-
-
Notifications
You must be signed in to change notification settings - Fork 2.1k
en dev star guides session control
v3.4.36 and above
Why do we need session control? Consider a Chinese idiom chain game plugin where a user or group needs to have multiple conversations with the bot rather than a one-time command. This is when session control becomes necessary.
User: /idiom-chain
Bot: Please send an idiom
User: One horse takes the lead (一马当先)
Bot: Foresight (先见之明)
User: Keen observation (明察秋毫)
...AstrBot provides out-of-the-box session control functionality:
Import:
import astrbot.api.message_components as Comp
from astrbot.core.utils.session_waiter import (
session_waiter,
SessionController,
)Code within the handler can be written as follows:
from astrbot.api.event import filter, AstrMessageEvent
@filter.command("idiom-chain")
async def handle_empty_mention(self, event: AstrMessageEvent):
"""Idiom chain game implementation"""
try:
yield event.plain_result("Please send an idiom~")
# How to use the session controller
@session_waiter(timeout=60, record_history_chains=False) # Register a session controller with a 60-second timeout, without recording message history
async def empty_mention_waiter(controller: SessionController, event: AstrMessageEvent):
idiom = event.message_str # The idiom sent by the user, e.g., "one horse takes the lead"
if idiom == "exit": # If the user wants to exit the idiom chain game by typing "exit"
await event.send(event.plain_result("Exited the idiom chain game~"))
controller.stop() # Stop the session controller, which will end immediately.
return
if len(idiom) != 4: # If the user's input is not a 4-character idiom
await event.send(event.plain_result("The idiom must be four characters~")) # Send a reply, cannot use yield
return
# Exit the current method without executing subsequent logic, but the session is not interrupted; subsequent user input will still enter the current session
# ...
message_result = event.make_result()
message_result.chain = [Comp.Plain("Foresight")] # import astrbot.api.message_components as Comp
await event.send(message_result) # Send a reply, cannot use yield
controller.keep(timeout=60, reset_timeout=True) # Reset timeout to 60s. If not reset, it will continue the previous timeout countdown.
# controller.stop() # Stop the session controller, which will end immediately.
# If history chains are recorded, you can retrieve them via controller.get_history_chains()
try:
await empty_mention_waiter(event)
except TimeoutError as _: # When timeout occurs, the session controller will raise TimeoutError
yield event.plain_result("You timed out!")
except Exception as e:
yield event.plain_result("An error occurred, please contact the administrator: " + str(e))
finally:
event.stop_event()
except Exception as e:
logger.error("handle_empty_mention error: " + str(e))Once the session controller is activated, messages subsequently sent by that sender will first be processed by the empty_mention_waiter function you defined above, until the session controller is stopped or times out.
Used by developers to control whether a session should end, and to retrieve message history chains.
- keep(): Keep this session alive
- timeout (float): Required. Session timeout duration.
- reset_timeout (bool): When set to True, it resets the timeout; timeout must be > 0, if <= 0 the session ends immediately. When set to False, it maintains the original timeout; new timeout = remaining timeout + timeout (can be < 0)
- stop(): End this session
- get_history_chains() -> List[List[Comp.BaseMessageComponent]]: Retrieve message history chains
By default, the AstrBot session controller uses sender_id (the sender's ID) as the identifier for distinguishing different sessions. If you want to treat an entire group as one session, you need to customize the session ID filter.
import astrbot.api.message_components as Comp
from astrbot.core.utils.session_waiter import (
session_waiter,
SessionFilter,
SessionController,
)
# Using the handler from above
# ...
class CustomFilter(SessionFilter):
def filter(self, event: AstrMessageEvent) -> str:
return event.get_group_id() if event.get_group_id() else event.unified_msg_origin
await empty_mention_waiter(event, session_filter=CustomFilter()) # Pass in session_filter here
# ...After this setup, when a user in a group sends a message, the session controller will treat the entire group as one session, and messages from other users in the group will also be considered part of the same session.
You can even use this feature to enable team-based activities within groups!
- 首页
- 文档入口
- Top Level
- community events
- deploy
- dev
- others
- platform
- 接入 OneBot v11 协议实现
- 接入钉钉 DingTalk
- 接入 Discord
- 接入 Kook
- 接入飞书
- 接入 LINE
- 接入 Matrix
- 接入 Mattermost
- 接入 Misskey 平台
- 接入 QQ 官方机器人平台
- 通过 QQ官方机器人 接入 QQ (Webhook)
- 通过 QQ官方机器人 接入 QQ (Websockets)
- 接入 Satori 协议
- 接入 server-satori (基于 Koishi)
- 接入 Slack
- 接入消息平台
- 接入 Telegram
- 接入 VoceChat
- AstrBot 接入企业微信
- 接入企业微信智能机器人平台
- AstrBot 接入微信公众平台
- 接入个人微信
- providers
- use
- Home
- Docs Entry
- Top Level
- config
- deploy
- Deploy AstrBot on 1Panel
- Deploy AstrBot on BT Panel
- Deploy AstrBot on CasaOS
- Deploy AstrBot from Source Code
- Community-Provided Deployment Methods
- Deploy via Compshare
- Deploy AstrBot with Docker
- Deploy AstrBot with Kubernetes
- Deploy AstrBot with AstrBot Launcher
- Other Deployments
- Package Manager Deployment (uv)
- Installation via System Package Manager
- Preface
- dev
- ospp
- others
- platform
- Connect OneBot v11 Protocol Implementations
- Connect to DingTalk
- Connecting to Discord
- Connect to KOOK
- Connecting to Lark
- Connecting to LINE
- Connecting to Matrix
- Connecting to Mattermost
- Connecting to Misskey Platform
- Connect QQ Official Bot
- Connect QQ via QQ Official Bot (Webhook)
- Connect QQ via QQ Official Bot (Websockets)
- Connect to Satori Protocol
- Connect server-satori (Koishi)
- Connecting to Slack
- Messaging Platforms
- Connecting to Telegram
- Connect to VoceChat
- Connect AstrBot to WeCom
- Connect to WeCom AI Bot Platform
- Connect AstrBot to WeChat Official Account Platform
- Connect Personal WeChat
- providers
- 接入 302.AI
- Agent Runners
- Built-in Agent Runner
- Connect to Coze
- Connect to Alibaba Cloud Bailian Application
- Connect to DeerFlow
- Connect to Dify
- Connect AIHubMix
- coze
- dashscope
- dify
- 大语言模型提供商
- NewAPI
- 接入 PPIO 派欧云
- 接入 LM Studio 使用 DeepSeek-R1 等模型
- Integrating Ollama
- Connecting to SiliconFlow
- Connecting Model Services
- Connecting to TokenPony
- use
- Agent Runner
- Agent Sandbox Environment ⛵️
- astrbot sandbox
- Docker-based Code Interpreter
- Built-in Commands
- Computer Use
- Context Compression
- Custom Rules
- Function Calling
- AstrBot Knowledge Base
- MCP
- AstrBot Star
- Proactive Capabilities
- Anthropic Skills
- Agent Handoff and SubAgent
- Unified Webhook Mode
- Web Search
- Admin Panel