fix: restore python linting. (#2228)

* fix: restore python linting.

Signed-off-by: ifuryst <ifuryst@gmail.com>

* update: extend the Python lint check to evaluation.

Signed-off-by: ifuryst <ifuryst@gmail.com>

* Update evaluation/logic_reasoning/instruction.txt

---------

Signed-off-by: ifuryst <ifuryst@gmail.com>
Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk>

.github/workflows/lint.yml

@@ -47,11 +47,4 @@ jobs:
       - name: Install pre-commit
         run: pip install pre-commit==3.7.0
       - name: Run pre-commit hooks
-        if: github.ref != 'refs/heads/main'
-        run: |
-          git fetch https://github.com/OpenDevin/OpenDevin.git main:main && \
-          pre-commit run \
-            --files \
-            $(git diff --name-only $(git merge-base main $(git branch --show-current)) $(git branch --show-current) | tr '\n' ' ') \
-            --show-diff-on-failure \
-            --config ./dev_config/python/.pre-commit-config.yaml
+        run: pre-commit run --files opendevin/**/* agenthub/**/* evaluation/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml

Makefile

@@ -172,7 +172,7 @@ install-precommit-hooks:
 
 lint-backend:
 	@echo "$(YELLOW)Running linters...$(RESET)"
-	@poetry run pre-commit run --files $$(git diff --name-only $$(git merge-base main $$(git branch --show-current)) $$(git branch --show-current) | tr '\n' ' ') --show-diff-on-failure --config $(PRECOMMIT_CONFIG_PATH)
+	@poetry run pre-commit run --files opendevin/**/* agenthub/**/* evaluation/**/* --show-diff-on-failure --config $(PRECOMMIT_CONFIG_PATH)
 
 lint-frontend:
 	@echo "$(YELLOW)Running linters for frontend...$(RESET)"

agenthub/browsing_agent/prompt.py

@@ -494,11 +494,13 @@ def _get_action_space(flags: Flags) -> AbstractActionSet:
             action_space = PythonActionSet(strict=flags.is_strict)
             if flags.multi_actions:
                 warn(
-                    f'Flag action_space={repr(flags.action_space)} incompatible with multi_actions={repr(flags.multi_actions)}.'
+                    f'Flag action_space={repr(flags.action_space)} incompatible with multi_actions={repr(flags.multi_actions)}.',
+                    stacklevel=2,
                 )
             if flags.demo_mode != 'off':
                 warn(
-                    f'Flag action_space={repr(flags.action_space)} incompatible with demo_mode={repr(flags.demo_mode)}.'
+                    f'Flag action_space={repr(flags.action_space)} incompatible with demo_mode={repr(flags.demo_mode)}.',
+                    stacklevel=2,
                 )
             return action_space
         case 'bid':

agenthub/browsing_agent/utils.py

@@ -16,7 +16,7 @@ def yaml_parser(message):
         valid = True
         retry_message = ''
     except yaml.YAMLError as e:
-        warn(str(e))
+        warn(str(e), stacklevel=2)
         value = {}
         valid = False
         retry_message = "Your response is not a valid yaml. Please try again and be careful to the format. Don't add any apology or comment, just the answer."

evaluation/EDA/game.py

@@ -9,6 +9,7 @@ from retry import retry
 
 LOGGER = logging.getLogger(__name__)
 
+
 class Q20Game:
     def __init__(
         self,
@@ -19,8 +20,10 @@ class Q20Game:
         temperature: float = 0.8,
         openai_api: bool = True,
         openai_api_key: Optional[str] = None,
-        guesser_kargs={},
+        guesser_kargs=None,
     ) -> None:
+        if guesser_kargs is None:
+            guesser_kargs = {}
         self.item = item
         self.answerer_model = answerer_model
         self.guesser_model = guesser_model

evaluation/gaia/scorer.py

@@ -17,8 +17,10 @@ def normalize_number_str(number_str: str) -> float:
 
 def split_string(
     s: str,
-    char_list: list[str] = [',', ';'],
+    char_list: list[str] = None,
 ) -> list[str]:
+    if char_list is None:
+        char_list = [',', ';']
     pattern = f"[{''.join(char_list)}]"
     return re.split(pattern, s)
 
@@ -51,7 +53,9 @@ def question_scorer(
         # check length is the same
         if len(gt_elems) != len(ma_elems):
             warnings.warn(
-                'Answer lists have different lengths, returning False.', UserWarning
+                'Answer lists have different lengths, returning False.',
+                UserWarning,
+                stacklevel=2,
             )
             return False
 

evaluation/logic_reasoning/instruction.txt

@@ -1,6 +1,6 @@
-You are a helpful assistant assigned with logic reasoning task. You need to determine the correctness of a query given some facts and fules. 
+You are a helpful assistant assigned with logic reasoning task. You need to determine the correctness of a query given some facts and rules.
 you can interact with an interactive Python (Jupyter Notebook) environment and receive the corresponding output when needed. The code should be enclosed using "<execute_ipython>" tag.
-In this task, you need to use the code in [[logic_inference_path.py]] to help you. Specifically, you first need to instantiate a **LogicInferenceEngine** class and use the **safe_execute_program** method to prove the **logic programs**. You should receive *answer*, *flag*, *error_message* from the output. 
+In this task, you need to use the code in [[logic_inference_path.py]] to help you. Specifically, you first need to instantiate a **LogicInferenceEngine** class and use the **safe_execute_program** method to prove the **logic programs**. You should receive *answer*, *flag*, *error_message* from the output.
 
 An example would be look like this:
     <execute_ipython>
@@ -17,4 +17,3 @@ dataset_name:
 
 logic_programs:
 [[logic_programs]]
-