refactor(chat): AI-native prompts, remove interview heuristics

- Drop interview_reply_length and utterance_substance; always run stage LLM
  and memory retrieval when enabled; trim Settings fields and .env.example.
- Replace guided/opening prompts with compact fact blocks plus unified
  behavior guidance; slim background_voice and persona to tone hints.
- InterviewAgent uses fixed chat_interview max_tokens/chars/segments.

Also includes stacked work: profile followup/extract path, evaluation rubric
and judge schema updates, transcript SPLIT handling in execution service,
user export markdown split tests, and golden case fixture.
This commit is contained in:
Kevin
2026-04-06 22:22:50 +08:00
parent ca8bcc8489
commit 2fded6fbd9
27 changed files with 426 additions and 1349 deletions

View File

@@ -0,0 +1,39 @@
{
"description": "金标准用户轮次:导入 regression set 后通过 POST .../cases 创建 casebody.user_utterances 取对应数组)。用于 baseline/candidate 实验对比。",
"cases": [
{
"title": "implicit_confirm_hometown",
"user_utterances": [
"你好。",
"我生于1962年长在湖南长沙小时候就在那边读的小学。",
"嗯,是的。",
"后来六十年代末家里也没搬,一直在那边。"
]
},
{
"title": "emotional_long_memory",
"user_utterances": [
"今天想说说我们村那棵老槐树。",
"日本鬼子在的时候,为了望风把高过墙头的树都砍了,村里人硬是想办法保住学校里那棵,怕得很又舍不得。",
"我现在一说起来心里还堵得慌,那时候老人们夜里都不敢大声说话。"
]
},
{
"title": "childhood_rich_no_job_yet",
"user_utterances": [
"我生在密云的一个村里,河边小时候常去玩。",
"那条河老早就改过道,我们村边上那段现在叫沙河了,明代就改过。",
"小学是庙改的,院子里有棵楸树,我们班男生都抱不过来。",
"操场北边是沙坨子,我们小孩爱往上爬,一脚深一脚浅的。"
]
},
{
"title": "interview_brief_ack",
"user_utterances": [
"我那年冬天第一次见李老师,她借我一件棉袄穿。",
"嗯对,就是那件蓝布的。",
"后来她调到县城了,我再也没见过她。"
]
}
]
}