基线：姓名档案修复、疑问句防误写、搜索与传输测试
这是进入 Pipecat Flows 改造前的回滚点。 提交时已核对本地与线上代码 md5 一致（engine.py 7e97bad8、 bot_server.py 1cf543ae），所以这个提交就是当前线上状态。 内容（此前一直在线上运行但未提交的改动）： - 姓名档案：用户自报"我叫林"同步写 confirmed 姓名，重连后恢复 - 疑问句防误写："谁吗"之类的疑问句不再被覆盖成姓名 - 新增 test_profile_memory.py（姓名档案专项回归） - 新增 test_profile_live.py（需要真实 LLM 的现场测试） - 搜索、身份、记忆测试的相应补充 背景：下一步要按 P1-Pipecat Flows Agent化与记忆改造交接.md 渐进引入 Pipecat Flows，交接文档明确要求先保护基线、不得 reset/checkout/覆盖现有改动。此提交即该基线。
This commit is contained in:
ylhan
@@ -214,6 +214,9 @@ class MemoryConfig:
|
||||
|
||||
@dataclass
|
||||
class AppConfig:
|
||||
# 单用户原型的稳定内部档案 ID。它只用于数据隔离，绝不是用户可见姓名。
|
||||
default_user_id: str = field(
|
||||
default_factory=lambda: _env("AI_DEFAULT_USER_ID", "u_ylhan"))
|
||||
#: 主 LLM 由 AI_LLM_PRIMARY 选择：
|
||||
#: "local" = 本机 vLLM（首 token 192ms，但占 21.5GB 显存）
|
||||
#: "deepseek" = 云端（首 token 786ms，网络往返约 700ms）
|
||||
|
||||
+105
-1
@@ -58,6 +58,29 @@ _SOURCE_SECTION_RE = re.compile(
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
_DISPLAY_NAME_PATTERNS = (
|
||||
re.compile(
|
||||
r"(?:我叫|我的(?:名字|姓名)(?:是|叫)|(?:你可以)?叫我)\s*"
|
||||
r"[“\"']?([^，,。！？!?；;：:\n\"”']{1,24})[”\"']?"
|
||||
r"(?=$|[，,。！？!?；;：:\n])",
|
||||
re.IGNORECASE,
|
||||
),
|
||||
# 兼容语音识别常见的“我是林”。只接受 1–4 个中文姓名字符，
|
||||
# 避免把“我是程序员/中国人”一类身份描述当作姓名。
|
||||
re.compile(
|
||||
r"我是\s*([\u4e00-\u9fff·]{1,4})"
|
||||
r"(?=$|[，,。！？!?；;：:\n])"
|
||||
),
|
||||
)
|
||||
|
||||
_NOT_NAMES = {
|
||||
"程序员", "工程师", "中国人", "学生", "老师", "医生", "男生", "女生",
|
||||
"用户", "访客", "谁", "什么", "哪位", "你", "他", "她", "它", "你的", "他的", "她的",
|
||||
}
|
||||
|
||||
_NAME_QUESTION_WORDS = ("谁", "什么", "哪位")
|
||||
_NAME_QUESTION_PARTICLES = ("吗", "么", "呢")
|
||||
|
||||
|
||||
class EventKind(str, Enum):
|
||||
IDENTITY = "identity" # 本轮的身份裁决结果
|
||||
@@ -143,6 +166,18 @@ class ConversationEngine:
|
||||
self.identity.switch(user_id, reason="会话指定")
|
||||
d = self.identity.current()
|
||||
await self.memory.start_session(sid, d.user_id)
|
||||
if d.confirmed:
|
||||
try:
|
||||
display_name = await self.memory.get_user_display_name(d.user_id)
|
||||
if display_name:
|
||||
self.identity.switch(
|
||||
d.user_id,
|
||||
display_name=display_name,
|
||||
reason="从用户档案恢复称呼",
|
||||
)
|
||||
d = self.identity.current()
|
||||
except Exception as exc: # noqa: BLE001 — 档案读取失败不阻塞会话
|
||||
log.warning("读取用户称呼失败（本轮继续）：%s", exc)
|
||||
self._session_id = sid
|
||||
self._history_identity_version = self._identity_version()
|
||||
log.info("会话开始 %s，身份 %s", sid, d.user_id)
|
||||
@@ -180,6 +215,10 @@ class ConversationEngine:
|
||||
|
||||
self._sync_identity_scope()
|
||||
identity = self.identity.current()
|
||||
display_name = extract_display_name(user_text)
|
||||
if display_name and identity.confirmed:
|
||||
await self._remember_display_name(identity, display_name, sid)
|
||||
identity = self.identity.current()
|
||||
metrics.identity_ms = (time.perf_counter() - t_start) * 1000
|
||||
yield Event(kind=EventKind.IDENTITY, identity=identity)
|
||||
|
||||
@@ -306,6 +345,43 @@ class ConversationEngine:
|
||||
log.warning("记忆检索失败（%s），本轮不带记忆继续", e)
|
||||
return []
|
||||
|
||||
async def _remember_display_name(
|
||||
self,
|
||||
identity: IdentityDecision,
|
||||
display_name: str,
|
||||
session_id: str,
|
||||
) -> None:
|
||||
"""同步保存用户明确自报的称呼，保证断开连接前已经落盘。"""
|
||||
turn_id = f"t_{uuid.uuid4().hex[:10]}"
