助手本体：会话引擎、LLM 路由、记忆、身份、语音适配
从 Obsidian 笔记库剥离为独立仓库。规划文档与 P0 报告留在笔记库， 代码（助手本体、TTS 服务、P0 基准脚本、ESP32 固件）在此。 架构：服务器是助手，本地是客户端 - 助手本体跑在 cadadmin-server，N5095 只做 USB 外设桥与网络桥接 - 起因：实测 N5095 无 AVX2，跑不动可用的语音模型 当前技术栈 - LLM：DeepSeek deepseek-flash（云端，必须关思考） - TTS：Qwen3-TTS 1.7B（服务器 3090，独立 HTTP 服务） - STT：Zipformer 中英双语 int8（CPU，中文识别率未测） 实测：端到端 16/16 通过，首音延迟 1545ms （对比：本地 LLM + vits-zh-ll 是 179ms，但音色不满意——音质与延迟 在此硬件上此消彼长） 设计要点 - MemoryStore 接口按"可能远程"设计（全 async、可超时、可失败） - user_id / session_id / track_id 三者分开，人脸只作候选不自动切身份 - 记忆查询强制带 owner_user_id，无按 id 单独取的口子 - 自动抽取的记忆是"候选"，默认不参与检索 - 异步写记忆绑定创建时的身份，不读"当前用户" - 引擎与传输解耦，只用文件音频即可端到端测试 模型与音频产物不进版本管理（1.1GB），由 download_models.sh 恢复
This commit is contained in:
ylhan
@@ -0,0 +1,176 @@
|
||||
#!/usr/bin/env python3
|
||||
"""记忆层测试。
|
||||
|
||||
重点不是"能存能取"，而是方案 §8 反复强调的隔离性质：
|
||||
- 未知身份不碰私人记忆
|
||||
- 删别人的记忆删不掉
|
||||
- 自动抽取的候选不参与检索
|
||||
- 删用户要连会话和摘要一起删干净
|
||||
|
||||
这些是"错了很难发现、发现了很严重"的类型，所以单独测。
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import shutil
|
||||
import sys
|
||||
import tempfile
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent.parent))
|
||||
|
||||
from app.memory import ( # noqa: E402
|
||||
ConfirmStatus, Memory, MemoryKind, Scope, SQLiteMemoryStore, Turn,
|
||||
)
|
||||
from app.memory.sqlite_store import FALLBACK_MAX_CORPUS # noqa: E402
|
||||
|
||||
OK, FAIL = [], []
|
||||
|
||||
|
||||
def check(name: str, cond: bool, detail: str = "") -> None:
|
||||
(OK if cond else FAIL).append(name)
|
||||
print(f" [{'PASS' if cond else 'FAIL'}] {name}" + (f" — {detail}" if detail else ""))
|
||||
|
||||
|
||||
async def run(store: SQLiteMemoryStore) -> None:
|
||||
await store.open()
|
||||
|
||||
print("\n=== 1. 基本读写 ===")
|
||||
await store.ensure_user("u_ylhan", "ylhan")
|
||||
await store.ensure_user("u_guest", "访客")
|
||||
mid = await store.remember(Memory(
|
||||
owner_user_id="u_ylhan", kind=MemoryKind.PREFERENCE,
|
||||
key="回复风格", value="喜欢简短直接，不要长篇解释"))
|
||||
check("写入返回 memory_id", isinstance(mid, int) and mid > 0, str(mid))
|
||||
got = await store.retrieve("u_ylhan", "回复风格")
|
||||
check("能检索到", len(got) == 1 and got[0].key == "回复风格")
|
||||
check("字段完整", got[0].kind == MemoryKind.PREFERENCE and got[0].value.startswith("喜欢"))
|
||||
|
||||
print("\n=== 2. 身份隔离（最关键）===")
|
||||
other = await store.retrieve("u_guest", "回复风格")
|
||||
check("别人检索不到", len(other) == 0, f"拿到 {len(other)} 条")
|
||||
listed = await store.list_memories("u_guest")
|
||||
check("别人列不出", len(listed) == 0)
|
||||
|
||||
# 用 memory_id 越权删
|
||||
deleted = await store.forget("u_guest", mid)
|
||||
check("越权删除失败", deleted is False)
|
||||
still = await store.retrieve("u_ylhan", "回复风格")
|
||||
check("原主记忆还在", len(still) == 1)
|
||||
|
||||
print("\n=== 3. 同键新值替换旧值 ===")
|
||||
await store.remember(Memory(
|
||||
owner_user_id="u_ylhan", kind=MemoryKind.PREFERENCE,
|
||||
key="回复风格", value="喜欢更活泼一点的说法"))
|
||||
rows = await store.retrieve("u_ylhan", "回复风格")
|
||||
check("同键只剩一条", len(rows) == 1, f"{len(rows)} 条")
|
||||
check("值已更新", "活泼" in rows[0].value, rows[0].value)
|
||||
|
||||
# 不同 key 不应互相覆盖
|
||||
await store.remember(Memory(owner_user_id="u_ylhan", kind=MemoryKind.PREFERENCE,
|
||||
key="称呼", value="叫他老韩"))
|
||||
rows2 = await store.list_memories("u_ylhan")
|
||||
check("不同 key 各自保留", len(rows2) == 2, f"{len(rows2)} 条")
|
||||
|
||||
print("\n=== 4. 候选记忆默认不参与检索 ===")
|
||||
# 判据是"这条候选不在结果里"，**不是"结果为空"**。
|
||||
# 后者是实现细节：检索在关键词不命中时会退回最近记忆
|
||||
# （见 sqlite_store.FALLBACK_MAX_CORPUS），结果本来就可能非空。
|
||||
CAND = "用户好像养了一只叫豆豆的猫"
|
||||
await store.remember(Memory(
|
||||
owner_user_id="u_ylhan", kind=MemoryKind.FACT, key="", value=CAND,
|
||||
confirm_status=ConfirmStatus.CANDIDATE))
|
||||
hit = await store.retrieve("u_ylhan", "豆豆")
|
||||
check("候选不出现在检索结果里", all(m.value != CAND for m in hit),
|
||||
f"拿到 {len(hit)} 条：{[m.value[:12] for m in hit]}")
|
||||
hit2 = await store.retrieve("u_ylhan", "豆豆", include_candidates=True)
|
||||
check("显式要求时可检索到", any(m.value == CAND for m in hit2),
|
||||
f"拿到 {len(hit2)} 条")
|
||||
allm = await store.list_memories("u_ylhan")
|
||||
check("候选确实已落库", any(m.confirm_status == ConfirmStatus.CANDIDATE for m in allm))
|
||||
|
||||
print("\n=== 5. 过期 ===")
|
||||
EXPIRED = "十分钟后提醒我关火"
|
||||
await store.remember(Memory(
|
||||
owner_user_id="u_ylhan", kind=MemoryKind.TASK, key="", value=EXPIRED,
|
||||
expires_at=time.time() - 1)) # 已过期
|
||||
expired = await store.retrieve("u_ylhan", "关火")
|
||||
check("过期记忆不出现在结果里", all(m.value != EXPIRED for m in expired),
|
||||
f"拿到 {len(expired)} 条")
|
||||
check("过期记忆也不在列表里",
|
||||
all(m.value != EXPIRED for m in await store.list_memories("u_ylhan")))
|
||||
|
||||
print("\n=== 6. 会话与轮次 ===")
|
||||
await store.start_session("sess_1", "u_ylhan")
|
||||
for i, (role, text) in enumerate([("user", "今天天气怎么样"),
|
||||
("assistant", "今天晴，十八到二十六度。")]):
|
||||
await store.add_turn(Turn(turn_id=f"t{i}", session_id="sess_1",
|
||||
user_id="u_ylhan", role=role, text=text))
|
||||
check("会话与轮次写入无异常", True)
|
||||
|
||||
print("\n=== 7. 中文检索打分 ===")
|
||||
r = SQLiteMemoryStore.relevance("客厅的灯", "客厅有一盏米家吸顶灯")
|
||||
