improving guardrails

* Preparing new version

docs/concepts/knowledge.mdx

@@ -146,81 +146,106 @@ Here are examples of how to use different types of knowledge sources:
 
 ### Text File Knowledge Source
 ```python
-from crewai.knowledge.source import CrewDoclingSource
+from crewai.knowledge.source.crew_docling_source import CrewDoclingSource
 
 # Create a text file knowledge source
 text_source = CrewDoclingSource(
     file_paths=["document.txt", "another.txt"]
 )
 
-# Create knowledge with text file source
-knowledge = Knowledge(
-    collection_name="text_knowledge",
-    sources=[text_source]
+# Create crew with text file source on agents or crew level
+agent = Agent(
+    ...
+    knowledge_sources=[text_source]
+)
+
+crew = Crew(
+    ...
+    knowledge_sources=[text_source]
 )
 ```
 
 ### PDF Knowledge Source
 ```python
-from crewai.knowledge.source import PDFKnowledgeSource
+from crewai.knowledge.source.pdf_knowledge_source import PDFKnowledgeSource
 
 # Create a PDF knowledge source
 pdf_source = PDFKnowledgeSource(
     file_paths=["document.pdf", "another.pdf"]
 )
 
-# Create knowledge with PDF source
-knowledge = Knowledge(
-    collection_name="pdf_knowledge",
-    sources=[pdf_source]
+# Create crew with PDF knowledge source on agents or crew level
+agent = Agent(
+    ...
+    knowledge_sources=[pdf_source]
+)
+
+crew = Crew(
+    ...
+    knowledge_sources=[pdf_source]
 )
 ```
 
 ### CSV Knowledge Source
 ```python
-from crewai.knowledge.source import CSVKnowledgeSource
+from crewai.knowledge.source.csv_knowledge_source import CSVKnowledgeSource
 
 # Create a CSV knowledge source
 csv_source = CSVKnowledgeSource(
     file_paths=["data.csv"]
 )
 
-# Create knowledge with CSV source
-knowledge = Knowledge(
-    collection_name="csv_knowledge",
-    sources=[csv_source]
+# Create crew with CSV knowledge source or on agent level
+agent = Agent(
+    ...
+    knowledge_sources=[csv_source]
+)
+
+crew = Crew(
+    ...
+    knowledge_sources=[csv_source]
 )
 ```
 
 ### Excel Knowledge Source
 ```python
-from crewai.knowledge.source import ExcelKnowledgeSource
+from crewai.knowledge.source.excel_knowledge_source import ExcelKnowledgeSource
 
 # Create an Excel knowledge source
 excel_source = ExcelKnowledgeSource(
     file_paths=["spreadsheet.xlsx"]
 )
 
-# Create knowledge with Excel source
-knowledge = Knowledge(
-    collection_name="excel_knowledge",
-    sources=[excel_source]
+# Create crew with Excel knowledge source on agents or crew level
+agent = Agent(
+    ...
+    knowledge_sources=[excel_source]
+)
+
+crew = Crew(
+    ...
+    knowledge_sources=[excel_source]
 )
 ```
 
 ### JSON Knowledge Source
 ```python
-from crewai.knowledge.source import JSONKnowledgeSource
+from crewai.knowledge.source.json_knowledge_source import JSONKnowledgeSource
 
 # Create a JSON knowledge source
 json_source = JSONKnowledgeSource(
     file_paths=["data.json"]
 )
 
-# Create knowledge with JSON source
-knowledge = Knowledge(
-    collection_name="json_knowledge",
-    sources=[json_source]
+# Create crew with JSON knowledge source on agents or crew level
+agent = Agent(
+    ...
+    knowledge_sources=[json_source]
+)
+
+crew = Crew(
+    ...
+    knowledge_sources=[json_source]
 )
 ```
 
@@ -232,7 +257,7 @@ Knowledge sources automatically chunk content for better processing.
 You can configure chunking behavior in your knowledge sources:
 
 ```python
-from crewai.knowledge.source import StringKnowledgeSource
+from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 
 source = StringKnowledgeSource(
     content="Your content here",

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crewai"
-version = "0.86.0"
+version = "0.95.0"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
 requires-python = ">=3.10,<3.13"

src/crewai/__init__.py

@@ -14,7 +14,7 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.86.0"
+__version__ = "0.95.0"
 __all__ = [
     "Agent",
     "Crew",

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

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.86.0,<1.0.0"
+    "crewai[tools]>=0.95.0,<1.0.0"
 ]
 
 [project.scripts]

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

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.86.0,<1.0.0",
+    "crewai[tools]>=0.95.0,<1.0.0",
 ]
 
 [project.scripts]

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

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.86.0"
+    "crewai[tools]>=0.95.0"
 ]
 
 [tool.crewai]

src/crewai/llm.py

@@ -4,6 +4,7 @@ import sys
 import threading
 import warnings
 from contextlib import contextmanager
+from importlib import resources
 from typing import Any, Dict, List, Optional, Union
 
 with warnings.catch_warnings():
@@ -78,6 +79,7 @@ CONTEXT_WINDOW_USAGE_RATIO = 0.75
 def suppress_warnings():
     with warnings.catch_warnings():
         warnings.filterwarnings("ignore")
+        warnings.filterwarnings("ignore", message="open_text is deprecated*", category=DeprecationWarning)
 
         # Redirect stdout and stderr
         old_stdout = sys.stdout
@@ -216,16 +218,17 @@ class LLM:
         return self.context_window_size
 
     def set_callbacks(self, callbacks: List[Any]):
-        callback_types = [type(callback) for callback in callbacks]
-        for callback in litellm.success_callback[:]:
-            if type(callback) in callback_types:
-                litellm.success_callback.remove(callback)
+        with suppress_warnings():
+            callback_types = [type(callback) for callback in callbacks]
+            for callback in litellm.success_callback[:]:
+                if type(callback) in callback_types:
+                    litellm.success_callback.remove(callback)
 
-        for callback in litellm._async_success_callback[:]:
-            if type(callback) in callback_types:
-                litellm._async_success_callback.remove(callback)
+            for callback in litellm._async_success_callback[:]:
+                if type(callback) in callback_types:
+                    litellm._async_success_callback.remove(callback)
 
-        litellm.callbacks = callbacks
+            litellm.callbacks = callbacks
 
     def set_env_callbacks(self):
         """
@@ -246,19 +249,20 @@ class LLM:
         This will set `litellm.success_callback` to ["langfuse", "langsmith"] and
         `litellm.failure_callback` to ["langfuse"].
         """
-        success_callbacks_str = os.environ.get("LITELLM_SUCCESS_CALLBACKS", "")
-        success_callbacks = []
-        if success_callbacks_str:
-            success_callbacks = [
-                callback.strip() for callback in success_callbacks_str.split(",")
-            ]
+        with suppress_warnings():
+            success_callbacks_str = os.environ.get("LITELLM_SUCCESS_CALLBACKS", "")
+            success_callbacks = []
+            if success_callbacks_str:
+                success_callbacks = [
+                    callback.strip() for callback in success_callbacks_str.split(",")
+                ]
 
-        failure_callbacks_str = os.environ.get("LITELLM_FAILURE_CALLBACKS", "")
-        failure_callbacks = []
-        if failure_callbacks_str:
-            failure_callbacks = [
-                callback.strip() for callback in failure_callbacks_str.split(",")
-            ]
+            failure_callbacks_str = os.environ.get("LITELLM_FAILURE_CALLBACKS", "")
+            failure_callbacks = []
+            if failure_callbacks_str:
+                failure_callbacks = [
+                    callback.strip() for callback in failure_callbacks_str.split(",")
+                ]
 
-        litellm.success_callback = success_callbacks
-        litellm.failure_callback = failure_callbacks
+            litellm.success_callback = success_callbacks
+            litellm.failure_callback = failure_callbacks

src/crewai/task.py

@@ -41,6 +41,7 @@ from crewai.tools.base_tool import BaseTool
 from crewai.utilities.config import process_config
 from crewai.utilities.converter import Converter, convert_to_model
 from crewai.utilities.i18n import I18N
+from crewai.utilities.printer import Printer
 
 
 class Task(BaseModel):
@@ -127,38 +128,40 @@ class Task(BaseModel):
     processed_by_agents: Set[str] = Field(default_factory=set)
     guardrail: Optional[Callable[[TaskOutput], Tuple[bool, Any]]] = Field(
         default=None,
-        description="Function to validate task output before proceeding to next task"
+        description="Function to validate task output before proceeding to next task",
     )
     max_retries: int = Field(
-        default=3,
-        description="Maximum number of retries when guardrail fails"
+        default=3, description="Maximum number of retries when guardrail fails"
     )
-    retry_count: int = Field(
-        default=0,
-        description="Current number of retries"
+    retry_count: int = Field(default=0, description="Current number of retries")
+    start_time: Optional[datetime.datetime] = Field(
+        default=None, description="Start time of the task execution"
+    )
+    end_time: Optional[datetime.datetime] = Field(
+        default=None, description="End time of the task execution"
     )
 
     @field_validator("guardrail")
     @classmethod
     def validate_guardrail_function(cls, v: Optional[Callable]) -> Optional[Callable]:
         """Validate that the guardrail function has the correct signature and behavior.
