fix:记忆架构优化

service/client_agent/runtime.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+import asyncio
 import contextvars
 import logging
 import uuid
@@ -72,13 +73,20 @@ class MemoryConversationContext:
 
 
 class MemoryAwareClientAgent:
-    """在现有客服 Agent 外包裹记忆召回、候选保存和降级处理。"""
+    """在现有客服 Agent 外包裹记忆召回、候选保存和降级处理。
 
-    def __init__(self, *, agent, memory_service, context, extractor=None):
+    候选记忆保存默认放入后台任务执行（background_saves=True），不阻塞
+    客服响应；测试或需要确定性顺序的场景可设为 False 改回同步执行。
+    """
+
+    def __init__(self, *, agent, memory_service, context, extractor=None,
+                 background_saves: bool = True):
         self.agent = agent
         self.memory_service = memory_service
         self.context = context
         self.extractor = extractor
+        self.background_saves = background_saves
+        self._pending_saves: set[asyncio.Task] = set()
 
     async def handle(self, session_id: str, query: str, *, trace_id: str, customer_id: int) -> dict:
         """执行记忆召回、客服回答、消息写入和候选记忆保存。"""
@@ -107,7 +115,7 @@ class MemoryAwareClientAgent:
             result = await self.agent.handle(
                 session_id, query, trace_id=trace_id, customer_id=customer_id
             )
-            if self.extractor is not None:
+            if self.extractor is not None and not self.background_saves:
                 await self._save_candidates(
                     customer_id,
                     session_id,
@@ -117,6 +125,15 @@ class MemoryAwareClientAgent:
                     trace_id=trace_id,
                 )
             result["memory_warnings"] = list(warnings)
+            if self.extractor is not None and self.background_saves:
+                self._spawn_save(
+                    customer_id,
+                    session_id,
+                    query,
+                    memory_context,
+                    warnings,
+                    trace_id=trace_id,
+                )
             return result
         finally:
             _active_customer.reset(message_token)
@@ -124,6 +141,35 @@ class MemoryAwareClientAgent:
             _active_warnings.reset(warnings_token)
             _active_memory_context.reset(context_token)
 
+    def _spawn_save(
+        self,
+        customer_id,
+        session_id,
+        query,
+        context,
+        warnings,
+        *,
+        trace_id: str | None = None,
+    ) -> None:
+        """把候选记忆保存放入后台任务；任务异常已自捕获，不击穿响应。"""
+        task = asyncio.create_task(
+            self._save_candidates(
+                customer_id,
+                session_id,
+                query,
+                context,
+                warnings,
+                trace_id=trace_id,
+            )
+        )
+        self._pending_saves.add(task)
+        task.add_done_callback(self._pending_saves.discard)
+
+    async def wait_for_pending_saves(self) -> None:
+        """等待全部后台保存完成，供测试与优雅退出使用。"""
+        if self._pending_saves:
+            await asyncio.gather(*list(self._pending_saves), return_exceptions=True)
+
     async def _save_candidates(
         self,
         customer_id,
@@ -157,9 +203,24 @@ class MemoryAwareClientAgent:
             try:
                 evidence_count = 1
                 if candidate.get("signal_type") == "interest_query":
-                    # 兴趣主题首次出现即保存为候选，后续由长期记忆按精确内容合并证据。
+                    # 兴趣主题先计数：达到阈值才固化为长期记忆，避免单次关注污染画像。
                     candidate["memory_type"] = "CUSTOMER_PREFERENCE"
                     candidate["source"] = "dialogue_inferred"
+                    try:
+                        _, reached = await self.memory_service.record_interest_signal(
+                            customer_id=customer_id, tag=candidate["tag"]
+                        )
+                    except Exception as exc:
+                        logger.exception(
+                            "client interest signal failed: trace_id=%s customer_id=%s tag=%s",
+                            trace_id,
+                            customer_id,
+                            candidate.get("tag"),
+                        )
+                        warnings.append(f"interest_signal_failed:{type(exc).__name__}")
+                        continue
+                    if not reached:
+                        continue
                 memory = MemoryUnitDTO(
                     customer_id=customer_id,
                     session_id=session_id,