Fix debug code challenge (#4632)

tests/challenges/debug_code/data/code.py

@@ -2,18 +2,12 @@
 from typing import List, Optional
 
 
-def two_sum(nums: List, target: int) -> Optional[int]:
+def two_sum(nums: List, target: int) -> Optional[List[int]]:
     seen = {}
     for i, num in enumerate(nums):
+        typo
         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/test.py

@@ -0,0 +1,31 @@
+# mypy: ignore-errors
+from code import two_sum
+from typing import List
+
+
+def test_two_sum(nums: List, target: int, expected_result: List[int]) -> None:
+    result = two_sum(nums, target)
+    print(result)
+    assert (
+        result == expected_result
+    ), f"AssertionError: Expected the output to be {expected_result}"
+
+
+if __name__ == "__main__":
+    # 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/data/two_sum_tests.py

@@ -1,30 +0,0 @@
-# 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

@@ -5,20 +5,27 @@ 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.challenges.utils import (
+    copy_file_into_workspace,
+    get_workspace_path,
+    run_interaction_loop,
+)
 from tests.utils import requires_api_key
 
 CYCLE_COUNT = 5
+EXPECTED_VALUES = ["[0, 1]", "[2, 5]", "[0, 3]"]
+DIRECTORY_PATH = Path(__file__).parent / "data"
+CODE_FILE_PATH = "code.py"
+TEST_FILE_PATH = "test.py"
 
 
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
 @challenge
 def test_debug_code_challenge_a(
-    debug_code_agent: Agent,
+    debug_code_agents: Agent,
     monkeypatch: pytest.MonkeyPatch,
     patched_api_requestor: MockerFixture,
     config: Config,
@@ -33,17 +40,20 @@ def test_debug_code_challenge_a(
     :config: The config object for the agent.
     :level_to_run: The level to run.
     """
+    debug_code_agent = debug_code_agents[level_to_run - 1]
 
-    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)
+    copy_file_into_workspace(debug_code_agent, DIRECTORY_PATH, CODE_FILE_PATH)
+    copy_file_into_workspace(debug_code_agent, DIRECTORY_PATH, TEST_FILE_PATH)
 
     run_interaction_loop(monkeypatch, debug_code_agent, CYCLE_COUNT)
 
-    append_to_file(file_path, test_file_path.read_text(), config)
+    output = execute_python_file(
+        get_workspace_path(debug_code_agent, TEST_FILE_PATH), config
+    )
 
-    output = execute_python_file(file_path, config)
     assert "error" not in output.lower(), f"Errors found in output: {output}!"
+
+    for expected_value in EXPECTED_VALUES:
+        assert (
+            expected_value in output
+        ), f"Expected output to contain {expected_value}, but it was not found in {output}!"