Merge commit e95582a: PR #20 proactive chat, topic chips, low-info turn plan

- Merge staging workflow parent and resolve conflicts with English/i18n and WS pool
- Re-greeting: language-aware fallbacks and prompts; router passes user_language
- RealtimeSession: topic suggestion callbacks + TTS sync path preserved

Co-authored-by: Cursor <cursoragent@cursor.com>

api/app/core/config.py

@@ -99,6 +99,12 @@ class Settings(BaseSettings):
     chat_reply_planner_llm_enabled: bool = False
     chat_reply_planner_max_tokens: int = Field(default=256, ge=64, le=1024)
     chat_reply_planner_temperature: float = Field(default=0.2, ge=0.0, le=1.0)
+    # 老对话回访问候：连接时若距上次消息超过该小时数，由 AI 主动发一条承接式开场（自防抖：发完即更新 last_message_at）
+    chat_re_greeting_enabled: bool = True
+    chat_re_greeting_idle_hours: float = Field(default=6.0, ge=0.25, le=240.0)
+    # 话题建议 chips：连接首帧附带 3-4 个 quick-start 话题（来自当前阶段的空 slots）
+    chat_topic_chips_enabled: bool = True
+    chat_topic_chips_max: int = Field(default=4, ge=1, le=8)
 
     # ── Memoir 叙事忠实度检查（FidelityCheckAgent）────────────────
     memoir_fidelity_check_enabled: bool = True