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.

api/app/agents/chat/occupation_context.py

@@ -6,17 +6,13 @@ from app.agents.chat.background_voice import normalize_background_voice
 
 
 def get_occupation_chat_hint(occupation: str | None, background_voice: str) -> str:
-    """default 路径的通用职业上下文；cadre/military 已有专属块，返回空串。"""
+    """一句职业事实（仅 default 路径）；cadre/military 语气由 background_voice 覆盖。"""
     if normalize_background_voice(background_voice) != "default":
         return ""
     occ = (occupation or "").strip()
     if not occ:
         return ""
-    return (
-        f"## 用户职业背景\n"
-        f"用户从事过「{occ}」相关工作。聊天时自然贴合这一背景，"
-        f"在用语和追问方向上适度靠近用户的职业经历与知识面，但不要刻意。"
-    )
+    return f"从事过「{occ}」相关工作，聊天可自然贴近其经历，不要刻意。"
 
 
 def get_occupation_narrative_hint(occupation: str | None, background_voice: str) -> str: