chore: 清理违反底座规则的死代码并修正接口文档编号

- 删除生产死代码 app/service/knowledge_tool_service.py 与
  app/infrastructure/milvus_knowledge_adapter.py：后者硬编码 Milvus 字段名，
  违反 AGENTS.md §E，且仅被前者引用；生产检索链路实际走
  knowledge_search_tool -> KnowledgeSearchService -> knowledge_schema 运行时探测。
- 删除上述两模块的单测，以及依赖 legacy 位置参数构造的
  tests/unit/service/test_knowledge_retrieval.py。
- app/service/knowledge_retrieval_service.py 整文件回退底座版本，
  移除 legacy 双构造与重复检索实现。
- docs/05-接口文档.md：客服画像候选改登记为 §8.5，恢复 §8.2 解析知识引用；
  既有 §8.1-§8.4 编号全部保持，修复此前出现两个 8.3 的问题。
- app/model/profile.py：current_customer_id 改为普通可空列映射，与
  alembic/baseline_generated.sql 及真实库一致；原 Computed 声明会让 ORM 把该列
  从 INSERT 中排除，与「必须显式写入」的实际 schema 不符。
- 新增 docs/客服Agent接入底座扩展说明_v1.md，供集成分支评审逐项确认。

验证：pytest tests/unit tests/contract -> 1275 passed, 2 skipped, 0 failed；
ruff check app tests tools alembic 通过；mypy app 通过（244 个源文件）。

tests/unit/infrastructure/test_milvus_knowledge_adapter.py

@@ -1,47 +0,0 @@
-import pytest
-
-from app.core.errors import ForbiddenAgentError
-from app.infrastructure.milvus_knowledge_adapter import MilvusKnowledgeClient
-
-
-class FakeMilvus:
-    def __init__(self) -> None:
-        self.kwargs = None
-
-    async def search(self, **kwargs):
-        self.kwargs = kwargs
-        return [[{
-            "distance": 0.91,
-            "entity": {
-                "knowledge_id": "101",
-                "snippet": "开户说明",
-                "title": "基金开户",
-                "tags": ["开户"],
-                "version": "v1",
-            },
-        }]]
-
-
-@pytest.mark.asyncio
-async def test_knowledge_adapter_uses_cosine_and_minimal_public_projection() -> None:
-    client = MilvusKnowledgeClient("http://unused")
-    fake = FakeMilvus()
-    client._client = fake
-
-    hits = await client.search("fin_faq_collection", [0.1] * 1024, 3)
-
-    assert hits[0]["knowledge_id"] == "101"
-    assert hits[0]["snippet"] == "开户说明"
-    assert hits[0]["score"] == 0.91
-    assert fake.kwargs["collection_name"] == "fin_faq_collection"
-    assert fake.kwargs["limit"] == 3
-    assert fake.kwargs["search_params"] == {"metric_type": "COSINE"}
-    assert fake.kwargs["output_fields"] == ["knowledge_id", "title", "snippet", "tags", "version"]
-
-
-@pytest.mark.asyncio
-async def test_knowledge_adapter_rejects_non_public_collection() -> None:
-    client = MilvusKnowledgeClient("http://unused")
-
-    with pytest.raises(ForbiddenAgentError):
-        await client.search("customer_vectors", [0.1] * 1024, 3)