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/features/memory/enrichment_scheduler.py

@@ -0,0 +1,50 @@
+"""Memory enrichment scheduling boundary."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+
+@dataclass(frozen=True)
+class MemoryEnrichmentRequest:
+    user_id: str
+    source_id: str
+    memoir_correlation_id: str | None = None
+
+
+class MemoryEnrichmentScheduler:
+    """Adapter around the Celery enrichment task name and queue policy."""
+
+    def schedule(self, request: MemoryEnrichmentRequest) -> str | None:
+        from app.tasks.memory_enrichment_tasks import schedule_memory_enrichment
+
+        return schedule_memory_enrichment(
+            request.user_id,
+            request.source_id,
+            memoir_correlation_id=request.memoir_correlation_id,
+        )
+
+    def schedule_many(
+        self,
+        user_id: str,
+        source_ids: list[str],
+        *,
+        memoir_correlation_id: str | None = None,
+    ) -> list[str]:
+        task_ids: list[str] = []
+        for source_id in source_ids:
+            if not source_id:
+                continue
+            task_id = self.schedule(
+                MemoryEnrichmentRequest(
+                    user_id=user_id,
+                    source_id=source_id,
+                    memoir_correlation_id=memoir_correlation_id,
+                )
+            )
+            if task_id:
+                task_ids.append(task_id)
+        return task_ids
+
+
+__all__ = ["MemoryEnrichmentRequest", "MemoryEnrichmentScheduler"]