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/app/agents/chat/interview_agent.py

@@ -18,7 +18,6 @@ from app.agents.chat.interview_state_hints import (
     update_recent_questions,
 )
 from app.agents.chat.interview_turn_plan import plan_interview_turn
-from app.agents.chat.reply_planner import maybe_refine_turn_plan_with_llm
 from app.agents.chat.personas import normalize_interview_persona
 from app.agents.chat.prompt_context import ChatPromptContext
 from app.agents.chat.prompts_conversation import (
@@ -30,6 +29,7 @@ from app.agents.chat.reply_limits import (
     segments_from_llm_response,
     truncate_chat_segments,
 )
+from app.agents.chat.reply_planner import maybe_refine_turn_plan_with_llm
 from app.agents.chat.stage_detection import keyword_fallback_primary_stage
 from app.agents.state_schema import MemoirStateSchema
 from app.core.agent_logging import (
@@ -38,7 +38,7 @@ from app.core.agent_logging import (
     log_agent_summary,
 )
 from app.core.config import settings
-from app.core.dependencies import get_llm_provider
+from app.core.llm_gateway import LlmGateway, LlmUseCase
 from app.core.logging import get_logger
 from app.features.conversation.input_normalize import normalize_chat_input_for_agent
 
@@ -89,8 +89,7 @@ def _finalize_chat_segments_after_llm(
 
 def _get_langchain_llm():
     try:
-        provider = get_llm_provider()
-        return getattr(provider, "langchain_llm", None)
+        return LlmGateway().langchain_llm_for(LlmUseCase("chat.interview"))
     except Exception:
         return None