Python
fix(sdk): placeholder values never overwrite the basic profile
alvinfei78882f3300de
diff --git a/hy_memory/agent/extractor.py b/hy_memory/agent/extractor.pyindex 5a81f44..daffebd 100644--- a/hy_memory/agent/extractor.py+++ b/hy_memory/agent/extractor.py@@ -682,6 +682,23 @@ Output:```John's occupation and location are HIS attributes, so they go into `memory` with "John" as the subject. They must NEVER land in `basic_info.occupation` / `basic_info.location` — `basic_info` is exclusively the user's own profile. Only `name` (Tim, from the user message's `name` field) belongs there.+## Example 11 — Counter-example: small talk has no basic_info++New Messages:+[{"role": "user", "content": "Hi"},+ {"role": "assistant", "content": "Hello! The user's name is The user. How can I help?"}]+Memory Date: 2025-09-03++Output:+```json+{+ "memory": [],+ "intentions": [],+ "basic_info": {}+}+```+The user stated nothing about themselves. The assistant's line is not a user turn, and "The user" is a placeholder, not a name. Output `{}` — never `{"name": "The user"}` or `{"name": "user"}`.+---"""@@ -749,6 +766,14 @@ Rules:fields (e.g. name, age, location, occupation, employer) **explicitly stated**in the NEW user messages. Never infer, never invent. If no field is explicitlystated, output `{{}}`.+ * HARD RULE: fill a field ONLY if the user stated it in a `user` turn.+ Anything said only by the assistant (including the assistant quoting an+ earlier memory such as "The user's name is X") does NOT count. If nothing+ qualifies, output `"basic_info": {{}}`.+ * NEVER write the field name itself or a placeholder as a value ("user",+ "The user", "用户", "name", "N/A", "unknown", "none", "-"). Omit the field.+ * Negative example: small talk such as `[user]: Hi` / `[assistant]: How can+ I help?`, or `[user]: Reply with exactly: PONG` → `"basic_info": {{}}`.* Exception for `name`: the `name` field on the user's own message, or a leadingline "The user's name is X" / "用户名叫X", is an authoritative source for`name` — even though the user never said it out loud.@@ -817,6 +842,14 @@ Rules:fields (e.g. name, age, location, occupation, employer) **explicitly stated**in the NEW user messages. Never infer, never invent. If no field is explicitlystated, output `{{}}`.+ * HARD RULE: fill a field ONLY if the user stated it in a `user` turn.+ Anything said only by the assistant (including the assistant quoting an+ earlier memory such as "The user's name is X") does NOT count. If nothing+ qualifies, output `"basic_info": {{}}`.+ * NEVER write the field name itself or a placeholder as a value ("user",+ "The user", "用户", "name", "N/A", "unknown", "none", "-"). Omit the field.+ * Negative example: small talk such as `[user]: Hi` / `[assistant]: How can+ I help?`, or `[user]: Reply with exactly: PONG` → `"basic_info": {{}}`.