-        
+
         While type hints provide static checking, this validator ensures runtime safety by:
         1. Verifying the function accepts exactly one parameter (the TaskOutput)
         2. Checking return type annotations match Tuple[bool, Any] if present
         3. Providing clear, immediate error messages for debugging
-        
+
         This runtime validation is crucial because:
         - Type hints are optional and can be ignored at runtime
         - Function signatures need immediate validation before task execution
         - Clear error messages help users debug guardrail implementation issues
-        
+
         Args:
             v: The guardrail function to validate
-            
+
         Returns:
             The validated guardrail function
-            
+
         Raises:
             ValueError: If the function signature is invalid or return annotation
                        doesn't match Tuple[bool, Any]
@@ -171,8 +174,13 @@ class Task(BaseModel):
             # Check return annotation if present, but don't require it
             return_annotation = sig.return_annotation
             if return_annotation != inspect.Signature.empty:
-                if not (return_annotation == Tuple[bool, Any] or str(return_annotation) == 'Tuple[bool, Any]'):
-                    raise ValueError("If return type is annotated, it must be Tuple[bool, Any]")
+                if not (
+                    return_annotation == Tuple[bool, Any]
+                    or str(return_annotation) == "Tuple[bool, Any]"
+                ):
+                    raise ValueError(
+                        "If return type is annotated, it must be Tuple[bool, Any]"
+                    )
         return v
 
     _telemetry: Telemetry = PrivateAttr(default_factory=Telemetry)
@@ -181,7 +189,6 @@ class Task(BaseModel):
     _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)
 
     @model_validator(mode="before")
     @classmethod
@@ -206,25 +213,19 @@ class Task(BaseModel):
                 "may_not_set_field", "This field is not to be set by the user.", {}
             )
 
-    def _set_start_execution_time(self) -> float:
-        return datetime.datetime.now().timestamp()
-
-    def _set_end_execution_time(self, start_time: float) -> None:
-        self._execution_time = datetime.datetime.now().timestamp() - start_time
-
     @field_validator("output_file")
     @classmethod
     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.
@@ -234,18 +235,24 @@ class Task(BaseModel):
 
         # Basic security checks
         if ".." in value:
-            raise ValueError("Path traversal attempts are not allowed in output_file paths")
-        
+            raise ValueError(
+                "Path traversal attempts are not allowed in output_file paths"
+            )
+
         # Check for shell expansion first
-        if value.startswith('~') or value.startswith('$'):
-            raise ValueError("Shell expansion characters are not allowed in output_file paths")
-            
+        if value.startswith("~") or value.startswith("$"):
+            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")
+        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: 
+        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:
@@ -302,6 +309,12 @@ class Task(BaseModel):
 
         return md5("|".join(source).encode(), usedforsecurity=False).hexdigest()
 
+    @property
+    def execution_duration(self) -> float | None:
+        if not self.start_time or not self.end_time:
+            return None
+        return (self.end_time - self.start_time).total_seconds()
+
     def execute_async(
         self,
         agent: BaseAgent | None = None,
@@ -342,7 +355,7 @@ class Task(BaseModel):
                 f"The task '{self.description}' has no agent assigned, therefore it can't be executed directly and should be executed in a Crew using a specific process that support that, like hierarchical."
             )
 
-        start_time = self._set_start_execution_time()
+        self.start_time = datetime.datetime.now()
         self._execution_span = self._telemetry.task_started(crew=agent.crew, task=self)
 
         self.prompt_context = context
@@ -378,10 +391,14 @@ class Task(BaseModel):
                     )
 
                 self.retry_count += 1
-                context = (
-                    f"### Previous attempt failed validation: {guardrail_result.error}\n\n\n"
-                    f"### Previous result:\n{task_output.raw}\n\n\n"
-                    "Try again, making sure to address the validation error."
+                context = self.i18n.errors("validation_error").format(
+                    guardrail_result_error=guardrail_result.error,
+                    task_output=task_output.raw
+                )
+                printer = Printer()
+                printer.print(
+                    content=f"Guardrail blocked, retrying, due to:{guardrail_result.error}\n",
+                    color="yellow",
                 )
                 return self._execute_core(agent, context, tools)
 
@@ -392,15 +409,17 @@ class Task(BaseModel):
 
             if isinstance(guardrail_result.result, str):
                 task_output.raw = guardrail_result.result
-                pydantic_output, json_output = self._export_output(guardrail_result.result)
+                pydantic_output, json_output = self._export_output(
+                    guardrail_result.result
+                )
                 task_output.pydantic = pydantic_output
                 task_output.json_dict = json_output
             elif isinstance(guardrail_result.result, TaskOutput):
                 task_output = guardrail_result.result
 
         self.output = task_output
+        self.end_time = datetime.datetime.now()
 
-        self._set_end_execution_time(start_time)
         if self.callback:
             self.callback(self.output)
 
@@ -412,7 +431,9 @@ class Task(BaseModel):
             content = (
                 json_output
                 if json_output
-                else pydantic_output.model_dump_json() if pydantic_output else result
+                else pydantic_output.model_dump_json()
+                if pydantic_output
+                else result
             )
             self._save_file(content)
 
@@ -434,11 +455,11 @@ class Task(BaseModel):
 
     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.
         """
@@ -455,7 +476,9 @@ class Task(BaseModel):
         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
+            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
 
@@ -472,22 +495,26 @@ class Task(BaseModel):
                     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
+                raise ValueError(
+                    f"Error interpolating output_file path: {str(e)}"
+                ) from e
 
-    def interpolate_only(self, input_string: Optional[str], inputs: Dict[str, Union[str, int, float]]) -> str:
+    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.
@@ -497,13 +524,17 @@ class Task(BaseModel):
         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")
+            raise ValueError(
+                "Inputs dictionary cannot be empty when interpolating variables"
+            )
 
         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__}")
+                    raise ValueError(
+                        f"Value for key '{key}' must be a string, integer, or float, got {type(value).__name__}"
+                    )
 
             escaped_string = input_string.replace("{", "{{").replace("}", "}}")
 
@@ -512,7 +543,9 @@ class Task(BaseModel):
 
             return escaped_string.format(**inputs)
         except KeyError as e:
-            raise KeyError(f"Template variable '{e.args[0]}' not found in inputs dictionary") from 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
 
@@ -597,10 +630,10 @@ class Task(BaseModel):
 
     def _save_file(self, result: Any) -> None:
         """Save task output to a file.
-        
+
         Args:
             result: The result to save to the file. Can be a dict or any stringifiable object.
