chore(deps): pin crewai-tools to compatible version ~=0.38.0

fixes [issue](https://github.com/crewAIInc/crewAI/issues/2390)

docs/concepts/event-listener.mdx

@@ -13,7 +13,7 @@ CrewAI provides a powerful event system that allows you to listen for and react
 CrewAI uses an event bus architecture to emit events throughout the execution lifecycle. The event system is built on the following components:
 
 1. **CrewAIEventsBus**: A singleton event bus that manages event registration and emission
-2. **CrewEvent**: Base class for all events in the system
+2. **BaseEvent**: Base class for all events in the system
 3. **BaseEventListener**: Abstract base class for creating custom event listeners
 
 When specific actions occur in CrewAI (like a Crew starting execution, an Agent completing a task, or a tool being used), the system emits corresponding events. You can register handlers for these events to execute custom code when they occur.
@@ -234,7 +234,7 @@ Each event handler receives two parameters:
 1. **source**: The object that emitted the event
 2. **event**: The event instance, containing event-specific data
 
-The structure of the event object depends on the event type, but all events inherit from `CrewEvent` and include:
+The structure of the event object depends on the event type, but all events inherit from `BaseEvent` and include:
 
 - **timestamp**: The time when the event was emitted
 - **type**: A string identifier for the event type

pyproject.toml

@@ -45,7 +45,7 @@ Documentation = "https://docs.crewai.com"
 Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
-tools = ["crewai-tools>=0.37.0"]
+tools = ["crewai-tools~=0.38.0"]
 embeddings = [
     "tiktoken~=0.7.0"
 ]

src/crewai/agents/crew_agent_executor.py

@@ -20,7 +20,6 @@ from crewai.utilities import I18N, Printer
 from crewai.utilities.constants import MAX_LLM_RETRY, TRAINING_DATA_FILE
 from crewai.utilities.events import (
     ToolUsageErrorEvent,
-    ToolUsageStartedEvent,
     crewai_event_bus,
 )
 from crewai.utilities.events.tool_usage_events import ToolUsageStartedEvent
@@ -153,8 +152,21 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                 formatted_answer = self._process_llm_response(answer)
 
                 if isinstance(formatted_answer, AgentAction):
+                    # Extract agent fingerprint if available
+                    fingerprint_context = {}
+                    if (
+                        self.agent
+                        and hasattr(self.agent, "security_config")
+                        and hasattr(self.agent.security_config, "fingerprint")
+                    ):
+                        fingerprint_context = {
+                            "agent_fingerprint": str(
+                                self.agent.security_config.fingerprint
+                            )
+                        }
+
                     tool_result = self._execute_tool_and_check_finality(
-                        formatted_answer
+                        formatted_answer, fingerprint_context=fingerprint_context
                     )
                     formatted_answer = self._handle_agent_action(
                         formatted_answer, tool_result
@@ -360,19 +372,35 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                     content=f"\033[95m## Final Answer:\033[00m \033[92m\n{formatted_answer.output}\033[00m\n\n"
                 )
 
-    def _execute_tool_and_check_finality(self, agent_action: AgentAction) -> ToolResult:
+    def _execute_tool_and_check_finality(
+        self,
+        agent_action: AgentAction,
+        fingerprint_context: Optional[Dict[str, str]] = None,
+    ) -> ToolResult:
         try:
+            fingerprint_context = fingerprint_context or {}
+
             if self.agent:
+                # Create tool usage event with fingerprint information
+                event_data = {
+                    "agent_key": self.agent.key,
+                    "agent_role": self.agent.role,
+                    "tool_name": agent_action.tool,
+                    "tool_args": agent_action.tool_input,
+                    "tool_class": agent_action.tool,
+                    "agent": self.agent,  # Pass the agent object for fingerprint extraction
+                }
+
+                # Include fingerprint context
+                if fingerprint_context:
+                    event_data.update(fingerprint_context)
+
+                # Emit the tool usage started event with agent information
                 crewai_event_bus.emit(
                     self,
-                    event=ToolUsageStartedEvent(
-                        agent_key=self.agent.key,
-                        agent_role=self.agent.role,
-                        tool_name=agent_action.tool,
-                        tool_args=agent_action.tool_input,
-                        tool_class=agent_action.tool,
-                    ),
+                    event=ToolUsageStartedEvent(**event_data),
                 )
+
             tool_usage = ToolUsage(
                 tools_handler=self.tools_handler,
                 tools=self.tools,
@@ -383,6 +411,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                 task=self.task,  # type: ignore[arg-type]
                 agent=self.agent,
                 action=agent_action,
+                fingerprint_context=fingerprint_context,  # Pass fingerprint context
             )
             tool_calling = tool_usage.parse_tool_calling(agent_action.text)
 
@@ -411,16 +440,23 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         except Exception as e:
             # TODO: drop
             if self.agent:
+                error_event_data = {
+                    "agent_key": self.agent.key,
+                    "agent_role": self.agent.role,
+                    "tool_name": agent_action.tool,
+                    "tool_args": agent_action.tool_input,
+                    "tool_class": agent_action.tool,
+                    "error": str(e),
+                    "agent": self.agent,  # Pass the agent object for fingerprint extraction
+                }
+
+                # Include fingerprint context
+                if fingerprint_context:
+                    error_event_data.update(fingerprint_context)
+
                 crewai_event_bus.emit(
                     self,
-                    event=ToolUsageErrorEvent(  # validation error
-                        agent_key=self.agent.key,
-                        agent_role=self.agent.role,
-                        tool_name=agent_action.tool,
-                        tool_args=agent_action.tool_input,
-                        tool_class=agent_action.tool,
-                        error=str(e),
-                    ),
+                    event=ToolUsageErrorEvent(**error_event_data),
                 )
             raise e
 

src/crewai/crew.py

@@ -1156,7 +1156,12 @@ class Crew(BaseModel):
         return required_inputs
 
     def copy(self):
-        """Create a deep copy of the Crew."""
+        """
+        Creates a deep copy of the Crew instance.
+        
+        Returns:
+            Crew: A new instance with copied components
+        """
 
         exclude = {
             "id",
@@ -1168,13 +1173,19 @@ class Crew(BaseModel):
             "_short_term_memory",
             "_long_term_memory",
             "_entity_memory",
+            "_telemetry",
             "agents",
             "tasks",
             "knowledge_sources",
             "knowledge",
+            "manager_agent",
+            "manager_llm",
+
         }
 
         cloned_agents = [agent.copy() for agent in self.agents]
+        manager_agent = self.manager_agent.copy() if self.manager_agent else None
+        manager_llm = shallow_copy(self.manager_llm) if self.manager_llm else None
 
         task_mapping = {}
 
@@ -1207,6 +1218,8 @@ class Crew(BaseModel):
             tasks=cloned_tasks,
             knowledge_sources=existing_knowledge_sources,
             knowledge=existing_knowledge,
+            manager_agent=manager_agent,
+            manager_llm=manager_llm,
         )
 
         return copied_crew

src/crewai/task.py

@@ -388,7 +388,7 @@ class Task(BaseModel):
             tools = tools or self.tools or []
 
             self.processed_by_agents.add(agent.role)
-            crewai_event_bus.emit(self, TaskStartedEvent(context=context))
+            crewai_event_bus.emit(self, TaskStartedEvent(context=context, task=self))
             result = agent.execute_task(
                 task=self,
                 context=context,
@@ -464,11 +464,11 @@ class Task(BaseModel):
                     )
                 )
                 self._save_file(content)
-            crewai_event_bus.emit(self, TaskCompletedEvent(output=task_output))
+            crewai_event_bus.emit(self, TaskCompletedEvent(output=task_output, task=self))
             return task_output
         except Exception as e:
             self.end_time = datetime.datetime.now()
-            crewai_event_bus.emit(self, TaskFailedEvent(error=str(e)))
+            crewai_event_bus.emit(self, TaskFailedEvent(error=str(e), task=self))
             raise e  # Re-raise the exception after emitting the event
 
     def prompt(self) -> str:

