Long tasks

​

Budgets

• In the delivery-only turn, the agent is told to stop browsing and hand in what it has, with success=False if the task is unfinished.
• Each Python cell has a 120-second limit. A cell that runs over restarts the agent’s Python worker: files and browser state survive, Python variables do not.

​

Partial results

from browser_use import Agent

agent = Agent(
    'List the titles of the first 150 stories on Hacker News, one page at a time. '
    "After each page, save the titles you have with checkpoint('titles.json', titles, partial=True)."
)
result = agent.run_sync(max_steps=3, timeout=600)
print(result.status, result.success)  # usually 'completed False': the delivery turn handed in what it had
print(result.final_result() or result.partial)

​

Follow-up tasks

import asyncio

from browser_use import Agent, Browser


async def main():
    browser = Browser(keep_alive=True)
    agent = Agent('Open https://news.ycombinator.com and return the top story title', browser=browser)
    try:
        print((await agent.run()).final_result())
        agent.add_new_task('Now open its comments and return the number of comments')
        print((await agent.run()).final_result())
    finally:
        await agent.close()
        await browser.stop()


asyncio.run(main())

​

Context

• Gateway and OpenAI (Responses API): server-side, once a request passes 150k tokens.
• Everything else: past 75% of max_context_chars (default: 4 characters per token of the model’s context window, or 240k when unknown) or 65% of the window in tokens, older turns are replaced by a summary checkpoint written by the same model. If the provider still rejects a request as over its context window, the agent compacts once and sends it again. An evidence archive in the workspace keeps the earlier messages (secrets redacted, images omitted).

​

Retries

• A rate limit, overload, 5xx or dropped connection from the provider is retried once per run, after the provider’s Retry-After (at most 60 seconds). Providers whose SDK already retries (OpenAI, Anthropic, OpenAI-compatible) are left to their SDK.
• A failure inside an HTTP 200 (a failed or cut-off stream, or a status=failed body with server_error, overloaded or request_timeout) gets the same one retry.
• Gateway and OpenAI (Responses API) requests are streamed: 300 seconds for the first event, then up to 930 seconds in all. Other models get 300 seconds per request. A request that gets no answer in time is asked again, and none runs past the start of the delivery turn.
• A dropped connection’s result.error names its cause, for example (OSError: [Errno 24] Too many open files).
• A failed cell is not retried automatically. The model reads the error and decides, within max_steps.

​

Live progress

import logging

from browser_use import Agent


class Progress(logging.Handler):
    def emit(self, record):
        print('progress:', record.getMessage())  # send to your UI, a websocket, an MCP client...


logging.getLogger('browser_use').addHandler(Progress())

Agent('What is the title of https://example.com?').run_sync()

​

Stop early