* Exception for `name`: the `name` field on the user's own message, or a leadingline "The user's name is X" / "用户名叫X", is an authoritative source for`name` — even though the user never said it out loud.diff --git a/hy_memory/agent/prompts_zh.py b/hy_memory/agent/prompts_zh.pyindex a0ed95b..9a9adce 100644--- a/hy_memory/agent/prompts_zh.py+++ b/hy_memory/agent/prompts_zh.py@@ -365,6 +365,13 @@ EXTRACT_PROMPT_ZH = """## 最近 k 条消息* basic_info:**只装用户本人的画像**。仅当 NEW user messages 中**明确**陈述稳定画像字段(如 姓名、年龄、所在地、职业、雇主)时才填写。绝不推断、绝不编造。没有任何字段被明确陈述时输出 `{{}}`。+ * **硬性规则**:只有用户在 `user` 回合里**明确说出**的字段才能填写。只在+ assistant 回合出现的内容(包括 assistant 引用旧记忆,如"The user's name is X"+ / "用户名是X")一律不算。没有符合条件的字段时,必须输出 `"basic_info": {{}}`。+ * **绝不**把字段名本身或占位符当值写入("用户"、"The user"、"user"、"name"、+ "姓名"、"N/A"、"unknown"、"未知"、"未提供"、"-"),宁可省略该字段。+ * 负例:寒暄如 `[user]: 你好` / `[assistant]: 我可以帮你。`,或+ `[user]: Reply with exactly: PONG` → `"basic_info": {{}}`。* `name` 的例外:用户自己那条消息上的 `name` 字段,或文首形如"用户名叫X" / "The user's name is X" 的那一行,都是 `name` 的权威来源——即使用户本人从未开口自报姓名。@@ -440,6 +447,13 @@ EXTRACT_PROMPT_ZH_NO_INTENTION = """## 最近 k 条消息* basic_info:**只装用户本人的画像**。仅当 NEW user messages 中**明确**陈述稳定画像字段(如 姓名、年龄、所在地、职业、雇主)时才填写。绝不推断、绝不编造。没有任何字段被明确陈述时输出 `{{}}`。+ * **硬性规则**:只有用户在 `user` 回合里**明确说出**的字段才能填写。只在+ assistant 回合出现的内容(包括 assistant 引用旧记忆,如"The user's name is X"+ / "用户名是X")一律不算。没有符合条件的字段时,必须输出 `"basic_info": {{}}`。+ * **绝不**把字段名本身或占位符当值写入("用户"、"The user"、"user"、"name"、+ "姓名"、"N/A"、"unknown"、"未知"、"未提供"、"-"),宁可省略该字段。+ * 负例:寒暄如 `[user]: 你好` / `[assistant]: 我可以帮你。`,或+ `[user]: Reply with exactly: PONG` → `"basic_info": {{}}`。* `name` 的例外:用户自己那条消息上的 `name` 字段,或文首形如"用户名叫X" / "The user's name is X" 的那一行,都是 `name` 的权威来源——即使用户本人从未开口自报姓名。@@ -669,6 +683,23 @@ Memory Date:2025-09-02```职业和所在地是 **John 的**属性,所以进 `memory` 并以"John"作主体,**绝不能**落到 `basic_info` 的 `occupation` / `location` —— `basic_info` 专属于用户本人。只有 `name`(Tim,来自用户消息的 `name` 字段)才该放进去。注意输出语言随输入语言(此例为英文)。+## 示例 11 —— 反例:寒暄没有 basic_info++新消息:+[{"role": "user", "content": "你好"},+ {"role": "assistant", "content": "你好!我可以帮你。之前记得 The user's name is 用户."}]+Memory Date:2025-09-03++输出:+```json+{+ "memory": [],+ "intentions": [],+ "basic_info": {}+}+```+用户没有说任何关于自己的信息。assistant 那句不是 user 回合,"用户" 也是占位符而不是名字。必须输出 `{}`——**绝不能**输出 `{"name": "用户"}`。+---"""diff --git a/hy_memory/agent/tools/basic_profile.py b/hy_memory/agent/tools/basic_profile.pyindex 37dfec0..6a72705 100644--- a/hy_memory/agent/tools/basic_profile.py+++ b/hy_memory/agent/tools/basic_profile.py@@ -26,6 +26,8 @@ from __future__ import annotationsimport asyncioimport logging+import re+import unicodedataimport uuidimport weakreffrom dataclasses import dataclass@@ -208,6 +210,147 @@ def _sanitize_kv(return result+# ================================================================+# 占位符守卫(P0-1)+# ================================================================+# 弱模型(如 qwen3.5-2b)在用户什么都没说时,会把 schema 字段说明里的词当值+# 填进 basic_info:{"name": "用户"} / "The user" / "N/A"。