Merge branch 'main' into devin/1735586761-fix-hierarchical-delegation

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

README.md

@@ -85,7 +85,6 @@ First, install CrewAI:
 ```shell
 pip install crewai
 ```
-
 If you want to install the 'crewai' package along with its optional features that include additional tools for agents, you can do so by using the following command:
 
 ```shell
@@ -93,6 +92,22 @@ pip install 'crewai[tools]'
 ```
 The command above installs the basic package and also adds extra components which require more dependencies to function.
 
+### Troubleshooting Dependencies
+
+If you encounter issues during installation or usage, here are some common solutions:
+
+#### Common Issues
+
+1. **ModuleNotFoundError: No module named 'tiktoken'**
+   - Install tiktoken explicitly: `pip install 'crewai[embeddings]'`
+   - If using embedchain or other tools: `pip install 'crewai[tools]'`
+
+2. **Failed building wheel for tiktoken**
+   - Ensure Rust compiler is installed (see installation steps above)
+   - For Windows: Verify Visual C++ Build Tools are installed
+   - Try upgrading pip: `pip install --upgrade pip`
+   - If issues persist, use a pre-built wheel: `pip install tiktoken --prefer-binary`
+
 ### 2. Setting Up Your Crew with the YAML Configuration
 
 To create a new CrewAI project, run the following CLI (Command Line Interface) command:

pyproject.toml

@@ -8,27 +8,38 @@ authors = [
     { name = "Joao Moura", email = "joao@crewai.com" }
 ]
 dependencies = [
+    # Core Dependencies
     "pydantic>=2.4.2",
     "openai>=1.13.3",
+    "litellm>=1.44.22",
+    "instructor>=1.3.3",
+    
+    # Text Processing
+    "pdfplumber>=0.11.4",
+    "regex>=2024.9.11",
+    
+    # Telemetry and Monitoring
     "opentelemetry-api>=1.22.0",
     "opentelemetry-sdk>=1.22.0",
     "opentelemetry-exporter-otlp-proto-http>=1.22.0",
-    "instructor>=1.3.3",
-    "regex>=2024.9.11",
-    "click>=8.1.7",
+    
+    # Data Handling
+    "chromadb>=0.5.23",
+    "openpyxl>=3.1.5",
+    "pyvis>=0.3.2",
+    
+    # Authentication and Security
+    "auth0-python>=4.7.1",
     "python-dotenv>=1.0.0",
+    
+    # Configuration and Utils
+    "click>=8.1.7",
     "appdirs>=1.4.4",
     "jsonref>=1.1.0",
     "json-repair>=0.25.2",
-    "auth0-python>=4.7.1",
-    "litellm>=1.44.22",
-    "pyvis>=0.3.2",
     "uv>=0.4.25",
     "tomli-w>=1.1.0",
     "tomli>=2.0.2",
-    "chromadb>=0.5.23",
-    "pdfplumber>=0.11.4",
-    "openpyxl>=3.1.5",
     "blinker>=1.9.0",
 ]
 
@@ -39,6 +50,9 @@ Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
 tools = ["crewai-tools>=0.17.0"]
+embeddings = [
+    "tiktoken~=0.7.0"
+]
 agentops = ["agentops>=0.3.0"]
 fastembed = ["fastembed>=0.4.1"]
 pdfplumber = [

src/crewai/agent.py

@@ -406,8 +406,17 @@ class Agent(BaseAgent):
             callbacks=[TokenCalcHandler(self._token_process)],
         )
 
-    def get_delegation_tools(self, agents: List[BaseAgent]):
-        agent_tools = AgentTools(agents=agents)
+    def get_delegation_tools(self, agents: List[BaseAgent], task: Optional[Task] = None) -> List[BaseTool]:
+        """Get the delegation tools for this agent.
+        
+        Args:
+            agents: List of agents that can be delegated to
+            task: Optional task context for delegation
+            
+        Returns:
+            List of delegation tools
+        """
+        agent_tools = AgentTools(agents=agents, task=task, i18n=self.i18n)
         tools = agent_tools.tools()
         return tools
 

src/crewai/agents/agent_builder/base_agent.py

@@ -232,7 +232,7 @@ class BaseAgent(ABC, BaseModel):
         pass
 
     @abstractmethod
-    def get_delegation_tools(self, agents: List["BaseAgent"]) -> List[BaseTool]:
+    def get_delegation_tools(self, agents: List["BaseAgent"], task=None) -> List[BaseTool]:
         """Set the task tools that init BaseAgenTools class."""
         pass
 

src/crewai/crew.py

@@ -798,15 +798,34 @@ class Crew(BaseModel):
         return None
 
     def _prepare_tools(self, agent: BaseAgent, task: Task, tools: List[Tool]) -> List[Tool]:
+        """Prepare tools for an agent, including delegation tools if allowed.
+        
+        Args:
+            agent: Agent that will receive the tools
+            task: Task being executed
+            tools: List of existing tools
+            
+        Returns:
+            List of tools with delegation and other tools added
+        """
         # Add delegation tools if agent allows delegation
         if agent.allow_delegation:
             if self.process == Process.hierarchical:
                 if self.manager_agent:
-                    tools = self._update_manager_tools(task, tools)
+                    # For hierarchical process, handle both manager and regular agent tools
+                    if agent == self.manager_agent:
+                        # Manager can delegate to all regular agents
+                        tools = self._inject_delegation_tools(tools, agent, [a for a in self.agents if a != agent], task=task)
+                    elif task and task.async_execution and task.agent:
+                        # For async tasks in hierarchical mode, only allow delegation to the task's assigned agent
+                        tools = self._inject_delegation_tools(tools, agent, [task.agent], task=task)
+                    else:
+                        # Regular agents can delegate to manager and other agents
+                        delegation_agents = [self.manager_agent] + [a for a in self.agents if a != agent]
+                        tools = self._inject_delegation_tools(tools, agent, delegation_agents, task=task)
                 else:
                     raise ValueError("Manager agent is required for hierarchical process.")
-
-            elif agent and agent.allow_delegation:
+            else:
                 tools = self._add_delegation_tools(task, tools)
 
         # Add code execution tools if agent allows code execution
@@ -839,8 +858,19 @@ class Crew(BaseModel):
 
         return tools
 
-    def _inject_delegation_tools(self, tools: List[Tool], task_agent: BaseAgent, agents: List[BaseAgent]):
-        delegation_tools = task_agent.get_delegation_tools(agents)
+    def _inject_delegation_tools(self, tools: List[Tool], task_agent: BaseAgent, agents: List[BaseAgent], task=None):
+        """Inject delegation tools for the given agent.
+        
+        Args:
+            tools: List of existing tools
+            task_agent: Agent that will receive the delegation tools
+            agents: List of agents that can be delegated to
+            task: Optional task context for delegation
+            
+        Returns:
+            List of tools with delegation tools added
+        """
+        delegation_tools = task_agent.get_delegation_tools(agents, task=task)
         return self._merge_tools(tools, delegation_tools)
 
     def _add_multimodal_tools(self, agent: BaseAgent, tools: List[Tool]):
@@ -852,8 +882,17 @@ class Crew(BaseModel):
         return self._merge_tools(tools, code_tools)
 
     def _add_delegation_tools(self, task: Task, tools: List[Tool]):
-        agents_for_delegation = [agent for agent in self.agents if agent != task.agent]
-        if len(self.agents) > 1 and len(agents_for_delegation) > 0 and task.agent:
+        agents_for_delegation = []
+        if self.process == Process.hierarchical and self.manager_agent:
+            # In hierarchical mode, allow delegation to manager if the task agent isn't the manager
+            if task.agent != self.manager_agent:
+                agents_for_delegation = [self.manager_agent]
+            # Also include regular agents for delegation
+            agents_for_delegation.extend([agent for agent in self.agents if agent != task.agent])
+        else:
+            agents_for_delegation = [agent for agent in self.agents if agent != task.agent]
+        
+        if len(agents_for_delegation) > 0 and task.agent:
             if not tools:
                 tools = []
             tools = self._inject_delegation_tools(tools, task.agent, agents_for_delegation)
@@ -868,9 +907,23 @@ class Crew(BaseModel):
     def _update_manager_tools(self, task: Task, tools: List[Tool]):
         if self.manager_agent:
             if task.agent:
-                tools = self._inject_delegation_tools(tools, task.agent, [task.agent])
+                # In hierarchical mode with async execution, only allow delegation to the task's assigned agent
+                if task.async_execution and self.process == Process.hierarchical:
+                    tools = self._inject_delegation_tools(tools, task.agent, [task.agent] if task.agent else [])
+                else:
+                    # In hierarchical mode, allow bidirectional delegation
+                    if self.process == Process.hierarchical:
+                        # For non-manager agents, allow delegation to manager and other agents
+                        if task.agent != self.manager_agent:
+                            delegation_agents = [self.manager_agent] + self.agents
+                            tools = self._inject_delegation_tools(tools, task.agent, [a for a in delegation_agents if a != task.agent])
+                        else:
+                            # For manager, allow delegation to all agents
+                            tools = self._inject_delegation_tools(tools, task.agent, [a for a in self.agents if a != task.agent])
+                    else:
+                        tools = self._inject_delegation_tools(tools, task.agent, self.agents, task=task)
             else:
-                tools = self._inject_delegation_tools(tools, self.manager_agent, self.agents)
+                tools = self._inject_delegation_tools(tools, self.manager_agent, self.agents, task=task)
         return tools
 
     def _get_context(self, task: Task, task_outputs: List[TaskOutput]):

src/crewai/task.py

@@ -179,6 +179,7 @@ class Task(BaseModel):
     _execution_span: Optional[Span] = PrivateAttr(default=None)
     _original_description: Optional[str] = PrivateAttr(default=None)
     _original_expected_output: Optional[str] = PrivateAttr(default=None)
+    _original_output_file: Optional[str] = PrivateAttr(default=None)
     _thread: Optional[threading.Thread] = PrivateAttr(default=None)
     _execution_time: Optional[float] = PrivateAttr(default=None)
 
@@ -213,8 +214,46 @@ class Task(BaseModel):
 
     @field_validator("output_file")
     @classmethod
-    def output_file_validation(cls, value: str) -> str:
-        """Validate the output file path by removing the / from the beginning of the path."""
+    def output_file_validation(cls, value: Optional[str]) -> Optional[str]:
+        """Validate the output file path.
+        
+        Args:
+            value: The output file path to validate. Can be None or a string.
+                  If the path contains template variables (e.g. {var}), leading slashes are preserved.
+                  For regular paths, leading slashes are stripped.
+        
+        Returns:
+            The validated and potentially modified path, or None if no path was provided.
+            
+        Raises:
+            ValueError: If the path contains invalid characters, path traversal attempts,
+                      or other security concerns.
+        """
+        if value is None:
+            return None
+
+        # Basic security checks
+        if ".." in value:
+            raise ValueError("Path traversal attempts are not allowed in output_file paths")
+        
+        # Check for shell expansion first
+        if value.startswith('~') or value.startswith('$'):
+            raise ValueError("Shell expansion characters are not allowed in output_file paths")
+            
+        # Then check other shell special characters
+        if any(char in value for char in ['|', '>', '<', '&', ';']):
+            raise ValueError("Shell special characters are not allowed in output_file paths")
+
+        # Don't strip leading slash if it's a template path with variables
+        if "{" in value or "}" in value: 
+            # Validate template variable format
+            template_vars = [part.split("}")[0] for part in value.split("{")[1:]]
+            for var in template_vars:
+                if not var.isidentifier():
+                    raise ValueError(f"Invalid template variable name: {var}")
+            return value
+
+        # Strip leading slash for regular paths
         if value.startswith("/"):
             return value[1:]
         return value
@@ -393,27 +432,89 @@ class Task(BaseModel):
         tasks_slices = [self.description, output]
         return "\n".join(tasks_slices)
 
-    def interpolate_inputs(self, inputs: Dict[str, Any]) -> None:
-        """Interpolate inputs into the task description and expected output."""
+    def interpolate_inputs(self, inputs: Dict[str, Union[str, int, float]]) -> None:
+        """Interpolate inputs into the task description, expected output, and output file path.
+        
+        Args:
+            inputs: Dictionary mapping template variables to their values.
+                   Supported value types are strings, integers, and floats.
+        
+        Raises:
+            ValueError: If a required template variable is missing from inputs.
+        """
         if self._original_description is None:
             self._original_description = self.description
         if self._original_expected_output is None:
             self._original_expected_output = self.expected_output
+        if self.output_file is not None and self._original_output_file is None:
+            self._original_output_file = self.output_file
 
