Fix lint errors in test_custom_llm.py

- Add noqa comment for hardcoded test JWT token
- Add return statement to satisfy ruff RET503 check

Co-Authored-By: João <joao@crewai.com>

README.md

@@ -775,4 +775,3 @@ A: Yes, CrewAI provides extensive beginner-friendly tutorials, courses, and docu
 ### Q: Can CrewAI automate human-in-the-loop workflows?
 
 A: Yes, CrewAI fully supports human-in-the-loop workflows, allowing seamless collaboration between human experts and AI agents for enhanced decision-making.
-# test

src/crewai/__init__.py

@@ -40,7 +40,7 @@ def _suppress_pydantic_deprecation_warnings() -> None:
 
 _suppress_pydantic_deprecation_warnings()
 
-__version__ = "0.203.0"
+__version__ = "0.203.1"
 _telemetry_submitted = False
 
 

src/crewai/cli/authentication/utils.py

@@ -30,6 +30,7 @@ def validate_jwt_token(
             algorithms=["RS256"],
             audience=audience,
             issuer=issuer,
+            leeway=10.0,
             options={
                 "verify_signature": True,
                 "verify_exp": True,

src/crewai/cli/templates/crew/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]>=0.203.0,<1.0.0"
+    "crewai[tools]>=0.203.1,<1.0.0"
 ]
 
 [project.scripts]

src/crewai/cli/templates/flow/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]>=0.203.0,<1.0.0",
+    "crewai[tools]>=0.203.1,<1.0.0",
 ]
 
 [project.scripts]

src/crewai/cli/templates/tool/pyproject.toml

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]>=0.203.0"
+    "crewai[tools]>=0.203.1"
 ]
 
 [tool.crewai]

src/crewai/events/listeners/tracing/utils.py

@@ -358,7 +358,8 @@ def prompt_user_for_trace_viewing(timeout_seconds: int = 20) -> bool:
             try:
                 response = input().strip().lower()
                 result[0] = response in ["y", "yes"]
-            except (EOFError, KeyboardInterrupt):
+            except (EOFError, KeyboardInterrupt, OSError, LookupError):
+                # Handle all input-related errors silently
                 result[0] = False
 
         input_thread = threading.Thread(target=get_input, daemon=True)
@@ -371,6 +372,7 @@ def prompt_user_for_trace_viewing(timeout_seconds: int = 20) -> bool:
         return result[0]
 
     except Exception:
+        # Suppress any warnings or errors and assume "no"
         return False
 
 

src/crewai/llm.py

@@ -299,6 +299,7 @@ class LLM(BaseLLM):
         callbacks: list[Any] | None = None,
         reasoning_effort: Literal["none", "low", "medium", "high"] | None = None,
         stream: bool = False,
+        supports_function_calling: bool | None = None,
         **kwargs,
     ):
         self.model = model
@@ -325,6 +326,7 @@ class LLM(BaseLLM):
         self.additional_params = kwargs
         self.is_anthropic = self._is_anthropic_model(model)
         self.stream = stream
+        self._supports_function_calling_override = supports_function_calling
 
         litellm.drop_params = True
 
@@ -1197,6 +1199,9 @@ class LLM(BaseLLM):
             )
 
     def supports_function_calling(self) -> bool:
+        if self._supports_function_calling_override is not None:
+            return self._supports_function_calling_override
+        
         try:
             provider = self._get_custom_llm_provider()
             return litellm.utils.supports_function_calling(

src/crewai/llms/base_llm.py

@@ -9,6 +9,7 @@ from typing import Any, Final
 
 DEFAULT_CONTEXT_WINDOW_SIZE: Final[int] = 4096
 DEFAULT_SUPPORTS_STOP_WORDS: Final[bool] = True
+DEFAULT_SUPPORTS_FUNCTION_CALLING: Final[bool] = True
 
 
 class BaseLLM(ABC):
@@ -82,6 +83,14 @@ class BaseLLM(ABC):
             RuntimeError: If the LLM request fails for other reasons.
         """
 