|
||||
|
||||
async def write_profile() -> None:
|
||||
await self.memory.set_user_display_name(identity.user_id, display_name)
|
||||
await self.memory.remember(Memory(
|
||||
owner_user_id=identity.user_id,
|
||||
kind=MemoryKind.FACT,
|
||||
key="姓名",
|
||||
value=display_name,
|
||||
confirm_status=ConfirmStatus.CONFIRMED,
|
||||
source_session_id=session_id,
|
||||
source_turn_id=turn_id,
|
||||
))
|
||||
|
||||
try:
|
||||
await asyncio.wait_for(
|
||||
write_profile(),
|
||||
timeout=max(1.0, self.cfg.context.memory_timeout_s),
|
||||
)
|
||||
log.info("已确认并保存用户称呼：%s", display_name)
|
||||
except Exception as exc: # noqa: BLE001 — 记忆失败仍允许本轮继续
|
||||
log.warning("保存用户称呼失败（仅本轮生效）：%s", exc)
|
||||
|
||||
# 自报称呼只用于个性化，保持原 user_id 和 trust_level，不构成认证。
|
||||
self.identity.switch(
|
||||
identity.user_id,
|
||||
display_name=display_name,
|
||||
reason="用户明确自报称呼",
|
||||
)
|
||||
|
||||
async def _stream_and_speak(self, messages: list[dict],
|
||||
metrics: TurnMetrics) -> AsyncIterator[Event]:
|
||||
"""执行 LLM/搜索工具闭环；最终文本仍然流式交给调用方做 TTS。"""
|
||||
@@ -476,6 +552,9 @@ def extract_memories(user_text: str, reply: str) -> list[Memory]:
|
||||
"""
|
||||
out: list[Memory] = []
|
||||
text = (user_text or "").strip()
|
||||
# 姓名由同步、已确认的档案路径处理；不要再产生一条 candidate 副本。
|
||||
if extract_display_name(text):
|
||||
return out
|
||||
for trigger, kind_hint in _REMEMBER_PATTERNS:
|
||||
if trigger in text:
|
||||
# 取触发词之后的正文
|
||||
@@ -491,6 +570,31 @@ def extract_memories(user_text: str, reply: str) -> list[Memory]:
|
||||
return out
|
||||
|
||||
|
||||
def extract_display_name(user_text: str) -> str | None:
|
||||
"""从用户明确的自我介绍中提取称呼；不使用模型猜测。"""
|
||||
text = " ".join((user_text or "").strip().split())
|
||||
if not text:
|
||||
return None
|
||||
for pattern in _DISPLAY_NAME_PATTERNS:
|
||||
match = pattern.search(text)
|
||||
if not match:
|
||||
continue
|
||||
name = " ".join(match.group(1).strip(" ‘'\"”").split())
|
||||
if not name or len(name) > 24 or name in _NOT_NAMES:
|
||||
continue
|
||||
# “知道我是谁吗”“我是林吗”不是自我介绍。语音识别可能不带问号，
|
||||
# 所以不能只依赖标点，需同时过滤疑问词和句末疑问助词。
|
||||
if any(word in name for word in _NAME_QUESTION_WORDS):
|
||||
continue
|
||||
if name.endswith(_NAME_QUESTION_PARTICLES):
|
||||
continue
|
||||
if name.startswith(("你", "他", "她", "它")) and len(name) > 1:
|
||||
continue
|
||||
return name
|
||||
return None
|
||||
|
||||
|
||||
__all__ = [
|
||||
"ConversationEngine", "Event", "EventKind", "TurnMetrics", "extract_memories",
|
||||
"ConversationEngine", "Event", "EventKind", "TurnMetrics",
|
||||
"extract_memories", "extract_display_name",
|
||||
]
|
||||
|
||||
@@ -66,6 +66,8 @@ class IdentityDecision:
|
||||
trust_level: str
|
||||
confirmed: bool # True = 经确认；False = 默认访客
|
||||
reason: str
|
||||
# 用户可见称呼，与内部稳定 user_id 分开；自报姓名不能提升信任等级。
|
||||
display_name: str = ""
|
||||
#: 未被采纳的候选，保留下来供上层提示"是否要切换成 X"
|
||||
suggestions: list[IdentityClaim] = field(default_factory=list)
|
||||
|
||||
|
||||
@@ -61,11 +61,17 @@ class ManualIdentityProvider(IdentityProvider):
|
||||
if not user_id:
|
||||
raise ValueError("user_id 不能为空")
|
||||
prev = self._decision.user_id
|
||||
visible_name = (
|
||||
display_name.strip()
|
||||
if display_name.strip()
|
||||
else self._decision.display_name if prev == user_id else ""
|
||||
)
|
||||
