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/image_prompt/orchestrator.py

@@ -74,7 +74,7 @@ class ImagePromptOrchestrator:
 
 def get_image_prompt_orchestrator() -> ImagePromptOrchestrator:
     """Celery / 后台任务入口：统一装配 LLM 与 MemoirImageSettings。"""
-    from app.core.dependencies import get_llm_provider
+    from app.core.llm_gateway import LlmGateway, LlmUseCase
 
-    llm = getattr(get_llm_provider(), "langchain_llm", None)
+    llm = LlmGateway().langchain_llm_for(LlmUseCase("image_prompt"))
     return ImagePromptOrchestrator(llm=llm, settings=MemoirImageSettings.from_env())