bump python version

.github/workflows/autogpts-ci.yml

@@ -34,7 +34,7 @@ jobs:
       fail-fast: false
     timeout-minutes: 20
     env:
-      min-python-version: '3.10'
+      min-python-version: '3.12'
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4

autogpts/autogpt/pyproject.toml

@@ -64,6 +64,8 @@ spacy = "^3.0.0"
 tenacity = "^8.2.2"
 tiktoken = "^0.5.0"
 webdriver-manager = "*"
+click-default-group = "^1.2.4"
+
 
 # OpenAI and Generic plugins import
 openapi-python-client = "^0.14.0"

autogpts/forge/pyproject.toml

@@ -28,6 +28,7 @@ agbenchmark = { path = "../../benchmark", optional = true }
 # agbenchmark = {git = "https://github.com/Significant-Gravitas/AutoGPT.git", subdirectory = "benchmark", optional = true}
 webdriver-manager = "^4.0.1"
 google-cloud-storage = "^2.13.0"
+click-default-group = "^1.2.4"
 
 [tool.poetry.extras]
 benchmark = ["agbenchmark"]

benchmark/agbenchmark/challenges/deprecated/code/1_password_generator/custom_python/test.py

@@ -18,7 +18,9 @@ class TestPasswordGenerator(unittest.TestCase):
     def test_password_content(self):
         password = password_generator.generate_password()
         self.assertTrue(any(c.isdigit() for c in password))
-        self.assertTrue(any(c in password_generator.string.punctuation for c in password))
+        self.assertTrue(
+            any(c in password_generator.string.punctuation for c in password)
+        )
 
 
 if __name__ == "__main__":

benchmark/agbenchmark/challenges/deprecated/code/4_tests/artifacts_in/testfile.py

@@ -1,17 +1,17 @@
-from sample_code import multiply_int
+# from sample_code import multiply_int
 
 
-def test_multiply_int(num: int, multiplier, expected_result: int) -> None:
-    result = multiply_int(num, multiplier)
-    print(result)
-    assert (
-        result == expected_result
-    ), f"AssertionError: Expected the output to be {expected_result}"
+# def test_multiply_int(num: int, multiplier, expected_result: int) -> None:
+#     result = multiply_int(num, multiplier)
+#     print(result)
+#     assert (
+#         result == expected_result
+#     ), f"AssertionError: Expected the output to be {expected_result}"
 
 
-if __name__ == "__main__":
-    # create a trivial test that has 4 as the num, and 2 as the multiplier. Make sure to fill in the expected result
-    num =
-    multiplier =
-    expected_result =
-    test_multiply_int()
+# if __name__ == "__main__":
+#     # create a trivial test that has 4 as the num, and 2 as the multiplier. Make sure to fill in the expected result
+#     num =
+#     multiplier =
+#     expected_result =
+#     test_multiply_int()

benchmark/agbenchmark/challenges/deprecated/code/d2.3_import/artifacts_in/test.py

@@ -1,7 +1,5 @@
 from typing import List
 
-from import
-
 
 def test_two_sum(nums: List, target: int, expected_result: List[int]) -> None:
     result = two_sum(nums, target)

benchmark/agbenchmark/challenges/verticals/code/2_password_generator/artifacts_out/password_generator.py

@@ -21,7 +21,6 @@ def generate_password(length: int = 8) -> str:
 
 if __name__ == "__main__":
     password_length = (
-        int(sys.argv[sys.argv.index("--length") + 1])
-        if "--length" in sys.argv else 8
+        int(sys.argv[sys.argv.index("--length") + 1]) if "--length" in sys.argv else 8
     )
     print(generate_password(password_length))

benchmark/agbenchmark/challenges/verticals/code/2_password_generator/custom_python/test.py

@@ -18,7 +18,9 @@ class TestPasswordGenerator(unittest.TestCase):
     def test_password_content(self):
         password = password_generator.generate_password()
         self.assertTrue(any(c.isdigit() for c in password))
-        self.assertTrue(any(c in password_generator.string.punctuation for c in password))
+        self.assertTrue(
+            any(c in password_generator.string.punctuation for c in password)
+        )
 
 
 if __name__ == "__main__":

benchmark/agbenchmark/challenges/verticals/code/6_battleship/artifacts_out/battleship.py

@@ -1,7 +1,13 @@
 from typing import Dict
 
-from abstract_class import (AbstractBattleship, Game, GameStatus,
-                            ShipPlacement, Turn, TurnResponse)
+from abstract_class import (
+    AbstractBattleship,
+    Game,
+    GameStatus,
+    ShipPlacement,
+    Turn,
+    TurnResponse,
+)
 
 
 class Battleship(AbstractBattleship):

benchmark/agbenchmark/challenges/webarena.py

@@ -258,7 +258,8 @@ class WebArenaChallengeSpec(BaseModel):
             f"{' and '.join(s.base_url for s in sites)}.\n\n"
             + "\n".join(
                 s.additional_info.format(url=s.base_url)
-                for s in sites if s.additional_info
+                for s in sites
+                if s.additional_info
             )
         ).strip()
 
@@ -462,7 +463,7 @@ class WebArenaChallenge(BaseChallenge):
 
 
 def load_webarena_challenges(
-    skip_unavailable: bool = True
+    skip_unavailable: bool = True,
 ) -> Iterator[type[WebArenaChallenge]]:
     logger.info("Loading WebArena challenges...")