self._decision = IdentityDecision(
|
||||
user_id=user_id,
|
||||
trust_level=TRUST_NORMAL,
|
||||
confirmed=True,
|
||||
reason=reason,
|
||||
display_name=visible_name,
|
||||
)
|
||||
if prev != user_id:
|
||||
self._version += 1
|
||||
|
||||
@@ -105,6 +105,14 @@ class MemoryStore(ABC):
|
||||
trust_level: str = "normal") -> None:
|
||||
"""建档。已存在则不动。身份认证与信任等级分开（方案 §6）。"""
|
||||
|
||||
@abstractmethod
|
||||
async def set_user_display_name(self, user_id: str, display_name: str) -> None:
|
||||
"""更新用户自报的称呼。它用于个性化，不提高身份信任等级。"""
|
||||
|
||||
@abstractmethod
|
||||
async def get_user_display_name(self, user_id: str) -> str:
|
||||
"""读取用户称呼；未设置或用户不存在时返回空字符串。"""
|
||||
|
||||
@abstractmethod
|
||||
async def start_session(self, session_id: str, user_id: str) -> None: ...
|
||||
|
||||
|
||||
@@ -176,6 +176,25 @@ class SQLiteMemoryStore(MemoryStore):
|
||||
c.commit()
|
||||
await self._run(op)
|
||||
|
||||
async def set_user_display_name(self, user_id: str, display_name: str) -> None:
|
||||
display_name = " ".join((display_name or "").split()).strip()
|
||||
if not user_id or not display_name:
|
||||
raise ValueError("user_id 和 display_name 不能为空")
|
||||
|
||||
def op(c: sqlite3.Connection):
|
||||
_ensure_user_row(c, user_id)
|
||||
c.execute("UPDATE users SET display_name=? WHERE user_id=?",
|
||||
(display_name, user_id))
|
||||
c.commit()
|
||||
await self._run(op)
|
||||
|
||||
async def get_user_display_name(self, user_id: str) -> str:
|
||||
def op(c: sqlite3.Connection):
|
||||
row = c.execute("SELECT display_name FROM users WHERE user_id=?",
|
||||
(user_id,)).fetchone()
|
||||
return str(row["display_name"] or "") if row else ""
|
||||
return await self._run(op)
|
||||
|
||||
async def start_session(self, session_id: str, user_id: str) -> None:
|
||||
def op(c: sqlite3.Connection):
|
||||
c.execute("INSERT INTO users(user_id, created_at) VALUES(?,?) "
|
||||
|
||||
+11
-1
@@ -47,7 +47,17 @@ def build_system_prompt(
|
||||
parts = [PERSONA_RULES]
|
||||
|
||||
if identity.confirmed:
|
||||
parts.append(f"\n当前用户：{identity.user_id}（已确认身份）。")
|
||||
if identity.display_name:
|
||||
parts.append(
|
||||
f"\n当前用户希望被称为“{identity.display_name}”。"
|
||||
"这是用户可见称呼，可以在合适时自然使用。"
|
||||
)
|
||||
else:
|
||||
parts.append("\n当前连接已绑定到一个用户档案，但尚未记录用户称呼。")
|
||||
parts.append(
|
||||
"内部 user_id 只用于数据隔离，绝不能把它当作用户名、姓名或称呼告诉用户。"
|
||||
"如果用户问‘我是谁’而没有已知称呼，应坦白还不知道，而不是回答内部 ID。"
|
||||
)
|
||||
else:
|
||||
# 方案 §6：未知身份只用访客上下文，不做个性化
|
||||
parts.append("\n当前用户身份未确认，按访客对待。"
|
||||
|
||||
@@ -36,6 +36,9 @@ def main() -> int:
|
||||
d = p.switch("u_ylhan", reason="对话确认")
|
||||
check("切换生效", d.user_id == "u_ylhan" and d.confirmed)
|
||||
check("信任等级为 normal", d.trust_level == "normal")
|
||||
named = p.switch("u_ylhan", display_name="林", reason="用户自报")
|
||||
check("显示名与内部 ID 分离", named.display_name == "林")
|
||||
check("同一身份空显示名不覆盖", p.switch("u_ylhan").display_name == "林")
|
||||
check("版本号 +1", p.version == 1, str(p.version))
|
||||
v = p.version
|
||||
p.switch("u_ylhan") # 切到同一个人
|
||||
|
||||
@@ -138,6 +138,10 @@ async def run(store: SQLiteMemoryStore) -> None:
|
||||
"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)
|
||||
|
||||
await store.set_user_display_name("u_x", "林")
|
||||
check("可显式更新用户称呼", await store.get_user_display_name("u_x") == "林")
|
||||