+    def supports_function_calling(self) -> bool:
+        """Check if the LLM supports function calling.
+
+        Returns:
+            True if the LLM supports function calling, False otherwise.
+        """
+        return DEFAULT_SUPPORTS_FUNCTION_CALLING
+
     def supports_stop_words(self) -> bool:
         """Check if the LLM supports stop words.
 

src/crewai/task.py

@@ -7,7 +7,7 @@ import uuid
 import warnings
 from collections.abc import Callable
 from concurrent.futures import Future
-from copy import copy
+from copy import copy as shallow_copy
 from hashlib import md5
 from pathlib import Path
 from typing import (
@@ -672,7 +672,9 @@ Follow these guidelines:
         copied_data = {k: v for k, v in copied_data.items() if v is not None}
 
         cloned_context = (
-            [task_mapping[context_task.key] for context_task in self.context]
+            self.context
+            if self.context is NOT_SPECIFIED
+            else [task_mapping[context_task.key] for context_task in self.context]
             if isinstance(self.context, list)
             else None
         )
@@ -681,7 +683,7 @@ Follow these guidelines:
             return next((agent for agent in agents if agent.role == role), None)
 
         cloned_agent = get_agent_by_role(self.agent.role) if self.agent else None
-        cloned_tools = copy(self.tools) if self.tools else []
+        cloned_tools = shallow_copy(self.tools) if self.tools else []
 
         return self.__class__(
             **copied_data,

src/crewai/tools/tool_usage.py

@@ -1,6 +1,6 @@
+import ast
 import datetime
 import json
-import re
 import time
 from difflib import SequenceMatcher
 from json import JSONDecodeError
@@ -44,183 +44,6 @@ OPENAI_BIGGER_MODELS = [
 ]
 
 
-def _safe_literal_parse(input_str: str) -> Any:
-    """
-    Safely parse a limited subset of Python literal syntax without using ast.literal_eval.
-    Only supports: strings (single/double quotes), numbers, booleans, None, lists, dicts.
-    Rejects any input that could lead to code execution.
-    
-    Args:
-        input_str: String to parse
-        
-    Returns:
-        Parsed Python object
-        
-    Raises:
-        ValueError: If input contains unsafe or unsupported syntax
-    """
-    if not isinstance(input_str, str):
-        raise ValueError("Input must be a string")
-    
-    stripped = input_str.strip()
-    if not stripped:
-        raise ValueError("Input cannot be empty")
-    
-    # Check for potentially dangerous patterns
-    dangerous_patterns = [
-        r'__.*__',  # dunder methods
-        r'import\b',  # import statements
-        r'exec\b',  # exec function
-        r'eval\b',  # eval function
-        r'lambda\b',  # lambda functions
-        r'def\b',  # function definitions
-        r'class\b',  # class definitions
-        r'@\w+',  # decorators
-        r'\.\.\.',  # ellipsis (could be used in slicing)
-        r'->[^\]]*\]',  # type hints in lists
-    ]
-    
-    for pattern in dangerous_patterns:
-        if re.search(pattern, stripped, re.IGNORECASE):
-            raise ValueError(f"Potentially dangerous pattern detected: {pattern}")
-    
-    # Only allow specific characters
-    allowed_chars = r'[\s\w\.\-\+\*/\(\)\[\]\{\}:\'"<>!=,!=\?%&|~^`]'
-    if not re.fullmatch(f'{allowed_chars}*', stripped):
-        raise ValueError("Input contains unsupported characters")
-    
-    # Try JSON parsing first (safest)
-    try:
-        return json.loads(stripped)
-    except (json.JSONDecodeError, TypeError):
-        pass
-    
-    # Manual parsing for simple Python literals (JSON with single quotes, etc.)
-    try:
-        return _parse_python_literal_safe(stripped)
-    except Exception as e:
-        raise ValueError(f"Failed to parse input safely: {e}")
-
-
-def _parse_python_literal_safe(input_str: str) -> Any:
-    """
-    Parse a limited subset of Python literals safely.
-    
-    Args:
-        input_str: String to parse
-        
-    Returns:
-        Parsed Python object
-    """
-    # Handle None
-    if input_str == 'None':
-        return None
-    
-    # Handle booleans
-    if input_str == 'True':
-        return True
-    if input_str == 'False':
-        return False
-    
-    # Handle numbers
-    if re.fullmatch(r'-?\d+$', input_str):
-        return int(input_str)
-    if re.fullmatch(r'-?\d+\.\d+$', input_str):
-        return float(input_str)
-    
-    # Handle strings with single quotes (convert to JSON format)
-    if (input_str.startswith("'") and input_str.endswith("'")) or \
-       (input_str.startswith('"') and input_str.endswith('"')):
-        # Simple string - just remove quotes and escape common sequences
-        inner = input_str[1:-1]
-        # Handle common escape sequences safely
-        inner = inner.replace("\\'", "'").replace('\\"', '"').replace("\\\\", "\\")
-        return inner
-    
-    # Handle lists
-    if input_str.startswith('[') and input_str.endswith(']'):
-        inner = input_str[1:-1].strip()
-        if not inner:
-            return []
-        
-        items = _split_items_safe(inner)
-        return [_parse_python_literal_safe(item.strip()) for item in items]
-    
-    # Handle dictionaries
-    if input_str.startswith('{') and input_str.endswith('}'):
-        inner = input_str[1:-1].strip()
-        if not inner:
-            return {}
-        
-        pairs = _split_items_safe(inner)
-        result = {}
-        for pair in pairs:
-            if ':' not in pair:
-                raise ValueError(f"Invalid dict pair: {pair}")
-            
-            key_str, value_str = pair.split(':', 1)
-            key = _parse_python_literal_safe(key_str.strip())
-            value = _parse_python_literal_safe(value_str.strip())
-            if not isinstance(key, str):
-                raise ValueError(f"Dict keys must be strings, got {type(key)}")
-            result[key] = value
-        
-        return result
-    
-    raise ValueError(f"Unsupported literal format: {input_str}")
-
-
-def _split_items_safe(input_str: str, delimiter: str = ',') -> list[str]:
-    """
-    Split a list or dict string into items, respecting nested structures.
-    
-    Args:
-        input_str: String to split
-        delimiter: Delimiter to split on
-        
-    Returns:
-        List of item strings
-    """
-    items = []
-    current = []
-    depth = 0
-    in_string = False
-    string_char = None
-    i = 0
-    
-    while i < len(input_str):
-        char = input_str[i]
-        
-        # Handle string literals
-        if char in ('"', "'") and (i == 0 or input_str[i-1] != '\\'):
-            if not in_string:
-                in_string = True
-                string_char = char
-            elif char == string_char:
-                in_string = False
-                string_char = None
-        
-        # Track nesting depth when not in strings
-        elif not in_string:
-            if char in ('[', '(', '{'):
-                depth += 1
-            elif char in (']', ')', '}'):
-                depth -= 1
-            elif char == delimiter and depth == 0:
-                items.append(''.join(current).strip())
-                current = []
-                i += 1
-                continue
-        
-        current.append(char)
-        i += 1
-    
-    if current:
-        items.append(''.join(current).strip())
-    
-    return items
-
-
 class ToolUsageError(Exception):
     """Exception raised for errors in the tool usage."""
 
@@ -701,14 +524,14 @@ class ToolUsage:
         except (JSONDecodeError, TypeError):
             pass  # Continue to the next parsing attempt
 
-        # Attempt 2: Parse as Python literal (safe alternative to ast.literal_eval)
+        # Attempt 2: Parse as Python literal
         try:
-            arguments = _safe_literal_parse(tool_input)
+            arguments = ast.literal_eval(tool_input)
             if isinstance(arguments, dict):
                 return arguments
-        except ValueError:
+        except (ValueError, SyntaxError):
+            repaired_input = repair_json(tool_input)
             # Continue to the next parsing attempt
-            pass
 
         # Attempt 3: Parse as JSON5
         try:

tests/cli/authentication/test_utils.py

@@ -1,7 +1,7 @@
-import jwt
 import unittest
 from unittest.mock import MagicMock, patch
 
+import jwt
 
 from crewai.cli.authentication.utils import validate_jwt_token
 
@@ -17,19 +17,22 @@ class TestUtils(unittest.TestCase):
             key="mock_signing_key"
         )
 
