chore: import upstream snapshot with attribution

docs/zh/sessions/sqlalchemy_session.md

@@ -0,0 +1,80 @@
+---
+search:
+  exclude: true
+---
+# SQLAlchemy 会话
+
+`SQLAlchemySession` 使用 SQLAlchemy 提供生产就绪的会话实现，使你可以使用 SQLAlchemy 支持的任何数据库（PostgreSQL、MySQL、SQLite 等）进行会话存储。
+
+## 安装
+
+SQLAlchemy 会话需要 `sqlalchemy` 额外依赖：
+
+```bash
+pip install openai-agents[sqlalchemy]
+```
+
+## 快速开始
+
+### 使用数据库 URL
+
+最简单的入门方式：
+
+```python
+import asyncio
+from agents import Agent, Runner
+from agents.extensions.memory import SQLAlchemySession
+
+async def main():
+    agent = Agent("Assistant")
+    
+    # Create session using database URL
+    session = SQLAlchemySession.from_url(
+        "user-123",
+        url="sqlite+aiosqlite:///:memory:",
+        create_tables=True
+    )
+    
+    result = await Runner.run(agent, "Hello", session=session)
+    print(result.final_output)
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+### 使用现有引擎
+
+适用于已有 SQLAlchemy 引擎的应用：
+
+```python
+import asyncio
+from agents import Agent, Runner
+from agents.extensions.memory import SQLAlchemySession
+from sqlalchemy.ext.asyncio import create_async_engine
+
+async def main():
+    # Create your database engine
+    engine = create_async_engine("postgresql+asyncpg://user:pass@localhost/db")
+    
+    agent = Agent("Assistant")
+    session = SQLAlchemySession(
+        "user-456",
+        engine=engine,
+        create_tables=True
+    )
+    
+    result = await Runner.run(agent, "Hello", session=session)
+    print(result.final_output)
+    
+    # Clean up
+    await engine.dispose()
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+
+## API 参考
+
+- [`SQLAlchemySession`][agents.extensions.memory.sqlalchemy_session.SQLAlchemySession] - 主类
+- [`Session`][agents.memory.session.Session] - 基础会话协议