-            
+
         Raises:
             ValueError: If output_file is not set
             RuntimeError: If there is an error writing to the file
@@ -618,6 +651,7 @@ class Task(BaseModel):
             with resolved_path.open("w", encoding="utf-8") as file:
                 if isinstance(result, dict):
                     import json
+
                     json.dump(result, file, ensure_ascii=False, indent=2)
                 else:
                     file.write(str(result))

src/crewai/tools/agent_tools/base_agent_tools.py

@@ -1,5 +1,5 @@
 import logging
-from typing import Optional, Union
+from typing import Optional
 
 from pydantic import Field
 
@@ -54,12 +54,12 @@ class BaseAgentTool(BaseTool):
     ) -> 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

src/crewai/tools/base_tool.py

@@ -1,12 +1,23 @@
+import warnings
 from abc import ABC, abstractmethod
 from inspect import signature
 from typing import Any, Callable, Type, get_args, get_origin
 
-from pydantic import BaseModel, ConfigDict, Field, create_model, validator
+from pydantic import (
+    BaseModel,
+    ConfigDict,
+    Field,
+    PydanticDeprecatedSince20,
+    create_model,
+    validator,
+)
 from pydantic import BaseModel as PydanticBaseModel
 
 from crewai.tools.structured_tool import CrewStructuredTool
 
+# Ignore all "PydanticDeprecatedSince20" warnings globally
+warnings.filterwarnings("ignore", category=PydanticDeprecatedSince20)
+
 
 class BaseTool(BaseModel, ABC):
     class _ArgsSchemaPlaceholder(PydanticBaseModel):

src/crewai/translations/en.json

@@ -34,7 +34,8 @@
     "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}",
-    "agent_tool_execution_error": "Error executing task with agent '{agent_role}'. Error: {error}"
+    "agent_tool_execution_error": "Error executing task with agent '{agent_role}'. Error: {error}",
+    "validation_error": "### Previous attempt failed validation: {guardrail_result_error}\n\n\n### Previous result:\n{task_output}\n\n\nTry again, making sure to address the validation 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.",

src/crewai/utilities/evaluators/crew_evaluator_handler.py

@@ -180,12 +180,12 @@ class CrewEvaluator:
             self._test_result_span = self._telemetry.individual_test_result_span(
                 self.crew,
                 evaluation_result.pydantic.quality,
-                current_task._execution_time,
+                current_task.execution_duration,
                 self.openai_model_name,
             )
             self.tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
             self.run_execution_times[self.iteration].append(
-                current_task._execution_time
+                current_task.execution_duration
             )
         else:
             raise ValueError("Evaluation result is not in the expected format")

src/crewai/utilities/internal_instructor.py

@@ -31,10 +31,10 @@ class InternalInstructor:
             import instructor
             from litellm import completion
 
-        self._client = instructor.from_litellm(
-            completion,
-            mode=instructor.Mode.TOOLS,
-        )
+            self._client = instructor.from_litellm(
+                completion,
+                mode=instructor.Mode.TOOLS,
+            )
 
     def to_json(self):
         model = self.to_pydantic()

src/crewai/utilities/planning_handler.py

@@ -1,4 +1,3 @@
-import json
 import logging
 from typing import Any, List, Optional
 
@@ -78,10 +77,10 @@ class CrewPlanner:
     def _get_agent_knowledge(self, task: Task) -> List[str]:
         """
         Safely retrieve knowledge source content from the task's agent.
-        
+
         Args:
             task: The task containing an agent with potential knowledge sources
-            
+
         Returns:
             List[str]: A list of knowledge source strings
         """
@@ -108,6 +107,6 @@ class CrewPlanner:
                     f"[{', '.join(str(tool) for tool in task.agent.tools)}]" if task.agent and task.agent.tools else '"agent has no tools"',
                     f',\n                "agent_knowledge": "[\\"{knowledge_list[0]}\\"]"' if knowledge_list and str(knowledge_list) != "None" else ""
                 )
-            
+
             tasks_summary.append(task_summary)
         return " ".join(tasks_summary)

tests/agents/agent_builder/base_agent_test.py

@@ -7,7 +7,7 @@ from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.tools.base_tool import BaseTool
 
 
-class TestAgent(BaseAgent):
+class MockAgent(BaseAgent):
     def execute_task(
         self,
         task: Any,
@@ -29,7 +29,7 @@ class TestAgent(BaseAgent):
 
 
 def test_key():
-    agent = TestAgent(
+    agent = MockAgent(
         role="test role",
         goal="test goal",
         backstory="test backstory",

tests/cassettes/test_crew_with_failing_task_guardrails.yaml

@@ -0,0 +1,988 @@
+interactions:
+- request:
+    body: !!binary |
+      CpotCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS8SwKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRLrCQoQmqG4kmRspGSV9KSDE2WH2hIInKDQhtLNgqEqDENyZXcgQ3JlYXRlZDABOeCb
+      nCGokxcYQYDspiGokxcYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuOTUuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogY2FhMWFlYjNkZDQzNjM4NjU2OGE1YzNmZTIx
+      MDFhZjVKMQoHY3Jld19pZBImCiQxOWRmM2Y3MS1kYzk0LTQ0ZjYtYmY0Zi0zNjBjZjY2YjJiYWZK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSo4FCgtjcmV3
+      X2FnZW50cxL+BAr7BFt7ImtleSI6ICI5N2Y0MTdmM2UxZTMxY2YwYzEwOWY3NTI5YWM4ZjZiYyIs
+      ICJpZCI6ICJjMzIyZGMzMS0zZDNlLTRlOTctYjgwNi02MDU3ZTZjNGQxZmUiLCAicm9sZSI6ICJQ
+      cm9ncmFtbWVyIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6
+      IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwg
+      ImRlbGVnYXRpb25fZW5hYmxlZD8iOiB0cnVlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogdHJ1
+      ZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiOTJh
+      MjRiMGJjY2ZiMGRjMGU0MzlkN2Q1OWJhOWY2ZjMiLCAiaWQiOiAiYzMzMGJlNDAtYWQxMS00YjM2
+      LWEwYTYtY2E4NWY5ZWFjYzZhIiwgInJvbGUiOiAiQ29kZSBSZXZpZXdlciIsICJ2ZXJib3NlPyI6
+      IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGlu
+      Z19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/Ijog
+      dHJ1ZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IHRydWUsICJtYXhfcmV0cnlfbGltaXQiOiAy
+      LCAidG9vbHNfbmFtZXMiOiBbXX1dSooCCgpjcmV3X3Rhc2tzEvsBCvgBW3sia2V5IjogIjc5YWEy
+      N2RmNzRlNjI3OWUzNGE4ODg4MTc0ODFjNDBmIiwgImlkIjogIjEyYmNjNTAwLWExNzgtNGQyZS05
+      NmQ4LWNkN2UwZmYzNzRhMCIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1
+      dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiUHJvZ3JhbW1lciIsICJhZ2VudF9rZXkiOiAiOTdm
+      NDE3ZjNlMWUzMWNmMGMxMDlmNzUyOWFjOGY2YmMiLCAidG9vbHNfbmFtZXMiOiBbInRlc3QgdG9v
+      bCJdfV16AhgBhQEAAQAAErMHChCxSjXt2/kv7CqAN8F+6ZMMEghR4jnKP0dHjSoMQ3JldyBDcmVh
+      dGVkMAE5iBNAIqiTFxhBiGZHIqiTFxhKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC45NS4wShoKDnB5
+      dGhvbl92ZXJzaW9uEggKBjMuMTEuN0ouCghjcmV3X2tleRIiCiA3NzNhODc2YjU3OTJkYjY5NTU5
+      ZmU4MmMzYWQyMzU5ZkoxCgdjcmV3X2lkEiYKJDk2YjRkMmFlLTQ3ZDUtNDA0MS1hNjJhLTAyMmMy
+      ZDUzZGZkZkocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABK
+      GgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFK
+      2QIKC2NyZXdfYWdlbnRzEskCCsYCW3sia2V5IjogIjA3N2M3YTg2N2UyMGQwYTY4Yjk3NGU0NzYw
+      NzEwOWYzIiwgImlkIjogIjVhOTJiYzM4LWFlNGEtNGViZC1iNTM2LTFkZGVjZDBkODBhYyIsICJy
