feat:

1. 建立问题库大纲，对应每个人生阶段槽位
2. 鼓励使用更生活化的交流语言共情与总结
3. 降低评审模型可能发生截断的概率
4. 成稿质量维度强化情感表达和上下文连贯性

api/app/agents/chat/orchestrator.py

@@ -213,7 +213,9 @@ class ChatOrchestrator:
                                 len(responses),
                             )
                         return AgentChatTurn(
-                            messages=responses, skip_tts=False, memory_retrieval_trace=None
+                            messages=responses,
+                            skip_tts=False,
+                            memory_retrieval_trace=None,
                         )
                     except Exception as e:
                         logger.error(f"资料收集处理失败: {e}", exc_info=True)
@@ -286,17 +288,13 @@ class ChatOrchestrator:
         scene_cues = extract_scene_cues(normalized_user_message)
         if scene_cues:
             cue_block = "\n".join(f"- {c}" for c in scene_cues)
-            scene_hint = (
-                f"\n\n[场景氛围提示——可借用这些感官细节自然接话，不要原样抄]\n{cue_block}"
-            )
+            scene_hint = f"\n\n[场景氛围提示——可借用这些感官细节自然接话，不要原样抄]\n{cue_block}"
             memory_evidence_text = (memory_evidence_text or "") + scene_hint
 
         profile_birth_year = user.birth_year if user else None
         profile_era_place = ""
         if user:
-            profile_era_place = (
-                (user.birth_place or user.grew_up_place or "").strip()
-            )
+            profile_era_place = (user.birth_place or user.grew_up_place or "").strip()
         prompt_state = build_runtime_interview_state(
             state,
             user_message=normalized_user_message,