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
+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",
|
||||
]
|
||||
|
||||
Reference in New Issue
Block a user