+      b2xlIjogIk11bHRpbW9kYWwgQW5hbHlzdCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIi
+      OiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6
+      ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2Rl
+      X2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6
+      IFtdfV1KhwIKCmNyZXdfdGFza3MS+AEK9QFbeyJrZXkiOiAiYzc1M2M2ODA2MzU5NDM2YTU4OTZm
+      ZWMwOWJhYTEyNWUiLCAiaWQiOiAiNmRhZTcyNzktMDhjNS00OGNiLWI5OWItYmUyYjAwMzhkYzgz
+      IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdl
+      bnRfcm9sZSI6ICJNdWx0aW1vZGFsIEFuYWx5c3QiLCAiYWdlbnRfa2V5IjogIjA3N2M3YTg2N2Uy
+      MGQwYTY4Yjk3NGU0NzYwNzEwOWYzIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASqQcK
+      EIW4ljcZA7v+rs1zMkO4T0wSCIcyNxRlQUYoKgxDcmV3IENyZWF0ZWQwATngxKQiqJMXGEHIIasi
+      qJMXGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjk1LjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4x
+      MS43Si4KCGNyZXdfa2V5EiIKIGNkNGRhNjRlNmRjM2I5ZWJkY2EyNDQ0YzFkNzMwMjgxSjEKB2Ny
+      ZXdfaWQSJgokMDY0ZDJmMmYtYWEzMy00MmU4LTgyYjAtMjc1YzM4MzY0MjU0ShwKDGNyZXdfcHJv
+      Y2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90
+      YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrUAgoLY3Jld19hZ2VudHMSxAIK
+      wQJbeyJrZXkiOiAiZDg1MTA2NGI5YjQ4NDE4YWMyNWY4ZDM3YzdlMzJiYjYiLCAiaWQiOiAiY2M4
+      OWQ4YTAtYjk5Yy00MDNkLTg1ODYtNjgzZDA1MGVjMjlhIiwgInJvbGUiOiAiSW1hZ2UgQW5hbHlz
+      dCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAi
+      ZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0
+      aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1h
+      eF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1KggIKCmNyZXdfdGFza3MS8wEK
+      8AFbeyJrZXkiOiAiZWU4NzI5Njk0MTBjOTRjMzM0ZjljZmZhMGE0MTVmZWMiLCAiaWQiOiAiNDY3
+      ZmVlNDktZDkzMi00Nzg1LWI1M2QtYTdkNWQxOTk3NzNmIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBm
+      YWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJJbWFnZSBBbmFseXN0
+      IiwgImFnZW50X2tleSI6ICJkODUxMDY0YjliNDg0MThhYzI1ZjhkMzdjN2UzMmJiNiIsICJ0b29s
+      c19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEqMHChD9ptX+M+ebjYJvJRIgLS+sEgi86MlIS3PYaCoM
+      Q3JldyBDcmVhdGVkMAE5MGUTI6iTFxhBqKoZI6iTFxhKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC45
+      NS4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMuMTEuN0ouCghjcmV3X2tleRIiCiBlMzk1NjdiNTA1
+      MjkwOWNhMzM0MDk4NGI4Mzg5ODBlYUoxCgdjcmV3X2lkEiYKJGQwM2I0NDRiLTBmMjAtNGY5Ni1i
+      MjA0LWQ3YzQ4MzYyNGM0YkocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21l
+      bW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2Fn
+      ZW50cxICGAFKzgIKC2NyZXdfYWdlbnRzEr4CCrsCW3sia2V5IjogIjlkYzhjY2UwMzA0NjgxOTYw
+      NDFiNGMzODBiNjE3Y2IwIiwgImlkIjogImM4Mjc0MmM1LWIzZjQtNDJkMC1iYjNmLTRkZWM4Y2Q4
+      MDNmNCIsICJyb2xlIjogIkltYWdlIEFuYWx5c3QiLCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0
+      ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxs
+      bSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9l
+      eGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBb
+      XX1dSoICCgpjcmV3X3Rhc2tzEvMBCvABW3sia2V5IjogImE5YTc2Y2E2OTU3ZDBiZmZhNjllYWIy
+      MGI2NjQ4MjJiIiwgImlkIjogImU4ZDFmNWM0LWJhNDEtNGQyNy1iMGZmLWU3MmNiNDA0MWJhMyIs
+      ICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50
+      X3JvbGUiOiAiSW1hZ2UgQW5hbHlzdCIsICJhZ2VudF9rZXkiOiAiOWRjOGNjZTAzMDQ2ODE5NjA0
+      MWI0YzM4MGI2MTdjYjAiLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKOAgoQEQqgiftV
+      3giK4F9VtKBNSBIIVzb/bxKe7icqDFRhc2sgQ3JlYXRlZDABOejyJyOokxcYQdhIKCOokxcYSi4K
+      CGNyZXdfa2V5EiIKIGUzOTU2N2I1MDUyOTA5Y2EzMzQwOTg0YjgzODk4MGVhSjEKB2NyZXdfaWQS
+      JgokZDAzYjQ0NGItMGYyMC00Zjk2LWIyMDQtZDdjNDgzNjI0YzRiSi4KCHRhc2tfa2V5EiIKIGE5
+      YTc2Y2E2OTU3ZDBiZmZhNjllYWIyMGI2NjQ4MjJiSjEKB3Rhc2tfaWQSJgokZThkMWY1YzQtYmE0
+      MS00ZDI3LWIwZmYtZTcyY2I0MDQxYmEzegIYAYUBAAEAABKXAQoQg/ksOtq7LbOO50GnDSOHQBII
+      YX08fxOToKwqClRvb2wgVXNhZ2UwATlI/lskqJMXGEEAY2IkqJMXGEoaCg5jcmV3YWlfdmVyc2lv
+      bhIICgYwLjk1LjBKIwoJdG9vbF9uYW1lEhYKFEFkZCBpbWFnZSB0byBjb250ZW50Sg4KCGF0dGVt
+      cHRzEgIYAXoCGAGFAQABAAASqAcKEEmW3y/PMPhkfMJ/43EA4SASCHMJp4PEDhFLKgxDcmV3IENy
+      ZWF0ZWQwATkAuLYlqJMXGEHAaL4lqJMXGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjk1LjBKGgoO
+      cHl0aG9uX3ZlcnNpb24SCAoGMy4xMS43Si4KCGNyZXdfa2V5EiIKIDAwYjk0NmJlNDQzNzE0YjNh
+      NDdjMjAxMDFlYjAyZDY2SjEKB2NyZXdfaWQSJgokNzJkZTEwZTQtNDkwZC00NDYwLTk1NzMtMmU5
+      ZmM5YTMwMWE1ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQ
+      AEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIY
+      AUrTAgoLY3Jld19hZ2VudHMSwwIKwAJbeyJrZXkiOiAiNGI4YTdiODQwZjk0YmY3ODE4YjVkNTNm
+      Njg5MjdmZDUiLCAiaWQiOiAiN2IyMGMyODMtNGFiNy00MjFlLTgzM2QtOWE5N2UzNjFjM2Q2Iiwg
+      InJvbGUiOiAiUmVwb3J0IFdyaXRlciIsICJ2ZXJib3NlPyI6IHRydWUsICJtYXhfaXRlciI6IDIw
+      LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdw
+      dC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhl
+      Y3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119
+      XUqCAgoKY3Jld190YXNrcxLzAQrwAVt7ImtleSI6ICJiNzEzYzgyZmViOTJjOWY1YzU4YjQwYTk3
+      NTU2YjdhYyIsICJpZCI6ICJhZjFhOTYxOC05MjRhLTRlNzktYjZlYi01OGRhMTM2OTU5YzUiLCAi
+      YXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9y
+      b2xlIjogIlJlcG9ydCBXcml0ZXIiLCAiYWdlbnRfa2V5IjogIjRiOGE3Yjg0MGY5NGJmNzgxOGI1
+      ZDUzZjY4OTI3ZmQ1IiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEIWRa5ZrcXnJ
+      3rJdzzJ56j8SCKr45vrXkeyTKgxUYXNrIENyZWF0ZWQwATn488glqJMXGEHoScklqJMXGEouCghj
+      cmV3X2tleRIiCiAwMGI5NDZiZTQ0MzcxNGIzYTQ3YzIwMTAxZWIwMmQ2NkoxCgdjcmV3X2lkEiYK
+      JDcyZGUxMGU0LTQ5MGQtNDQ2MC05NTczLTJlOWZjOWEzMDFhNUouCgh0YXNrX2tleRIiCiBiNzEz
+      YzgyZmViOTJjOWY1YzU4YjQwYTk3NTU2YjdhY0oxCgd0YXNrX2lkEiYKJGFmMWE5NjE4LTkyNGEt
+      NGU3OS1iNmViLTU4ZGExMzY5NTljNXoCGAGFAQABAAA=
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '5789'
+      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:
+      - Sat, 04 Jan 2025 19:22:17 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Report Writer. You''re
+      an expert at writing structured reports.\nYour personal goal is: Create properly
+      formatted reports\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: Write a report about AI with exactly
+      3 key points.\n\nThis is the expect criteria for your final answer: A properly
+      formatted report\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:
+      - '934'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=v_wJZ5m7qCjrnRfks0gT2GAk9yR14BdIDAQiQR7xxI8-1735266215000-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      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:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-Am40qBAFJtuaFsOlTsBHFCoYUvLhN\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1736018532,\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\\n# Report on Artificial Intelligence (AI)\\n\\n## Introduction\\nArtificial
+      Intelligence (AI) is a rapidly evolving technology that simulates human intelligence
+      processes by machines, particularly computer systems. AI has a profound impact
+      on various sectors, enhancing efficiency, improving decision-making, and leading
+      to groundbreaking innovations. This report highlights three key points regarding
+      the significance and implications of AI technology.\\n\\n## Key Point 1: Transformative
+      Potential in Various Industries\\nAI's transformative potential is evident across
+      multiple industries, including healthcare, finance, transportation, and agriculture.