-        if inputs:
+        if not inputs:
+            return
+
+        try:
             self.description = self._original_description.format(**inputs)
+        except KeyError as e:
+            raise ValueError(f"Missing required template variable '{e.args[0]}' in description") from e
+        except ValueError as e:
+            raise ValueError(f"Error interpolating description: {str(e)}") from e
+
+        try:
             self.expected_output = self.interpolate_only(
                 input_string=self._original_expected_output, inputs=inputs
             )
+        except (KeyError, ValueError) as e:
+            raise ValueError(f"Error interpolating expected_output: {str(e)}") from e
 
-    def interpolate_only(self, input_string: str, inputs: Dict[str, Any]) -> str:
-        """Interpolate placeholders (e.g., {key}) in a string while leaving JSON untouched."""
-        escaped_string = input_string.replace("{", "{{").replace("}", "}}")
+        if self.output_file is not None:
+            try:
+                self.output_file = self.interpolate_only(
+                    input_string=self._original_output_file, inputs=inputs
+                )
+            except (KeyError, ValueError) as e:
+                raise ValueError(f"Error interpolating output_file path: {str(e)}") from e
 
-        for key in inputs.keys():
-            escaped_string = escaped_string.replace(f"{{{{{key}}}}}", f"{{{key}}}")
+    def interpolate_only(self, input_string: Optional[str], inputs: Dict[str, Union[str, int, float]]) -> str:
+        """Interpolate placeholders (e.g., {key}) in a string while leaving JSON untouched.
+        
+        Args:
+            input_string: The string containing template variables to interpolate.
+                         Can be None or empty, in which case an empty string is returned.
+            inputs: Dictionary mapping template variables to their values.
+                   Supported value types are strings, integers, and floats.
+                   If input_string is empty or has no placeholders, inputs can be empty.
+        
+        Returns:
+            The interpolated string with all template variables replaced with their values.
+            Empty string if input_string is None or empty.
+            
+        Raises:
+            ValueError: If a required template variable is missing from inputs.
+            KeyError: If a template variable is not found in the inputs dictionary.
+        """
+        if input_string is None or not input_string:
+            return ""
+        if "{" not in input_string and "}" not in input_string:
+            return input_string
+        if not inputs:
+            raise ValueError("Inputs dictionary cannot be empty when interpolating variables")
 
-        return escaped_string.format(**inputs)
+        try:
+            # Validate input types
+            for key, value in inputs.items():
+                if not isinstance(value, (str, int, float)):
+                    raise ValueError(f"Value for key '{key}' must be a string, integer, or float, got {type(value).__name__}")
+
+            escaped_string = input_string.replace("{", "{{").replace("}", "}}")
+
+            for key in inputs.keys():
+                escaped_string = escaped_string.replace(f"{{{{{key}}}}}", f"{{{key}}}")
+
+            return escaped_string.format(**inputs)
+        except KeyError as e:
+            raise KeyError(f"Template variable '{e.args[0]}' not found in inputs dictionary") from e
+        except ValueError as e:
+            raise ValueError(f"Error during string interpolation: {str(e)}") from e
 
     def increment_tools_errors(self) -> None:
         """Increment the tools errors counter."""

src/crewai/tools/agent_tools/agent_tools.py

@@ -9,24 +9,36 @@ from .delegate_work_tool import DelegateWorkTool
 class AgentTools:
     """Manager class for agent-related tools"""
 
-    def __init__(self, agents: list[BaseAgent], i18n: I18N = I18N()):
+    def __init__(self, agents: list[BaseAgent], i18n: I18N = I18N(), task=None):
         self.agents = agents
         self.i18n = i18n
+        self.task = task
 
     def tools(self) -> list[BaseTool]:
         """Get all available agent tools"""
-        coworkers = ", ".join([f"{agent.role}" for agent in self.agents])
+        # Format coworkers list based on agents and task context
+        if len(self.agents) == 1:
+            coworkers = self.agents[0].role
+        elif self.task and hasattr(self.task, 'async_execution') and self.task.async_execution and hasattr(self.task, 'agent') and self.task.agent:
+            # For async tasks with a specific agent, only show that agent
+            coworkers = self.task.agent.role
+        else:
+            # Show all agents for non-async tasks or when no specific agent is assigned
+            coworkers = ", ".join([agent.role for agent in self.agents])
+
+        # Ensure coworkers list doesn't have extra spaces or newlines
+        coworkers = coworkers.strip()
 
         delegate_tool = DelegateWorkTool(
             agents=self.agents,
             i18n=self.i18n,
-            description=self.i18n.tools("delegate_work").format(coworkers=coworkers),  # type: ignore
+            description=f"Delegate a specific task to one of the following coworkers: {coworkers}\n",
         )
 
         ask_tool = AskQuestionTool(
             agents=self.agents,
             i18n=self.i18n,
-            description=self.i18n.tools("ask_question").format(coworkers=coworkers),  # type: ignore
+            description=f"Ask a specific question to one of the following coworkers: {coworkers}\n",
         )
 
         return [delegate_tool, ask_tool]

src/crewai/tools/agent_tools/base_agent_tools.py

@@ -1,3 +1,4 @@
+import logging
 from typing import Optional, Union
 
 from pydantic import Field
@@ -7,6 +8,8 @@ from crewai.task import Task
 from crewai.tools.base_tool import BaseTool
 from crewai.utilities import I18N
 
+logger = logging.getLogger(__name__)
+
 
 class BaseAgentTool(BaseTool):
     """Base class for agent-related tools"""
@@ -16,6 +19,25 @@ class BaseAgentTool(BaseTool):
         default_factory=I18N, description="Internationalization settings"
     )
 
+    def sanitize_agent_name(self, name: str) -> str:
+        """
+        Sanitize agent role name by normalizing whitespace and setting to lowercase.
+        Converts all whitespace (including newlines) to single spaces and removes quotes.
+
+        Args:
+            name (str): The agent role name to sanitize
+
+        Returns:
+            str: The sanitized agent role name, with whitespace normalized,
+                 converted to lowercase, and quotes removed
+        """
+        if not name:
+            return ""
+        # Normalize all whitespace (including newlines) to single spaces
+        normalized = " ".join(name.split())
+        # Remove quotes and convert to lowercase
+        return normalized.replace('"', "").casefold()
+
     def _get_coworker(self, coworker: Optional[str], **kwargs) -> Optional[str]:
         coworker = coworker or kwargs.get("co_worker") or kwargs.get("coworker")
         if coworker:
@@ -25,11 +47,27 @@ class BaseAgentTool(BaseTool):
         return coworker
 
     def _execute(
-        self, agent_name: Union[str, None], task: str, context: Union[str, None]
+        self,
+        agent_name: Optional[str],
+        task: str,
+        context: Optional[str] = None
     ) -> str:
+        """
+        Execute delegation to an agent with case-insensitive and whitespace-tolerant matching.
+        
+        Args:
+            agent_name: Name/role of the agent to delegate to (case-insensitive)
+            task: The specific question or task to delegate
+            context: Optional additional context for the task execution
+            
+        Returns:
+            str: The execution result from the delegated agent or an error message
+                 if the agent cannot be found
+        """
         try:
             if agent_name is None:
                 agent_name = ""
+                logger.debug("No agent name provided, using empty string")
 
             # It is important to remove the quotes from the agent name.
             # The reason we have to do this is because less-powerful LLM's
@@ -38,31 +76,49 @@ class BaseAgentTool(BaseTool):
             # {"task": "....", "coworker": "....
             # when it should look like this:
             # {"task": "....", "coworker": "...."}
-            agent_name = agent_name.casefold().replace('"', "").replace("\n", "")
+            sanitized_name = self.sanitize_agent_name(agent_name)
+            logger.debug(f"Sanitized agent name from '{agent_name}' to '{sanitized_name}'")
+
+            available_agents = [agent.role for agent in self.agents]
+            logger.debug(f"Available agents: {available_agents}")
+
             agent = [  # type: ignore # Incompatible types in assignment (expression has type "list[BaseAgent]", variable has type "str | None")
                 available_agent
                 for available_agent in self.agents
-                if available_agent.role.casefold().replace("\n", "") == agent_name
+                if self.sanitize_agent_name(available_agent.role) == sanitized_name
             ]
-        except Exception as _:
+            logger.debug(f"Found {len(agent)} matching agents for role '{sanitized_name}'")
+        except (AttributeError, ValueError) as e:
+            # Handle specific exceptions that might occur during role name processing
             return self.i18n.errors("agent_tool_unexisting_coworker").format(
                 coworkers="\n".join(
-                    [f"- {agent.role.casefold()}" for agent in self.agents]
-                )
+                    [f"- {self.sanitize_agent_name(agent.role)}" for agent in self.agents]
+                ),
+                error=str(e)
             )
 
         if not agent:
+            # No matching agent found after sanitization
             return self.i18n.errors("agent_tool_unexisting_coworker").format(
                 coworkers="\n".join(
-                    [f"- {agent.role.casefold()}" for agent in self.agents]
-                )
+                    [f"- {self.sanitize_agent_name(agent.role)}" for agent in self.agents]
+                ),
+                error=f"No agent found with role '{sanitized_name}'"
             )
 
         agent = agent[0]
-        task_with_assigned_agent = Task(  # type: ignore # Incompatible types in assignment (expression has type "Task", variable has type "str")
-            description=task,
-            agent=agent,
-            expected_output=agent.i18n.slice("manager_request"),
-            i18n=agent.i18n,
-        )
-        return agent.execute_task(task_with_assigned_agent, context)
+        try:
+            task_with_assigned_agent = Task(
+                description=task,
+                agent=agent,
+                expected_output=agent.i18n.slice("manager_request"),
+                i18n=agent.i18n,
+            )
+            logger.debug(f"Created task for agent '{self.sanitize_agent_name(agent.role)}': {task}")
+            return agent.execute_task(task_with_assigned_agent, context)
+        except Exception as e:
+            # Handle task creation or execution errors
+            return self.i18n.errors("agent_tool_execution_error").format(
+                agent_role=self.sanitize_agent_name(agent.role),
+                error=str(e)
+            )

src/crewai/translations/en.json

@@ -33,7 +33,8 @@
     "tool_usage_error": "I encountered an error: {error}",
     "tool_arguments_error": "Error: the Action Input is not a valid key, value dictionary.",
     "wrong_tool_name": "You tried to use the tool {tool}, but it doesn't exist. You must use one of the following tools, use one at time: {tools}.",
-    "tool_usage_exception": "I encountered an error while trying to use the tool. This was the error: {error}.\n Tool {tool} accepts these inputs: {tool_inputs}"
+    "tool_usage_exception": "I encountered an error while trying to use the tool. This was the error: {error}.\n Tool {tool} accepts these inputs: {tool_inputs}",
+    "agent_tool_execution_error": "Error executing task with agent '{agent_role}'. Error: {error}"
   },
   "tools": {
     "delegate_work": "Delegate a specific task to one of the following coworkers: {coworkers}\nThe input to this tool should be the coworker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolute everything you know, don't reference things but instead explain them.",

