AbstractAgent class can't be extended without importing private util module

[clhodapp]

Initial Checks

• I confirm that I'm using the latest version of Pydantic AI
• I confirm that I searched for my issue in https://github.com/pydantic/pydantic-ai/issues before opening this issue

Description

At present, the definition of AbstractAgent requires the user to implement the abstract overide method, defined as such:

@contextmanager
@abstractmethod
def override(
    self,
    *,
    deps: AgentDepsT | _utils.Unset = _utils.UNSET,
    model: models.Model | models.KnownModelName | str | _utils.Unset = _utils.UNSET,
    toolsets: Sequence[AbstractToolset[AgentDepsT]] | _utils.Unset = _utils.UNSET,
    tools: Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]] | _utils.Unset = _utils.UNSET,
) -> Iterator[None]:
    """Context manager to temporarily override agent dependencies, model, toolsets, or tools.

    This is particularly useful when testing.
    You can find an example of this [here](../testing.md#overriding-model-via-pytest-fixtures).

    Args:
	deps: The dependencies to use instead of the dependencies passed to the agent run.
	model: The model to use instead of the model passed to the agent run.
	toolsets: The toolsets to use instead of the toolsets passed to the agent constructor and agent run.
	tools: The tools to use instead of the tools registered with the agent.
    """
    raise NotImplementedError
    yield

The problem is that _utils is a private module, and thus is improper to reference from outside of PydanticAI itself.

This implicitly makes it impossible to actually implement AbstractAgent from outside of PydanticAI without violating the "rules" of good Python.

Python, Pydantic AI & LLM client version

Python - 3.12
PydanticAI - 0.8.1
LLM Client - All

[DouweM]

@clhodapp Good catch! We can import Unset and UNSET directly into pydantic_ai.agent.abstract to make them public. Would you be up for submitting a PR that does that?

[clhodapp]

Sure thing. Should be easy.