+      In healthcare, AI algorithms can analyze complex medical data, leading to improved
+      diagnostics, personalized medicine, and predictive analytics, thereby enhancing
+      patient outcomes. The financial sector employs AI for risk management, fraud
+      detection, and automated trading, which increases operational efficiency and
+      minimizes human error. In transportation, AI is integral to the development
+      of autonomous vehicles and smart traffic systems, optimizing routes and reducing
+      congestion. Furthermore, agriculture benefits from AI applications through precision
+      farming, which maximizes yield while minimizing environmental impact.\\n\\n##
+      Key Point 2: Ethical Considerations and Challenges\\nAs AI technologies become
+      more pervasive, ethical considerations arise regarding their implementation
+      and use. Concerns include data privacy, algorithmic bias, and the displacement
+      of jobs due to automation. Ensuring that AI systems are transparent, fair, and
+      accountable is crucial in addressing these issues. Organizations must develop
+      comprehensive guidelines and regulatory frameworks to mitigate bias in AI algorithms
+      and protect user data. Moreover, addressing the social implications of AI, such
+      as potential job displacement, is essential, necessitating investment in workforce
+      retraining and education to prepare for an AI-driven economy.\\n\\n## Key Point
+      3: Future Directions and Developments\\nLooking ahead, the future of AI promises
+      continued advancements and integration into everyday life. Emerging trends include
+      the development of explainable AI (XAI), enhancing interpretability and understanding
+      of AI decision-making processes. Advances in natural language processing (NLP)
+      will facilitate better human-computer interactions, allowing for more intuitive
+      applications. Additionally, as AI technology becomes increasingly sophisticated,
+      its role in addressing global challenges, such as climate change and healthcare
+      disparities, is expected to expand. Stakeholders must collaborate to ensure
+      that these developments align with ethical standards and societal needs, fostering
+      a responsible AI future.\\n\\n## Conclusion\\nArtificial Intelligence stands
+      at the forefront of technological innovation, with the potential to revolutionize
+      industries and address complex global challenges. However, it is imperative
+      to navigate the ethical considerations and challenges it poses. By fostering
+      responsible AI development, we can harness its transformative power while ensuring
+      equitability and transparency for future generations.\",\n        \"refusal\":
+      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 170,\n    \"completion_tokens\":
+      524,\n    \"total_tokens\": 694,\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:
+      - 8fcd9890790e0133-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 04 Jan 2025 19:22:19 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=pumYGlf1gsbVoFNTM1vh9Okj41SgxP3y65T5YWWPU1U-1736018539-1.0.1.1-wmaotkWMviN4lKh6M3P04A8p61Ehm.rTehDpsJhxYhNBNU5.kznMCa3cNXePaEbsKkk4PU2QcWjHj2C7yDrjkw;
+        path=/; expires=Sat, 04-Jan-25 19:52:19 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=SlnUP7AT9jJlQiN.Fm1c7MDyo78_hBRAz8PoabvHVSU-1736018539826-0.0.1.1-604800000;
+        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:
+      - '7717'
+      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:
+      - '149999790'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_08d237d56b0168a0f4512417380485db
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      Cs4CCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSpQIKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKOAgoQw9qUJPsh6jiJZX4qW3ry4hIIT7E0SNH7Ub4qDFRhc2sgQ3JlYXRlZDABOQBO
+      BAmqkxcYQQgdBQmqkxcYSi4KCGNyZXdfa2V5EiIKIDAwYjk0NmJlNDQzNzE0YjNhNDdjMjAxMDFl
+      YjAyZDY2SjEKB2NyZXdfaWQSJgokNzJkZTEwZTQtNDkwZC00NDYwLTk1NzMtMmU5ZmM5YTMwMWE1
+      Si4KCHRhc2tfa2V5EiIKIGI3MTNjODJmZWI5MmM5ZjVjNThiNDBhOTc1NTZiN2FjSjEKB3Rhc2tf
+      aWQSJgokYWYxYTk2MTgtOTI0YS00ZTc5LWI2ZWItNThkYTEzNjk1OWM1egIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '337'
+      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:
+      - Sat, 04 Jan 2025 19:22:22 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Report Writer. You''re
+      an expert at writing structured reports.\nYour personal goal is: Create properly
+      formatted reports\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: Write a report about AI with exactly
+      3 key points.\n\nThis is the expect criteria for your final answer: A properly
+      formatted report\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nThis is the context you''re working with:\n### Previous attempt
+      failed validation: Output must start with ''REPORT:'' no formatting, just the
+      word REPORT\n\n\n### Previous result:\n# Report on Artificial Intelligence (AI)\n\n##
+      Introduction\nArtificial Intelligence (AI) is a rapidly evolving technology
+      that simulates human intelligence processes by machines, particularly computer
+      systems. AI has a profound impact on various sectors, enhancing efficiency,
+      improving decision-making, and leading to groundbreaking innovations. This report
+      highlights three key points regarding the significance and implications of AI
+      technology.\n\n## Key Point 1: Transformative Potential in Various Industries\nAI''s
+      transformative potential is evident across multiple industries, including healthcare,
+      finance, transportation, and agriculture. In healthcare, AI algorithms can analyze
+      complex medical data, leading to improved diagnostics, personalized medicine,
+      and predictive analytics, thereby enhancing patient outcomes. The financial
+      sector employs AI for risk management, fraud detection, and automated trading,
+      which increases operational efficiency and minimizes human error. In transportation,
+      AI is integral to the development of autonomous vehicles and smart traffic systems,
+      optimizing routes and reducing congestion. Furthermore, agriculture benefits
+      from AI applications through precision farming, which maximizes yield while
+      minimizing environmental impact.\n\n## Key Point 2: Ethical Considerations and
+      Challenges\nAs AI technologies become more pervasive, ethical considerations
+      arise regarding their implementation and use. Concerns include data privacy,
+      algorithmic bias, and the displacement of jobs due to automation. Ensuring that
+      AI systems are transparent, fair, and accountable is crucial in addressing these
+      issues. Organizations must develop comprehensive guidelines and regulatory frameworks
+      to mitigate bias in AI algorithms and protect user data. Moreover, addressing
+      the social implications of AI, such as potential job displacement, is essential,
+      necessitating investment in workforce retraining and education to prepare for
+      an AI-driven economy.\n\n## Key Point 3: Future Directions and Developments\nLooking
+      ahead, the future of AI promises continued advancements and integration into
+      everyday life. Emerging trends include the development of explainable AI (XAI),
+      enhancing interpretability and understanding of AI decision-making processes.
+      Advances in natural language processing (NLP) will facilitate better human-computer
+      interactions, allowing for more intuitive applications. Additionally, as AI
+      technology becomes increasingly sophisticated, its role in addressing global
+      challenges, such as climate change and healthcare disparities, is expected to
+      expand. Stakeholders must collaborate to ensure that these developments align
+      with ethical standards and societal needs, fostering a responsible AI future.\n\n##
+      Conclusion\nArtificial Intelligence stands at the forefront of technological
+      innovation, with the potential to revolutionize industries and address complex
+      global challenges. However, it is imperative to navigate the ethical considerations
+      and challenges it poses. By fostering responsible AI development, we can harness
+      its transformative power while ensuring equitability and transparency for future
+      generations.\n\n\nTry again, making sure to address the validation error.\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:
+      - '4351'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=SlnUP7AT9jJlQiN.Fm1c7MDyo78_hBRAz8PoabvHVSU-1736018539826-0.0.1.1-604800000;
+        __cf_bm=pumYGlf1gsbVoFNTM1vh9Okj41SgxP3y65T5YWWPU1U-1736018539-1.0.1.1-wmaotkWMviN4lKh6M3P04A8p61Ehm.rTehDpsJhxYhNBNU5.kznMCa3cNXePaEbsKkk4PU2QcWjHj2C7yDrjkw
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      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:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-Am40yJsMPHsTOmn9Obwyx2caqoJ1R\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1736018540,\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:  \\nREPORT:  \\n\\n# Report on Artificial Intelligence (AI)\\n\\n##
+      Introduction\\nArtificial Intelligence (AI) is a rapidly evolving technology
+      that simulates human intelligence processes by machines, particularly computer
+      systems. AI has a profound impact on various sectors, enhancing efficiency,
+      improving decision-making, and leading to groundbreaking innovations. This report
+      highlights three key points regarding the significance and implications of AI
+      technology.\\n\\n## Key Point 1: Transformative Potential in Various Industries\\nAI's
+      transformative potential is evident across multiple industries, including healthcare,
+      finance, transportation, and agriculture. In healthcare, AI algorithms can analyze
+      complex medical data, leading to improved diagnostics, personalized medicine,
+      and predictive analytics, thereby enhancing patient outcomes. The financial
+      sector employs AI for risk management, fraud detection, and automated trading,
+      which increases operational efficiency and minimizes human error. In transportation,
+      AI is integral to the development of autonomous vehicles and smart traffic systems,
+      optimizing routes and reducing congestion. Furthermore, agriculture benefits
+      from AI applications through precision farming, which maximizes yield while
+      minimizing environmental impact.\\n\\n## Key Point 2: Ethical Considerations
+      and Challenges\\nAs AI technologies become more pervasive, ethical considerations
+      arise regarding their implementation and use. Concerns include data privacy,
+      algorithmic bias, and the displacement of jobs due to automation. Ensuring that
+      AI systems are transparent, fair, and accountable is crucial in addressing these
+      issues. Organizations must develop comprehensive guidelines and regulatory frameworks
+      to mitigate bias in AI algorithms and protect user data. Moreover, addressing
+      the social implications of AI, such as potential job displacement, is essential,
+      necessitating investment in workforce retraining and education to prepare for
+      an AI-driven economy.\\n\\n## Key Point 3: Future Directions and Developments\\nLooking
+      ahead, the future of AI promises continued advancements and integration into
+      everyday life. Emerging trends include the development of explainable AI (XAI),
+      enhancing interpretability and understanding of AI decision-making processes.
