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。

app/tests/test_identity.py

@@ -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

app/tests/test_memory.py

@@ -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,

app/tests/test_profile_live.py

@@ -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()))

app/tests/test_profile_memory.py

@@ -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()))

app/tests/test_search.py

@@ -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