+        jwt_token = "aaaaa.bbbbbb.cccccc"  # noqa: S105
+
         decoded_token = validate_jwt_token(
-            jwt_token="aaaaa.bbbbbb.cccccc",
+            jwt_token=jwt_token,
             jwks_url="https://mock_jwks_url",
             issuer="https://mock_issuer",
             audience="app_id_xxxx",
         )
 
         mock_jwt.decode.assert_called_with(
-            "aaaaa.bbbbbb.cccccc",
+            jwt_token,
             "mock_signing_key",
             algorithms=["RS256"],
             audience="app_id_xxxx",
             issuer="https://mock_issuer",
+            leeway=10.0,
             options={
                 "verify_signature": True,
                 "verify_exp": True,
@@ -43,9 +46,9 @@ class TestUtils(unittest.TestCase):
 
     def test_validate_jwt_token_expired(self, mock_jwt, mock_pyjwkclient):
         mock_jwt.decode.side_effect = jwt.ExpiredSignatureError
-        with self.assertRaises(Exception):
+        with self.assertRaises(Exception):  # noqa: B017
             validate_jwt_token(
-                jwt_token="aaaaa.bbbbbb.cccccc",
+                jwt_token="aaaaa.bbbbbb.cccccc",  # noqa: S106
                 jwks_url="https://mock_jwks_url",
                 issuer="https://mock_issuer",
                 audience="app_id_xxxx",
@@ -53,9 +56,9 @@ class TestUtils(unittest.TestCase):
 
     def test_validate_jwt_token_invalid_audience(self, mock_jwt, mock_pyjwkclient):
         mock_jwt.decode.side_effect = jwt.InvalidAudienceError
-        with self.assertRaises(Exception):
+        with self.assertRaises(Exception):  # noqa: B017
             validate_jwt_token(
-                jwt_token="aaaaa.bbbbbb.cccccc",
+                jwt_token="aaaaa.bbbbbb.cccccc",  # noqa: S106
                 jwks_url="https://mock_jwks_url",
                 issuer="https://mock_issuer",
                 audience="app_id_xxxx",
@@ -63,9 +66,9 @@ class TestUtils(unittest.TestCase):
 
     def test_validate_jwt_token_invalid_issuer(self, mock_jwt, mock_pyjwkclient):
         mock_jwt.decode.side_effect = jwt.InvalidIssuerError
-        with self.assertRaises(Exception):
+        with self.assertRaises(Exception):  # noqa: B017
             validate_jwt_token(
-                jwt_token="aaaaa.bbbbbb.cccccc",
+                jwt_token="aaaaa.bbbbbb.cccccc",  # noqa: S106
                 jwks_url="https://mock_jwks_url",
                 issuer="https://mock_issuer",
                 audience="app_id_xxxx",
@@ -75,9 +78,9 @@ class TestUtils(unittest.TestCase):
         self, mock_jwt, mock_pyjwkclient
     ):
         mock_jwt.decode.side_effect = jwt.MissingRequiredClaimError
-        with self.assertRaises(Exception):
+        with self.assertRaises(Exception):  # noqa: B017
             validate_jwt_token(
-                jwt_token="aaaaa.bbbbbb.cccccc",
+                jwt_token="aaaaa.bbbbbb.cccccc",  # noqa: S106
                 jwks_url="https://mock_jwks_url",
                 issuer="https://mock_issuer",
                 audience="app_id_xxxx",
@@ -85,9 +88,9 @@ class TestUtils(unittest.TestCase):
 
     def test_validate_jwt_token_jwks_error(self, mock_jwt, mock_pyjwkclient):
         mock_jwt.decode.side_effect = jwt.exceptions.PyJWKClientError
-        with self.assertRaises(Exception):
+        with self.assertRaises(Exception):  # noqa: B017
             validate_jwt_token(
-                jwt_token="aaaaa.bbbbbb.cccccc",
+                jwt_token="aaaaa.bbbbbb.cccccc",  # noqa: S106
                 jwks_url="https://mock_jwks_url",
                 issuer="https://mock_issuer",
                 audience="app_id_xxxx",
@@ -95,9 +98,9 @@ class TestUtils(unittest.TestCase):
 
