Adds bu-2-0-mini-preview as an accepted model id and makes it the
constructor default, so a bare ChatBrowserUse() now routes there.
bu-2-0 is unchanged: still accepted, still documented as the premium
option, and bu-latest still resolves to it. Keeping 'latest' on the
stable line means existing callers pinned to that alias do not silently
move onto a preview model; only the bare-constructor default moves.
Pricing is registered alongside the model so cost tracking does not
silently report $0 for what is now the default. This model has no cache
discount, so cached reads bill at the input rate.
Examples, README and the model reference are updated to the new default.
The model reference also claimed bu-latest resolved to bu-1-0, which has
not been true since bu-2-0 shipped; corrected here.
Update README and examples to use the new ChatBrowserUse LLM and BrowserUse API key for authentication. This simplifies setup and aligns with the new API.
Co-authored-by: mailmertunsal <mailmertunsal@gmail.com>
- Updated `simple.py` to initialize `Browser` and `Tools` instances, improving agent configuration.
- Fixed action decorator in `notification.py` by removing trailing space for consistency.
- Adjusted test behavior in `test_browser_session_tab_management.py` to skip tests on initial tab count issues, improving test reliability.
- Stopped server in `test_browser_watchdog_downloads_upload_full_circle.py` to ensure proper cleanup before skipping tests.
These changes aim to enhance clarity and maintainability across examples and tests.
- Add --no-thinking flag to disable thinking in agent system prompt
- Default is true (thinking enabled) for backward compatibility
- Pass thinking parameter through entire evaluation pipeline
- Update GitHub Actions workflow to handle thinking parameter
Saurav Panda