+      Advances in natural language processing (NLP) will facilitate better human-computer
+      interactions, allowing for more intuitive applications. Additionally, as AI
+      technology becomes increasingly sophisticated, its role in addressing global
+      challenges, such as climate change and healthcare disparities, is expected to
+      expand. Stakeholders must collaborate to ensure that these developments align
+      with ethical standards and societal needs, fostering a responsible AI future.\\n\\n##
+      Conclusion\\nArtificial Intelligence stands at the forefront of technological
+      innovation, with the potential to revolutionize industries and address complex
+      global challenges. However, it is imperative to navigate the ethical considerations
+      and challenges it poses. By fostering responsible AI development, we can harness
+      its transformative power while ensuring equitability and transparency for future
+      generations.\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      725,\n    \"completion_tokens\": 526,\n    \"total_tokens\": 1251,\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:
+      - 8fcd98c269880133-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 04 Jan 2025 19:22:28 GMT
+      Server:
+      - cloudflare
+      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:
+      - '8620'
+      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:
+      - '149998942'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_de480c9e17954e77dece1b2fe013a0d0
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      Cs4CCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSpQIKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKOAgoQCwIBgw9XNdGpuGOOIANe2hIIriM3k2t+0NQqDFRhc2sgQ3JlYXRlZDABOcjF
+      ABuskxcYQfBlARuskxcYSi4KCGNyZXdfa2V5EiIKIDAwYjk0NmJlNDQzNzE0YjNhNDdjMjAxMDFl
+      YjAyZDY2SjEKB2NyZXdfaWQSJgokNzJkZTEwZTQtNDkwZC00NDYwLTk1NzMtMmU5ZmM5YTMwMWE1
+      Si4KCHRhc2tfa2V5EiIKIGI3MTNjODJmZWI5MmM5ZjVjNThiNDBhOTc1NTZiN2FjSjEKB3Rhc2tf
+      aWQSJgokYWYxYTk2MTgtOTI0YS00ZTc5LWI2ZWItNThkYTEzNjk1OWM1egIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '337'
+      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:
+      - Sat, 04 Jan 2025 19:22:32 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Report Writer. You''re
+      an expert at writing structured reports.\nYour personal goal is: Create properly
+      formatted reports\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: Write a report about AI with exactly
+      3 key points.\n\nThis is the expect criteria for your final answer: A properly
+      formatted report\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nThis is the context you''re working with:\n### Previous attempt
+      failed validation: Output must end with ''END REPORT'' no formatting, just the
+      word END REPORT\n\n\n### Previous result:\nREPORT:  \n\n# Report on Artificial
+      Intelligence (AI)\n\n## Introduction\nArtificial Intelligence (AI) is a rapidly
+      evolving technology that simulates human intelligence processes by machines,
+      particularly computer systems. AI has a profound impact on various sectors,
+      enhancing efficiency, improving decision-making, and leading to groundbreaking
+      innovations. This report highlights three key points regarding the significance
+      and implications of AI technology.\n\n## Key Point 1: Transformative Potential
+      in Various Industries\nAI''s transformative potential is evident across multiple
+      industries, including healthcare, finance, transportation, and agriculture.
+      In healthcare, AI algorithms can analyze complex medical data, leading to improved
+      diagnostics, personalized medicine, and predictive analytics, thereby enhancing
+      patient outcomes. The financial sector employs AI for risk management, fraud
+      detection, and automated trading, which increases operational efficiency and
+      minimizes human error. In transportation, AI is integral to the development
+      of autonomous vehicles and smart traffic systems, optimizing routes and reducing
+      congestion. Furthermore, agriculture benefits from AI applications through precision
+      farming, which maximizes yield while minimizing environmental impact.\n\n##
+      Key Point 2: Ethical Considerations and Challenges\nAs AI technologies become
+      more pervasive, ethical considerations arise regarding their implementation
+      and use. Concerns include data privacy, algorithmic bias, and the displacement
+      of jobs due to automation. Ensuring that AI systems are transparent, fair, and
+      accountable is crucial in addressing these issues. Organizations must develop
+      comprehensive guidelines and regulatory frameworks to mitigate bias in AI algorithms
+      and protect user data. Moreover, addressing the social implications of AI, such
+      as potential job displacement, is essential, necessitating investment in workforce
+      retraining and education to prepare for an AI-driven economy.\n\n## Key Point
+      3: Future Directions and Developments\nLooking ahead, the future of AI promises
+      continued advancements and integration into everyday life. Emerging trends include
+      the development of explainable AI (XAI), enhancing interpretability and understanding
+      of AI decision-making processes. Advances in natural language processing (NLP)
+      will facilitate better human-computer interactions, allowing for more intuitive
+      applications. Additionally, as AI technology becomes increasingly sophisticated,
+      its role in addressing global challenges, such as climate change and healthcare
+      disparities, is expected to expand. Stakeholders must collaborate to ensure
+      that these developments align with ethical standards and societal needs, fostering
+      a responsible AI future.\n\n## Conclusion\nArtificial Intelligence stands at
+      the forefront of technological innovation, with the potential to revolutionize
+      industries and address complex global challenges. However, it is imperative
+      to navigate the ethical considerations and challenges it poses. By fostering
+      responsible AI development, we can harness its transformative power while ensuring
+      equitability and transparency for future generations.\n\n\nTry again, making
+      sure to address the validation error.\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:
+      - '4369'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=SlnUP7AT9jJlQiN.Fm1c7MDyo78_hBRAz8PoabvHVSU-1736018539826-0.0.1.1-604800000;
+        __cf_bm=pumYGlf1gsbVoFNTM1vh9Okj41SgxP3y65T5YWWPU1U-1736018539-1.0.1.1-wmaotkWMviN4lKh6M3P04A8p61Ehm.rTehDpsJhxYhNBNU5.kznMCa3cNXePaEbsKkk4PU2QcWjHj2C7yDrjkw
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      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:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-Am4176wzYnk3HmSTkkakM4yl6xVYS\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1736018549,\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\\n# Report on Artificial Intelligence (AI)\\n\\n## Introduction\\nArtificial
+      Intelligence (AI) is a revolutionary technology designed to simulate human intelligence
+      processes, enabling machines to perform tasks that typically require human cognition.
