feat: add governed public knowledge retrieval

app/service/knowledge_tool_service.py

@@ -0,0 +1,55 @@
+from typing import Protocol
+
+from app.core.config import get_settings
+from app.core.contracts import RequestContext
+from app.core.knowledge_contracts import KnowledgeQuery, KnowledgeSearchResult
+from app.infrastructure.db import SessionFactory
+from app.infrastructure.milvus_knowledge_adapter import MilvusKnowledgeClient
+from app.service.knowledge_authority import KnowledgeMysqlAuthority
+from app.service.knowledge_config import KnowledgeRuntimeConfig
+from app.service.knowledge_retrieval_service import KnowledgeRetrievalService
+from app.service.model_gateway import DatabaseModelGateway
+
+
+class EmbeddingGateway(Protocol):
+    async def embed(self, *, endpoint_code: str, text: str, timeout_ms: int) -> list[float]: ...
+
+
+class DatabaseEmbeddingAdapter:
+    def __init__(
+        self, endpoint_code: str, timeout_ms: int, *, gateway: EmbeddingGateway
+    ) -> None:
+        self._endpoint_code = endpoint_code
+        self._timeout_ms = timeout_ms
+        self._gateway = gateway
+
+    async def embed(self, text: str) -> list[float]:
+        return await self._gateway.embed(
+            endpoint_code=self._endpoint_code, text=text, timeout_ms=self._timeout_ms
+        )
+
+
+async def query_knowledge_tool(
+    arguments: KnowledgeQuery, context: RequestContext
+) -> KnowledgeSearchResult:
+    settings = get_settings()
+    if not settings.knowledge_embedding_endpoint_code:
+        return KnowledgeSearchResult(
+            degraded=True, degradation_reason="embedding_endpoint_unconfigured"
+        )
+    # 知识向量端点与默认聊天端点隔离，避免回答模型被误用于检索。
+    embedder = DatabaseEmbeddingAdapter(
+        settings.knowledge_embedding_endpoint_code,
+        settings.knowledge_embedding_timeout_ms,
+        gateway=DatabaseModelGateway(),
+    )
+    vector_store = MilvusKnowledgeClient(
+        settings.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)
+        service = KnowledgeRetrievalService(
+            embedder, vector_store, KnowledgeRuntimeConfig(), authority
+        )
+        return await service.search(arguments, context)