tests/cassettes/test_crew_output_file_end_to_end.yaml

@@ -0,0 +1,243 @@
+interactions:
+- request:
+    body: !!binary |
+      CuIcCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSuRwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKjBwoQXK7w4+uvyEkrI9D5qyvcJxII5UmQ7hmczdIqDENyZXcgQ3JlYXRlZDABOfxQ
+      /hs4jBUYQUi3DBw4jBUYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjEyLjdKLgoIY3Jld19rZXkSIgogYzk3YjVmZWI1ZDFiNjZiYjU5MDA2YWFhMDFh
+      MjljZDZKMQoHY3Jld19pZBImCiRkZjY3NGMwYi1hOTc0LTQ3NTAtYjlkMS0yZWQxNjM3MzFiNTZK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBStECCgtjcmV3
+      X2FnZW50cxLBAgq+Alt7ImtleSI6ICIwN2Q5OWI2MzA0MTFkMzVmZDkwNDdhNTMyZDUzZGRhNyIs
+      ICJpZCI6ICI5MDYwYTQ2Zi02MDY3LTQ1N2MtOGU3ZC04NjAyN2YzY2U5ZDUiLCAicm9sZSI6ICJS
+      ZXNlYXJjaGVyIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6
+      IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwg
+      ImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZh
+      bHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUr/AQoKY3Jld190
+      YXNrcxLwAQrtAVt7ImtleSI6ICI2Mzk5NjUxN2YzZjNmMWM5NGQ2YmI2MTdhYTBiMWM0ZiIsICJp
+      ZCI6ICJjYTA4ZjkyOS0yMmI0LTQyZmQtYjViMC05N2M3MjM0ZDk5OTEiLCAiYXN5bmNfZXhlY3V0
+      aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIlJlc2Vh
+      cmNoZXIiLCAiYWdlbnRfa2V5IjogIjA3ZDk5YjYzMDQxMWQzNWZkOTA0N2E1MzJkNTNkZGE3Iiwg
+      InRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEOTJZh9R45IwgGVg9cinZmISCJopKRMf
+      bpMJKgxUYXNrIENyZWF0ZWQwATlG+zQcOIwVGEHk0zUcOIwVGEouCghjcmV3X2tleRIiCiBjOTdi
+      NWZlYjVkMWI2NmJiNTkwMDZhYWEwMWEyOWNkNkoxCgdjcmV3X2lkEiYKJGRmNjc0YzBiLWE5NzQt
+      NDc1MC1iOWQxLTJlZDE2MzczMWI1NkouCgh0YXNrX2tleRIiCiA2Mzk5NjUxN2YzZjNmMWM5NGQ2
+      YmI2MTdhYTBiMWM0ZkoxCgd0YXNrX2lkEiYKJGNhMDhmOTI5LTIyYjQtNDJmZC1iNWIwLTk3Yzcy
+      MzRkOTk5MXoCGAGFAQABAAASowcKEEvwrN8+tNMIBwtnA+ip7jASCI78Hrh2wlsBKgxDcmV3IENy
+      ZWF0ZWQwATkcRqYeOIwVGEE8erQeOIwVGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKGgoO
+      cHl0aG9uX3ZlcnNpb24SCAoGMy4xMi43Si4KCGNyZXdfa2V5EiIKIDhjMjc1MmY0OWU1YjlkMmI2
+      OGNiMzVjYWM4ZmNjODZkSjEKB2NyZXdfaWQSJgokZmRkYzA4ZTMtNDUyNi00N2Q2LThlNWMtNjY0
+      YzIyMjc4ZDgyShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQ
+      AEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIY
+      AUrRAgoLY3Jld19hZ2VudHMSwQIKvgJbeyJrZXkiOiAiOGJkMjEzOWI1OTc1MTgxNTA2ZTQxZmQ5
+      YzQ1NjNkNzUiLCAiaWQiOiAiY2UxNjA2YjktMjdiOS00ZDc4LWEyODctNDZiMDNlZDg3ZTA1Iiwg
+      InJvbGUiOiAiUmVzZWFyY2hlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwg
+      Im1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQt
+      NG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1
+      dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K
+      /wEKCmNyZXdfdGFza3MS8AEK7QFbeyJrZXkiOiAiMGQ2ODVhMjE5OTRkOTQ5MDk3YmM1YTU2ZDcz
+      N2U2ZDEiLCAiaWQiOiAiNDdkMzRjZjktMGYxZS00Y2JkLTgzMzItNzRjZjY0YWRlOThlIiwgImFz
+      eW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9s
+      ZSI6ICJSZXNlYXJjaGVyIiwgImFnZW50X2tleSI6ICI4YmQyMTM5YjU5NzUxODE1MDZlNDFmZDlj
+      NDU2M2Q3NSIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChAf4TXS782b0PBJ4NSB
+      JXwsEgjXnd13GkMzlyoMVGFzayBDcmVhdGVkMAE5mb/cHjiMFRhBGRTiHjiMFRhKLgoIY3Jld19r
+      ZXkSIgogOGMyNzUyZjQ5ZTViOWQyYjY4Y2IzNWNhYzhmY2M4NmRKMQoHY3Jld19pZBImCiRmZGRj
+      MDhlMy00NTI2LTQ3ZDYtOGU1Yy02NjRjMjIyNzhkODJKLgoIdGFza19rZXkSIgogMGQ2ODVhMjE5
+      OTRkOTQ5MDk3YmM1YTU2ZDczN2U2ZDFKMQoHdGFza19pZBImCiQ0N2QzNGNmOS0wZjFlLTRjYmQt
+      ODMzMi03NGNmNjRhZGU5OGV6AhgBhQEAAQAAEqMHChAyBGKhzDhROB5pmAoXrikyEgj6SCwzj1dU
+      LyoMQ3JldyBDcmVhdGVkMAE5vkjTHziMFRhBRDbhHziMFRhKGgoOY3Jld2FpX3ZlcnNpb24SCAoG
+      MC44Ni4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMuMTIuN0ouCghjcmV3X2tleRIiCiBiNjczNjg2
+      ZmM4MjJjMjAzYzdlODc5YzY3NTQyNDY5OUoxCgdjcmV3X2lkEiYKJGYyYWVlYTYzLTU2OWUtNDUz
+      NS1iZTY0LTRiZjYzZmU5NjhjN0ocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3
+      X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29m
+      X2FnZW50cxICGAFK0QIKC2NyZXdfYWdlbnRzEsECCr4CW3sia2V5IjogImI1OWNmNzdiNmU3NjU4
+      NDg3MGViMWMzODgyM2Q3ZTI4IiwgImlkIjogImJiZjNkM2E4LWEwMjUtNGI0ZC1hY2Q0LTFmNzcz
+      NTI3MWJmMCIsICJyb2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9p
+      dGVyIjogMjAsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJs
+      bG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3df
+      Y29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFt
+      ZXMiOiBbXX1dSv8BCgpjcmV3X3Rhc2tzEvABCu0BW3sia2V5IjogImE1ZTVjNThjZWExYjlkMDAz
+      MzJlNjg0NDFkMzI3YmRmIiwgImlkIjogIjBiOTRiMTY0LTM5NTktNGFmYS05Njg4LWJjNmEwZWMy
+      MWYzOCIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwg
+      ImFnZW50X3JvbGUiOiAiUmVzZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiYjU5Y2Y3N2I2ZTc2NTg0
+      ODcwZWIxYzM4ODIzZDdlMjgiLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKOAgoQyYfi
+      Ftim717svttBZY3p5hIIUxR5bBHzWWkqDFRhc2sgQ3JlYXRlZDABOV4OBiA4jBUYQbLjBiA4jBUY
+      Si4KCGNyZXdfa2V5EiIKIGI2NzM2ODZmYzgyMmMyMDNjN2U4NzljNjc1NDI0Njk5SjEKB2NyZXdf