每个占位符都会+# supersede 掉真实值,演化链变成 费天翔 → Fei → 用户 → The user。+# 规则:占位符永远不入库;读侧组装 KV 时占位符也不覆盖已有真实值。++_PLACEHOLDER_VALUES = frozenset({+ "用户", "该用户", "本用户", "用户本人",+ "the user", "the user's", "user", "a user", "this user",+ "n/a", "na", "none", "null", "nil", "unknown", "unspecified",+ "not provided", "not specified", "not mentioned",+ "未提供", "未知", "不详", "未说明", "未提及", "无",+ "-", "?",+})++# 内置字段的中文标签:弱模型也会把字段说明的中文词当值。+_FIELD_LABELS: Dict[str, tuple] = {+ "name": ("姓名", "名字", "用户名", "用户姓名", "用户名字"),+ "age": ("年龄", "用户年龄"),+ "location": ("所在地", "地点", "城市", "用户所在地"),+ "occupation": ("职业", "工作", "用户职业"),+ "employer": ("雇主", "公司", "用户雇主"),+}++# 去掉标点/符号后再比较,让 "The user." / "用户。" / "N/A" 都命中。+# "-" / "?" 本身就是纯标点,剥完为空串,同样判为占位符。+_PUNCT_RE = re.compile(r"[\s\.,;:!?'\"`~()\[\]{}<>/\\|_\-\u3000-\u303f\uff00-\uff0f\uff1a-\uff20]+")+++def _placeholder_key(value: str) -> str:+ s = unicodedata.normalize("NFKC", str(value or "")).strip().lower()+ s = s.replace("\u2019", "'")+ s = _PUNCT_RE.sub(" ", s)+ return " ".join(s.split())+++_PLACEHOLDER_KEYS = frozenset(_placeholder_key(v) for v in _PLACEHOLDER_VALUES)+++def is_placeholder_value(field_name: str, value: Any) -> bool:+ """value 是否为占位符(空 / 用户 / The user / N/A / 字段名本身 等)。++ 大小写不敏感、首尾空白与标点不敏感。数字(如 age=30)永远不是占位符。+ """+ if value is None:+ return True+ if isinstance(value, bool):+ return False+ if isinstance(value, (int, float)):+ return False+ key = _placeholder_key(value)+ if not key:+ return True+ if key in _PLACEHOLDER_KEYS:+ return True+ field_key = _placeholder_key(field_name)+ if field_key and key in (field_key, field_key.replace("_", " ")):+ return True+ for label in _FIELD_LABELS.get(field_name, ()):+ if key == _placeholder_key(label):+ return True+ return False+++def _drop_placeholders(kv: Dict[str, Any]) -> Dict[str, Any]:+ return {k: v for k, v in kv.items() if not is_placeholder_value(k, v)}+++# ================================================================+# 来源守卫(P0-1):basic_info 只认 user 回合+# ================================================================+# 抽取器偶尔把 assistant 回合里的内容(包括 assistant 引用的旧占位记忆+# "The user's name is 用户.")当成用户画像再写一次。writer 把 user 回合原文+# 交给 filter_basic_info_by_user_text(),值不在 user 原文里的字段一律丢弃。+#+# 匹配规则(大小写、空白不敏感,NFKC 归一):+# - 严格字段(name / age / location / employer):值必须作为子串出现在 user+# 原文里。"我叫费天翔" → name=费天翔 通过;"Fei Tianxiang" 与 "fei tianxiang"+# 通过;"杭州" 写成 "Hangzhou" 则丢弃(宁缺毋滥:身份字段错一次就会+# supersede 掉真实值)。+# - 其余字段(occupation 及业务自定义字段):允许模型轻度改写。只要值与 user+# 原文的最长公共子串 ≥ 2 个字符且覆盖值长度的一半以上即通过,例如+# "AI 基础设施从业者" vs "做 AI 基础设施"(公共子串 "ai基础设施" 覆盖 6/9)。+# 完全凭空的值(与 user 原文无公共片段)仍被丢弃。++STRICT_SOURCE_FIELDS = frozenset({"name", "age", "location", "employer"})+++def _match_key(text: Any) -> str:+ s = unicodedata.normalize("NFKC", str(text if text is not None else "")).lower()+ s = s.replace("\u2019", "'")+ return "".join(s.split())+++def _longest_common_substring(a: str, b: str) -> int:+ if not a or not b:+ return 0+ best = 0+ prev = [0] * (len(b) + 1)+ for ca in a:+ cur = [0] * (len(b) + 1)+ for j, cb in enumerate(b, 1):+ if ca == cb:+ cur[j] = prev[j - 1] + 1+ if cur[j] > best:+ best = cur[j]+ prev = cur+ return best+++def value_in_user_text(field_name: str, value: Any, user_text: str) -> bool:+ """value 是否出自 user 原文(规则见上方注释)。"""