​

marvin.utilities.tools

​

Constants

​

T

T = TypeVar('T')

​

Classes

​

ResultTool

class ResultTool(type: Literal['result-tool'] = 'result-tool')

Methods:

• run

  def run(self, ctx: RunContext)
  

​

Functions

​

update_fn

def update_fn(func: Callable[..., T] | None = None, name: str | None = None, description: str | None = None) -> Callable[[Callable[..., T]], Callable[..., T]] | Callable[..., T]

Update a function’s name and optionally set its docstring.

Can be used either as a decorator with keyword arguments or as a direct function.

Args: func: The function to update (optional). If provided, updates are applied directly. If not provided, returns a decorator. name: The new name for the function (optional). If provided, must not be empty. description: Optional docstring for the function

Example:

​

As a function:

def my_fn(x): return x updated_fn = update_fn(my_fn, name=‘hello_there’)

​

As a decorator with name:

@update_fn(name=‘hello_there’) def my_fn(x): return x

​

As a decorator with name and description:

@update_fn(name=‘hello_there’, description=‘Says hello’) def my_fn(x): return x

​

As a decorator with no arguments:

@update_fn() def my_fn(x): return x

​

Works with async functions too:

@update_fn(name=‘async_hello’) async def my_async_fn(x): return x

​

wrap_tool_errors

def wrap_tool_errors(tool_fn: Callable[..., Any])

Pydantic AI doesn’t catch errors except for ModelRetry, so we need to make sure we catch them ourselves and raise a ModelRetry instead.

Parent Module: utilities