ai-agent-book 精选快照(<2MB 代码与文档,来自 github.com/bojieli/ai-agent-book)
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
This commit is contained in:
@@ -0,0 +1,48 @@
|
||||
---
|
||||
title: "Follow up tasks"
|
||||
description: "Follow up tasks with the same browser session."
|
||||
icon: "link"
|
||||
mode: "wide"
|
||||
---
|
||||
|
||||
## Chain Agent Tasks
|
||||
|
||||
Keep your browser session alive and chain multiple tasks together. Perfect for conversational workflows or multi-step processes.
|
||||
|
||||
```python
|
||||
from dotenv import load_dotenv
|
||||
|
||||
from browser_use import Agent, Browser
|
||||
|
||||
|
||||
load_dotenv()
|
||||
|
||||
import asyncio
|
||||
|
||||
|
||||
async def main():
|
||||
browser = Browser(keep_alive=True)
|
||||
|
||||
await browser.start()
|
||||
|
||||
agent = Agent(task='search for browser-use.', browser_session=browser)
|
||||
await agent.run(max_steps=2)
|
||||
agent.add_new_task('return the title of first result')
|
||||
await agent.run()
|
||||
|
||||
await browser.kill()
|
||||
|
||||
asyncio.run(main())
|
||||
```
|
||||
|
||||
## How It Works
|
||||
|
||||
1. **Persistent Browser**: `BrowserProfile(keep_alive=True)` prevents browser from closing between tasks
|
||||
2. **Task Chaining**: Use `agent.add_new_task()` to add follow-up tasks
|
||||
3. **Context Preservation**: Agent maintains memory and browser state across tasks
|
||||
4. **Interactive Flow**: Perfect for conversational interfaces
|
||||
5. **Break down long flows**: If you have very long flows, you can keep the browser alive and send new agents to it.
|
||||
|
||||
<Note>
|
||||
The browser session remains active throughout the entire chain, preserving all cookies, local storage, and page state.
|
||||
</Note>
|
||||
Reference in New Issue
Block a user