+ v = _match_key(value)+ t = _match_key(user_text)+ if not v or not t:+ return False+ if v in t:+ return True+ if field_name in STRICT_SOURCE_FIELDS:+ return False+ common = _longest_common_substring(v, t)+ return common >= 2 and common * 2 >= len(v)+++def filter_basic_info_by_user_text(+ kv: Dict[str, Any],+ user_text: Optional[str],+) -> Dict[str, Any]:+ """只保留值出现在 user 原文里的字段;user_text 为空时整份丢弃。"""+ if not isinstance(kv, dict) or not kv:+ return {}+ if not (user_text or "").strip():+ return {}+ return {+ k: v for k, v in kv.items()+ if value_in_user_text(k, v, user_text or "")+ }++# ================================================================# 公共入口:upsert_basic_profile# ================================================================@@ -287,6 +430,8 @@ async def _upsert_basic_profile_unlocked(# L0 Basic Info 从输入、唯一性到落盘都只属于 user_id。new_kv = _sanitize_kv(kv or {}, allowed_fields=allowed_fields)+ # 单调性守卫:占位符永远不覆盖已有值,过滤后为空就不写新版本、不产生新链头。+ new_kv = _drop_placeholders(new_kv)if not new_kv:return BasicProfileUpsertResult(success=True, changed=False, reason="no valid fields after sanitize"@@ -513,5 +658,8 @@ def _assemble_full_kv_from_nodes(for k, v in kv.items():if allowed_set is not None and k not in allowed_set:continue+ # 历史上已落盘的占位符版本(如 name=用户)不覆盖更早的真实值。+ if is_placeholder_value(k, v):+ continuefull_kv[k] = vreturn full_kvdiff --git a/hy_memory/pipelines/writer.py b/hy_memory/pipelines/writer.pyindex 23d5a52..95eebfd 100644--- a/hy_memory/pipelines/writer.py+++ b/hy_memory/pipelines/writer.py@@ -41,7 +41,10 @@ from ..core.workload import ()from ..agent.mem_agent import MemAgent, ProcessModefrom ..agent.reconciler import MemoryReconciler-from ..agent.tools.basic_profile import upsert_basic_profile+from ..agent.tools.basic_profile import (+ filter_basic_info_by_user_text,+ upsert_basic_profile,+)from ..models.memory import MemoryNode, MemoryLayer, MemoryStatus, SourceTypefrom ..data.vector_store import create_vector_storefrom ..data.vector_store_base import VectorStoreBase@@ -3305,6 +3308,20 @@ class MemoryWriter(WritePipeline):tool_calls_raw = None # v0.1.5.13+ 不再有真实 LLM tool_calls;保留字段做兼容tool_results_summary: List[Dict[str, Any]] = []+ # 来源守卫:basic_info 只认 user 回合。值不在任何 user 消息里的字段+ # (例如 assistant 引用旧占位记忆 "The user's name is 用户.")一律丢弃;+ # 有 messages 但没有 user 消息时整份丢弃。纯文本 add(无 messages)的+ # content 即调用方给出的用户原文,按 user 回合处理。