check("相关文本有分", r > 0.3, f"{r:.2f}")
|
||||
r2 = SQLiteMemoryStore.relevance("客厅的灯", "喜欢听爵士乐")
|
||||
check("无关文本为 0", r2 == 0.0, f"{r2:.2f}")
|
||||
r3 = SQLiteMemoryStore.relevance("回复风格", "回复风格：喜欢简短")
|
||||
check("子串直接命中", r3 == 1.0, f"{r3:.2f}")
|
||||
|
||||
print("\n=== 8. 删除用户要清干净 ===")
|
||||
n = await store.purge_user("u_ylhan")
|
||||
check("返回删除的记忆数", n >= 3, f"{n} 条")
|
||||
check("记忆已清空", len(await store.list_memories("u_ylhan")) == 0)
|
||||
check("检索也拿不到", len(await store.retrieve("u_ylhan", "回复风格")) == 0)
|
||||
# 会话和轮次靠外键级联删除
|
||||
rows = await store._run(lambda c: c.execute(
|
||||
"SELECT COUNT(*) AS n FROM turns WHERE user_id=?", ("u_ylhan",)).fetchone()["n"])
|
||||
check("轮次一并删除", rows == 0, f"残留 {rows} 条")
|
||||
rows2 = await store._run(lambda c: c.execute(
|
||||
"SELECT COUNT(*) AS n FROM sessions WHERE user_id=?", ("u_ylhan",)).fetchone()["n"])
|
||||
check("会话一并删除", rows2 == 0, f"残留 {rows2} 条")
|
||||
|
||||
print("\n=== 9. 重复建用户不报错、不覆盖 ===")
|
||||
await store.ensure_user("u_x", "第一次")
|
||||
await store.ensure_user("u_x", "第二次")
|
||||
name = await store._run(lambda c: c.execute(
|
||||
"SELECT display_name FROM users WHERE user_id=?", ("u_x",)).fetchone()["display_name"])
|
||||
check("已存在则不改", name == "第一次", name)
|
||||
|
||||
print("\n=== 10. 兜底检索要限量（否则就成了每轮全量注入）===")
|
||||
await store.ensure_user("u_big")
|
||||
await store.remember(Memory(owner_user_id="u_big", kind=MemoryKind.FACT,
|
||||
value="常喝拿铁"))
|
||||
# "推荐个饮品"和"常喝拿铁"没有任何共同字符，字面打分为 0
|
||||
got = await store.retrieve("u_big", "推荐个饮品")
|
||||
check("记忆少时兜底返回最近一条", len(got) == 1, f"{len(got)} 条")
|
||||
|
||||
for i in range(FALLBACK_MAX_CORPUS + 2):
|
||||
await store.remember(Memory(owner_user_id="u_big", kind=MemoryKind.FACT,
|
||||
value=f"无关记录编号{i}"))
|
||||
got2 = await store.retrieve("u_big", "推荐个饮品")
|
||||
check("记忆多时不再无条件兜底", len(got2) == 0, f"{len(got2)} 条")
|
||||
got3 = await store.retrieve("u_big", "拿铁")
|
||||
check("关键词命中仍生效", any("拿铁" in m.value for m in got3), f"{len(got3)} 条")
|
||||
|
||||
await store.close()
|
||||
|
||||
|
||||
def main() -> int:
|
||||
tmp = Path(tempfile.mkdtemp(prefix="memtest_"))
|
||||
try:
|
||||
store = SQLiteMemoryStore(tmp / "memory.db")
|
||||
asyncio.run(run(store))
|
||||
finally:
|
||||
shutil.rmtree(tmp, ignore_errors=True)
|
||||
|
||||
print("\n" + "=" * 62)
|
||||
print(f"通过 {len(OK)} / {len(OK) + len(FAIL)}")
|
||||
for n in FAIL:
|
||||
print(f" 未通过: {n}")
|
||||
return 0 if not FAIL else 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
Reference in New Issue
Block a user