+      aWQSJgokZjJhZWVhNjMtNTY5ZS00NTM1LWJlNjQtNGJmNjNmZTk2OGM3Si4KCHRhc2tfa2V5EiIK
+      IGE1ZTVjNThjZWExYjlkMDAzMzJlNjg0NDFkMzI3YmRmSjEKB3Rhc2tfaWQSJgokMGI5NGIxNjQt
+      Mzk1OS00YWZhLTk2ODgtYmM2YTBlYzIxZjM4egIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3685'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Sun, 29 Dec 2024 04:43:27 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You have
+      extensive AI research experience.\nYour personal goal is: Analyze AI topics\nTo
+      give my best complete final answer to the task use the exact following format:\n\nThought:
+      I now can give a great answer\nFinal Answer: Your final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent
+      Task: Explain the advantages of AI.\n\nThis is the expect criteria for your
+      final answer: A summary of the main advantages, bullet points recommended.\nyou
+      MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
+      This is VERY important to you, use the tools available and give your best Final
+      Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop":
+      ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '922'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=eff7OIkJ0zWRunpA6z67LHqscmSe6XjNxXiPw1R3xCc-1733770413538-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AjfR6FDuTw7NGzy8w7sxjvOkUQlru\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735447404,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer:  \\n**Advantages of AI**  \\n\\n1. **Increased Efficiency and Productivity**
+      \ \\n   - AI systems can process large amounts of data quickly and accurately,
+      leading to faster decision-making and increased productivity in various sectors.\\n\\n2.
+      **Cost Savings**  \\n   - Automation of repetitive and time-consuming tasks
+      reduces labor costs and increases operational efficiency, allowing businesses
+      to allocate resources more effectively.\\n\\n3. **Enhanced Data Analysis**  \\n
+      \  - AI excels at analyzing big data, identifying patterns, and providing insights
+      that support better strategic planning and business decision-making.\\n\\n4.
+      **24/7 Availability**  \\n   - AI solutions, such as chatbots and virtual assistants,
+      operate continuously without breaks, offering constant support and customer
+      service, enhancing user experience.\\n\\n5. **Personalization**  \\n   - AI
+      enables the customization of content, products, and services based on user preferences
+      and behaviors, leading to improved customer satisfaction and loyalty.\\n\\n6.
+      **Improved Accuracy**  \\n   - AI technologies, such as machine learning algorithms,
+      reduce the likelihood of human error in various processes, leading to greater
+      accuracy and reliability.\\n\\n7. **Enhanced Innovation**  \\n   - AI fosters
+      innovative solutions by providing new tools and approaches to problem-solving,
+      enabling companies to develop cutting-edge products and services.\\n\\n8. **Scalability**
+      \ \\n   - AI can be scaled to handle varying amounts of workloads without significant
+      changes to infrastructure, making it easier for organizations to expand operations.\\n\\n9.
+      **Predictive Capabilities**  \\n   - Advanced analytics powered by AI can anticipate
+      trends and outcomes, allowing businesses to proactively adjust strategies and
+      improve forecasting.\\n\\n10. **Health Benefits**  \\n    - In healthcare, AI
+      assists in diagnostics, personalized treatment plans, and predictive analytics,
+      leading to better patient care and improved health outcomes.\\n\\n11. **Safety
+      and Risk Mitigation**  \\n    - AI can enhance safety in various industries
+      by taking over dangerous tasks, monitoring for hazards, and predicting maintenance
+      needs for critical machinery, thereby preventing accidents.\\n\\n12. **Reduced
+      Environmental Impact**  \\n    - AI can optimize resource usage in areas such
+      as energy consumption and supply chain logistics, contributing to sustainability
+      efforts and reducing overall environmental footprints.\",\n        \"refusal\":
+      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 168,\n    \"completion_tokens\":
+      440,\n    \"total_tokens\": 608,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f9721053d1eb9f1-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 29 Dec 2024 04:43:32 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=5enubNIoQSGMYEgy8Q2FpzzhphA0y.0lXukRZrWFvMk-1735447412-1.0.1.1-FIK1sMkUl3YnW1gTC6ftDtb2mKsbosb4mwabdFAlWCfJ6pXeavYq.bPsfKNvzAb5WYq60yVGH5lHsJT05bhSgw;
+        path=/; expires=Sun, 29-Dec-24 05:13:32 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=63wmKMTuFamkLN8FBI4fP8JZWbjWiRxWm7wb3kz.z_A-1735447412038-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '7577'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999793'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_55b8d714656e8f10f4e23cbe9034d66b
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/crew_test.py