check("不存在的用户称呼为空", await store.get_user_display_name("u_missing") == "")
|
||||
|
||||
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,
|
||||
|
||||
@@ -0,0 +1,62 @@
|
||||
#!/usr/bin/env python3
|
||||
"""用生产记忆库和真实 LLM 验证当前用户称呼，不加载 STT/TTS。"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
|
||||
ROOT = Path(__file__).resolve().parent.parent.parent
|
||||
sys.path.insert(0, str(ROOT))
|
||||
|
||||
from app.config import AppConfig # noqa: E402
|
||||
from app.engine import ConversationEngine, EventKind # noqa: E402
|
||||
from app.identity import ManualIdentityProvider # noqa: E402
|
||||
from app.llm import FallbackProvider, create_provider # noqa: E402
|
||||
from app.memory import SQLiteMemoryStore # noqa: E402
|
||||
|
||||
|
||||
class SilentTTS:
|
||||
sample_rate = 16000
|
||||
|
||||
def synthesize(self, _text):
|
||||
return np.zeros(0, dtype=np.float32)
|
||||
|
||||
|
||||
async def main() -> int:
|
||||
cfg = AppConfig.load()
|
||||
cfg.search.enabled = False
|
||||
cfg.memory.auto_extract_enabled = False
|
||||
memory = SQLiteMemoryStore(cfg.memory.db_path)
|
||||
await memory.open()
|
||||
llm = FallbackProvider(
|
||||
create_provider(cfg.llm), create_provider(cfg.llm_fallback))
|
||||
engine = ConversationEngine(
|
||||
cfg, llm, memory, ManualIdentityProvider(), SilentTTS())
|
||||
try:
|
||||
await engine.start_session(user_id=cfg.default_user_id)
|
||||
loaded_name = engine.identity.current().display_name
|
||||
reply_parts = []
|
||||
async for event in engine.respond_to_text("我是谁？请只说我的称呼。"):
|
||||
if event.kind == EventKind.RESPONSE_DELTA:
|
||||
reply_parts.append(event.text)
|
||||
reply = "".join(reply_parts).strip()
|
||||
if loaded_name != "林":
|
||||
raise AssertionError(f"档案称呼未恢复：{loaded_name!r}")
|
||||
if "林" not in reply or cfg.default_user_id in reply:
|
||||
raise AssertionError(f"回答未正确使用称呼：{reply!r}")
|
||||
print(f"恢复称呼: {loaded_name}")
|
||||
print(f"真实回答: {reply}")
|
||||
print("生产记忆 + 真实 LLM 验收：PASS")
|
||||
return 0
|
||||
finally:
|
||||
await engine.end_session()
|
||||
await memory.close()
|
||||
await llm.aclose()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(asyncio.run(main()))
|
||||
@@ -0,0 +1,114 @@
|
||||
#!/usr/bin/env python3
|
||||
"""用户称呼跨会话持久化与内部 ID 隔离回归测试。"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import shutil
|
||||
import sys
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
|
||||
ROOT = Path(__file__).resolve().parent.parent.parent
|
||||
sys.path.insert(0, str(ROOT))
|
||||
|
||||
from app.config import AppConfig # noqa: E402
|
||||
from app.engine import ( # noqa: E402
|
||||
ConversationEngine, extract_display_name, extract_memories,
|
||||
)
|
||||
from app.identity import ManualIdentityProvider # noqa: E402
|
||||
from app.llm.base import Chunk, ChunkKind # noqa: E402
|
||||
from app.memory import ConfirmStatus, SQLiteMemoryStore # noqa: E402
|
||||
|
||||
|
||||
class FakeLLM:
|
||||
name = "fake"
|
||||
last_backend = "fake"
|
||||
|
||||
def __init__(self):
|
||||
self.system_prompts = []
|
||||
|
||||
async def stream(self, messages, *, tools=None, max_tokens=None):
|
||||
self.system_prompts.append(messages[0]["content"])
|
||||
yield Chunk(kind=ChunkKind.CONTENT, text="好的。")
|
||||
yield Chunk(kind=ChunkKind.DONE, finish_reason="stop")
|
||||
|
||||
|
||||
class FakeTTS:
|
||||
sample_rate = 16000
|
||||
|
||||
def synthesize(self, _text):
|
||||
return np.ones(160, dtype=np.float32) * 0.1
|
||||
|
||||
|
||||
async def consume(engine: ConversationEngine, text: str) -> None:
|
||||
async for _event in engine.respond_to_text(text):
|
||||
pass
|
||||
|
||||
|
||||
async def test_cross_session_profile() -> None:
|
||||
tmp = Path(tempfile.mkdtemp(prefix="profile_memory_"))
|
||||
store = SQLiteMemoryStore(tmp / "memory.db")
|
||||
await store.open()
|
||||
try:
|
||||
cfg = AppConfig()
|
||||
cfg.search.enabled = False
|
||||
cfg.memory.auto_extract_enabled = False
|
||||
|
||||
first_llm = FakeLLM()
|
||||
first = ConversationEngine(
|
||||
cfg, first_llm, store, ManualIdentityProvider(), FakeTTS())
|
||||
await first.start_session("profile_s1", user_id="u_internal")
|
||||
await consume(first, "你好，我叫林。")
|
||||
await first.end_session()
|
||||
|
||||
assert await store.get_user_display_name("u_internal") == "林"
|
||||
memories = await store.list_memories("u_internal")
|
||||
names = [m for m in memories if m.key == "姓名"]
|
||||
assert len(names) == 1
|
||||
assert names[0].value == "林"
|
||||
assert names[0].confirm_status == ConfirmStatus.CONFIRMED
|
||||
|
||||
# 模拟 disconnect 后重新创建整个 ConversationEngine/IdentityProvider。
|
||||
second_llm = FakeLLM()
|
||||
second = ConversationEngine(
|
||||
cfg, second_llm, store, ManualIdentityProvider(), FakeTTS())
|
||||
await second.start_session("profile_s2", user_id="u_internal")
|
||||
assert second.identity.current().display_name == "林"
|
||||
await consume(second, "我是谁？")
|
||||
prompt = second_llm.system_prompts[-1]
|
||||
assert "林" in prompt
|
||||
assert "u_internal" not in prompt
|
||||
assert "内部 user_id" in prompt
|
||||
await consume(second, "知道我是谁吗？")
|
||||
assert await store.get_user_display_name("u_internal") == "林"
|
||||
await consume(second, "我叫什么？")
|
||||
assert await store.get_user_display_name("u_internal") == "林"
|
||||
await second.end_session()
|
||||
finally:
|
||||
await store.close()
|
||||
shutil.rmtree(tmp, ignore_errors=True)
|
||||
|
||||
|
||||
async def main() -> int:
|
||||
assert extract_display_name("我叫林") == "林"
|
||||
assert extract_display_name("你好我叫lin。") == "lin"
|
||||
assert extract_display_name("我的名字是小林。") == "小林"
|
||||
assert extract_display_name("你可以叫我老韩。") == "老韩"
|
||||
assert extract_display_name("我是林。") == "林"
|
||||
assert extract_display_name("我是程序员。") is None
|
||||
assert extract_display_name("我叫什么？") is None
|
||||
assert extract_display_name("我是谁？") is None
|
||||
assert extract_display_name("知道我是谁吗？") is None
|
||||
assert extract_display_name("我是林吗？") is None
|
||||
assert extract_display_name("我叫什么名字？") is None
|
||||
assert extract_memories("记住，我叫林。", "") == []
|
||||
await test_cross_session_profile()
|
||||
print("用户称呼跨会话回归测试：22/22 PASS")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(asyncio.run(main()))
|
||||
@@ -62,6 +62,7 @@ class FakeSearch(SearXNGSearchClient):
|
||||
class FakeMemory:
|
||||
async def start_session(self, *_args): pass
|
||||
async def end_session(self, *_args): pass
|
||||
async def get_user_display_name(self, *_args): return ""
|
||||
async def retrieve(self, *_args, **_kwargs): return []
|
||||
async def add_turn(self, *_args): pass
|
||||
|
||||
|
||||
Reference in New Issue
Block a user