src/crewai/telemetry/telemetry.py

@@ -112,6 +112,23 @@ class Telemetry:
             self._add_attribute(span, "crew_memory", crew.memory)
             self._add_attribute(span, "crew_number_of_tasks", len(crew.tasks))
             self._add_attribute(span, "crew_number_of_agents", len(crew.agents))
+
+            # Add fingerprint data
+            if hasattr(crew, "fingerprint") and crew.fingerprint:
+                self._add_attribute(span, "crew_fingerprint", crew.fingerprint.uuid_str)
+                self._add_attribute(
+                    span,
+                    "crew_fingerprint_created_at",
+                    crew.fingerprint.created_at.isoformat(),
+                )
+                # Add fingerprint metadata if it exists
+                if hasattr(crew.fingerprint, "metadata") and crew.fingerprint.metadata:
+                    self._add_attribute(
+                        span,
+                        "crew_fingerprint_metadata",
+                        json.dumps(crew.fingerprint.metadata),
+                    )
+
             if crew.share_crew:
                 self._add_attribute(
                     span,
@@ -129,17 +146,43 @@ class Telemetry:
                                 "max_rpm": agent.max_rpm,
                                 "i18n": agent.i18n.prompt_file,
                                 "function_calling_llm": (
-                                    agent.function_calling_llm.model
-                                    if agent.function_calling_llm
+                                    getattr(
+                                        getattr(agent, "function_calling_llm", None),
+                                        "model",
+                                        "",
+                                    )
+                                    if getattr(agent, "function_calling_llm", None)
                                     else ""
                                 ),
                                 "llm": agent.llm.model,
                                 "delegation_enabled?": agent.allow_delegation,
-                                "allow_code_execution?": agent.allow_code_execution,
-                                "max_retry_limit": agent.max_retry_limit,
+                                "allow_code_execution?": getattr(
+                                    agent, "allow_code_execution", False
+                                ),
+                                "max_retry_limit": getattr(agent, "max_retry_limit", 3),
                                 "tools_names": [
                                     tool.name.casefold() for tool in agent.tools or []
                                 ],
+                                # Add agent fingerprint data if sharing crew details
+                                "fingerprint": (
+                                    getattr(
+                                        getattr(agent, "fingerprint", None),
+                                        "uuid_str",
+                                        None,
+                                    )
+                                ),
+                                "fingerprint_created_at": (
+                                    created_at.isoformat()
+                                    if (
+                                        created_at := getattr(
+                                            getattr(agent, "fingerprint", None),
+                                            "created_at",
+                                            None,
+                                        )
+                                    )
+                                    is not None
+                                    else None
+                                ),
                             }
                             for agent in crew.agents
                         ]
@@ -169,6 +212,17 @@ class Telemetry:
                                 "tools_names": [
                                     tool.name.casefold() for tool in task.tools or []
                                 ],
+                                # Add task fingerprint data if sharing crew details
+                                "fingerprint": (
+                                    task.fingerprint.uuid_str
+                                    if hasattr(task, "fingerprint") and task.fingerprint
+                                    else None
+                                ),
+                                "fingerprint_created_at": (
+                                    task.fingerprint.created_at.isoformat()
+                                    if hasattr(task, "fingerprint") and task.fingerprint
+                                    else None
+                                ),
                             }
                             for task in crew.tasks
                         ]
@@ -196,14 +250,20 @@ class Telemetry:
                                 "max_iter": agent.max_iter,
                                 "max_rpm": agent.max_rpm,
                                 "function_calling_llm": (
-                                    agent.function_calling_llm.model
-                                    if agent.function_calling_llm
+                                    getattr(
+                                        getattr(agent, "function_calling_llm", None),
+                                        "model",
+                                        "",
+                                    )
+                                    if getattr(agent, "function_calling_llm", None)
                                     else ""
                                 ),
                                 "llm": agent.llm.model,
                                 "delegation_enabled?": agent.allow_delegation,
-                                "allow_code_execution?": agent.allow_code_execution,
-                                "max_retry_limit": agent.max_retry_limit,
+                                "allow_code_execution?": getattr(
+                                    agent, "allow_code_execution", False
+                                ),
+                                "max_retry_limit": getattr(agent, "max_retry_limit", 3),
                                 "tools_names": [
                                     tool.name.casefold() for tool in agent.tools or []
                                 ],
@@ -252,6 +312,39 @@ class Telemetry:
             self._add_attribute(created_span, "task_key", task.key)
             self._add_attribute(created_span, "task_id", str(task.id))
 
+            # Add fingerprint data
+            if hasattr(crew, "fingerprint") and crew.fingerprint:
+                self._add_attribute(
+                    created_span, "crew_fingerprint", crew.fingerprint.uuid_str
+                )
+
+            if hasattr(task, "fingerprint") and task.fingerprint:
+                self._add_attribute(
+                    created_span, "task_fingerprint", task.fingerprint.uuid_str
+                )
+                self._add_attribute(
+                    created_span,
+                    "task_fingerprint_created_at",
+                    task.fingerprint.created_at.isoformat(),
+                )
+                # Add fingerprint metadata if it exists
+                if hasattr(task.fingerprint, "metadata") and task.fingerprint.metadata:
+                    self._add_attribute(
+                        created_span,
+                        "task_fingerprint_metadata",
+                        json.dumps(task.fingerprint.metadata),
+                    )
+
+            # Add agent fingerprint if task has an assigned agent
+            if hasattr(task, "agent") and task.agent:
+                agent_fingerprint = getattr(
+                    getattr(task.agent, "fingerprint", None), "uuid_str", None
+                )
+                if agent_fingerprint:
+                    self._add_attribute(
+                        created_span, "agent_fingerprint", agent_fingerprint
+                    )
+
             if crew.share_crew:
                 self._add_attribute(
                     created_span, "formatted_description", task.description
@@ -270,6 +363,21 @@ class Telemetry:
             self._add_attribute(span, "task_key", task.key)
             self._add_attribute(span, "task_id", str(task.id))
 
+            # Add fingerprint data to execution span
+            if hasattr(crew, "fingerprint") and crew.fingerprint:
+                self._add_attribute(span, "crew_fingerprint", crew.fingerprint.uuid_str)
+
+            if hasattr(task, "fingerprint") and task.fingerprint:
+                self._add_attribute(span, "task_fingerprint", task.fingerprint.uuid_str)
+
+            # Add agent fingerprint if task has an assigned agent
+            if hasattr(task, "agent") and task.agent:
+                agent_fingerprint = getattr(
+                    getattr(task.agent, "fingerprint", None), "uuid_str", None
+                )
+                if agent_fingerprint:
+                    self._add_attribute(span, "agent_fingerprint", agent_fingerprint)
+
             if crew.share_crew:
                 self._add_attribute(span, "formatted_description", task.description)
                 self._add_attribute(
@@ -291,7 +399,12 @@ class Telemetry:
         Note:
             If share_crew is enabled, this will also record the task output
         """
+
         def operation():
+            # Ensure fingerprint data is present on completion span
+            if hasattr(task, "fingerprint") and task.fingerprint:
+                self._add_attribute(span, "task_fingerprint", task.fingerprint.uuid_str)
+
             if crew.share_crew:
                 self._add_attribute(
                     span,
@@ -312,6 +425,7 @@ class Telemetry:
             tool_name (str): Name of the tool being repeatedly used
             attempts (int): Number of attempts made with this tool
         """
+
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Tool Repeated Usage")
@@ -329,14 +443,16 @@ class Telemetry:
 
         self._safe_telemetry_operation(operation)
 
-    def tool_usage(self, llm: Any, tool_name: str, attempts: int):
+    def tool_usage(self, llm: Any, tool_name: str, attempts: int, agent: Any = None):
         """Records the usage of a tool by an agent.
 
         Args:
             llm (Any): The language model being used
             tool_name (str): Name of the tool being used
             attempts (int): Number of attempts made with this tool
+            agent (Any, optional): The agent using the tool
         """
+
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Tool Usage")
@@ -349,17 +465,31 @@ class Telemetry:
             self._add_attribute(span, "attempts", attempts)
             if llm:
                 self._add_attribute(span, "llm", llm.model)
+
+            # Add agent fingerprint data if available
+            if agent and hasattr(agent, "fingerprint") and agent.fingerprint:
+                self._add_attribute(
+                    span, "agent_fingerprint", agent.fingerprint.uuid_str
+                )
+                if hasattr(agent, "role"):
+                    self._add_attribute(span, "agent_role", agent.role)
+
             span.set_status(Status(StatusCode.OK))
             span.end()
 
         self._safe_telemetry_operation(operation)
 
-    def tool_usage_error(self, llm: Any):
+    def tool_usage_error(
+        self, llm: Any, agent: Any = None, tool_name: Optional[str] = None
+    ):
         """Records when a tool usage results in an error.
 
         Args:
             llm (Any): The language model being used when the error occurred
+            agent (Any, optional): The agent using the tool
+            tool_name (str, optional): Name of the tool that caused the error
         """
+
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Tool Usage Error")
@@ -370,6 +500,18 @@ class Telemetry:
             )
             if llm:
                 self._add_attribute(span, "llm", llm.model)
+
+            if tool_name:
+                self._add_attribute(span, "tool_name", tool_name)
+
+            # Add agent fingerprint data if available
+            if agent and hasattr(agent, "fingerprint") and agent.fingerprint:
+                self._add_attribute(
+                    span, "agent_fingerprint", agent.fingerprint.uuid_str
+                )
+                if hasattr(agent, "role"):
+                    self._add_attribute(span, "agent_role", agent.role)
+
             span.set_status(Status(StatusCode.OK))
             span.end()
 
@@ -386,6 +528,7 @@ class Telemetry:
             exec_time (int): Execution time in seconds
             model_name (str): Name of the model used
         """
+
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Crew Individual Test Result")
@@ -420,6 +563,7 @@ class Telemetry:
             inputs (dict[str, Any] | None): Input parameters for the test
             model_name (str): Name of the model used in testing
         """
+
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Crew Test Execution")
@@ -446,6 +590,7 @@ class Telemetry:
 
     def deploy_signup_error_span(self):
         """Records when an error occurs during the deployment signup process."""
+
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Deploy Signup Error")
@@ -460,6 +605,7 @@ class Telemetry:
         Args:
             uuid (Optional[str]): Unique identifier for the deployment
         """
+
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Start Deployment")
@@ -472,6 +618,7 @@ class Telemetry:
 
     def create_crew_deployment_span(self):
         """Records the creation of a new crew deployment."""
+
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Create Crew Deployment")
@@ -487,6 +634,7 @@ class Telemetry:
             uuid (Optional[str]): Unique identifier for the crew
             log_type (str, optional): Type of logs being retrieved. Defaults to "deployment".
         """
+
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Get Crew Logs")
@@ -504,6 +652,7 @@ class Telemetry:
         Args:
             uuid (Optional[str]): Unique identifier for the crew being removed
         """
+
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Remove Crew")
@@ -634,6 +783,7 @@ class Telemetry:
         Args:
             flow_name (str): Name of the flow being created
         """
+
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Flow Creation")
@@ -650,6 +800,7 @@ class Telemetry:
             flow_name (str): Name of the flow being plotted
             node_names (list[str]): List of node names in the flow
         """
+
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Flow Plotting")
@@ -667,6 +818,7 @@ class Telemetry:
             flow_name (str): Name of the flow being executed
             node_names (list[str]): List of nodes being executed in the flow
         """
+
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Flow Execution")

src/crewai/tools/tool_usage.py

@@ -22,6 +22,7 @@ from crewai.utilities.events.tool_usage_events import (
     ToolSelectionErrorEvent,
     ToolUsageErrorEvent,
     ToolUsageFinishedEvent,
+    ToolUsageStartedEvent,
     ToolValidateInputErrorEvent,
 )
 
@@ -69,6 +70,7 @@ class ToolUsage:
         function_calling_llm: Any,
         agent: Any,
         action: Any,
+        fingerprint_context: Optional[Dict[str, str]] = None,
     ) -> None:
         self._i18n: I18N = agent.i18n
         self._printer: Printer = Printer()
@@ -85,6 +87,7 @@ class ToolUsage:
         self.task = task
         self.action = action
         self.function_calling_llm = function_calling_llm
+        self.fingerprint_context = fingerprint_context or {}
 
         # Set the maximum parsing attempts for bigger models
         if (
@@ -117,7 +120,10 @@ class ToolUsage:
                 self._printer.print(content=f"\n\n{error}\n", color="red")
             return error
 
-        if isinstance(tool, CrewStructuredTool) and tool.name == self._i18n.tools("add_image")["name"]:  # type: ignore
+        if (
+            isinstance(tool, CrewStructuredTool)
+            and tool.name == self._i18n.tools("add_image")["name"]  # type: ignore
+        ):
             try:
                 result = self._use(tool_string=tool_string, tool=tool, calling=calling)
                 return result
@@ -181,18 +187,26 @@ class ToolUsage:
 
                 if calling.arguments:
                     try:
-                        acceptable_args = tool.args_schema.model_json_schema()["properties"].keys()  # type: ignore
+                        acceptable_args = tool.args_schema.model_json_schema()[
+                            "properties"
+                        ].keys()  # type: ignore
                         arguments = {
                             k: v
                             for k, v in calling.arguments.items()
                             if k in acceptable_args
                         }
+                        # Add fingerprint metadata if available
+                        arguments = self._add_fingerprint_metadata(arguments)
                         result = tool.invoke(input=arguments)
                     except Exception:
                         arguments = calling.arguments
+                        # Add fingerprint metadata if available
+                        arguments = self._add_fingerprint_metadata(arguments)
                         result = tool.invoke(input=arguments)
                 else:
-                    result = tool.invoke(input={})
+                    # Add fingerprint metadata even to empty arguments
+                    arguments = self._add_fingerprint_metadata({})
+                    result = tool.invoke(input=arguments)
             except Exception as e:
                 self.on_tool_error(tool=tool, tool_calling=calling, e=e)
                 self._run_attempts += 1
@@ -202,7 +216,7 @@ class ToolUsage:
                         error=e, tool=tool.name, tool_inputs=tool.description
                     )
                     error = ToolUsageErrorException(
-                        f'\n{error_message}.\nMoving on then. {self._i18n.slice("format").format(tool_names=self.tools_names)}'
+                        f"\n{error_message}.\nMoving on then. {self._i18n.slice('format').format(tool_names=self.tools_names)}"
                     ).message
                     self.task.increment_tools_errors()
                     if self.agent.verbose:
@@ -244,6 +258,7 @@ class ToolUsage:
             tool_calling=calling,
             from_cache=from_cache,
             started_at=started_at,
+            result=result,
         )
 
         if (
@@ -380,7 +395,7 @@ class ToolUsage:
                 raise
             else:
                 return ToolUsageErrorException(
-                    f'{self._i18n.errors("tool_arguments_error")}'
+                    f"{self._i18n.errors('tool_arguments_error')}"
                 )
 
         if not isinstance(arguments, dict):
@@ -388,7 +403,7 @@ class ToolUsage:
                 raise
             else:
                 return ToolUsageErrorException(
-                    f'{self._i18n.errors("tool_arguments_error")}'
+                    f"{self._i18n.errors('tool_arguments_error')}"
                 )
 
         return ToolCalling(
@@ -416,7 +431,7 @@ class ToolUsage:
                 if self.agent.verbose:
                     self._printer.print(content=f"\n\n{e}\n", color="red")
                 return ToolUsageErrorException(  # type: ignore # Incompatible return value type (got "ToolUsageErrorException", expected "ToolCalling | InstructorToolCalling")
-                    f'{self._i18n.errors("tool_usage_error").format(error=e)}\nMoving on then. {self._i18n.slice("format").format(tool_names=self.tools_names)}'
+                    f"{self._i18n.errors('tool_usage_error').format(error=e)}\nMoving on then. {self._i18n.slice('format').format(tool_names=self.tools_names)}"
                 )
             return self._tool_calling(tool_string)
 
@@ -480,8 +495,13 @@ class ToolUsage:
             "tool_name": self.action.tool,
             "tool_args": str(self.action.tool_input),
             "tool_class": self.__class__.__name__,
+            "agent": self.agent,  # Adding agent for fingerprint extraction
         }
 
+        # Include fingerprint context if available
+        if self.fingerprint_context:
+            tool_selection_data.update(self.fingerprint_context)
+
         crewai_event_bus.emit(
             self,
             ToolValidateInputErrorEvent(**tool_selection_data, error=final_error),
@@ -492,7 +512,12 @@ class ToolUsage:
         crewai_event_bus.emit(self, ToolUsageErrorEvent(**{**event_data, "error": e}))
 
     def on_tool_use_finished(
-        self, tool: Any, tool_calling: ToolCalling, from_cache: bool, started_at: float
+        self,
+        tool: Any,
+        tool_calling: ToolCalling,
+        from_cache: bool,
+        started_at: float,
+        result: Any,
     ) -> None:
         finished_at = time.time()
         event_data = self._prepare_event_data(tool, tool_calling)
@@ -501,12 +526,13 @@ class ToolUsage:
                 "started_at": datetime.datetime.fromtimestamp(started_at),
                 "finished_at": datetime.datetime.fromtimestamp(finished_at),
                 "from_cache": from_cache,
+                "output": result,
             }
         )
         crewai_event_bus.emit(self, ToolUsageFinishedEvent(**event_data))
 
     def _prepare_event_data(self, tool: Any, tool_calling: ToolCalling) -> dict:
-        return {
+        event_data = {
             "agent_key": self.agent.key,
             "agent_role": (self.agent._original_role or self.agent.role),
             "run_attempts": self._run_attempts,
@@ -514,4 +540,43 @@ class ToolUsage:
             "tool_name": tool.name,
             "tool_args": tool_calling.arguments,
             "tool_class": tool.__class__.__name__,
+            "agent": self.agent,  # Adding agent for fingerprint extraction
         }
+
+        # Include fingerprint context if available
+        if self.fingerprint_context:
+            event_data.update(self.fingerprint_context)
+
+        return event_data
+
+    def _add_fingerprint_metadata(self, arguments: dict) -> dict:
+        """Add fingerprint metadata to tool arguments if available.
+
+        Args:
+            arguments: The original tool arguments
+
+        Returns:
+            Updated arguments dictionary with fingerprint metadata
+        """
+        # Create a shallow copy to avoid modifying the original
+        arguments = arguments.copy()
+
+        # Add security metadata under a designated key
+        if not "security_context" in arguments:
+            arguments["security_context"] = {}
+
+        security_context = arguments["security_context"]
+
+        # Add agent fingerprint if available
+        if hasattr(self, "agent") and hasattr(self.agent, "security_config"):
+            security_context["agent_fingerprint"] = self.agent.security_config.fingerprint.to_dict()
+
+        # Add task fingerprint if available
+        if hasattr(self, "task") and hasattr(self.task, "security_config"):
+            security_context["task_fingerprint"] = self.task.security_config.fingerprint.to_dict()
+
+        # Add crew fingerprint if available
+        if hasattr(self, "crew") and hasattr(self.crew, "security_config"):
+            security_context["crew_fingerprint"] = self.crew.security_config.fingerprint.to_dict()
+
+        return arguments

src/crewai/utilities/evaluators/task_evaluator.py

@@ -45,7 +45,7 @@ class TaskEvaluator:
 
     def evaluate(self, task, output) -> TaskEvaluation:
         crewai_event_bus.emit(
-            self, TaskEvaluationEvent(evaluation_type="task_evaluation")
+            self, TaskEvaluationEvent(evaluation_type="task_evaluation", task=task)
         )
         evaluation_query = (
             f"Assess the quality of the task completed based on the description, expected output, and actual results.\n\n"

src/crewai/utilities/events/agent_events.py

@@ -4,13 +4,13 @@ from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.tools.base_tool import BaseTool
 from crewai.tools.structured_tool import CrewStructuredTool
 
-from .base_events import CrewEvent
+from .base_events import BaseEvent
 
 if TYPE_CHECKING:
     from crewai.agents.agent_builder.base_agent import BaseAgent
 
 
-class AgentExecutionStartedEvent(CrewEvent):
+class AgentExecutionStartedEvent(BaseEvent):
     """Event emitted when an agent starts executing a task"""
 
     agent: BaseAgent
@@ -21,8 +21,20 @@ class AgentExecutionStartedEvent(CrewEvent):
 
     model_config = {"arbitrary_types_allowed": True}
 
+    def __init__(self, **data):
+        super().__init__(**data)
+        # Set fingerprint data from the agent
+        if hasattr(self.agent, "fingerprint") and self.agent.fingerprint:
+            self.source_fingerprint = self.agent.fingerprint.uuid_str
+            self.source_type = "agent"
+            if (
+                hasattr(self.agent.fingerprint, "metadata")
+                and self.agent.fingerprint.metadata
+            ):
+                self.fingerprint_metadata = self.agent.fingerprint.metadata
 