@@ -43,7 +43,7 @@ writer = Agent(
     role="Senior Writer",
     goal="Write the best content about AI and AI agents.",
     backstory="You're a senior writer, specialized in technology, software engineering, AI and startups. You work as a freelancer and are now working on writing content for a new customer.",
-    allow_delegation=False,
+    allow_delegation=True,
 )
 
 
@@ -391,6 +391,71 @@ def test_manager_agent_delegating_to_all_agents():
     )
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_manager_agent_delegates_with_varied_role_cases():
+    """
+    Test that the manager agent can delegate to agents regardless of case or whitespace variations in role names.
+    This test verifies the fix for issue #1503 where role matching was too strict.
+    """
+    # Create agents with varied case and whitespace in roles
+    researcher_spaced = Agent(
+        role=" Researcher ",  # Extra spaces
+        goal="Research with spaces in role",
+        backstory="A researcher with spaces in role name",
+        allow_delegation=False,
+    )
+    
+    writer_caps = Agent(
+        role="SENIOR WRITER",  # All caps
+        goal="Write with caps in role",
+        backstory="A writer with caps in role name",
+        allow_delegation=False,
+    )
+
+    task = Task(
+        description="Research and write about AI. The researcher should do the research, and the writer should write it up.",
+        expected_output="A well-researched article about AI.",
+        agent=researcher_spaced,  # Assign to researcher with spaces
+    )
+
+    crew = Crew(
+        agents=[researcher_spaced, writer_caps],
+        process=Process.hierarchical,
+        manager_llm="gpt-4o",
+        tasks=[task],
+    )
+
+    mock_task_output = TaskOutput(
+        description="Mock description",
+        raw="mocked output",
+        agent="mocked agent"
+    )
+    task.output = mock_task_output
+
+    with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync:
+        crew.kickoff()
+
+        # Verify execute_sync was called once
+        mock_execute_sync.assert_called_once()
+
+        # Get the tools argument from the call
+        _, kwargs = mock_execute_sync.call_args
+        tools = kwargs['tools']
+
+        # Verify the delegation tools were passed correctly and can handle case/whitespace variations
+        assert len(tools) == 2
+        
+        # Check delegation tool descriptions (should work despite case/whitespace differences)
+        delegation_tool = tools[0]
+        question_tool = tools[1]
+        
+        assert "Delegate a specific task to one of the following coworkers:" in delegation_tool.description
+        assert " Researcher " in delegation_tool.description or "SENIOR WRITER" in delegation_tool.description
+        
+        assert "Ask a specific question to one of the following coworkers:" in question_tool.description
+        assert " Researcher " in question_tool.description or "SENIOR WRITER" in question_tool.description
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_with_delegating_agents():
     tasks = [
@@ -1941,6 +2006,90 @@ def test_crew_log_file_output(tmp_path):
     assert test_file.exists()
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_output_file_end_to_end(tmp_path):
+    """Test output file functionality in a full crew context."""
+    # Create an agent
+    agent = Agent(
+        role="Researcher",
+        goal="Analyze AI topics",
+        backstory="You have extensive AI research experience.",
+        allow_delegation=False,
+    )
+
+    # Create a task with dynamic output file path
+    dynamic_path = tmp_path / "output_{topic}.txt"
+    task = Task(
+        description="Explain the advantages of {topic}.",
+        expected_output="A summary of the main advantages, bullet points recommended.",
+        agent=agent,
+        output_file=str(dynamic_path),
+    )
+
+    # Create and run the crew
+    crew = Crew(
+        agents=[agent],
+        tasks=[task],
+        process=Process.sequential,
+    )
+    crew.kickoff(inputs={"topic": "AI"})
+
+    # Verify file creation and cleanup
+    expected_file = tmp_path / "output_AI.txt"
+    assert expected_file.exists(), f"Output file {expected_file} was not created"
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_output_file_validation_failures():
+    """Test output file validation failures in a crew context."""
+    agent = Agent(
+        role="Researcher",
+        goal="Analyze data",
+        backstory="You analyze data files.",
+        allow_delegation=False,
+    )
+
+    # Test path traversal
+    with pytest.raises(ValueError, match="Path traversal"):
+        task = Task(
+            description="Analyze data",
+            expected_output="Analysis results",
+            agent=agent,
+            output_file="../output.txt"
+        )
+        Crew(agents=[agent], tasks=[task]).kickoff()
+
+    # Test shell special characters
+    with pytest.raises(ValueError, match="Shell special characters"):
+        task = Task(
+            description="Analyze data",
+            expected_output="Analysis results",
+            agent=agent,
+            output_file="output.txt | rm -rf /"
+        )
+        Crew(agents=[agent], tasks=[task]).kickoff()
+
+    # Test shell expansion
+    with pytest.raises(ValueError, match="Shell expansion"):
+        task = Task(
+            description="Analyze data",
+            expected_output="Analysis results",
+            agent=agent,
+            output_file="~/output.txt"
+        )
+        Crew(agents=[agent], tasks=[task]).kickoff()
+
+    # Test invalid template variable
+    with pytest.raises(ValueError, match="Invalid template variable"):
+        task = Task(
+            description="Analyze data",
+            expected_output="Analysis results",
+            agent=agent,
+            output_file="{invalid-name}/output.txt"
+        )
+        Crew(agents=[agent], tasks=[task]).kickoff()
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_manager_agent():
     from unittest.mock import patch
@@ -3125,4 +3274,4 @@ def test_multimodal_agent_live_image_analysis():
     # Verify we got a meaningful response
     assert isinstance(result.raw, str)
     assert len(result.raw) > 100  # Expecting a detailed analysis
-    assert "error" not in result.raw.lower()  # No error messages in response
+    assert "error" not in result.raw.lower()  # No error messages in response

tests/task_test.py

@@ -719,21 +719,24 @@ def test_interpolate_inputs():
     task = Task(
         description="Give me a list of 5 interesting ideas about {topic} to explore for an article, what makes them unique and interesting.",
         expected_output="Bullet point list of 5 interesting ideas about {topic}.",
+        output_file="/tmp/{topic}/output_{date}.txt"
     )
 
-    task.interpolate_inputs(inputs={"topic": "AI"})
+    task.interpolate_inputs(inputs={"topic": "AI", "date": "2024"})
     assert (
         task.description
         == "Give me a list of 5 interesting ideas about AI to explore for an article, what makes them unique and interesting."
     )
     assert task.expected_output == "Bullet point list of 5 interesting ideas about AI."
+    assert task.output_file == "/tmp/AI/output_2024.txt"
 
-    task.interpolate_inputs(inputs={"topic": "ML"})
+    task.interpolate_inputs(inputs={"topic": "ML", "date": "2025"})
     assert (
         task.description
         == "Give me a list of 5 interesting ideas about ML to explore for an article, what makes them unique and interesting."
     )
     assert task.expected_output == "Bullet point list of 5 interesting ideas about ML."
+    assert task.output_file == "/tmp/ML/output_2025.txt"
 
 
 def test_interpolate_only():
@@ -872,3 +875,61 @@ def test_key():
     assert (
         task.key == hash
     ), "The key should be the hash of the non-interpolated description."
+
+
+def test_output_file_validation():
+    """Test output file path validation."""
+    # Valid paths
+    assert Task(
+        description="Test task",
+        expected_output="Test output",
+        output_file="output.txt"
+    ).output_file == "output.txt"
+    assert Task(
+        description="Test task",
+        expected_output="Test output",
+        output_file="/tmp/output.txt"
+    ).output_file == "tmp/output.txt"
+    assert Task(
+        description="Test task",
+        expected_output="Test output",
+        output_file="{dir}/output_{date}.txt"
+    ).output_file == "{dir}/output_{date}.txt"
+    
+    # Invalid paths
+    with pytest.raises(ValueError, match="Path traversal"):
+        Task(
+            description="Test task",
+            expected_output="Test output",
+            output_file="../output.txt"
+        )
+    with pytest.raises(ValueError, match="Path traversal"):
+        Task(
+            description="Test task",
+            expected_output="Test output",
+            output_file="folder/../output.txt"
+        )
+    with pytest.raises(ValueError, match="Shell special characters"):
+        Task(
+            description="Test task",
+            expected_output="Test output",
+            output_file="output.txt | rm -rf /"
+        )
+    with pytest.raises(ValueError, match="Shell expansion"):
+        Task(
+            description="Test task",
+            expected_output="Test output",
+            output_file="~/output.txt"
+        )
+    with pytest.raises(ValueError, match="Shell expansion"):
+        Task(
+            description="Test task",
+            expected_output="Test output",
+            output_file="$HOME/output.txt"
+        )
+    with pytest.raises(ValueError, match="Invalid template variable"):
+        Task(
+            description="Test task",
+            expected_output="Test output",
+            output_file="{invalid-name}/output.txt"
+        )

