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
2026-04-09 15:32:35 +08:00
parent 064ad2161d
commit e1341c6d18
49 changed files with 938 additions and 271 deletions
--- a/api/app/features/memory/chunker.py
+++ b/api/app/features/memory/chunker.py
@@ -1,7 +1,6 @@
 """Transcript chunker — split raw text into retrieval-ready chunks."""


-
 def chunk_transcript(
    text: str, *, max_chars: int = 800, overlap_chars: int = 100
 ) -> list[str]: