会话

Agents SDK 提供了内置会话内存，可以自动维护多次代理运行之间的对话历史记录，无需手动处理 .to_input_list() 来进行轮次间的转换。

会话存储特定会话的对话历史记录，允许代理在无需显式手动内存管理的情况下保持上下文。这对于构建聊天应用程序或多轮对话特别有用，您希望代理记住之前的交互。

快速上手

from agents import Agent, Runner, SQLiteSession

# Create agent
agent = Agent(
    name="Assistant",
    instructions="Reply very concisely.",
)

# Create a session instance with a session ID
session = SQLiteSession("conversation_123")

# First turn
result = await Runner.run(
    agent,
    "What city is the Golden Gate Bridge in?",
    session=session
)
print(result.final_output)  # "San Francisco"

# Second turn - agent automatically remembers previous context
result = await Runner.run(
    agent,
    "What state is it in?",
    session=session
)
print(result.final_output)  # "California"

# Also works with synchronous runner
result = Runner.run_sync(
    agent,
    "What's the population?",
    session=session
)
print(result.final_output)  # "Approximately 39 million"

工作原理

启用会话内存时

1. 每次运行前：运行器会自动检索会话的对话历史记录，并将其添加到输入项的前面。
2. 每次运行后：在运行过程中生成的所有新项目（用户输入、助手回复、工具调用等）都会自动存储在会话中。
3. 上下文保留：使用相同会话的每个后续运行都包含完整的对话历史记录，从而使代理能够保持上下文。

这消除了手动调用 .to_input_list() 以及在运行之间管理对话状态的需要。

内存操作

基本操作

会话支持几种管理对话历史记录的操作

from agents import SQLiteSession

session = SQLiteSession("user_123", "conversations.db")

# Get all items in a session
items = await session.get_items()

# Add new items to a session
new_items = [
    {"role": "user", "content": "Hello"},
    {"role": "assistant", "content": "Hi there!"}
]
await session.add_items(new_items)

# Remove and return the most recent item
last_item = await session.pop_item()
print(last_item)  # {"role": "assistant", "content": "Hi there!"}

# Clear all items from a session
await session.clear_session()

使用 pop_item 进行修正

当您想要撤销或修改对话中的最后一个项目时，pop_item 方法特别有用

from agents import Agent, Runner, SQLiteSession

agent = Agent(name="Assistant")
session = SQLiteSession("correction_example")

# Initial conversation
result = await Runner.run(
    agent,
    "What's 2 + 2?",
    session=session
)
print(f"Agent: {result.final_output}")

# User wants to correct their question
assistant_item = await session.pop_item()  # Remove agent's response
user_item = await session.pop_item()  # Remove user's question

# Ask a corrected question
result = await Runner.run(
    agent,
    "What's 2 + 3?",
    session=session
)
print(f"Agent: {result.final_output}")

会话类型

SDK 提供了几种会话实现，用于不同的用例

OpenAI Conversations API 会话

通过 OpenAIConversationsSession 使用 OpenAI 的 Conversations API。

from agents import Agent, Runner, OpenAIConversationsSession

# Create agent
agent = Agent(
    name="Assistant",
    instructions="Reply very concisely.",
)

# Create a new conversation
session = OpenAIConversationsSession()

# Optionally resume a previous conversation by passing a conversation ID
# session = OpenAIConversationsSession(conversation_id="conv_123")

# Start conversation
result = await Runner.run(
    agent,
    "What city is the Golden Gate Bridge in?",
    session=session
)
print(result.final_output)  # "San Francisco"

# Continue the conversation
result = await Runner.run(
    agent,
    "What state is it in?",
    session=session
)
print(result.final_output)  # "California"

SQLite 会话

默认的、轻量级的会话实现，使用 SQLite

from agents import SQLiteSession

# In-memory database (lost when process ends)
session = SQLiteSession("user_123")

# Persistent file-based database
session = SQLiteSession("user_123", "conversations.db")

# Use the session
result = await Runner.run(
    agent,
    "Hello",
    session=session
)

SQLAlchemy 会话

使用 SQLAlchemy 支持的任何数据库的生产就绪型会话

from agents.extensions.memory import SQLAlchemySession

# Using database URL
session = SQLAlchemySession.from_url(
    "user_123",
    url="postgresql+asyncpg://user:pass@localhost/db",
    create_tables=True
)

# Using existing engine
from sqlalchemy.ext.asyncio import create_async_engine
engine = create_async_engine("postgresql+asyncpg://user:pass@localhost/db")
session = SQLAlchemySession("user_123", engine=engine, create_tables=True)

请参阅 SQLAlchemy 会话 以获取详细文档。

高级 SQLite 会话

具有对话分支、使用情况分析和结构化查询的增强型 SQLite 会话

from agents.extensions.memory import AdvancedSQLiteSession

# Create with advanced features
session = AdvancedSQLiteSession(
    session_id="user_123",
    db_path="conversations.db",
    create_tables=True
)

# Automatic usage tracking
result = await Runner.run(agent, "Hello", session=session)
await session.store_run_usage(result)  # Track token usage

# Conversation branching
await session.create_branch_from_turn(2)  # Branch from turn 2

请参阅 高级 SQLite 会话 以获取详细文档。

加密会话

用于任何会话实现的透明加密包装器

from agents.extensions.memory import EncryptedSession, SQLAlchemySession

# Create underlying session
underlying_session = SQLAlchemySession.from_url(
    "user_123",
    url="sqlite+aiosqlite:///conversations.db",
    create_tables=True
)

# Wrap with encryption and TTL
session = EncryptedSession(
    session_id="user_123",
    underlying_session=underlying_session,
    encryption_key="your-secret-key",
    ttl=600  # 10 minutes
)

result = await Runner.run(agent, "Hello", session=session)

请参阅 加密会话 以获取详细文档。

其他会话类型

还有一些其他的内置选项。请参阅 examples/memory/ 和 extensions/memory/ 下的源代码。

会话管理

会话 ID 命名

使用有意义的会话 ID 来帮助您组织对话

• 基于用户："user_12345"
• 基于线程："thread_abc123"
• 基于上下文："support_ticket_456"

内存持久化

• 使用内存中的 SQLite (SQLiteSession("session_id")) 进行临时对话
• 使用基于文件的 SQLite (SQLiteSession("session_id", "path/to/db.sqlite")) 进行持久对话
• 使用 SQLAlchemy 驱动的会话 (SQLAlchemySession("session_id", engine=engine, create_tables=True)) 用于与 SQLAlchemy 支持的现有数据库的生产系统
• 使用 Dapr 状态存储会话 (DaprSession.from_address("session_id", state_store_name="statestore", dapr_address="localhost:50001")) 用于支持 30 多个数据库后端、内置遥测、跟踪和数据隔离的生产云原生部署
• 当您希望将历史记录存储在 OpenAI Conversations API 中时，使用 OpenAI 托管存储 (OpenAIConversationsSession())
• 使用加密会话 (EncryptedSession(session_id, underlying_session, encryption_key)) 使用透明加密和基于 TTL 的过期时间来包装任何会话
• 考虑为其他生产系统（Redis、Django 等）实现自定义会话后端，以用于更高级的用例

多个会话

from agents import Agent, Runner, SQLiteSession

agent = Agent(name="Assistant")

# Different sessions maintain separate conversation histories
session_1 = SQLiteSession("user_123", "conversations.db")
session_2 = SQLiteSession("user_456", "conversations.db")

result1 = await Runner.run(
    agent,
    "Help me with my account",
    session=session_1
)
result2 = await Runner.run(
    agent,
    "What are my charges?",
    session=session_2
)

会话共享

# Different agents can share the same session
support_agent = Agent(name="Support")
billing_agent = Agent(name="Billing")
session = SQLiteSession("user_123")

# Both agents will see the same conversation history
result1 = await Runner.run(
    support_agent,
    "Help me with my account",
    session=session
)
result2 = await Runner.run(
    billing_agent,
    "What are my charges?",
    session=session
)

完整示例

这是一个完整的示例，展示了会话内存的作用

import asyncio
from agents import Agent, Runner, SQLiteSession


async def main():
    # Create an agent
    agent = Agent(
        name="Assistant",
        instructions="Reply very concisely.",
    )

    # Create a session instance that will persist across runs
    session = SQLiteSession("conversation_123", "conversation_history.db")

    print("=== Sessions Example ===")
    print("The agent will remember previous messages automatically.\n")

    # First turn
    print("First turn:")
    print("User: What city is the Golden Gate Bridge in?")
    result = await Runner.run(
        agent,
        "What city is the Golden Gate Bridge in?",
        session=session
    )
    print(f"Assistant: {result.final_output}")
    print()

    # Second turn - the agent will remember the previous conversation
    print("Second turn:")
    print("User: What state is it in?")
    result = await Runner.run(
        agent,
        "What state is it in?",
        session=session
    )
    print(f"Assistant: {result.final_output}")
    print()

    # Third turn - continuing the conversation
    print("Third turn:")
    print("User: What's the population of that state?")
    result = await Runner.run(
        agent,
        "What's the population of that state?",
        session=session
    )
    print(f"Assistant: {result.final_output}")
    print()

    print("=== Conversation Complete ===")
    print("Notice how the agent remembered the context from previous turns!")
    print("Sessions automatically handles conversation history.")


if __name__ == "__main__":
    asyncio.run(main())

自定义会话实现

您可以通过创建一个遵循 Session 协议的类来实现您自己的会话内存

from agents.memory.session import SessionABC
from agents.items import TResponseInputItem
from typing import List

class MyCustomSession(SessionABC):
    """Custom session implementation following the Session protocol."""

    def __init__(self, session_id: str):
        self.session_id = session_id
        # Your initialization here

    async def get_items(self, limit: int | None = None) -> List[TResponseInputItem]:
        """Retrieve conversation history for this session."""
        # Your implementation here
        pass

    async def add_items(self, items: List[TResponseInputItem]) -> None:
        """Store new items for this session."""
        # Your implementation here
        pass

    async def pop_item(self) -> TResponseInputItem | None:
        """Remove and return the most recent item from this session."""
        # Your implementation here
        pass

    async def clear_session(self) -> None:
        """Clear all items for this session."""
        # Your implementation here
        pass

# Use your custom session
agent = Agent(name="Assistant")
result = await Runner.run(
    agent,
    "Hello",
    session=MyCustomSession("my_session")
)

社区会话实现

社区开发了额外的会话实现

包	描述
openai-django-sessions	基于 Django ORM 的会话，用于任何 Django 支持的数据库（PostgreSQL、MySQL、SQLite 等）

如果您构建了一个会话实现，请随时提交文档 PR 以将其添加到此处！

API 参考

有关详细的 API 文档，请参阅

• Session - 协议接口
• OpenAIConversationsSession - OpenAI Conversations API 实现
• SQLiteSession - 基本 SQLite 实现
• SQLAlchemySession - SQLAlchemy 驱动的实现
• DaprSession - Dapr 状态存储实现
• AdvancedSQLiteSession - 具有分支和分析的增强型 SQLite
• EncryptedSession - 用于任何会话的加密包装器