-class AgentExecutionCompletedEvent(CrewEvent):
+
+class AgentExecutionCompletedEvent(BaseEvent):
     """Event emitted when an agent completes executing a task"""
 
     agent: BaseAgent
@@ -30,11 +42,35 @@ class AgentExecutionCompletedEvent(CrewEvent):
     output: str
     type: str = "agent_execution_completed"
 
+    def __init__(self, **data):
+        super().__init__(**data)
+        # Set fingerprint data from the agent
+        if hasattr(self.agent, "fingerprint") and self.agent.fingerprint:
+            self.source_fingerprint = self.agent.fingerprint.uuid_str
+            self.source_type = "agent"
+            if (
+                hasattr(self.agent.fingerprint, "metadata")
+                and self.agent.fingerprint.metadata
+            ):
+                self.fingerprint_metadata = self.agent.fingerprint.metadata
 
-class AgentExecutionErrorEvent(CrewEvent):
+
+class AgentExecutionErrorEvent(BaseEvent):
     """Event emitted when an agent encounters an error during execution"""
 
     agent: BaseAgent
     task: Any
     error: str
     type: str = "agent_execution_error"
+
+    def __init__(self, **data):
+        super().__init__(**data)
+        # Set fingerprint data from the agent
+        if hasattr(self.agent, "fingerprint") and self.agent.fingerprint:
+            self.source_fingerprint = self.agent.fingerprint.uuid_str
+            self.source_type = "agent"
+            if (
+                hasattr(self.agent.fingerprint, "metadata")
+                and self.agent.fingerprint.metadata
+            ):
+                self.fingerprint_metadata = self.agent.fingerprint.metadata

src/crewai/utilities/events/base_events.py

@@ -1,10 +1,28 @@
 from datetime import datetime
+from typing import Any, Dict, Optional
 
 from pydantic import BaseModel, Field
 
+from crewai.utilities.serialization import to_serializable
 
-class CrewEvent(BaseModel):
-    """Base class for all crew events"""
+
+class BaseEvent(BaseModel):
+    """Base class for all events"""
 
     timestamp: datetime = Field(default_factory=datetime.now)
     type: str
+    source_fingerprint: Optional[str] = None  # UUID string of the source entity
+    source_type: Optional[str] = None  # "agent", "task", "crew"
+    fingerprint_metadata: Optional[Dict[str, Any]] = None  # Any relevant metadata
+
+    def to_json(self, exclude: set[str] | None = None):
+        """
+        Converts the event to a JSON-serializable dictionary.
+
+        Args:
+            exclude (set[str], optional): Set of keys to exclude from the result. Defaults to None.
+
+        Returns:
+            dict: A JSON-serializable dictionary.
+        """
+        return to_serializable(self, exclude=exclude)

src/crewai/utilities/events/crew_events.py

@@ -1,81 +1,102 @@
-from typing import Any, Dict, Optional, Union
+from typing import TYPE_CHECKING, Any, Dict, Optional, Union
 
-from pydantic import InstanceOf
+from crewai.utilities.events.base_events import BaseEvent
 
-from crewai.utilities.events.base_events import CrewEvent
+if TYPE_CHECKING:
+    from crewai.crew import Crew
+else:
+    Crew = Any
 
 
-class CrewKickoffStartedEvent(CrewEvent):
-    """Event emitted when a crew starts execution"""
+class CrewBaseEvent(BaseEvent):
+    """Base class for crew events with fingerprint handling"""
 
     crew_name: Optional[str]
+    crew: Optional[Crew] = None
+
+    def __init__(self, **data):
+        super().__init__(**data)
+        self.set_crew_fingerprint()
+
+    def set_crew_fingerprint(self) -> None:
+        if self.crew and hasattr(self.crew, "fingerprint") and self.crew.fingerprint:
+            self.source_fingerprint = self.crew.fingerprint.uuid_str
+            self.source_type = "crew"
+            if (
+                hasattr(self.crew.fingerprint, "metadata")
+                and self.crew.fingerprint.metadata
+            ):
+                self.fingerprint_metadata = self.crew.fingerprint.metadata
+
+    def to_json(self, exclude: set[str] | None = None):
+        if exclude is None:
+            exclude = set()
+        exclude.add("crew")
+        return super().to_json(exclude=exclude)
+
+
+class CrewKickoffStartedEvent(CrewBaseEvent):
+    """Event emitted when a crew starts execution"""
+
     inputs: Optional[Dict[str, Any]]
     type: str = "crew_kickoff_started"
 
 
-class CrewKickoffCompletedEvent(CrewEvent):
+class CrewKickoffCompletedEvent(CrewBaseEvent):
     """Event emitted when a crew completes execution"""
 
-    crew_name: Optional[str]
     output: Any
     type: str = "crew_kickoff_completed"
 
 
-class CrewKickoffFailedEvent(CrewEvent):
+class CrewKickoffFailedEvent(CrewBaseEvent):
     """Event emitted when a crew fails to complete execution"""
 
     error: str
-    crew_name: Optional[str]
     type: str = "crew_kickoff_failed"
 
 
-class CrewTrainStartedEvent(CrewEvent):
+class CrewTrainStartedEvent(CrewBaseEvent):
     """Event emitted when a crew starts training"""
 
-    crew_name: Optional[str]
     n_iterations: int
     filename: str
     inputs: Optional[Dict[str, Any]]
     type: str = "crew_train_started"
 
 
-class CrewTrainCompletedEvent(CrewEvent):
+class CrewTrainCompletedEvent(CrewBaseEvent):
     """Event emitted when a crew completes training"""
 
-    crew_name: Optional[str]
     n_iterations: int
     filename: str
     type: str = "crew_train_completed"
 
 
-class CrewTrainFailedEvent(CrewEvent):
+class CrewTrainFailedEvent(CrewBaseEvent):
     """Event emitted when a crew fails to complete training"""
 
     error: str
-    crew_name: Optional[str]
     type: str = "crew_train_failed"
 
 
-class CrewTestStartedEvent(CrewEvent):
+class CrewTestStartedEvent(CrewBaseEvent):
     """Event emitted when a crew starts testing"""
 
-    crew_name: Optional[str]
     n_iterations: int
     eval_llm: Optional[Union[str, Any]]
     inputs: Optional[Dict[str, Any]]
     type: str = "crew_test_started"
 
 
-class CrewTestCompletedEvent(CrewEvent):
+class CrewTestCompletedEvent(CrewBaseEvent):
     """Event emitted when a crew completes testing"""
 
-    crew_name: Optional[str]
     type: str = "crew_test_completed"
 
 
-class CrewTestFailedEvent(CrewEvent):
+class CrewTestFailedEvent(CrewBaseEvent):
     """Event emitted when a crew fails to complete testing"""
 
     error: str
-    crew_name: Optional[str]
     type: str = "crew_test_failed"

src/crewai/utilities/events/crewai_event_bus.py

@@ -4,10 +4,10 @@ from typing import Any, Callable, Dict, List, Type, TypeVar, cast
 
 from blinker import Signal
 
-from crewai.utilities.events.base_events import CrewEvent
+from crewai.utilities.events.base_events import BaseEvent
 from crewai.utilities.events.event_types import EventTypes
 
-EventT = TypeVar("EventT", bound=CrewEvent)
+EventT = TypeVar("EventT", bound=BaseEvent)
 
 
 class CrewAIEventsBus:
@@ -30,7 +30,7 @@ class CrewAIEventsBus:
     def _initialize(self) -> None:
         """Initialize the event bus internal state"""
         self._signal = Signal("crewai_event_bus")
-        self._handlers: Dict[Type[CrewEvent], List[Callable]] = {}
+        self._handlers: Dict[Type[BaseEvent], List[Callable]] = {}
 
     def on(
         self, event_type: Type[EventT]
@@ -59,7 +59,7 @@ class CrewAIEventsBus:
 
         return decorator
 
-    def emit(self, source: Any, event: CrewEvent) -> None:
+    def emit(self, source: Any, event: BaseEvent) -> None:
         """
         Emit an event to all registered handlers
 

src/crewai/utilities/events/flow_events.py

@@ -2,10 +2,10 @@ from typing import Any, Dict, Optional, Union
 
 from pydantic import BaseModel, ConfigDict
 
-from .base_events import CrewEvent
+from .base_events import BaseEvent
 
 
-class FlowEvent(CrewEvent):
+class FlowEvent(BaseEvent):
     """Base class for all flow events"""
 
     type: str

src/crewai/utilities/events/llm_events.py

@@ -1,7 +1,7 @@
 from enum import Enum
 from typing import Any, Dict, List, Optional, Union
 
-from crewai.utilities.events.base_events import CrewEvent
+from crewai.utilities.events.base_events import BaseEvent
 
 
 class LLMCallType(Enum):
@@ -11,17 +11,22 @@ class LLMCallType(Enum):
     LLM_CALL = "llm_call"
 
 
-class LLMCallStartedEvent(CrewEvent):
-    """Event emitted when a LLM call starts"""
+class LLMCallStartedEvent(BaseEvent):
+    """Event emitted when a LLM call starts
+
+    Attributes:
+        messages: Content can be either a string or a list of dictionaries that support
+            multimodal content (text, images, etc.)
+    """
 
     type: str = "llm_call_started"
-    messages: Union[str, List[Dict[str, str]]]
+    messages: Union[str, List[Dict[str, Any]]]
     tools: Optional[List[dict]] = None
     callbacks: Optional[List[Any]] = None
     available_functions: Optional[Dict[str, Any]] = None
 
 
-class LLMCallCompletedEvent(CrewEvent):
+class LLMCallCompletedEvent(BaseEvent):
     """Event emitted when a LLM call completes"""
 
     type: str = "llm_call_completed"
@@ -29,14 +34,14 @@ class LLMCallCompletedEvent(CrewEvent):
     call_type: LLMCallType
 
