Commit Graph

213 Commits

Author SHA1 Message Date
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
magmueller d35b1ebc71 Draft rerun - but breaks if index change 2024-11-27 10:36:50 +01:00
magmueller 9db5f60aa0 Removed token calculation from agent to simplify 2024-11-24 19:55:38 +01:00
magmueller 8aa4321efe Merge branch 'main' into hot-fix/max-token-message-manager 2024-11-23 18:31:10 +01:00
magmueller cd688d0b6e Improved naming of output history 2024-11-23 13:12:14 +01:00
magmueller 84dd41eebf Overwrite str method 2024-11-23 12:46:08 +01:00
magmueller fd73b1642f Return trace 2024-11-22 23:32:51 +01:00
magmueller e5d7dc2e3f Agent history tests included 2024-11-22 13:08:37 +01:00
magmueller 6ab82b7921 Print error trace and fix saveing message 2024-11-22 09:40:14 +01:00
magmueller e4ed949141 Seperate results which stay in context and which not to avoid max token limit 2024-11-20 15:42:32 +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