     def test_validate_jwt_token_invalid_token(self, mock_jwt, mock_pyjwkclient):
         mock_jwt.decode.side_effect = jwt.InvalidTokenError
-        with self.assertRaises(Exception):
+        with self.assertRaises(Exception):  # noqa: B017
             validate_jwt_token(
-                jwt_token="aaaaa.bbbbbb.cccccc",
+                jwt_token="aaaaa.bbbbbb.cccccc",  # noqa: S106
                 jwks_url="https://mock_jwks_url",
                 issuer="https://mock_issuer",
                 audience="app_id_xxxx",

tests/test_custom_llm.py

@@ -1,4 +1,4 @@
-from typing import Any, Dict, List, Optional, Union
+from typing import Any
 
 import pytest
 
@@ -159,11 +159,11 @@ class JWTAuthLLM(BaseLLM):
 
     def call(
         self,
-        messages: Union[str, List[Dict[str, str]]],
-        tools: Optional[List[dict]] = None,
-        callbacks: Optional[List[Any]] = None,
-        available_functions: Optional[Dict[str, Any]] = None,
-    ) -> Union[str, Any]:
+        messages: str | list[dict[str, str]],
+        tools: list[dict] | None = None,
+        callbacks: list[Any] | None = None,
+        available_functions: dict[str, Any] | None = None,
+    ) -> str | Any:
         """Record the call and return a predefined response."""
         self.calls.append(
             {
@@ -192,7 +192,7 @@ class JWTAuthLLM(BaseLLM):
 
 def test_custom_llm_with_jwt_auth():
     """Test a custom LLM implementation with JWT authentication."""
-    jwt_llm = JWTAuthLLM(jwt_token="example.jwt.token")
+    jwt_llm = JWTAuthLLM(jwt_token="example.jwt.token")  # noqa: S106
 
     # Test that create_llm returns the JWT-authenticated LLM instance directly
     result_llm = create_llm(jwt_llm)
@@ -238,11 +238,11 @@ class TimeoutHandlingLLM(BaseLLM):
 
     def call(
         self,
-        messages: Union[str, List[Dict[str, str]]],
-        tools: Optional[List[dict]] = None,
-        callbacks: Optional[List[Any]] = None,
-        available_functions: Optional[Dict[str, Any]] = None,
-    ) -> Union[str, Any]:
+        messages: str | list[dict[str, str]],
+        tools: list[dict] | None = None,
+        callbacks: list[Any] | None = None,
+        available_functions: dict[str, Any] | None = None,
+    ) -> str | Any:
         """Simulate API calls with timeout handling and retry logic.
 
         Args:
@@ -282,35 +282,34 @@ class TimeoutHandlingLLM(BaseLLM):
                         )
                     # Otherwise, continue to the next attempt (simulating backoff)
                     continue
-                else:
-                    # Success on first attempt
-                    return "First attempt response"
-            else:
-                # This is a retry attempt (attempt > 0)
-                # Always record retry attempts
-                self.calls.append(
-                    {
-                        "retry_attempt": attempt,
-                        "messages": messages,
-                        "tools": tools,
-                        "callbacks": callbacks,
-                        "available_functions": available_functions,
-                    }
-                )
+                # Success on first attempt
+                return "First attempt response"
+            # This is a retry attempt (attempt > 0)
+            # Always record retry attempts
+            self.calls.append(
+                {
+                    "retry_attempt": attempt,
+                    "messages": messages,
+                    "tools": tools,
+                    "callbacks": callbacks,
+                    "available_functions": available_functions,
+                }
+            )
 
