mirror of
https://github.com/browser-use/browser-use
synced 2026-05-13 17:56:35 +02:00
89c63fdd63
* 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>
46 lines
1.1 KiB
Python
46 lines
1.1 KiB
Python
from typing import Callable, Dict, Type
|
|
|
|
from pydantic import BaseModel, ConfigDict
|
|
|
|
|
|
class RegisteredAction(BaseModel):
|
|
"""Model for a registered action"""
|
|
|
|
name: str
|
|
description: str
|
|
function: Callable
|
|
param_model: Type[BaseModel]
|
|
requires_browser: bool = False
|
|
|
|
model_config = ConfigDict(arbitrary_types_allowed=True)
|
|
|
|
def prompt_description(self) -> str:
|
|
"""Get a description of the action for the prompt"""
|
|
skip_keys = ['title']
|
|
s = f'{self.description}: \n'
|
|
s += '{' + str(self.name) + ': '
|
|
s += str(
|
|
{
|
|
k: {sub_k: sub_v for sub_k, sub_v in v.items() if sub_k not in skip_keys}
|
|
for k, v in self.param_model.schema()['properties'].items()
|
|
}
|
|
)
|
|
s += '}'
|
|
return s
|
|
|
|
|
|
class ActionModel(BaseModel):
|
|
"""Base model for dynamically created action models"""
|
|
|
|
model_config = ConfigDict(arbitrary_types_allowed=True)
|
|
|
|
|
|
class ActionRegistry(BaseModel):
|
|
"""Model representing the action registry"""
|
|
|
|
actions: Dict[str, RegisteredAction] = {}
|
|
|
|
def get_prompt_description(self) -> str:
|
|
"""Get a description of all actions for the prompt"""
|
|
return '\n'.join([action.prompt_description() for action in self.actions.values()])
|