer, "--as", "bot"],
        capture_output=True, text=True,
    )


def process_once(seen):
    if not os.path.isdir(EVENTS_DIR):
        return
    os.makedirs(DONE_DIR, exist_ok=True)
    for fn in sorted(os.listdir(EVENTS_DIR)):
        fp = os.path.join(EVENTS_DIR, fn)
        if not fn.endswith(".json") or not os.path.isfile(fp):
            continue
        try:
            event = json.load(open(fp, encoding="utf-8"))
        except (json.JSONDecodeError, OSError):
            continue
        parsed = extract(event)
        if parsed:
            mid, chat_id, q = parsed
            if mid not in seen:
                answer = ask_kb(q)
                reply(chat_id, mid, answer)
                mark_seen(mid)
                seen.add(mid)
                print(f"[kb-bot] answered {mid}: {q[:40]}")
        os.replace(fp, os.path.join(DONE_DIR, fn))


def main():
    seen = load_seen()
    watch = "--watch" in sys.argv[1:]
    while True:
        process_once(seen)
        if not watch:
            break
        time.sleep(3)


if __name__ == "__main__":
    main()