+      Its rapid development has brought forth significant changes across various sectors,
+      improving operational efficiencies, enhancing decision-making, and fostering
+      innovation. This report outlines three key points regarding the impact and implications
+      of AI technology.\\n\\n## Key Point 1: Transformative Potential in Various Industries\\nAI's
+      transformative potential is observable across numerous sectors including healthcare,
+      finance, transportation, and agriculture. In the healthcare sector, AI algorithms
+      are increasingly used to analyze vast amounts of medical data, which sharpens
+      diagnostics, facilitates personalized treatment plans, and enhances predictive
+      analytics, thus leading to better patient care. In finance, AI contributes to
+      risk assessment, fraud detection, and automated trading, heightening efficiency
+      and reducing the risk of human error. The transportation industry leverages
+      AI technologies for developments in autonomous vehicles and smart transportation
+      systems that optimize routes and alleviate traffic congestion. Furthermore,
+      agriculture benefits from AI by applying precision farming techniques that optimize
+      yield and mitigate environmental effects.\\n\\n## Key Point 2: Ethical Considerations
+      and Challenges\\nWith the increasing deployment of AI technologies, numerous
+      ethical considerations surface, particularly relating to privacy, algorithmic
+      fairness, and the displacement of jobs. Addressing issues such as data security,
+      bias in AI algorithms, and the societal impact of automation is paramount. Organizations
+      are encouraged to develop stringent guidelines and regulatory measures aimed
+      at minimizing bias and ensuring that AI systems uphold values of transparency
+      and accountability. Additionally, the implications of job displacement necessitate
+      strategies for workforce retraining and educational reforms to adequately prepare
+      the workforce for an economy increasingly shaped by AI technologies.\\n\\n##
+      Key Point 3: Future Directions and Developments\\nThe future of AI is poised
+      for remarkable advancements, with trends indicating a growing integration into
+      daily life and widespread applications. The emergence of explainable AI (XAI)
+      aims to enhance the transparency and interpretability of AI decision-making
+      processes, fostering trust and understanding among users. Improvements in natural
+      language processing (NLP) are likely to lead to more seamless and intuitive
+      human-computer interactions. Furthermore, AI's potential to address global challenges,
+      including climate change and disparities in healthcare access, is becoming increasingly
+      significant. Collaborative efforts among stakeholders will be vital to ensuring
+      that AI advancements are ethical and responsive to societal needs, paving the
+      way for a responsible and equitable AI landscape.\\n\\n## Conclusion\\nAI technology
+      is at the forefront of innovation, with the capacity to transform industries
+      and tackle pressing global issues. As we navigate through the complexities and
+      ethical challenges posed by AI, it is crucial to prioritize responsible development
+      and implementation. By harnessing AI's transformative capabilities with a focus
+      on equity and transparency, we can pave the way for a promising future that
+      benefits all.\\n\\nEND REPORT\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      730,\n    \"completion_tokens\": 571,\n    \"total_tokens\": 1301,\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:
+      - 8fcd98f9fc060133-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 04 Jan 2025 19:22:36 GMT
+      Server:
+      - cloudflare
+      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:
+      - '7203'
+      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:
+      - '149998937'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_cab0502e7d8a8564e56d8f741cf451ec
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      Cs4CCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSpQIKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKOAgoQO/xpq2/yF233Vf8OitYSiBIIdyOEucIqtF8qDFRhc2sgQ3JlYXRlZDABOXDe
+      ZdqtkxcYQUDaZ9qtkxcYSi4KCGNyZXdfa2V5EiIKIDAwYjk0NmJlNDQzNzE0YjNhNDdjMjAxMDFl
+      YjAyZDY2SjEKB2NyZXdfaWQSJgokNzJkZTEwZTQtNDkwZC00NDYwLTk1NzMtMmU5ZmM5YTMwMWE1
+      Si4KCHRhc2tfa2V5EiIKIGI3MTNjODJmZWI5MmM5ZjVjNThiNDBhOTc1NTZiN2FjSjEKB3Rhc2tf
+      aWQSJgokYWYxYTk2MTgtOTI0YS00ZTc5LWI2ZWItNThkYTEzNjk1OWM1egIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '337'
+      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:
+      - Sat, 04 Jan 2025 19:22:37 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Report Writer. You''re
+      an expert at writing structured reports.\nYour personal goal is: Create properly
+      formatted reports\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: Write a report about AI with exactly
+      3 key points.\n\nThis is the expect criteria for your final answer: A properly
+      formatted report\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nThis is the context you''re working with:\n### Previous attempt
+      failed validation: Output must start with ''REPORT:'' no formatting, just the
+      word REPORT\n\n\n### Previous result:\n# Report on Artificial Intelligence (AI)\n\n##
+      Introduction\nArtificial Intelligence (AI) is a revolutionary technology designed
+      to simulate human intelligence processes, enabling machines to perform tasks
+      that typically require human cognition. Its rapid development has brought forth
+      significant changes across various sectors, improving operational efficiencies,
+      enhancing decision-making, and fostering innovation. This report outlines three
+      key points regarding the impact and implications of AI technology.\n\n## Key
+      Point 1: Transformative Potential in Various Industries\nAI''s transformative
+      potential is observable across numerous sectors including healthcare, finance,
+      transportation, and agriculture. In the healthcare sector, AI algorithms are
+      increasingly used to analyze vast amounts of medical data, which sharpens diagnostics,
+      facilitates personalized treatment plans, and enhances predictive analytics,
+      thus leading to better patient care. In finance, AI contributes to risk assessment,
+      fraud detection, and automated trading, heightening efficiency and reducing
+      the risk of human error. The transportation industry leverages AI technologies
+      for developments in autonomous vehicles and smart transportation systems that
+      optimize routes and alleviate traffic congestion. Furthermore, agriculture benefits
+      from AI by applying precision farming techniques that optimize yield and mitigate
+      environmental effects.\n\n## Key Point 2: Ethical Considerations and Challenges\nWith
+      the increasing deployment of AI technologies, numerous ethical considerations
+      surface, particularly relating to privacy, algorithmic fairness, and the displacement
+      of jobs. Addressing issues such as data security, bias in AI algorithms, and
+      the societal impact of automation is paramount. Organizations are encouraged
+      to develop stringent guidelines and regulatory measures aimed at minimizing
+      bias and ensuring that AI systems uphold values of transparency and accountability.
+      Additionally, the implications of job displacement necessitate strategies for
+      workforce retraining and educational reforms to adequately prepare the workforce
+      for an economy increasingly shaped by AI technologies.\n\n## Key Point 3: Future
+      Directions and Developments\nThe future of AI is poised for remarkable advancements,
+      with trends indicating a growing integration into daily life and widespread
+      applications. The emergence of explainable AI (XAI) aims to enhance the transparency
+      and interpretability of AI decision-making processes, fostering trust and understanding
+      among users. Improvements in natural language processing (NLP) are likely to
+      lead to more seamless and intuitive human-computer interactions. Furthermore,
+      AI''s potential to address global challenges, including climate change and disparities
+      in healthcare access, is becoming increasingly significant. Collaborative efforts
+      among stakeholders will be vital to ensuring that AI advancements are ethical
+      and responsive to societal needs, paving the way for a responsible and equitable
+      AI landscape.\n\n## Conclusion\nAI technology is at the forefront of innovation,
+      with the capacity to transform industries and tackle pressing global issues.
+      As we navigate through the complexities and ethical challenges posed by AI,
+      it is crucial to prioritize responsible development and implementation. By harnessing
+      AI''s transformative capabilities with a focus on equity and transparency, we
+      can pave the way for a promising future that benefits all.\n\nEND REPORT\n\n\nTry
+      again, making sure to address the validation error.\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:
+      - '4669'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=SlnUP7AT9jJlQiN.Fm1c7MDyo78_hBRAz8PoabvHVSU-1736018539826-0.0.1.1-604800000;
+        __cf_bm=pumYGlf1gsbVoFNTM1vh9Okj41SgxP3y65T5YWWPU1U-1736018539-1.0.1.1-wmaotkWMviN4lKh6M3P04A8p61Ehm.rTehDpsJhxYhNBNU5.kznMCa3cNXePaEbsKkk4PU2QcWjHj2C7yDrjkw
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      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:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-Am41EaJaKZSumZe8ph2I32d6QNbTP\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1736018556,\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\\nREPORT: \\n\\n# Report on Artificial Intelligence (AI)\\n\\n##
+      Introduction\\nArtificial Intelligence (AI) is a revolutionary technology designed
+      to simulate human intelligence processes, enabling machines to perform tasks
+      that typically require human cognition. Its rapid development has brought forth
+      significant changes across various sectors, improving operational efficiencies,
+      enhancing decision-making, and fostering innovation. This report outlines three
+      key points regarding the impact and implications of AI technology.\\n\\n## Key
+      Point 1: Transformative Potential in Various Industries\\nAI's transformative
+      potential is observable across numerous sectors including healthcare, finance,
+      transportation, and agriculture. In the healthcare sector, AI algorithms are
+      increasingly used to analyze vast amounts of medical data, which sharpens diagnostics,
+      facilitates personalized treatment plans, and enhances predictive analytics,
+      thus leading to better patient care. In finance, AI contributes to risk assessment,
+      fraud detection, and automated trading, heightening efficiency and reducing
+      the risk of human error. The transportation industry leverages AI technologies
+      for developments in autonomous vehicles and smart transportation systems that
+      optimize routes and alleviate traffic congestion. Furthermore, agriculture benefits
+      from AI by applying precision farming techniques that optimize yield and mitigate
+      environmental effects.\\n\\n## Key Point 2: Ethical Considerations and Challenges\\nWith
+      the increasing deployment of AI technologies, numerous ethical considerations
+      surface, particularly relating to privacy, algorithmic fairness, and the displacement
+      of jobs. Addressing issues such as data security, bias in AI algorithms, and
+      the societal impact of automation is paramount. Organizations are encouraged
+      to develop stringent guidelines and regulatory measures aimed at minimizing
+      bias and ensuring that AI systems uphold values of transparency and accountability.
