Skip to content

feat: check browser status each step + wait for captcha if being solved #2599

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 4 commits into
base: main
Choose a base branch
from

Conversation

reformedot
Copy link
Collaborator

@reformedot reformedot commented Aug 4, 2025

Summary by cubic

Added a browser status check before each agent step to wait if the browser is busy, including when a captcha is being solved.

  • New Features
    • Added methods to detect if the browser is busy using a CDP call.
    • Agent now waits for the browser to be ready before starting each step.

Copy link

github-actions bot commented Aug 4, 2025

Agent Task Evaluation Results: 1/3 (33%)

View detailed results
Task Result Reason
captcha_cloudflare ❌ Fail The agent failed to solve the captcha on the specified page, resulting in no success message or dictionary being displayed. Consequently, it could not extract the 'hostname' value, which was required to be 'example.com'. Therefore, the task was not completed successfully.
amazon_laptop ✅ Pass The agent successfully navigated to amazon.com, searched for 'laptop', and returned the name and details of the first product listing. The output includes the product title, price, rating, number of reviews, and description, fulfilling the task requirements.
browser_use_pip ❌ Fail The agent failed to provide the required pip installation command 'pip install browser-use'. Instead, it reported being blocked by Google CAPTCHA challenges and did not complete the task. Therefore, the task is incomplete and unsuccessful.

Check the evaluate-tasks job for detailed task execution logs.

@cubic-dev-ai cubic-dev-ai bot mentioned this pull request Aug 9, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant