feat: 示例问题按场景过滤,防止跨场景混淆

后端:
- filter_by_scene(): 关键词判断问题归属场景,过滤跨场景问题
  legal: 仲裁/诉讼/合同/税务/股权等
  decision: 扩张/定价/招人/融资/现金流/竞争等
  life: 孩子/父母/养老/健康/睡眠等
  emotion: 焦虑/失眠/自我怀疑/崩溃/拖延症等
- generate_daily_topics: prompt加场景边界说明,返回前双重过滤(老板视角+场景归属)
- /samples: prompt加场景边界说明,返回前双重过滤
- /topics: prompt加禁止清单+正确视角示例

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>

api.py

@@ -18,7 +18,7 @@ from bossai import (
     ExpertStore, ConsultationStore, RatingStore,
     DocumentGenerator, RegulationUpdateManager, FactFinder,
     ChatStore, redact,
-    DailyTopicStore, generate_daily_topics, filter_boss_perspective,
+    DailyTopicStore, generate_daily_topics, filter_boss_perspective, filter_by_scene,
 )
 
 # ===== 日志脱敏 =====
@@ -461,10 +461,14 @@ def generate_samples(req: SampleRequest):
         return {"samples": builtin.get(req.scene, builtin["legal"])}
 
     scene_config = {
-        "legal": {"desc": "法律/法务", "focus": "劳动用工、合同审查、债权债务、股东纠纷、税务风险、诉讼仲裁等法律问题"},
+        "legal": {"desc": "法律/法务", "focus": "劳动用工、合同审查、债权债务、股东纠纷、税务风险、诉讼仲裁等法律问题",
-        "decision": {"desc": "经营决策", "focus": "扩张收缩、定价策略、招人裁员、融资合伙、项目承接、业务转型等经营决策"},
+                  "boundary": "只关注法律/法务问题,不要生成纯经营策略、纯情绪疏导、纯生活问题"},
-        "life": {"desc": "生活助理", "focus": "家庭沟通、子女教育、父母养老、睡眠压力、出差日程、健康习惯等个人生活问题,不是企业经营问题"},
+        "decision": {"desc": "经营决策", "focus": "扩张收缩、定价策略、招人裁员、融资合伙、项目承接、业务转型等经营决策",
-        "emotion": {"desc": "情绪疏导", "focus": "压力、焦虑、愤怒、拖延、疲惫等情绪状态,老板可能倾诉的心理感受"},
+                     "boundary": "只关注经营决策问题。不要生成纯法律问题(如合同违约金怎么约定)、纯情绪问题(如焦虑失眠、自我怀疑、凌晨怀疑人生)、纯生活问题。情绪相关的决策问题可以,但必须是'该怎么做'而非'我很难受'"},
+        "life": {"desc": "生活助理", "focus": "家庭沟通、子女教育、父母养老、睡眠压力、出差日程、健康习惯等个人生活问题,不是企业经营问题",
+                 "boundary": "只关注个人生活问题,不要生成纯法律问题、纯经营决策问题、纯情绪疏导问题"},
+        "emotion": {"desc": "情绪疏导", "focus": "压力、焦虑、愤怒、拖延、疲惫等情绪状态,老板可能倾诉的心理感受",
+                    "boundary": "关注情绪与心理疏导,核心是情绪感受和心理状态,不是经营策略或法律方案"},
     }
     config = scene_config.get(req.scene, scene_config["legal"])
 
