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/features/evaluation/router.py

@@ -173,9 +173,7 @@ async def get_playground_conversation_judge(
 async def memoir_phase1_ready(
     conversation_id: str,
     _auth: InternalEvalAuth,
-    svc: Annotated[
-        MemoirReadinessService, Depends(get_memoir_readiness_service)
-    ],
+    svc: Annotated[MemoirReadinessService, Depends(get_memoir_readiness_service)],
     segment_ids: Annotated[
         list[str],
         Query(
@@ -202,9 +200,7 @@ async def memoir_phase1_ready(
 async def memoir_submit_phase1(
     conversation_id: str,
     _auth: InternalEvalAuth,
-    svc: Annotated[
-        MemoirReadinessService, Depends(get_memoir_readiness_service)
-    ],
+    svc: Annotated[MemoirReadinessService, Depends(get_memoir_readiness_service)],
 ):
     try:
         return await svc.submit_memoir_phase1_for_conversation(