 
-class LLMCallFailedEvent(CrewEvent):
+class LLMCallFailedEvent(BaseEvent):
     """Event emitted when a LLM call fails"""
 
     error: str
     type: str = "llm_call_failed"
 
 
-class LLMStreamChunkEvent(CrewEvent):
+class LLMStreamChunkEvent(BaseEvent):
     """Event emitted when a streaming chunk is received"""
 
     type: str = "llm_stream_chunk"

src/crewai/utilities/events/task_events.py

@@ -1,32 +1,84 @@
-from typing import Optional
+from typing import Any, Optional
 
 from crewai.tasks.task_output import TaskOutput
-from crewai.utilities.events.base_events import CrewEvent
+from crewai.utilities.events.base_events import BaseEvent
 
 
-class TaskStartedEvent(CrewEvent):
+class TaskStartedEvent(BaseEvent):
     """Event emitted when a task starts"""
 
     type: str = "task_started"
     context: Optional[str]
+    task: Optional[Any] = None
+
+    def __init__(self, **data):
+        super().__init__(**data)
+        # Set fingerprint data from the task
+        if hasattr(self.task, "fingerprint") and self.task.fingerprint:
+            self.source_fingerprint = self.task.fingerprint.uuid_str
+            self.source_type = "task"
+            if (
+                hasattr(self.task.fingerprint, "metadata")
+                and self.task.fingerprint.metadata
+            ):
+                self.fingerprint_metadata = self.task.fingerprint.metadata
 
 
-class TaskCompletedEvent(CrewEvent):
+class TaskCompletedEvent(BaseEvent):
     """Event emitted when a task completes"""
 
     output: TaskOutput
     type: str = "task_completed"
+    task: Optional[Any] = None
+
+    def __init__(self, **data):
+        super().__init__(**data)
+        # Set fingerprint data from the task
+        if hasattr(self.task, "fingerprint") and self.task.fingerprint:
+            self.source_fingerprint = self.task.fingerprint.uuid_str
+            self.source_type = "task"
+            if (
+                hasattr(self.task.fingerprint, "metadata")
+                and self.task.fingerprint.metadata
+            ):
+                self.fingerprint_metadata = self.task.fingerprint.metadata
 
 
-class TaskFailedEvent(CrewEvent):
+class TaskFailedEvent(BaseEvent):
     """Event emitted when a task fails"""
 
     error: str
     type: str = "task_failed"
+    task: Optional[Any] = None
+
+    def __init__(self, **data):
+        super().__init__(**data)
+        # Set fingerprint data from the task
+        if hasattr(self.task, "fingerprint") and self.task.fingerprint:
+            self.source_fingerprint = self.task.fingerprint.uuid_str
+            self.source_type = "task"
+            if (
+                hasattr(self.task.fingerprint, "metadata")
+                and self.task.fingerprint.metadata
+            ):
+                self.fingerprint_metadata = self.task.fingerprint.metadata
 
 
-class TaskEvaluationEvent(CrewEvent):
+class TaskEvaluationEvent(BaseEvent):
     """Event emitted when a task evaluation is completed"""
 
     type: str = "task_evaluation"
     evaluation_type: str
+    task: Optional[Any] = None
+
+    def __init__(self, **data):
+        super().__init__(**data)
+        # Set fingerprint data from the task
+        if hasattr(self.task, "fingerprint") and self.task.fingerprint:
+            self.source_fingerprint = self.task.fingerprint.uuid_str
+            self.source_type = "task"
+            if (
+                hasattr(self.task.fingerprint, "metadata")
+                and self.task.fingerprint.metadata
+            ):
+                self.fingerprint_metadata = self.task.fingerprint.metadata

src/crewai/utilities/events/tool_usage_events.py

@@ -1,10 +1,10 @@
 from datetime import datetime
-from typing import Any, Callable, Dict
+from typing import Any, Callable, Dict, Optional
 
-from .base_events import CrewEvent
+from .base_events import BaseEvent
 
 
-class ToolUsageEvent(CrewEvent):
+class ToolUsageEvent(BaseEvent):
     """Base event for tool usage tracking"""
 
     agent_key: str
@@ -14,9 +14,22 @@ class ToolUsageEvent(CrewEvent):
     tool_class: str
     run_attempts: int | None = None
     delegations: int | None = None
+    agent: Optional[Any] = None
 
     model_config = {"arbitrary_types_allowed": True}
 
+    def __init__(self, **data):
+        super().__init__(**data)
+        # Set fingerprint data from the agent
+        if self.agent and hasattr(self.agent, "fingerprint") and self.agent.fingerprint:
+            self.source_fingerprint = self.agent.fingerprint.uuid_str
+            self.source_type = "agent"
+            if (
+                hasattr(self.agent.fingerprint, "metadata")
+                and self.agent.fingerprint.metadata
+            ):
+                self.fingerprint_metadata = self.agent.fingerprint.metadata
+
 
 class ToolUsageStartedEvent(ToolUsageEvent):
     """Event emitted when a tool execution is started"""
@@ -30,6 +43,7 @@ class ToolUsageFinishedEvent(ToolUsageEvent):
     started_at: datetime
     finished_at: datetime
     from_cache: bool = False
+    output: Any
     type: str = "tool_usage_finished"
 
 
@@ -54,7 +68,7 @@ class ToolSelectionErrorEvent(ToolUsageEvent):
     type: str = "tool_selection_error"
 
 
-class ToolExecutionErrorEvent(CrewEvent):
+class ToolExecutionErrorEvent(BaseEvent):
     """Event emitted when a tool execution encounters an error"""
 
     error: Any
@@ -62,3 +76,16 @@ class ToolExecutionErrorEvent(CrewEvent):
     tool_name: str
     tool_args: Dict[str, Any]
     tool_class: Callable
+    agent: Optional[Any] = None
+
+    def __init__(self, **data):
+        super().__init__(**data)
+        # Set fingerprint data from the agent
+        if self.agent and hasattr(self.agent, "fingerprint") and self.agent.fingerprint:
+            self.source_fingerprint = self.agent.fingerprint.uuid_str
+            self.source_type = "agent"
+            if (
+                hasattr(self.agent.fingerprint, "metadata")
+                and self.agent.fingerprint.metadata
+            ):
+                self.fingerprint_metadata = self.agent.fingerprint.metadata

src/crewai/utilities/serialization.py

@@ -5,35 +5,17 @@ from typing import Any, Dict, List, Union
 
 from pydantic import BaseModel
 
-from crewai.flow import Flow
-
 SerializablePrimitive = Union[str, int, float, bool, None]
 Serializable = Union[
     SerializablePrimitive, List["Serializable"], Dict[str, "Serializable"]
 ]
 
 
-def export_state(flow: Flow) -> dict[str, Serializable]:
-    """Exports the Flow's internal state as JSON-compatible data structures.
-
-    Performs a one-way transformation of a Flow's state into basic Python types
-    that can be safely serialized to JSON. To prevent infinite recursion with
-    circular references, the conversion is limited to a depth of 5 levels.
-
-    Args:
-        flow: The Flow object whose state needs to be exported
-
-    Returns:
-        dict[str, Any]: The transformed state using JSON-compatible Python
-            types.
-    """
-    result = to_serializable(flow._state)
-    assert isinstance(result, dict)
-    return result
-
-
 def to_serializable(
-    obj: Any, exclude: set[str] | None = None, max_depth: int = 5, _current_depth: int = 0
+    obj: Any,
+    exclude: set[str] | None = None,
+    max_depth: int = 5,
+    _current_depth: int = 0,
 ) -> Serializable:
     """Converts a Python object into a JSON-compatible representation.
 

tests/cassettes/test_multimodal_agent_describing_image_successfully.yaml

@@ -0,0 +1,378 @@
+interactions:
+- request:
+    body: !!binary |
+      CpIKCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS6QkKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRLBBwoQ08SlQ6w2FsCauTgZCqberRIITfOsgNi1qJkqDENyZXcgQ3JlYXRlZDABOdjG
+      6D/PcDAYQahPEkDPcDAYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTA4LjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi45Si4KCGNyZXdfa2V5EiIKIDkwNzMxMTU4MzVlMWNhZjJhNmUxNTIyZDA1
+      YTBiNTFkSjEKB2NyZXdfaWQSJgokMzdjOGM4NzgtN2NmZC00YjEyLWE4YzctYzIyZDZlOTIxODBk
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrgAgoLY3Jl
+      d19hZ2VudHMS0AIKzQJbeyJrZXkiOiAiNzYyM2ZjNGY3ZDk0Y2YzZmRiZmNjMjlmYjBiMDIyYmIi
+      LCAiaWQiOiAiYmVjMjljMTAtOTljYi00MzQwLWIwYTItMWU1NTVkNGRmZGM0IiwgInJvbGUiOiAi
+      VmlzdWFsIFF1YWxpdHkgSW5zcGVjdG9yIiwgInZlcmJvc2U/IjogdHJ1ZSwgIm1heF9pdGVyIjog
+      MjUsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAi
+      b3BlbmFpL2dwdC00byIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2Rl
+      X2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6
+      IFtdfV1KjQIKCmNyZXdfdGFza3MS/gEK+wFbeyJrZXkiOiAiMDExM2E5ZTg0N2M2NjI2ZDY0ZDZk
+      Yzk4M2IwNDA5MTgiLCAiaWQiOiAiZWQzYmY1YWUtZTBjMS00MjIxLWFhYTgtMThlNjVkYTMyZjc1
+      IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdl
+      bnRfcm9sZSI6ICJWaXN1YWwgUXVhbGl0eSBJbnNwZWN0b3IiLCAiYWdlbnRfa2V5IjogIjc2MjNm
+      YzRmN2Q5NGNmM2ZkYmZjYzI5ZmIwYjAyMmJiIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQAB
+      AAASjgIKECo77ESam8oLrZMmgLLaoksSCLE6x14/Kb1vKgxUYXNrIENyZWF0ZWQwATlI/chAz3Aw
+      GEEAgMpAz3AwGEouCghjcmV3X2tleRIiCiA5MDczMTE1ODM1ZTFjYWYyYTZlMTUyMmQwNWEwYjUx
+      ZEoxCgdjcmV3X2lkEiYKJDM3YzhjODc4LTdjZmQtNGIxMi1hOGM3LWMyMmQ2ZTkyMTgwZEouCgh0
+      YXNrX2tleRIiCiAwMTEzYTllODQ3YzY2MjZkNjRkNmRjOTgzYjA0MDkxOEoxCgd0YXNrX2lkEiYK
+      JGVkM2JmNWFlLWUwYzEtNDIyMS1hYWE4LTE4ZTY1ZGEzMmY3NXoCGAGFAQABAAA=
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate, zstd
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1301'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.31.1
+    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:
+      - Wed, 26 Mar 2025 19:24:52 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Visual Quality Inspector.
+      Senior quality control expert with expertise in visual inspection\nYour personal
+      goal is: Perform detailed quality analysis of product images\nYou ONLY have
+      access to the following tools, and should NEVER make up tools that are not listed
+      here:\n\nTool Name: Add image to content\nTool Arguments: {''image_url'': {''description'':
+      ''The URL or path of the image to add'', ''type'': ''str''}, ''action'': {''description'':
+      ''Optional context or question about the image'', ''type'': ''Union[str, NoneType]''}}\nTool
+      Description: See image to understand its content, you can optionally ask a question
+      about the image\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought:
+      you should always think about what to do\nAction: the action to take, only one
+      name of [Add image to content], just the name, exactly as it''s written.\nAction
+      Input: the input to the action, just a simple JSON object, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
+      all necessary information is gathered, return the following format:\n\n```\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question\n```"}, {"role": "user", "content": "\nCurrent Task: \n        Analyze
+      the product image at https://www.us.maguireshoes.com/cdn/shop/files/FW24-Edito-Lucena-Distressed-01_1920x.jpg?v=1736371244
+      with focus on:\n        1. Quality of materials\n        2. Manufacturing defects\n        3.
+      Compliance with standards\n        Provide a detailed report highlighting any
+      issues found.\n        \n\nThis is the expected criteria for your final answer:
+      A detailed report highlighting any issues found\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", "stop": ["\nObservation:"],
+      "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '2033'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BFQepLwSYYzdKLylSFsgcJeg6GTqS\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1743017091,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: I need to examine the product
+      image to assess the quality of materials, look for any manufacturing defects,
+      and check compliance with standards.\\n\\nAction: Add image to content\\nAction
+      Input: {\\\"image_url\\\": \\\"https://www.us.maguireshoes.com/cdn/shop/files/FW24-Edito-Lucena-Distressed-01_1920x.jpg?v=1736371244\\\",
+      \\\"action\\\": \\\"Analyze the quality of materials, manufacturing defects,
+      and compliance with standards.\\\"}\",\n        \"refusal\": null,\n        \"annotations\":
+      []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 413,\n    \"completion_tokens\":
+      101,\n    \"total_tokens\": 514,\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  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_7e8d90e604\"\n}\n"
+    headers:
+      CF-RAY:
+      - 926907d79dcff1e7-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 26 Mar 2025 19:24:53 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=WK433.4kW8cr9rwvOlk4EZ2SfRYK9lAPwXCBYEvLcmU-1743017093-1.0.1.1-kVZyUew5rUbMk.2koGJF_rmX.fTseqN241n2M40n8KvBGoKgy6KM6xBmvFbIVWxUs2Y5ZAz8mWy9CrGjaNKSfCzxmv4.pq78z_DGHr37PgI;
+        path=/; expires=Wed, 26-Mar-25 19:54:53 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=T77PMcuNYeyzK0tQyDOe7EScjVBVzW_7DpD3YQBqmUc-1743017093675-0.0.1.1-604800000;
+        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
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1729'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '50000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '49999'
+      x-ratelimit-remaining-tokens:
+      - '149999534'
+      x-ratelimit-reset-requests:
+      - 1ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_2399c3355adf16734907c73611a7d330
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CtgBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSrwEKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKYAQoQp2ACB2xRGve4HGtU2RdWCBIIlQcsbhK22ykqClRvb2wgVXNhZ2UwATlACEXG
+      z3AwGEHAjGPGz3AwGEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjEwOC4wSiMKCXRvb2xfbmFtZRIW
+      ChRBZGQgaW1hZ2UgdG8gY29udGVudEoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate, zstd
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '219'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.31.1
+    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:
+      - Wed, 26 Mar 2025 19:24:57 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Visual Quality Inspector.
+      Senior quality control expert with expertise in visual inspection\nYour personal
+      goal is: Perform detailed quality analysis of product images\nYou ONLY have
+      access to the following tools, and should NEVER make up tools that are not listed
+      here:\n\nTool Name: Add image to content\nTool Arguments: {''image_url'': {''description'':
+      ''The URL or path of the image to add'', ''type'': ''str''}, ''action'': {''description'':
+      ''Optional context or question about the image'', ''type'': ''Union[str, NoneType]''}}\nTool
+      Description: See image to understand its content, you can optionally ask a question
+      about the image\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought:
+      you should always think about what to do\nAction: the action to take, only one
+      name of [Add image to content], just the name, exactly as it''s written.\nAction
+      Input: the input to the action, just a simple JSON object, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
+      all necessary information is gathered, return the following format:\n\n```\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question\n```"}, {"role": "user", "content": "\nCurrent Task: \n        Analyze
+      the product image at https://www.us.maguireshoes.com/cdn/shop/files/FW24-Edito-Lucena-Distressed-01_1920x.jpg?v=1736371244
+      with focus on:\n        1. Quality of materials\n        2. Manufacturing defects\n        3.
+      Compliance with standards\n        Provide a detailed report highlighting any
+      issues found.\n        \n\nThis is the expected criteria for your final answer:
+      A detailed report highlighting any issues found\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:"}, {"role": "user", "content": [{"type": "text",
+      "text": "Analyze the quality of materials, manufacturing defects, and compliance
+      with standards."}, {"type": "image_url", "image_url": {"url": "https://www.us.maguireshoes.com/cdn/shop/files/FW24-Edito-Lucena-Distressed-01_1920x.jpg?v=1736371244"}}]},
+      {"role": "assistant", "content": "Thought: I need to examine the product image
+      to assess the quality of materials, look for any manufacturing defects, and
+      check compliance with standards.\n\nAction: Add image to content\nAction Input:
+      {\"image_url\": \"https://www.us.maguireshoes.com/cdn/shop/files/FW24-Edito-Lucena-Distressed-01_1920x.jpg?v=1736371244\",
+      \"action\": \"Analyze the quality of materials, manufacturing defects, and compliance
+      with standards.\"}"}], "model": "gpt-4o", "stop": ["\nObservation:"], "temperature":
+      0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '2797'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=WK433.4kW8cr9rwvOlk4EZ2SfRYK9lAPwXCBYEvLcmU-1743017093-1.0.1.1-kVZyUew5rUbMk.2koGJF_rmX.fTseqN241n2M40n8KvBGoKgy6KM6xBmvFbIVWxUs2Y5ZAz8mWy9CrGjaNKSfCzxmv4.pq78z_DGHr37PgI;
+        _cfuvid=T77PMcuNYeyzK0tQyDOe7EScjVBVzW_7DpD3YQBqmUc-1743017093675-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BFQetNNvmPgPxhzaKiHYsPqm8aN0i\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1743017095,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Observation: The image displays a black
+      leather boot with a pointed toe and a low heel. \\n\\nQuality of Materials:\\n1.
+      The leather appears to be of good quality, displaying a consistent texture and
+      finish, which suggests durability.\\n2. The material has a slight sheen, indicating
+      a possible finishing treatment that enhances the appearance and may offer some
+      protection.\\n\\nManufacturing Defects:\\n1. There are no visible stitching
+      errors; the seams appear straight and clean.\\n2. No apparent glue marks or
+      uneven edges, which indicates good craftsmanship.\\n3. There is a slight distressed
+      effect, but it appears intentional as part of the design rather than a defect.\\n\\nCompliance
+      with Standards:\\n1. The shoe design seems to comply with typical fashion standards,
+      showing a balance of aesthetics and functionality.\\n2. The heel height and
+      shape appear to provide stability, aligning with safety standards for footwear.\\n\\nFinal
+      Answer: The analysis of the product image reveals that the black leather boot
+      is made of high-quality materials with no visible manufacturing defects. The
+      craftsmanship is precise, with clean seams and a well-executed design. The distressed
+      effect appears intentional and part of the aesthetic. The boot seems to comply
+      with fashion and safety standards, offering both style and functionality. No
+      significant issues were found.\",\n        \"refusal\": null,\n        \"annotations\":
+      []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 1300,\n    \"completion_tokens\":
+      250,\n    \"total_tokens\": 1550,\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  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_3a5b33c01a\"\n}\n"
+    headers:
+      CF-RAY:
+      - 926907e45f33f1e7-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 26 Mar 2025 19:25:01 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '7242'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-input-images:
+      - '250000'
+      x-ratelimit-limit-requests:
+      - '50000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-input-images:
+      - '249999'
+      x-ratelimit-remaining-requests:
+      - '49999'
+      x-ratelimit-remaining-tokens:
+      - '149998641'
+      x-ratelimit-reset-input-images:
+      - 0s
+      x-ratelimit-reset-requests:
+      - 1ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_c5dd144c8ac1bb3bd96ffbba40707b2d
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/crew_test.py

