feat(api): 收敛对话与记忆流程边界，引入 LLM 网关与专用服务

- MemoryService 异步路径委托 MemoryIngestService / MemoryRetrievalService；富化派发经 MemoryEnrichmentScheduler
- WebSocket pipeline 经 ChatTurnService 与显式 DTO 编排单轮对话；回忆录片段入队由 MemoirIngestScheduler 封装
- 新增 LlmGateway（LlmUseCase），各 agent、任务与适配器对齐 ports
- 补充 memory 提示适配、runtime 类型、memory-retrieval 文档、ai-touchpoints 说明与扫描脚本及配套测试

Made-with: Cursor

api/tests/test_interview_prompts.py

@@ -2,6 +2,7 @@
 
 from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
 
+from app.agents.chat.helpers import format_history_string
 from app.agents.chat.interview_state_hints import (
     AUTOBIOGRAPHICAL_BOUNDARY_FALLBACK_ZH,
     DUPLICATE_QUESTION_GUARD_FALLBACK_ZH,
@@ -10,20 +11,19 @@ from app.agents.chat.interview_state_hints import (
     extract_scene_cues,
     segments_are_only_duplicate_guard_fallback,
 )
+from app.agents.chat.output_rules import chat_output_rules
+from app.agents.chat.personas import normalize_interview_persona
+from app.agents.chat.prompts_conversation import (
+    get_guided_conversation_prompt,
+    get_opening_prompt,
+)
+from app.agents.chat.slot_question_bank import SLOT_QUESTION_OUTLINES
 from app.agents.state_schema import (
     KnownFact,
     MemoirStateSchema,
     PersonaThread,
     default_slots,
 )
-from app.agents.chat.helpers import format_history_string
-from app.agents.chat.personas import normalize_interview_persona
-from app.agents.chat.output_rules import chat_output_rules
-from app.agents.chat.prompts_conversation import (
-    get_guided_conversation_prompt,
-    get_opening_prompt,
-)
-from app.agents.chat.slot_question_bank import SLOT_QUESTION_OUTLINES
 
 
 def test_guided_prompt_does_not_embed_raw_user_message_in_system_text():
@@ -132,6 +132,21 @@ def test_guided_prompt_host_tone_and_context_forward():
     assert "行为" in p and "影响" in p
 
 
+def test_guided_prompt_leaves_turn_level_question_contract_to_turn_plan() -> None:
+    p = get_guided_conversation_prompt(
+        current_stage="career",
+        empty_slots=["job"],
+        filled_slots={},
+        detected_user_stage="career",
+        user_profile_context="",
+        persona="default",
+    )
+    assert "随后**必须**用**一条**" not in p
+    assert "短承接后须带回一条" not in p
+    assert "仍须**勾回回忆叙事**" not in p
+    assert "具体问几问、是否必须追问，见顶部" in p
+
+
 def test_education_and_family_change_outlines_differ():
     edu = SLOT_QUESTION_OUTLINES[("education", "change")]
     fam = SLOT_QUESTION_OUTLINES[("family", "change")]