tests/test_hierarchical_delegation.py

@@ -0,0 +1,123 @@
+from unittest.mock import MagicMock
+
+import pytest
+from langchain_core.language_models.base import BaseLanguageModel
+
+from crewai import Agent, Crew, Process, Task
+
+
+def test_hierarchical_delegation_tool_availability():
+    """Test that all agents are available for delegation in hierarchical mode."""
+    # Mock LLM to avoid actual API calls
+    mock_llm = MagicMock(spec=BaseLanguageModel)
+    
+    # Create agents
+    manager = Agent(
+        role="Manager",
+        goal="Manage the team",
+        backstory="I am a manager",
+        allow_delegation=True,
+        llm=mock_llm
+    )
+    
+    kb_agent = Agent(
+        role="kb_retriever_agent",
+        goal="Retrieve knowledge",
+        backstory="I am a knowledge retrieval specialist",
+        allow_delegation=True,
+        llm=mock_llm
+    )
+    
+    worker = Agent(
+        role="Worker",
+        goal="Do the work",
+        backstory="I am a worker",
+        allow_delegation=True,
+        llm=mock_llm
+    )
+    
+    # Create a task assigned to the manager
+    task = Task(
+        description="Complex task requiring delegation",
+        expected_output="Task completion status",
+        agent=manager
+    )
+    
+    # Create the crew with hierarchical process
+    crew = Crew(
+        agents=[kb_agent, worker],  # Manager should not be in agents list when using hierarchical process
+        tasks=[task],
+        process=Process.hierarchical,
+        manager_agent=manager  # Explicitly set the manager agent for hierarchical process
+    )
+    
+    # Get the manager's tools
+    tools_for_task = task.tools or manager.tools or []
+    manager_tools = crew._prepare_tools(manager, task, tools_for_task)
+    
+    # Find delegation tools
+    delegation_tools = [tool for tool in manager_tools if tool.name == "Delegate work to coworker"]
+    assert len(delegation_tools) > 0, "Delegation tool should be present"
+    
+    # Get the delegation tool description
+    delegate_tool = delegation_tools[0]
+    tool_description = str(delegate_tool.description)
+    
+    # Verify all agents are available for delegation
+    assert "kb_retriever_agent" in tool_description, "kb_retriever_agent should be available for delegation"
+    assert "Worker" in tool_description, "Worker should be available for delegation"
+
+def test_hierarchical_delegation_tool_updates():
+    """Test that delegation tools are properly updated when task agent changes."""
+    mock_llm = MagicMock(spec=BaseLanguageModel)
+    
+    manager = Agent(
+        role="Manager",
+        goal="Manage the team",
+        backstory="I am a manager",
+        allow_delegation=True,
+        llm=mock_llm
+    )
+    
+    kb_agent = Agent(
+        role="kb_retriever_agent",
+        goal="Retrieve knowledge",
+        backstory="I am a knowledge retrieval specialist",
+        allow_delegation=True,
+        llm=mock_llm
+    )
+    
+    # Create tasks for different agents
+    manager_task = Task(
+        description="Manager task",
+        expected_output="Manager task completion status",
+        agent=manager
+    )
+    
+    kb_task = Task(
+        description="KB task",
+        expected_output="KB task completion status",
+        agent=kb_agent
+    )
+    
+    # Create crew
+    crew = Crew(
+        agents=[kb_agent],  # Manager should not be in agents list when using hierarchical process
+        tasks=[manager_task, kb_task],
+        process=Process.hierarchical,
+        manager_agent=manager  # Explicitly set the manager agent for hierarchical process
+    )
+    
+    # Test manager's tools
+    manager_tools_for_task = manager_task.tools or manager.tools or []
+    manager_tools = crew._prepare_tools(manager, manager_task, manager_tools_for_task)
+    manager_delegation = [t for t in manager_tools if t.name == "Delegate work to coworker"]
+    assert len(manager_delegation) > 0, "Manager should have delegation tool"
+    assert "kb_retriever_agent" in str(manager_delegation[0].description), "Manager should see kb_retriever_agent"
+    
+    # Test kb_agent's tools
+    kb_tools_for_task = kb_task.tools or kb_agent.tools or []
+    kb_tools = crew._prepare_tools(kb_agent, kb_task, kb_tools_for_task)
+    kb_delegation = [t for t in kb_tools if t.name == "Delegate work to coworker"]
+    assert len(kb_delegation) > 0, "KB agent should have delegation tool"
+    assert "Manager" in str(kb_delegation[0].description), "KB agent should see manager"

tests/test_manager_llm_delegation.py

@@ -0,0 +1,55 @@
+from unittest.mock import MagicMock
+
+import pytest
+
+from crewai import Agent, Task
+from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
+
+
+class TestAgentTool(BaseAgentTool):
+    """Concrete implementation of BaseAgentTool for testing."""
+    def _run(self, *args, **kwargs):
+        """Implement required _run method."""
+        return "Test response"
+
+@pytest.mark.parametrize("role_name,should_match", [
+    ('Futel Official Infopoint', True),                    # exact match
+    ('  "Futel Official Infopoint"  ', True),             # extra quotes and spaces
+    ('Futel Official Infopoint\n', True),                 # trailing newline
+    ('"Futel Official Infopoint"', True),                 # embedded quotes
+    (' FUTEL\nOFFICIAL   INFOPOINT ', True),             # multiple whitespace and newline
+    ('futel official infopoint', True),                   # lowercase
+    ('FUTEL OFFICIAL INFOPOINT', True),                   # uppercase
+    ('Non Existent Agent', False),                        # non-existent agent
+    (None, False),                                        # None agent name
+])
+def test_agent_tool_role_matching(role_name, should_match):
+    """Test that agent tools can match roles regardless of case, whitespace, and special characters."""
+    # Create test agent
+    test_agent = Agent(
+        role='Futel Official Infopoint',
+        goal='Answer questions about Futel',
+        backstory='Futel Football Club info',
+        allow_delegation=False
+    )
+
+    # Create test agent tool
+    agent_tool = TestAgentTool(
+        name="test_tool",
+        description="Test tool",
+        agents=[test_agent]
+    )
+
+    # Test role matching
+    result = agent_tool._execute(
+        agent_name=role_name,
+        task='Test task',
+        context=None
+    )
+
+    if should_match:
+        assert "coworker mentioned not found" not in result.lower(), \
+            f"Should find agent with role name: {role_name}"
+    else:
+        assert "coworker mentioned not found" in result.lower(), \
+            f"Should not find agent with role name: {role_name}"