- Updated GoToUrlAction to include a new_tab parameter for opening URLs in a new tab or navigating in the current tab.
- Removed the OpenTabAction as its functionality is now integrated into GoToUrlAction.
- Enhanced scroll action to allow scrolling up or down based on a boolean parameter.
- Cleaned up commented-out code related to accessibility tree retrieval for better readability.
* Add http_credentials to browser context.
* Detect index change caused by page change in `multi_act`
* Fix: Add sameSite cookie validation and auto-correction
* added drag drop action
* added drag drop action
* pre-commit run -a (again)
* added active_tab state management
* add anthropic RateLimitError to list of defined rate limit errors
* Add Retry handling to bedrock example
* fix pydantic issue causing config to be overwritten
* fix config setup
* Add botocore, organize imports
* ignore langchain beta warnings
* silence pydantic deprecation warnings
* Update bedrock_claude for ruff
* ruff checks
* Update pyproject.toml and bedrock_claude.py
* ignore signal registration errors in edge case environments
* ruff fixes
* add example of getting 2FA code from 1password
* add rebrowser and creepjs to stealth tests
* Fix typos discovered by codespell
* uv add --dev codespell
* Update browser_use/browser/context.py
* lint
* Add explanations override_system_message and extend_system_message
* Update custom-functions.mdx
.get_current_page() is an async function which have to be awaited.
* Fix: Remove unnecessary await from _verified_api_keys
* Fix: Correct indentation for cookie loading log message in BrowserContext
* Fix: resolve undefined response variable in Deepseek model raw tool calling mode
* fix: increment consecutive_failure on every step error
* Fix azure example not working due to agent memory changes
* dont expose debug port on all addresses and keep security enabled by default
* custom browser addition
---------
Co-authored-by: Bartlomiej Wietrak <bartekwietrak@gmail.com>
Co-authored-by: Alin Jiang <alineveryday@outlook.com>
Co-authored-by: dipfocus <dipfocus@gmail.com>
Co-authored-by: PaperBoardOfficial <hiremohitforsoftwarerole@gmail.com>
Co-authored-by: Christian Clauss <cclauss@me.com>
Co-authored-by: Alezander9 <alexander.j.yue@gmail.com>
Co-authored-by: dheerajoruganty <db2winfb@gmail.com>
Co-authored-by: Nick Sweeting <git@sweeting.me>
Co-authored-by: Dheeraj Oruganty <53569374+dheerajoruganty@users.noreply.github.com>
Co-authored-by: Bart <46058081+b0rgcube@users.noreply.github.com>
Co-authored-by: Nick Sweeting <github@sweeting.me>
Co-authored-by: pppp606 <ppppp303@gmail.com>
Co-authored-by: Oswy <74738120+oswy-cpu@users.noreply.github.com>
Co-authored-by: BurnyCoder <happymancz@email.cz>
Co-authored-by: zhushijie <mr.zhushijie@gmail.com>
Co-authored-by: john-rtr <jonathan.ratier@gmail.com>
Co-authored-by: mathisarends-viadee <mathis.arends@viadee.de>
Co-authored-by: lorenss-m <saeclmusic@gmail.com>
Co-authored-by: Magnus Müller <67061560+MagMueller@users.noreply.github.com>
- Introduce warning message for the last step in the agent
- Add `success` parameter to `ActionResult` and `DoneAction`
- Modify `AgentStepInfo` to check for last step
- Update `AgentHistoryList` methods to handle optional values and success status
* Validator
* Test mind2web
* Cleaned up logger
* Pytest logger
* Cleaned up logger
* Disable flag for human input
* Multiple clicks per button
* Multiple clicks per button
* More structured system prompt
* Fields with description
* System prompt example
* One logger
* Cleaner logging
* Log step in step function
* Fix critical clicking error - wrong argument used
* Improved thought process of agent
* Improve system prompt
* Remove human input message
* Custome action registration
* Pydantic model for custom actions
* Pydantic model for custome output
* Runs through, model outputs functions, but not called yet
* Work in progress - description for custome actions
* Description works, but schema not yet
* Model can call the right action - but is not executed
* Seperate is_controller_action and is_custom_action
* Works! Model can call custom function
* Use registry for action, but result is not feed back to model
* Include result in messages
* Works with custom function - but typing is not correct
* Renamed registry
* First test cases
* Captcha tests
* Pydantic for tests
* Improve prompts for multy step
* System prompt structure
* Handle errors like validation error
* Refactor error handling in agent
* Refactor error handling in agent
* Improved logging
* Update view
* Fix click parameter to index
* Simplify dynamic actions
* Use run instead of step
* Rename history
* Rename AgentService to Agent
* Rename ControllerService to Controller
* Pytest file
* Rename get state
* Rename BrowserService
* reversed dom extraction recursion to while
* Rename use_vision
* Rename use_vision
* reversed dom tree items and made browser less anoying
* Renaming and fixing type errors
* Renamed class names for agent
* updated requirements
* Update prompt
* Action registration works for user and controller
* Fix done call by returning ActionResult
* Fix if result is none
* Rename AgentOutput and ActionModel
* Improved prompt Passes 6/8 tests from test_agent_actions
* Calculate token cost
* Improve display
* Simplified logger
* Test function calling
* created super simple xpath extraction algo
* Tests logging
* tiny fixes to dom extraction
* Remove test
* Dont log number of clicks
* Pytest file
* merged per element js checks
* Check if driver is still open
* super fast processing
* fixed agent planning and stuff
* Fix example
* Fix example
* Improve error
* Improved error correction
* New line for step
* small type error fixes
* Test for pydantic
* Fix line
* Removed sample
* fixed readme and examples
---------
Co-authored-by: magmueller <mamagnus00@gmail.com>
