group_fqcd_jr/tools/probe_memory_state.py

"""记忆系统状态探针（只读）：一次看清「库里有没有」「事件消费到哪了」。

用途：排查"记忆系统是否真的在工作"时，先跑这个脚本拿到事实基线，
再去看日志定位是哪一段断了。全部是 SELECT，不写任何数据。

用法：
    D:/conda/envs/jr_py313/python.exe tools/probe_memory_state.py [customer_id]
"""

from __future__ import annotations

import asyncio
import sys
from typing import Any

from sqlalchemy import text

from app.infrastructure.db import SessionFactory

TABLES = (
    "memory_unit",
    "memory_evidence",
    "memory_conflict",
    "memory_sync_outbox",
    "user_facts",
    "profile_snapshots",
)


async def _scalar(session: Any, sql: str, **params: Any) -> Any:
    try:
        return await session.scalar(text(sql), params)
    except Exception as exc:  # 表不存在/连不上库都要能看，而不是整个脚本崩掉
        return f"ERROR {type(exc).__name__}: {exc}"


async def main() -> None:
    customer_id = int(sys.argv[1]) if len(sys.argv) > 1 else None
    async with SessionFactory() as session:
        print("=" * 60)
        print("1) 记忆相关表的总行数")
        print("=" * 60)
        for table in TABLES:
            print(f"  {table:<22} {await _scalar(session, f'SELECT COUNT(*) FROM {table}')}")

        print()
        print("=" * 60)
        print("2) memory_unit 按状态分组")
        print("=" * 60)
        try:
            rows = (await session.execute(
                text("SELECT status, COUNT(*) c FROM memory_unit GROUP BY status"))).all()
            for row in rows:
                print(f"  {row[0]:<12} {row[1]}")
        except Exception as exc:
            print(f"  ERROR {type(exc).__name__}: {exc}")

        print()
        print("=" * 60)
        print("3) domain_event_outbox 按 (event_type, status) 分组")
        print("   —— 这里能看到事件是不是堆在 pending（= Worker 没跑 / 处理失败）")
        print("=" * 60)
        try:
            rows = (await session.execute(text(
                "SELECT event_type, status, COUNT(*) c, MAX(occurred_at) latest "
                "FROM domain_event_outbox GROUP BY event_type, status ORDER BY c DESC"
            ))).all()
            if not rows:
                print("  (空)")
            for row in rows:
                print(f"  {row[0]:<38} {row[1]:<10} {row[2]:<6} latest={row[3]}")
        except Exception as exc:
            print(f"  ERROR {type(exc).__name__}: {exc}")

        if customer_id is not None:
            print()
            print("=" * 60)
            print(f"4) 客户 {customer_id} 的记忆明细")
            print("=" * 60)
            try:
                rows = (await session.execute(text(
                    "SELECT memory_uuid, memory_key, content, memory_type, status, "
                    "confidence, source_type, updated_at "
                    "FROM memory_unit WHERE customer_id=:cid ORDER BY updated_at DESC LIMIT 20"
                ), {"cid": customer_id})).all()
                if not rows:
                    print("  (该客户没有任何 memory_unit 行)")
                for row in rows:
                    print(f"  [{row[4]}] {row[1]} = {row[2]!r}")
                    print(f"      type={row[3]} conf={row[5]} src={row[6]} at={row[7]}")
            except Exception as exc:
                print(f"  ERROR {type(exc).__name__}: {exc}")

            print()
            print(f"  user_facts:")
            try:
                rows = (await session.execute(text(
                    "SELECT fact_key, confidence FROM user_facts "
                    "WHERE customer_id=:cid LIMIT 20"), {"cid": customer_id})).all()
                for row in rows:
                    print(f"      {row[0]} (conf={row[1]})")
                if not rows:
                    print("      (无)")
            except Exception as exc:
                print(f"      ERROR {type(exc).__name__}: {exc}")

            print(f"  profile_snapshots:")
            try:
                rows = (await session.execute(text(
                    "SELECT version, is_current, generated_at FROM profile_snapshots "
                    "WHERE customer_id=:cid ORDER BY id DESC LIMIT 5"), {"cid": customer_id})).all()
                for row in rows:
                    print(f"      v{row[0]} current={row[1]} at={row[2]}")
                if not rows:
                    print("      (无)")
            except Exception as exc:
                print(f"      ERROR {type(exc).__name__}: {exc}")


if __name__ == "__main__":
    asyncio.run(main())