Rearrange tests & fix CI (#4596)

* Rearrange tests into unit/integration/challenge categories

* Fix linting + `tests.challenges` imports

* Fix obscured duplicate test in test_url_validation.py

* Move VCR conftest to tests.vcr

* Specify tests to run & their order (unit -> integration -> challenges) in CI

* Fail Docker CI when tests fail

* Fix import & linting errors in tests

* Fix `get_text_summary`

* Fix linting errors

* Clean up pytest args in CI

* Remove bogus tests from GoCodeo

tests/challenges/debug_code/data/two_sum.py

@@ -0,0 +1,19 @@
+# mypy: ignore-errors
+from typing import List, Optional
+
+
+def two_sum(nums: List, target: int) -> Optional[int]:
+    seen = {}
+    for i, num in enumerate(nums):
+        complement = target - num
+        if complement in seen:
+            return [seen[complement], i]
+        seen[num] = i
+    return None
+
+
+# Example usage:
+nums = [2, 7, 11, 15]
+target = 9
+result = two_sum(nums, target)
+print(result)  # Output: [0, 1]

tests/challenges/debug_code/data/two_sum_tests.py

@@ -0,0 +1,30 @@
+# mypy: ignore-errors
+# we need a new line at the top of the file to avoid a syntax error
+
+
+def test_two_sum(nums, target, expected_result):
+    # These tests are appended to the two_sum file so we can ignore this error for now
+    result = two_sum(nums, target)
+    print(result)
+    assert (
+        result == expected_result
+    ), f"AssertionError: Expected the output to be {expected_result}"
+
+
+# test the trivial case with the first two numbers
+nums = [2, 7, 11, 15]
+target = 9
+expected_result = [0, 1]
+test_two_sum(nums, target, expected_result)
+
+# test for ability to use zero and the same number twice
+nums = [2, 7, 0, 15, 12, 0]
+target = 0
+expected_result = [2, 5]
+test_two_sum(nums, target, expected_result)
+
+# test for first and last index usage and negative numbers
+nums = [-6, 7, 11, 4]
+target = -2
+expected_result = [0, 3]
+test_two_sum(nums, target, expected_result)

tests/challenges/debug_code/test_debug_code_challenge_a.py

@@ -0,0 +1,49 @@
+from pathlib import Path
+
+import pytest
+from pytest_mock import MockerFixture
+
+from autogpt.agent import Agent
+from autogpt.commands.execute_code import execute_python_file
+from autogpt.commands.file_operations import append_to_file, write_to_file
+from autogpt.config import Config
+from tests.challenges.challenge_decorator.challenge_decorator import challenge
+from tests.challenges.utils import run_interaction_loop
+from tests.utils import requires_api_key
+
+CYCLE_COUNT = 5
+
+
+@pytest.mark.vcr
+@requires_api_key("OPENAI_API_KEY")
+@challenge
+def test_debug_code_challenge_a(
+    debug_code_agent: Agent,
+    monkeypatch: pytest.MonkeyPatch,
+    patched_api_requestor: MockerFixture,
+    config: Config,
+    level_to_run: int,
+) -> None:
+    """
+    Test whether the agent can debug a simple code snippet.
+
+    :param debug_code_agent: The agent to test.
+    :param monkeypatch: pytest's monkeypatch utility for modifying builtins.
+    :patched_api_requestor: Sends api requests to our API CI pipeline
+    :config: The config object for the agent.
+    :level_to_run: The level to run.
+    """
+
+    file_path = str(debug_code_agent.workspace.get_path("code.py"))
+
+    code_file_path = Path(__file__).parent / "data" / "two_sum.py"
+    test_file_path = Path(__file__).parent / "data" / "two_sum_tests.py"
+
+    write_to_file(file_path, code_file_path.read_text(), config)
+
+    run_interaction_loop(monkeypatch, debug_code_agent, CYCLE_COUNT)
+
+    append_to_file(file_path, test_file_path.read_text(), config)
+
+    output = execute_python_file(file_path, config)
+    assert "error" not in output.lower(), f"Errors found in output: {output}!"