+ if isinstance(basic_info_raw, dict) and basic_info_raw:+ _user_text = self._basic_info_user_text(request)+ _kept = filter_basic_info_by_user_text(basic_info_raw, _user_text)+ if len(_kept) != len(basic_info_raw):+ logger.info(+ f"[write] basic_info dropped fields not stated in user turns: "+ f"{sorted(set(basic_info_raw) - set(_kept))}"+ )+ basic_info_raw = _kept+if isinstance(basic_info_raw, dict) and basic_info_raw:try:_bp_result = await upsert_basic_profile(@@ -3580,6 +3597,27 @@ class MemoryWriter(WritePipeline):"llm_total_tokens": getattr(_er, "tokens_used", 0) or 0,}+ @staticmethod+ def _basic_info_user_text(request) -> str:+ """basic_info 来源校验用的 user 原文。++ - 有 messages:只取 role=user 的 content 与 user 自带的 ``name``(name 是+ basic_info.name 的权威来源);没有 user 消息时返回空串(整份丢弃)。+ - 无 messages(纯文本 add):content 本身就是用户原文。+ """+ messages = getattr(request, "messages", None) or []+ if not messages:+ return str(getattr(request, "content", "") or "")+ parts: List[str] = []+ for m in messages:+ if getattr(m, "role", None) != "user":+ continue+ name = getattr(m, "name", None)+ if name:+ parts.append(str(name))+ parts.append(str(getattr(m, "content", "") or ""))+ return "\n".join(parts)+@staticmethoddef _mark_agent_failure(response: WriteResponse,diff --git a/tests/test_basic_info_placeholder_guard.py b/tests/test_basic_info_placeholder_guard.pynew file mode 100644index 0000000..65935e3--- /dev/null+++ b/tests/test_basic_info_placeholder_guard.py@@ -0,0 +1,238 @@+"""P0-1:占位符不得污染 L0 基础画像。++弱模型(qwen3.5-2b)在用户什么都没说时把 basic_info 填成 {"name": "用户"} /+"The user" / "N/A",每个占位符都 supersede 掉真实值,演化链变成+费天翔 → Fei → 用户 → The user。三层防御:+(a) upsert 单调性守卫;(b) writer 只认 user 回合;(c) prompt 硬约束。+本文件锁住 (a)(b) 与 (c) 的 prompt 文案,覆盖改进建议第 10 节验收 1–4。+"""+import asyncio+from datetime import datetime, timedelta++import pytest++from hy_memory.agent.extractor import EXTRACT_FEW_SHOT_EN+from hy_memory.agent.prompts_zh import EXTRACT_FEW_SHOT_ZH+from hy_memory.agent.tools.basic_profile import (+ _assemble_full_kv_from_nodes,+ filter_basic_info_by_user_text,+ is_placeholder_value,+ upsert_basic_profile,+ value_in_user_text,+)+from hy_memory.models.memory import MemoryLayer, MemoryNode, MemoryStatus+from hy_memory.pipelines.base import ChatMessage, WriteRequest+from hy_memory.pipelines.writer import MemoryWriter++FIELDS = ["name", "age", "location", "occupation", "employer"]+++class FakeStore:+ def __init__(self, nodes=None):+ self.nodes = list(nodes or [])++ async def list_by_user(self, **kwargs):+ return [n for n in self.nodes if n.user_id == kwargs.get("user_id")]++ async def get_by_id(self, node_id):+ return next((n for n in self.nodes if n.node_id == node_id), None)++ async def upsert(self, node):+ self.nodes.append(node)++ async def update_payload(self, node_id, updates):+ node = await self.get_by_id(node_id)+ for key, value in updates.items():+ if key == "status" and isinstance(value, str):+ value = MemoryStatus(value)+ setattr(node, key, value)+++class FakeEmbed:+ async def embed_queued(self, text):+ return [0.1] * 8+++def l0_versions(store):+ return [n for n in store.nodes if n.layer == MemoryLayer.L0_BASIC_INFO]+++def write_basic_info(store, request, llm_basic_info):+ """模拟 writer 的 basic_info 段:来源守卫 → upsert。"""