@@ -11,7 +11,9 @@ import pydantic_core
 import pytest
 
 from crewai.agent import Agent
+from crewai.agents import CacheHandler
 from crewai.agents.cache import CacheHandler
+from crewai.agents.crew_agent_executor import CrewAgentExecutor
 from crewai.crew import Crew
 from crewai.crews.crew_output import CrewOutput
 from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
@@ -3731,6 +3733,44 @@ def test_multimodal_agent_image_tool_handling():
         assert result["content"][1]["type"] == "image_url"
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_multimodal_agent_describing_image_successfully():
+    """
+    Test that a multimodal agent can process images without validation errors.
+    This test reproduces the scenario from issue #2475.
+    """
+    llm = LLM(model="openai/gpt-4o", temperature=0.7)  # model with vision capabilities
+
+    expert_analyst = Agent(
+        role="Visual Quality Inspector",
+        goal="Perform detailed quality analysis of product images",
+        backstory="Senior quality control expert with expertise in visual inspection",
+        llm=llm,
+        verbose=True,
+        allow_delegation=False,
+        multimodal=True,
+    )
+
+    inspection_task = Task(
+        description="""
+        Analyze the product image at https://www.us.maguireshoes.com/cdn/shop/files/FW24-Edito-Lucena-Distressed-01_1920x.jpg?v=1736371244 with focus on:
+        1. Quality of materials
+        2. Manufacturing defects
+        3. Compliance with standards
+        Provide a detailed report highlighting any issues found.
+        """,
+        expected_output="A detailed report highlighting any issues found",
+        agent=expert_analyst,
+    )
+
+    crew = Crew(agents=[expert_analyst], tasks=[inspection_task])
+    result = crew.kickoff()
+
+    task_output = result.tasks_output[0]
+    assert isinstance(task_output, TaskOutput)
+    assert task_output.raw == result.raw
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_multimodal_agent_live_image_analysis():
     """
@@ -4025,3 +4065,52 @@ def test_crew_with_knowledge_sources_works_with_copy():
     assert len(crew_copy.tasks) == len(crew.tasks)
 
     assert len(crew_copy.tasks) == len(crew.tasks)
+
+
+def test_crew_kickoff_for_each_works_with_manager_agent_copy():
+    researcher = Agent(
+        role="Researcher",
+        goal="Conduct thorough research and analysis on AI and AI agents",
+        backstory="You're an expert researcher, specialized in technology, software engineering, AI, and startups. You work as a freelancer and are currently researching for a new client.",
+        allow_delegation=False
+    )
+
+    writer = Agent(
+        role="Senior Writer",
+        goal="Create compelling 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 currently writing content for a new client.",
+        allow_delegation=False
+    )
+
+    # Define task
+    task = Task(
+        description="Generate a list of 5 interesting ideas for an article, then write one captivating paragraph for each idea that showcases the potential of a full article on this topic. Return the list of ideas with their paragraphs and your notes.",
+        expected_output="5 bullet points, each with a paragraph and accompanying notes.",
+    )
+
+    # Define manager agent
+    manager = Agent(
+        role="Project Manager",
+        goal="Efficiently manage the crew and ensure high-quality task completion",
+        backstory="You're an experienced project manager, skilled in overseeing complex projects and guiding teams to success. Your role is to coordinate the efforts of the crew members, ensuring that each task is completed on time and to the highest standard.",
+        allow_delegation=True
+    )
+
+    # Instantiate crew with a custom manager
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[task],
+        manager_agent=manager,
+        process=Process.hierarchical,
+        verbose=True
+    )
+
+    crew_copy = crew.copy()
+    assert crew_copy.manager_agent is not None
+    assert crew_copy.manager_agent.id != crew.manager_agent.id
+    assert crew_copy.manager_agent.role == crew.manager_agent.role
+    assert crew_copy.manager_agent.goal == crew.manager_agent.goal
+    assert crew_copy.manager_agent.backstory == crew.manager_agent.backstory
+    assert isinstance(crew_copy.manager_agent.agent_executor, CrewAgentExecutor)
+    assert isinstance(crew_copy.manager_agent.cache_handler, CacheHandler)
+

tests/test_multimodal_validation.py

@@ -0,0 +1,46 @@
+import os
+
+import pytest
+
+from crewai import LLM, Agent, Crew, Task
+
+
+@pytest.mark.skip(reason="Only run manually with valid API keys")
+def test_multimodal_agent_with_image_url():
+    """
+    Test that a multimodal agent can process images without validation errors.
+    This test reproduces the scenario from issue #2475.
+    """
+    OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+    if not OPENAI_API_KEY:
+        pytest.skip("OPENAI_API_KEY environment variable not set")
+
+    llm = LLM(
+        model="openai/gpt-4o",  # model with vision capabilities
+        api_key=OPENAI_API_KEY,
+        temperature=0.7
+    )
+
+    expert_analyst = Agent(
+        role="Visual Quality Inspector",
+        goal="Perform detailed quality analysis of product images",
+        backstory="Senior quality control expert with expertise in visual inspection",
+        llm=llm,
+        verbose=True,
+        allow_delegation=False,
+        multimodal=True
+    )
+
+    inspection_task = Task(
+        description="""
+        Analyze the product image at https://www.us.maguireshoes.com/collections/spring-25/products/lucena-black-boot with focus on:
+        1. Quality of materials
+        2. Manufacturing defects
+        3. Compliance with standards
+        Provide a detailed report highlighting any issues found.
+        """,
+        expected_output="A detailed report highlighting any issues found",
+        agent=expert_analyst
+    )
+
+    crew = Crew(agents=[expert_analyst], tasks=[inspection_task])

tests/tools/test_tool_usage.py

@@ -1,5 +1,7 @@
+import datetime
 import json
 import random
+import time
 from unittest.mock import MagicMock, patch
 
 import pytest
@@ -11,6 +13,7 @@ from crewai.tools.tool_usage import ToolUsage
 from crewai.utilities.events import crewai_event_bus
 from crewai.utilities.events.tool_usage_events import (
     ToolSelectionErrorEvent,
+    ToolUsageFinishedEvent,
     ToolValidateInputErrorEvent,
 )
 
@@ -624,3 +627,161 @@ def test_tool_validate_input_error_event():
         assert event.agent_role == "test_role"
         assert event.tool_name == "test_tool"
         assert "must be a valid dictionary" in event.error
+
+
+def test_tool_usage_finished_event_with_result():
+    """Test that ToolUsageFinishedEvent is emitted with correct result attributes."""
+    # Create mock agent with proper string values
+    mock_agent = MagicMock()
+    mock_agent.key = "test_agent_key"
+    mock_agent.role = "test_agent_role"
+    mock_agent._original_role = "test_agent_role"
+    mock_agent.i18n = MagicMock()
+    mock_agent.verbose = False
+
+    # Create mock task
+    mock_task = MagicMock()
+    mock_task.delegations = 0
+
+    # Create mock tool
+    class TestTool(BaseTool):
+        name: str = "Test Tool"
+        description: str = "A test tool"
+
+        def _run(self, input: dict) -> str:
+            return "test result"
+
+    test_tool = TestTool()
+
+    # Create mock tool calling
+    mock_tool_calling = MagicMock()
+    mock_tool_calling.arguments = {"arg1": "value1"}
+
+    # Create ToolUsage instance
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[test_tool],
+        original_tools=[test_tool],
+        tools_description="Test Tool Description",
+        tools_names="Test Tool",
+        task=mock_task,
+        function_calling_llm=None,
+        agent=mock_agent,
+        action=MagicMock(),
+    )
+
+    # Track received events
+    received_events = []
+
+    @crewai_event_bus.on(ToolUsageFinishedEvent)
+    def event_handler(source, event):
+        received_events.append(event)
+
+    # Call on_tool_use_finished with test data
+    started_at = time.time()
+    result = "test output result"
+    tool_usage.on_tool_use_finished(
+        tool=test_tool,
+        tool_calling=mock_tool_calling,
+        from_cache=False,
+        started_at=started_at,
+        result=result,
+    )
+
+    # Verify event was emitted
+    assert len(received_events) == 1, "Expected one event to be emitted"
+    event = received_events[0]
+    assert isinstance(event, ToolUsageFinishedEvent)
+
+    # Verify event attributes
+    assert event.agent_key == "test_agent_key"
+    assert event.agent_role == "test_agent_role"
+    assert event.tool_name == "Test Tool"
+    assert event.tool_args == {"arg1": "value1"}
+    assert event.tool_class == "TestTool"
+    assert event.run_attempts == 1  # Default value from ToolUsage
+    assert event.delegations == 0
+    assert event.from_cache is False
+    assert event.output == "test output result"
+    assert isinstance(event.started_at, datetime.datetime)
+    assert isinstance(event.finished_at, datetime.datetime)
+    assert event.type == "tool_usage_finished"
+
+
+def test_tool_usage_finished_event_with_cached_result():
+    """Test that ToolUsageFinishedEvent is emitted with correct result attributes when using cached result."""
+    # Create mock agent with proper string values
+    mock_agent = MagicMock()
+    mock_agent.key = "test_agent_key"
+    mock_agent.role = "test_agent_role"
+    mock_agent._original_role = "test_agent_role"
+    mock_agent.i18n = MagicMock()
+    mock_agent.verbose = False
+
+    # Create mock task
+    mock_task = MagicMock()
+    mock_task.delegations = 0
+
+    # Create mock tool
+    class TestTool(BaseTool):
+        name: str = "Test Tool"
+        description: str = "A test tool"
+
+        def _run(self, input: dict) -> str:
+            return "test result"
+
+    test_tool = TestTool()
+
+    # Create mock tool calling
+    mock_tool_calling = MagicMock()
+    mock_tool_calling.arguments = {"arg1": "value1"}
+
+    # Create ToolUsage instance
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[test_tool],
+        original_tools=[test_tool],
+        tools_description="Test Tool Description",
+        tools_names="Test Tool",
+        task=mock_task,
+        function_calling_llm=None,
+        agent=mock_agent,
+        action=MagicMock(),
+    )
+
+    # Track received events
+    received_events = []
+
+    @crewai_event_bus.on(ToolUsageFinishedEvent)
+    def event_handler(source, event):
+        received_events.append(event)
+
+    # Call on_tool_use_finished with test data and from_cache=True
+    started_at = time.time()
+    result = "cached test output result"
+    tool_usage.on_tool_use_finished(
+        tool=test_tool,
+        tool_calling=mock_tool_calling,
+        from_cache=True,
+        started_at=started_at,
+        result=result,
+    )
+
+    # Verify event was emitted
+    assert len(received_events) == 1, "Expected one event to be emitted"
+    event = received_events[0]
+    assert isinstance(event, ToolUsageFinishedEvent)
+
+    # Verify event attributes
+    assert event.agent_key == "test_agent_key"
+    assert event.agent_role == "test_agent_role"
+    assert event.tool_name == "Test Tool"
+    assert event.tool_args == {"arg1": "value1"}
+    assert event.tool_class == "TestTool"
+    assert event.run_attempts == 1  # Default value from ToolUsage
+    assert event.delegations == 0
+    assert event.from_cache is True
+    assert event.output == "cached test output result"
+    assert isinstance(event.started_at, datetime.datetime)
+    assert isinstance(event.finished_at, datetime.datetime)
+    assert event.type == "tool_usage_finished"

