feat: configure local customer service knowledge runtime

app/core/config.py

@@ -46,6 +46,7 @@ class Settings(BaseSettings):
     message_broker_outbox_topic: str = "agent.outbox"
     message_broker_dlq_topic: str = "agent.dlq"
     milvus_uri: str
+    milvus_local_uri: str = ""
     milvus_token: str = ""
     milvus_collection: str = "jr_memory"
     neo4j_uri: str
@@ -101,6 +102,11 @@ class Settings(BaseSettings):
     offsite_smtp_use_ssl: bool = True
     offsite_smtp_timeout_seconds: float = Field(default=30, gt=0)
 
+    @property
+    def resolved_milvus_uri(self) -> str:
+        """本地开发优先使用 Lite 文件；部署环境仅配置标准 Milvus URI。"""
+        return self.milvus_local_uri or self.milvus_uri
+
     model_config = SettingsConfigDict(env_file=".env", env_file_encoding="utf-8", extra="ignore")
 
 

app/infrastructure/milvus_knowledge_adapter.py

@@ -26,6 +26,10 @@ class MilvusKnowledgeClient:
             raise RecoverableAgentError("知识检索参数无效")
         try:
             client = await self._ensure_client()
+            # Lite 重启后集合默认未加载；远程 Milvus 对重复加载保持幂等。
+            load_collection = getattr(client, "load_collection", None)
+            if load_collection is not None:
+                await load_collection(collection_name=collection)
             batches = await client.search(
                 collection_name=collection,
                 data=[vector],

app/service/agent/bootstrap.py

@@ -84,7 +84,7 @@ def get_vector_memory_adapter() -> VectorMemoryAdapter | None:
         from pymilvus import MilvusClient  # type: ignore[import-untyped]
 
         settings = get_settings()
-        client = MilvusClient(uri=settings.milvus_uri, token=settings.milvus_token or None)
+        client = MilvusClient(uri=settings.resolved_milvus_uri, token=settings.milvus_token or None)
         return VectorMemoryAdapter(client, settings.milvus_collection)
     except Exception:
         logger.warning("vector memory adapter unavailable; semantic recall disabled",

app/service/health_service.py

@@ -79,7 +79,7 @@ class HealthService:
         try:
             async with asyncio.timeout(self._milvus_timeout_seconds):
                 client = await asyncio.to_thread(
-                    _create_milvus_client, settings.milvus_uri, settings.milvus_token
+                    _create_milvus_client, settings.resolved_milvus_uri, settings.milvus_token
                 )
                 await client.get_server_version()
             return True, "ok"

app/service/knowledge_config.py

@@ -5,7 +5,7 @@ class KnowledgeRuntimeConfig:
         "policy_explain": ("fin_policy_collection", 5),
     }
 
-    def __init__(self, *, vector_dim: int = 1024, similarity_threshold: float = 0.70) -> None:
+    def __init__(self, *, vector_dim: int = 1024, similarity_threshold: float = 0.60) -> None:
         self.routes = dict(self.DEFAULT_ROUTES)
         self.vector_dim = vector_dim
         self.similarity_threshold = similarity_threshold

app/service/knowledge_tool_service.py

@@ -43,9 +43,9 @@ async def query_knowledge_tool(
         settings.knowledge_embedding_timeout_ms,
         gateway=DatabaseModelGateway(),
     )
-    vector_store = MilvusKnowledgeClient(
-        settings.milvus_uri, token=settings.milvus_token or None
-    )
+    # 兼容旧测试替身；真实 Settings 会优先提供本地/远程统一解析后的地址。
+    milvus_uri = getattr(settings, "resolved_milvus_uri", settings.milvus_uri)
+    vector_store = MilvusKnowledgeClient(milvus_uri, token=settings.milvus_token or None)
     # 权威元数据只读回查，确保对客答案始终来自已发布、有效的知识条目。
     async with SessionFactory() as session:
         authority = KnowledgeMysqlAuthority(session)