@@ -473,6 +477,7 @@ def generate_samples(req: SampleRequest):
         f"你是{config['desc']}领域的专业顾问。请生成 4 个该领域的典型问题,"
         f"用户(中小企业老板)可能会问的问题。\n\n"
         f"问题方向:{config['focus']}\n\n"
+        f"场景边界:{config['boundary']}\n\n"
     )
     if req.topic:
         prompt += f"具体话题:{req.topic}\n\n"
@@ -538,9 +543,11 @@ def generate_samples(req: SampleRequest):
         if start == -1 or end == -1:
             return {"samples": builtin.get(req.scene, builtin["legal"])}
         samples = json.loads(answer[start:end + 1])
-        # 过滤:老板视角 + 非字符串 + 去重
+        # 过滤:老板视角 + 场景归属 + 非字符串
-        samples = filter_boss_perspective(
+        samples = filter_by_scene(
+            filter_boss_perspective(
                 [s for s in samples if isinstance(s, str) and s.strip()]
+            ), req.scene
         )[:4]
         if len(samples) < 2:
             return {"samples": builtin.get(req.scene, builtin["legal"])}

bossai.py

@@ -3349,6 +3349,87 @@ def filter_boss_perspective(questions: list[str]) -> list[str]:
     return valid
 
 
+# ===== 场景过滤:防止问题跨场景混淆 =====
+
+# 各场景的归属关键词:问题包含这些关键词时,应归属对应场景
+SCENE_KEYWORDS = {
+    "emotion": [
+        "睡不着", "失眠", "焦虑", "抑郁", "崩溃", "自我怀疑", "自我贬低",
+        "撑不下去", "孤独", "愤怒", "委屈", "难受", "压力很大", "心力交瘁",
+        "怀疑人生", "怀疑自己", "不想干了", "想放弃", "绝望", "恐惧",
+        "情绪", "心态", "心理", "疏导", "陪伴", "倾诉",
+        "凌晨三点怀疑", "破PPT", "怀疑这", "贬低自己",
+        "吵架后", "吵了一架", "背叛了我", "背叛感",
+        "害怕做决定", "下不了手", "拖延症", "就是拖延",
+    ],
+    "legal": [
+        "仲裁", "诉讼", "起诉", "合同", "违约", "欠款", "催收",
+        "税务", "发票", "社保", "工伤", "辞退", "开除员工",
+        "股东", "股权", "分红", "退股", "合伙人撤资",
+        "法规", "法律", "合规", "稽查", "罚款",
+        "知识产权", "商标", "专利", "侵权",
+        "借条", "担保", "抵押", "保全", "执行",
+    ],
+    "decision": [
+        "扩张", "开分店", "开第二家", "裁员", "招人", "融资",
+        "定价", "涨价", "降价", "促销", "备货",
+        "业务线", "转型", "外包", "预算", "现金流",
+        "投资", "回报率", "盈亏", "亏损业务",
+        "接单", "大单", "账期", "框架合同",
+        "竞争", "竞品", "市场份额",
+        "Q1", "Q2", "Q3", "Q4", "季度", "年度规划",
+        "客户流失", "复购率", "转化率",
+    ],
+    "life": [
+        "孩子", "子女", "父母", "养老", "家庭", "夫妻",
+        "亲子", "青春期", "兴趣班", "留学", "接班",
+        "体检", "健康", "运动", "饮食", "睡眠",
+        "出差", "行程", "时间管理",
+        "应酬", "酒", "体重", "颈椎",
+    ],
+}
+
+
+def filter_by_scene(questions: list[str], target_scene: str) -> list[str]:
+    """过滤掉不属于目标场景的问题。
+
+    判断规则:
+    1. 问题包含其他场景的归属关键词 → 过滤掉(归属错误)
+    2. 问题包含目标场景的归属关键词 → 保留
+    3. 中性问题(不含任何场景关键词) → 保留(可能确实是该场景的问题)
+
+    特殊处理:
+    - emotion 场景较宽泛,只过滤明显属于 legal/decision/life 的问题
+    - legal 和 decision 有交叉(如"合伙人退股"),归 legal
+
+    Args:
+        questions: 问题列表
+        target_scene: 目标场景 legal/decision/life/emotion
+
+    Returns:
+        过滤后的属于目标场景的问题列表
+    """
+    valid = []
+    for q in questions:
+        q = str(q).strip()
+        if not q:
+            continue
+        # 检查是否包含其他场景的归属关键词
+        wrong_scene = False
+        for scene, keywords in SCENE_KEYWORDS.items():
+            if scene == target_scene:
+                continue
+            # emotion 场景不拦截(情绪问题可能出现在任何场景的焦虑中)
+            if target_scene == "emotion":
+                continue
+            if any(kw in q for kw in keywords):
+                wrong_scene = True
+                break
+        if not wrong_scene:
+            valid.append(q)
+    return valid
+
+
 def generate_daily_topics(kimi_client, store: DailyTopicStore) -> dict:
     """AI 生成当天 4 个场景的热点问题并存库。
 
@@ -3367,6 +3448,14 @@ def generate_daily_topics(kimi_client, store: DailyTopicStore) -> dict:
         "emotion": "情绪与心理问题,聚焦中小企业老板的焦虑:创业压力、合伙人冲突、孤独感、决策焦虑、拖延症、自我怀疑、危机应对等",
     }
 
+    # 场景边界:明确告诉AI什么问题不该出现在当前场景
+    scene_boundaries = {
+        "legal": "本场景只关注法律/法务问题。不要生成纯经营策略问题(如'该不该扩张')、纯情绪问题(如'压力很大怎么办')、纯生活问题(如'孩子教育')。",
+        "decision": "本场景只关注经营决策问题。不要生成纯法律问题(如'合同违约金怎么约定')、纯情绪问题(如'焦虑失眠怎么办'、'自我怀疑'、'凌晨怀疑人生')、纯生活问题(如'父母养老')。情绪相关的决策问题可以,但必须是'该怎么做'而非'我很难受'。",
+        "life": "本场景只关注个人生活问题。不要生成纯法律问题、纯经营决策问题、纯情绪疏导问题。问题应围绕家庭、健康、教育、养老、时间管理等生活领域。",
+        "emotion": "本场景关注情绪与心理疏导。可以涉及经营中的情绪反应,但核心是'情绪感受和心理状态',不是'经营策略'或'法律方案'。",
+    }
+
     # 获取当前日期用于 prompt
     today_str = datetime.now().strftime("%Y年%m月%d日")
     # 获取当前热点事件提示(简单版:用日期季节推断)
@@ -3389,6 +3478,7 @@ def generate_daily_topics(kimi_client, store: DailyTopicStore) -> dict:
 
     results = {}
     for scene, desc in scene_desc.items():
+        boundary = scene_boundaries.get(scene, "")
         prompt = f"""你是左右(BossAi)的内容编辑,负责为中小企业老板生成今日热点问题。
 
 当前日期:{today_str}
@@ -3396,6 +3486,8 @@ def generate_daily_topics(kimi_client, store: DailyTopicStore) -> dict:
 
 场景:{desc}
 
+场景边界:{boundary}
+
 请生成25-30个该场景下老板最焦虑、最关注的热点问题。
 
 要求:
@@ -3440,16 +3532,17 @@ def generate_daily_topics(kimi_client, store: DailyTopicStore) -> dict:
                 results[scene] = {"count": 0, "source": "ai", "error": "JSON解析失败"}
                 continue
             questions = json.loads(answer[start:end + 1])
-            # 过滤:老板视角 + 去重
+            # 过滤:老板视角 + 场景归属 + 去重
             boss_questions = filter_boss_perspective(questions)
+            scene_questions = filter_by_scene(boss_questions, scene)
             valid = []
             seen = set()
-            for q in boss_questions:
+            for q in scene_questions:
                 if q not in seen:
                     valid.append(q)
                     seen.add(q)
             if len(valid) < 10:
-                results[scene] = {"count": 0, "source": "ai", "error": f"过滤后有效问题不足10个(原始{len(questions)}个)"}
+                results[scene] = {"count": 0, "source": "ai", "error": f"过滤后有效问题不足10个(原始{len(questions)}个,老板视角{len(boss_questions)}个,场景匹配{len(scene_questions)}个)"}
                 continue
             store.upsert(scene, valid[:30], source="ai")
             results[scene] = {"count": len(valid[:30]), "source": "ai"}