Commit Graph

21 Commits

Author SHA1 Message Date
Nick Sweeting
a17ee667d8 dont repr screenshot in terminal 2025-05-22 07:01:10 -07:00
Nick Sweeting
86ec6a78b0 new BrowserSession and BrowserProfile design, renamed BrowserState to BrowserStateSummary and more 2025-05-20 02:31:54 -07:00
Nick Sweeting
23252192a0 remove non-functional group tabs code 2025-05-04 19:40:27 +08:00
Nick Sweeting
2be4ba4f70 more pyupgrade changes 2025-05-02 20:50:21 +08:00
Nick Sweeting
fb6fa259a8 apply ruff safe fixes 2025-03-28 18:11:36 -07:00
Nick Sweeting
d95527ab27 Merge branch 'main' into enhancement/add_tabGroups_chrome 2025-03-25 16:34:08 -07:00
Nick Sweeting
73369f910c fix discovery of elements that have both shadow and non shadow child nodes 2025-03-24 14:28:00 -07:00
SwapnilSonker
92fe9212a9 #544 issue resolved , used chrometabs api 2025-02-08 22:48:46 +05:30
magmueller
e7c49bfcac Error handling for restricted domains 2025-01-23 16:53:23 -08:00
magmueller
66ea4a3509 Restric urls 2025-01-23 15:44:14 -08:00
magmueller
2bd6e20953 Include how many pixels are above / below 2025-01-20 10:12:12 -08:00
magmueller
60fbbcae93 Split HistoryTreeProcessor in views and service 2024-12-03 09:26:17 +01:00
magmueller
c581a1b251 First draft multi-action runs 2024-12-01 21:00:22 +01:00
magmueller
9dfc1f3faf Seperate class for browserhistory - fixed type errors 2024-11-28 23:59:49 +01:00
magmueller
519881a7b3 Rerun works 2024-11-28 21:10:25 +01:00
magmueller
de7e38b75c History is saved and loaded 2024-11-28 19:37:18 +01:00
Gregor Žunič
829ed138fd clicking version - still missing iframe/shadow elements penetration 2024-11-25 21:45:05 +01:00
Gregor Žunič
b0c390f2c0 fixed multi tab management, clicking timeouts, general bugfixes 2024-11-20 17:33:49 +01:00
Gregor Žunič
155f49acc4 started the switch from selenium to playwright 2024-11-18 20:38:00 +01:00
Gregor Žunič
89c63fdd63 Added custom actions registry and fixed extraction layer (#20)
* 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>
2024-11-15 21:42:02 +01:00
Gregor Žunič
68201df624 src -> browser_use 2024-11-06 18:18:00 +01:00