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/memoir/orchestrator.py

@@ -49,11 +49,18 @@ class MemoirOrchestrator:
     回忆录生成编排器。
     遍历 segments → ExtractionAgent → ClassificationAgent → 按 category 聚合 →
     调用 process_category 生成叙事并持久化。
+
+    可注入 ``extraction_agent`` / ``classification_agent`` 以便测试替身。
     """
 
-    def __init__(self) -> None:
-        self.extraction_agent = ExtractionAgent()
-        self.classification_agent = ClassificationAgent()
+    def __init__(
+        self,
+        *,
+        extraction_agent: ExtractionAgent | None = None,
+        classification_agent: ClassificationAgent | None = None,
+    ) -> None:
+        self.extraction_agent = extraction_agent or ExtractionAgent()
+        self.classification_agent = classification_agent or ClassificationAgent()
 
     def prepare_batches(
         self,