-                # Simulate a failure if fail_count > 0
-                if self.fail_count > 0:
-                    self.fail_count -= 1
-                    # If we've used all retries, raise an error
-                    if attempt == self.max_retries - 1:
-                        raise TimeoutError(
-                            f"LLM request failed after {self.max_retries} attempts"
-                        )
-                    # Otherwise, continue to the next attempt (simulating backoff)
-                    continue
-                else:
-                    # Success on retry
-                    return "Response after retry"
+            # Simulate a failure if fail_count > 0
+            if self.fail_count > 0:
+                self.fail_count -= 1
+                # If we've used all retries, raise an error
+                if attempt == self.max_retries - 1:
+                    raise TimeoutError(
+                        f"LLM request failed after {self.max_retries} attempts"
+                    )
+                # Otherwise, continue to the next attempt (simulating backoff)
+                continue
+            # Success on retry
+            return "Response after retry"
+
+        return "Response after retry"
 
     def supports_function_calling(self) -> bool:
         """Return True to indicate that function calling is supported.
@@ -358,3 +357,25 @@ def test_timeout_handling_llm():
     with pytest.raises(TimeoutError, match="LLM request failed after 2 attempts"):
         llm.call("Test message")
     assert len(llm.calls) == 2  # Initial call + failed retry attempt
+
+
+class MinimalCustomLLM(BaseLLM):
+    """Minimal custom LLM implementation that doesn't override supports_function_calling."""
+
+    def __init__(self):
+        super().__init__(model="minimal-model")
+
+    def call(
+        self,
+        messages: str | list[dict[str, str]],
+        tools: list[dict] | None = None,
+        callbacks: list[Any] | None = None,
+        available_functions: dict[str, Any] | None = None,
+    ) -> str | Any:
+        return "Minimal response"
+
+
+def test_base_llm_supports_function_calling_default():
+    """Test that BaseLLM supports function calling by default."""
+    llm = MinimalCustomLLM()
+    assert llm.supports_function_calling() is True

tests/test_llm.py

@@ -711,3 +711,18 @@ def test_ollama_does_not_modify_when_last_is_user(ollama_llm):
     formatted = ollama_llm._format_messages_for_provider(original_messages)
 
     assert formatted == original_messages
+
+
+def test_supports_function_calling_with_override_true():
+    llm = LLM(model="custom-model/my-model", supports_function_calling=True)
+    assert llm.supports_function_calling() is True
+
+
+def test_supports_function_calling_with_override_false():
+    llm = LLM(model="gpt-4o-mini", supports_function_calling=False)
+    assert llm.supports_function_calling() is False
+
+
+def test_supports_function_calling_without_override():
+    llm = LLM(model="gpt-4o-mini")
+    assert llm.supports_function_calling() is True

tests/test_task.py

@@ -1218,7 +1218,7 @@ def test_create_directory_false():
     assert not resolved_dir.exists()
 
     with pytest.raises(
-        RuntimeError, match="Directory .* does not exist and create_directory is False"
+        RuntimeError, match=r"Directory .* does not exist and create_directory is False"
     ):
         task._save_file("test content")
 
@@ -1635,3 +1635,48 @@ def test_task_interpolation_with_hyphens():
     assert "say hello world" in task.prompt()
 
     assert result.raw == "Hello, World!"
+
+
+def test_task_copy_with_none_context():
+    original_task = Task(
+        description="Test task",
+        expected_output="Test output",
+        context=None
+    )
+
+    new_task = original_task.copy(agents=[], task_mapping={})
+    assert original_task.context is None
+    assert new_task.context is None
+
+
+def test_task_copy_with_not_specified_context():
+    from crewai.utilities.constants import NOT_SPECIFIED
+    original_task = Task(
+        description="Test task",
+        expected_output="Test output",
+    )
+
+    new_task = original_task.copy(agents=[], task_mapping={})
+    assert original_task.context is NOT_SPECIFIED
+    assert new_task.context is NOT_SPECIFIED
+
+
+def test_task_copy_with_list_context():
+    """Test that copying a task with list context works correctly."""
+    task1 = Task(
+        description="Task 1",
+        expected_output="Output 1"
+    )
+    task2 = Task(
+        description="Task 2",
+        expected_output="Output 2",
+        context=[task1]
+    )
+
+    task_mapping = {task1.key: task1}
+
+    copied_task2 = task2.copy(agents=[], task_mapping=task_mapping)
+
+    assert isinstance(copied_task2.context, list)
+    assert len(copied_task2.context) == 1
+    assert copied_task2.context[0] is task1