56fc83bf3e
## Problem I found a bug with `Github.CountStargazers` where a stargazer count of `0` was interpreted as a null result. In other words, 0 wasn't passed back to the Engine correctly. Separately, the tool function was also not authorized correctly. ## Fix - Don't use a falsy comparison when evaluating `result` inside the `ToolOutputFactory` - Add unit tests for `ToolOutputFactory` to give us confidence in the business logic - Added `ToolContext` to pass in the authorization token correctly. Before ``` User (nate@arcade-ai.com): how many stars does the ArcadeAI/Docs repo have on github? Assistant (gpt-4o): I successfully checked the repository, but unfortunately, I cannot provide the number of stars for the ArcadeAI/Docs repository. Please try checking directly on GitHub for the most accurate information. Called tool 'Github_CountStargazers' Parameters:{"owner":"ArcadeAI","name":"Docs"} 'Github_CountStargazers' tool returned:Github.CountStargazers called successfully ``` After ``` User (nate@arcade-ai.com): how many stars does the ArcadeAI/Docs repo have on github? Assistant (gpt-4o): The ArcadeAI/Docs repository on GitHub has 0 stars. Called tool 'Github_CountStargazers' Parameters:{"owner":"ArcadeAI","name":"Docs"} 'Github_CountStargazers' tool returned:0
75 lines
2.1 KiB
Python
75 lines
2.1 KiB
Python
from typing import Any
|
|
|
|
import pytest
|
|
from pydantic import BaseModel
|
|
|
|
from arcade.core.output import ToolOutputFactory
|
|
|
|
|
|
@pytest.fixture
|
|
def output_factory():
|
|
return ToolOutputFactory()
|
|
|
|
|
|
class SampleOutputModel(BaseModel):
|
|
result: Any
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"data, expected_value",
|
|
[
|
|
(None, ""),
|
|
("success", "success"),
|
|
("", ""),
|
|
(None, ""),
|
|
(123, 123),
|
|
(0, 0),
|
|
(123.45, 123.45),
|
|
(True, True),
|
|
(False, False),
|
|
],
|
|
)
|
|
def test_success(output_factory, data, expected_value):
|
|
data_obj = SampleOutputModel(result=data) if data is not None else None
|
|
output = output_factory.success(data=data_obj)
|
|
assert output.value == expected_value
|
|
assert output.error is None
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"message, developer_message",
|
|
[
|
|
("Error occurred", None),
|
|
("Error occurred", "Detailed error message"),
|
|
],
|
|
)
|
|
def test_fail(output_factory, message, developer_message):
|
|
output = output_factory.fail(message=message, developer_message=developer_message)
|
|
assert output.error is not None
|
|
assert output.error.message == message
|
|
assert output.error.developer_message == developer_message
|
|
assert output.error.can_retry is False
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"message, developer_message, additional_prompt_content, retry_after_ms",
|
|
[
|
|
("Retry error", None, None, None),
|
|
("Retry error", "Retrying", "Please try again with this additional data: foobar", 1000),
|
|
],
|
|
)
|
|
def test_fail_retry(
|
|
output_factory, message, developer_message, additional_prompt_content, retry_after_ms
|
|
):
|
|
output = output_factory.fail_retry(
|
|
message=message,
|
|
developer_message=developer_message,
|
|
additional_prompt_content=additional_prompt_content,
|
|
retry_after_ms=retry_after_ms,
|
|
)
|
|
assert output.error is not None
|
|
assert output.error.message == message
|
|
assert output.error.developer_message == developer_message
|
|
assert output.error.can_retry is True
|
|
assert output.error.additional_prompt_content == additional_prompt_content
|
|
assert output.error.retry_after_ms == retry_after_ms
|