+ user_text = MemoryWriter._basic_info_user_text(request)+ kv = filter_basic_info_by_user_text(llm_basic_info, user_text)+ if not kv:+ return None+ return asyncio.run(upsert_basic_profile(+ user_id=request.user_id, kv=kv, vector_store=store,+ embed_service=FakeEmbed(), allowed_fields=FIELDS,+ ))+++def req(*msgs, content=""):+ return WriteRequest(+ content=content,+ messages=[ChatMessage(role=r, content=c) for r, c in msgs],+ user_id="u1",+ )+++# ── 验收 1:寒暄不产生新的 L0 版本 ──++def test_small_talk_creates_no_l0_version():+ store = FakeStore()+ r = req(("user", "你好"), ("assistant", "我可以帮你。"))+ write_basic_info(store, r, {"name": "用户"})+ write_basic_info(store, r, {})+ assert l0_versions(store) == []+++def test_placeholder_only_upsert_writes_nothing():+ store = FakeStore()+ for kv in ({"name": "用户"}, {"name": "The user"}, {"name": "N/A"},+ {"location": "unknown", "occupation": "未提供"}, {"name": "name"}):+ res = asyncio.run(upsert_basic_profile(+ user_id="u1", kv=kv, vector_store=store,+ embed_service=FakeEmbed(), allowed_fields=FIELDS,+ ))+ assert res.success and not res.changed+ assert l0_versions(store) == []+++# ── 验收 2:assistant 引用 "name is 用户" 不写入 ──++def test_assistant_quoting_placeholder_does_not_write():+ store = FakeStore()+ r = req(+ ("user", "你看那条记忆"),+ ("assistant", "那条 The user's name is 用户. 更说明问题"),+ )+ write_basic_info(store, r, {"name": "用户"})+ assert l0_versions(store) == []+++def test_value_only_in_assistant_turn_is_dropped():+ r = req(("user", "帮我查下天气"), ("assistant", "好的,费天翔,杭州今天晴。"))+ text = MemoryWriter._basic_info_user_text(r)+ assert filter_basic_info_by_user_text(+ {"name": "费天翔", "location": "杭州"}, text+ ) == {}+++def test_no_user_messages_drops_basic_info():+ r = req(("assistant", "我叫费天翔,常住杭州"))+ assert MemoryWriter._basic_info_user_text(r) == ""+ assert filter_basic_info_by_user_text({"name": "费天翔"}, "") == {}+++# ── 验收 3:用户自报姓名 ──++def test_user_states_name():+ store = FakeStore()+ r = req(("user", "我叫费天翔,常住杭州,做 AI 基础设施。"))+ res = write_basic_info(store, r, {+ "name": "费天翔", "location": "杭州", "occupation": "AI 基础设施从业者",+ })+ assert res.success and res.created+ assert l0_versions(store)[0].custom["basic_info_kv"] == {+ "name": "费天翔", "location": "杭州", "occupation": "AI 基础设施从业者",+ }+++def test_user_message_name_attribute_counts_as_user_text():+ r = WriteRequest(+ messages=[ChatMessage(role="user", name="Tim", content="What's up?")],+ user_id="u1",+ )+ text = MemoryWriter._basic_info_user_text(r)+ assert filter_basic_info_by_user_text({"name": "Tim"}, text) == {"name": "Tim"}+++def test_plain_text_add_is_user_text():+ r = WriteRequest(content="I'm Fei Tianxiang, 35, living in Hangzhou.", user_id="u1")+ text = MemoryWriter._basic_info_user_text(r)+ assert filter_basic_info_by_user_text(+ {"name": "fei tianxiang", "age": 35, "location": "Hangzhou"}, text+ ) == {"name": "fei tianxiang", "age": 35, "location": "Hangzhou"}+++def test_strict_fields_require_containment_loose_fields_allow_rewording():+ text = "我叫费天翔,常住杭州,做 AI 基础设施。"