tests/utilities/events/test_crewai_event_bus.py

@@ -1,10 +1,10 @@
 from unittest.mock import Mock
 
-from crewai.utilities.events.base_events import CrewEvent
+from crewai.utilities.events.base_events import BaseEvent
 from crewai.utilities.events.crewai_event_bus import crewai_event_bus
 
 
-class TestEvent(CrewEvent):
+class TestEvent(BaseEvent):
     pass
 
 
@@ -24,7 +24,7 @@ def test_specific_event_handler():
 def test_wildcard_event_handler():
     mock_handler = Mock()
 
-    @crewai_event_bus.on(CrewEvent)
+    @crewai_event_bus.on(BaseEvent)
     def handler(source, event):
         mock_handler(source, event)
 

tests/utilities/test_serialization.py

@@ -5,8 +5,7 @@ from unittest.mock import Mock
 import pytest
 from pydantic import BaseModel
 
-from crewai.flow import Flow
-from crewai.flow.state_utils import export_state, to_serializable, to_string
+from crewai.utilities.serialization import to_serializable, to_string
 
 
 class Address(BaseModel):
@@ -23,16 +22,6 @@ class Person(BaseModel):
     skills: List[str]
 
 
-@pytest.fixture
-def mock_flow():
-    def create_flow(state):
-        flow = Mock(spec=Flow)
-        flow._state = state
-        return flow
-
-    return create_flow
-
-
 @pytest.mark.parametrize(
     "test_input,expected",
     [
@@ -47,9 +36,8 @@ def mock_flow():
         ({"nested": [1, [2, 3], {4, 5}]}, {"nested": [1, [2, 3], [4, 5]]}),
     ],
 )
-def test_basic_serialization(mock_flow, test_input, expected):
-    flow = mock_flow(test_input)
-    result = export_state(flow)
+def test_basic_serialization(test_input, expected):
+    result = to_serializable(test_input)
     assert result == expected
 
 
@@ -60,9 +48,8 @@ def test_basic_serialization(mock_flow, test_input, expected):
         (datetime(2024, 1, 1, 12, 30), "2024-01-01T12:30:00"),
     ],
 )
-def test_temporal_serialization(mock_flow, input_date, expected):
-    flow = mock_flow({"date": input_date})
-    result = export_state(flow)
+def test_temporal_serialization(input_date, expected):
+    result = to_serializable({"date": input_date})
     assert result["date"] == expected
 
 
@@ -75,9 +62,8 @@ def test_temporal_serialization(mock_flow, input_date, expected):
         ("normal", "value", str),
     ],
 )
-def test_dictionary_key_serialization(mock_flow, key, value, expected_key_type):
-    flow = mock_flow({key: value})
-    result = export_state(flow)
+def test_dictionary_key_serialization(key, value, expected_key_type):
+    result = to_serializable({key: value})
     assert len(result) == 1
     result_key = next(iter(result.keys()))
     assert isinstance(result_key, expected_key_type)
@@ -91,14 +77,13 @@ def test_dictionary_key_serialization(mock_flow, key, value, expected_key_type):
         (str.upper, "upper"),
     ],
 )
-def test_callable_serialization(mock_flow, callable_obj, expected_in_result):
-    flow = mock_flow({"func": callable_obj})
-    result = export_state(flow)
+def test_callable_serialization(callable_obj, expected_in_result):
+    result = to_serializable({"func": callable_obj})
     assert isinstance(result["func"], str)
     assert expected_in_result in result["func"].lower()
 
 
-def test_pydantic_model_serialization(mock_flow):
+def test_pydantic_model_serialization():
     address = Address(street="123 Main St", city="Tech City", country="Pythonia")
 
     person = Person(
@@ -109,23 +94,21 @@ def test_pydantic_model_serialization(mock_flow):
         skills=["Python", "Testing"],
     )
 
-    flow = mock_flow(
-        {
-            "single_model": address,
-            "nested_model": person,
-            "model_list": [address, address],
-            "model_dict": {"home": address},
-        }
-    )
+    data = {
+        "single_model": address,
+        "nested_model": person,
+        "model_list": [address, address],
+        "model_dict": {"home": address},
+    }
 
-    result = export_state(flow)
+    result = to_serializable(data)
     assert (
         to_string(result)
         == '{"single_model": {"street": "123 Main St", "city": "Tech City", "country": "Pythonia"}, "nested_model": {"name": "John Doe", "age": 30, "address": {"street": "123 Main St", "city": "Tech City", "country": "Pythonia"}, "birthday": "1994-01-01", "skills": ["Python", "Testing"]}, "model_list": [{"street": "123 Main St", "city": "Tech City", "country": "Pythonia"}, {"street": "123 Main St", "city": "Tech City", "country": "Pythonia"}], "model_dict": {"home": {"street": "123 Main St", "city": "Tech City", "country": "Pythonia"}}}'
     )
 
 
-def test_depth_limit(mock_flow):
+def test_depth_limit():
     """Test max depth handling with a deeply nested structure"""
 
     def create_nested(depth):
@@ -134,8 +117,7 @@ def test_depth_limit(mock_flow):
         return {"next": create_nested(depth - 1)}
 
     deep_structure = create_nested(10)
-    flow = mock_flow(deep_structure)
-    result = export_state(flow)
+    result = to_serializable(deep_structure)
 
     assert result == {
         "next": {

uv.lock

@@ -1,4 +1,5 @@
 version = 1
+revision = 1
 requires-python = ">=3.10, <3.13"
 resolution-markers = [
     "python_full_version < '3.11' and sys_platform == 'darwin'",
@@ -694,7 +695,7 @@ requires-dist = [
     { name = "blinker", specifier = ">=1.9.0" },
     { name = "chromadb", specifier = ">=0.5.23" },
     { name = "click", specifier = ">=8.1.7" },
-    { name = "crewai-tools", marker = "extra == 'tools'", specifier = ">=0.37.0" },
+    { name = "crewai-tools", marker = "extra == 'tools'", specifier = "~=0.38.0" },
     { name = "docling", marker = "extra == 'docling'", specifier = ">=2.12.0" },
     { name = "fastembed", marker = "extra == 'fastembed'", specifier = ">=0.4.1" },
     { name = "instructor", specifier = ">=1.3.3" },
@@ -721,6 +722,7 @@ requires-dist = [
     { name = "tomli-w", specifier = ">=1.1.0" },
     { name = "uv", specifier = ">=0.4.25" },
 ]
+provides-extras = ["tools", "embeddings", "agentops", "fastembed", "pdfplumber", "pandas", "openpyxl", "mem0", "docling", "aisuite"]
 
 [package.metadata.requires-dev]
 dev = [
@@ -2973,7 +2975,6 @@ name = "nvidia-nccl-cu12"
 version = "2.20.5"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/c1/bb/d09dda47c881f9ff504afd6f9ca4f502ded6d8fc2f572cacc5e39da91c28/nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1fc150d5c3250b170b29410ba682384b14581db722b2531b0d8d33c595f33d01", size = 176238458 },
     { url = "https://files.pythonhosted.org/packages/4b/2a/0a131f572aa09f741c30ccd45a8e56316e8be8dfc7bc19bf0ab7cfef7b19/nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl", hash = "sha256:057f6bf9685f75215d0c53bf3ac4a10b3e6578351de307abad9e18a99182af56", size = 176249402 },
 ]
 
@@ -2983,7 +2984,6 @@ version = "12.6.85"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/9d/d7/c5383e47c7e9bf1c99d5bd2a8c935af2b6d705ad831a7ec5c97db4d82f4f/nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:eedc36df9e88b682efe4309aa16b5b4e78c2407eac59e8c10a6a47535164369a", size = 19744971 },
-    { url = "https://files.pythonhosted.org/packages/31/db/dc71113d441f208cdfe7ae10d4983884e13f464a6252450693365e166dcf/nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cf4eaa7d4b6b543ffd69d6abfb11efdeb2db48270d94dfd3a452c24150829e41", size = 19270338 },
 ]
 
 [[package]]