+ assert value_in_user_text("name", "费天翔", text)+ assert not value_in_user_text("location", "Hangzhou", text)+ assert value_in_user_text("occupation", "AI 基础设施从业者", text)+ assert not value_in_user_text("occupation", "软件工程师", text)+++# ── 验收 4:已有真实值不被后续占位符覆盖 ──++def test_existing_name_not_overwritten_by_placeholder():+ store = FakeStore()+ write_basic_info(store, req(("user", "我叫费天翔")), {"name": "费天翔"})+ assert len(l0_versions(store)) == 1+ for kv in ({"name": "用户"}, {"name": "The user."}, {"name": "N/A"}):+ res = asyncio.run(upsert_basic_profile(+ user_id="u1", kv=kv, vector_store=store,+ embed_service=FakeEmbed(), allowed_fields=FIELDS,+ ))+ assert not res.changed+ assert len(l0_versions(store)) == 1+ assert _assemble_full_kv_from_nodes(list(store.nodes)) == {"name": "费天翔"}+++def test_mixed_kv_keeps_real_fields_and_drops_placeholders():+ store = FakeStore()+ res = asyncio.run(upsert_basic_profile(+ user_id="u1", kv={"name": "用户", "location": "杭州"}, vector_store=store,+ embed_service=FakeEmbed(), allowed_fields=FIELDS,+ ))+ assert res.diff_kv == {"location": "杭州"}+++def test_already_poisoned_chain_heals_on_read():+ now = datetime.utcnow()++ def node(nid, kv, days_ago):+ return MemoryNode(+ node_id=nid, user_id="u1", agent_id="",+ layer=MemoryLayer.L0_BASIC_INFO, content="profile",+ custom={"basic_info_kv": kv},+ gmt_created=now - timedelta(days=days_ago),+ )++ chain = [+ node("a", {"name": "费天翔"}, 4), node("b", {"name": "Fei"}, 3),+ node("c", {"name": "用户"}, 2), node("d", {"name": "The user"}, 1),+ ]+ assert _assemble_full_kv_from_nodes(chain) == {"name": "Fei"}++[email protected]("value", [+ "", " ", "用户", "用户。", "The user", "the user.", "THE USER", "user",+ "The user's", "n/a", "N/A", "na", "None", "null", "unknown", "未提供",+ "未知", "不详", "-", "?", "name", " Name ", "姓名",+])+def test_placeholder_values(value):+ assert is_placeholder_value("name", value)++[email protected]("field,value", [+ ("name", "费天翔"), ("name", "Fei"), ("name", "Username42"),+ ("age", 30), ("age", 0), ("location", "杭州"), ("employer", "Tencent"),+])+def test_real_values_are_not_placeholders(field, value):+ assert not is_placeholder_value(field, value)+++# ── (c) prompt 硬约束 ──++def test_prompts_carry_hard_rule_and_small_talk_counter_example():+ from hy_memory.agent import extractor, prompts_zh++ en_rules = [v for v in vars(extractor).values()+ if isinstance(v, str) and "HARD RULE: fill a field ONLY" in v]+ zh_rules = [v for v in vars(prompts_zh).values()+ if isinstance(v, str) and "**硬性规则**" in v]+ assert len(en_rules) >= 2 and len(zh_rules) >= 2+ assert "small talk has no basic_info" in EXTRACT_FEW_SHOT_EN+ assert "寒暄没有 basic_info" in EXTRACT_FEW_SHOT_ZH