+      Additionally, the implications of job displacement necessitate strategies for
+      workforce retraining and educational reforms to adequately prepare the workforce
+      for an economy increasingly shaped by AI technologies.\\n\\n## Key Point 3:
+      Future Directions and Developments\\nThe future of AI is poised for remarkable
+      advancements, with trends indicating a growing integration into daily life and
+      widespread applications. The emergence of explainable AI (XAI) aims to enhance
+      the transparency and interpretability of AI decision-making processes, fostering
+      trust and understanding among users. Improvements in natural language processing
+      (NLP) are likely to lead to more seamless and intuitive human-computer interactions.
+      Furthermore, AI's potential to address global challenges, including climate
+      change and disparities in healthcare access, is becoming increasingly significant.
+      Collaborative efforts among stakeholders will be vital to ensuring that AI advancements
+      are ethical and responsive to societal needs, paving the way for a responsible
+      and equitable AI landscape.\\n\\n## Conclusion\\nAI technology is at the forefront
+      of innovation, with the capacity to transform industries and tackle pressing
+      global issues. As we navigate through the complexities and ethical challenges
+      posed by AI, it is crucial to prioritize responsible development and implementation.
+      By harnessing AI's transformative capabilities with a focus on equity and transparency,
+      we can pave the way for a promising future that benefits all.\\n\\nEND REPORT\",\n
+      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 774,\n    \"completion_tokens\":
+      574,\n    \"total_tokens\": 1348,\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:
+      - 8fcd9928eaa40133-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 04 Jan 2025 19:22:46 GMT
+      Server:
+      - cloudflare
+      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:
+      - '9767'
+      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:
+      - '149998862'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_d3d0e47180363d07d988cb5ab639597c
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_task_execution_times.yaml

@@ -0,0 +1,146 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
+      an expert researcher, specialized in technology, software engineering, AI and
+      startups. You work as a freelancer and is now working on doing research and
+      analysis for a new customer.\nYour personal goal is: Make the best research
+      and analysis on content about AI and AI agents\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: Give me
+      a list of 5 interesting ideas to explore for na article, what makes them unique
+      and interesting.\n\nThis is the expect criteria for your final answer: Bullet
+      point list of 5 interesting ideas.\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:
+      - '1177'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      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-AlfwrGToOoVtDhb3ryZMpA07aZy4m\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735926029,\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- **The Role of Emotional Intelligence in AI Agents**: Explore how
+      developing emotional intelligence in AI can change user interactions. Investigate
+      algorithms that enable AI agents to recognize and respond to human emotions,
+      enhancing user experience in sectors such as therapy, customer service, and
+      education. This idea is unique as it blends psychology with artificial intelligence,
+      presenting a new frontier for AI applications.\\n\\n- **AI Agents in Problem-Solving
+      for Climate Change**: Analyze how AI agents can contribute to developing innovative
+      solutions for climate change challenges. Focus on their role in predicting climate
+      patterns, optimizing energy consumption, and managing resources more efficiently.
+      This topic is unique because it highlights the practical impact of AI on one
+      of the most pressing global issues.\\n\\n- **The Ethics of Autonomous Decision-Making
+      AI**: Delve into the ethical implications surrounding AI agents that make autonomous
+      decisions, especially in critical areas like healthcare, transportation, and
+      law enforcement. This idea raises questions about accountability and bias, making
+      it a vital discussion point as AI continues to advance. The unique aspect lies
+      in the intersection of technology and moral philosophy.\\n\\n- **AI Agents Shaping
+      the Future of Remote Work**: Investigate how AI agents are transforming remote
+      work environments through automation, communication facilitation, and performance
+      monitoring. Discuss unique applications such as virtual assistants, project
+      management tools, and AI-driven team collaboration platforms. This topic is
+      particularly relevant as the workforce becomes increasingly remote, making it
+      an appealing area of exploration.\\n\\n- **Cultural Impacts of AI Agents in
+      Media and Entertainment**: Examine how AI-driven characters and narratives are
+      changing the media landscape, from video games to films and animations. Analyze
+      audience reception and the role of AI in personalizing content. This concept
+      is unique due to its intersection with digital culture and artistic expression,
+      offering insights into how technology influences social norms and preferences.\",\n
+      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 220,\n    \"completion_tokens\":
+      376,\n    \"total_tokens\": 596,\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:
+      - 8fc4c6324d42ad5a-POA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 03 Jan 2025 17:40:34 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=zdRUS9YIvR7oCmJGeB7BOAnmxI7FOE5Jae5yRZDCnPE-1735926034-1.0.1.1-gvIEXrMfT69wL2mv4ApivWX67OOpDegjf1LE6g9u3GEDuQdLQok.vlLZD.SdGzK0bMug86JZhBeDZMleJlI2EQ;
+        path=/; expires=Fri, 03-Jan-25 18:10:34 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=CW_cKQGYWY3cL.S6Xo5z0cmkmWHy5Q50OA_KjPEijNk-1735926034530-0.0.1.1-604800000;
+        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:
+      - '5124'
+      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:
+      - '149999729'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_95ae59da1099e02c0d95bf25ba179fed
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cli/deploy/test_deploy_main.py

@@ -177,12 +177,12 @@ class TestDeployCommand(unittest.TestCase):
     def test_get_crew_status(self):
         mock_response = MagicMock()
         mock_response.status_code = 200
-        mock_response.json.return_value = {"name": "TestCrew", "status": "active"}
+        mock_response.json.return_value = {"name": "InternalCrew", "status": "active"}
         self.mock_client.crew_status_by_name.return_value = mock_response
 
         with patch("sys.stdout", new=StringIO()) as fake_out:
             self.deploy_command.get_crew_status()
-            self.assertIn("TestCrew", fake_out.getvalue())
+            self.assertIn("InternalCrew", fake_out.getvalue())
             self.assertIn("active", fake_out.getvalue())
 
     def test_get_crew_logs(self):

tests/crew_test.py

@@ -3337,3 +3337,110 @@ def test_multimodal_agent_live_image_analysis():
     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
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_with_failing_task_guardrails():
+    """Test that crew properly handles failing guardrails and retries with validation feedback."""
+
+    def strict_format_guardrail(result: TaskOutput):
+        """Validates that the output follows a strict format:
+        - Must start with 'REPORT:'
+        - Must end with 'END REPORT'
+        """
+        content = result.raw.strip()
+
+        if not ('REPORT:' in content or '**REPORT:**' in content):
+            return (False, "Output must start with 'REPORT:' no formatting, just the word REPORT")
+
+        if not ('END REPORT' in content or '**END REPORT**' in content):
+            return (False, "Output must end with 'END REPORT' no formatting, just the word END REPORT")
+
+        return (True, content)
+
+    researcher = Agent(
+        role="Report Writer",
+        goal="Create properly formatted reports",
+        backstory="You're an expert at writing structured reports.",
+    )
+
+    task = Task(
+        description="""Write a report about AI with exactly 3 key points.""",
+        expected_output="A properly formatted report",
+        agent=researcher,
+        guardrail=strict_format_guardrail,
+        max_retries=3
+    )
+
+    crew = Crew(
+        agents=[researcher],
+        tasks=[task],
+    )
+
+    result = crew.kickoff()
+
+    # Verify the final output meets all format requirements
+    content = result.raw.strip()
+    assert content.startswith('REPORT:'), "Output should start with 'REPORT:'"
+    assert content.endswith('END REPORT'), "Output should end with 'END REPORT'"
+
+    # Verify task output
+    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_crew_guardrail_feedback_in_context():
+    """Test that guardrail feedback is properly appended to task context for retries."""
+
+    def format_guardrail(result: TaskOutput):
+        """Validates that the output contains a specific keyword."""
+        if "IMPORTANT" not in result.raw:
+            return (False, "Output must contain the keyword 'IMPORTANT'")
+        return (True, result.raw)
+
+    # Create execution contexts list to track contexts
+    execution_contexts = []
+
+    researcher = Agent(
+        role="Writer",
+        goal="Write content with specific keywords",
+        backstory="You're an expert at following specific writing requirements.",
+        allow_delegation=False
+    )
+
+    task = Task(
+        description="Write a short response.",
+        expected_output="A response containing the keyword 'IMPORTANT'",
+        agent=researcher,
+        guardrail=format_guardrail,
+        max_retries=2
+    )
+
+    crew = Crew(agents=[researcher], tasks=[task])
+
+    with patch.object(Agent, "execute_task") as mock_execute_task:
+        # Define side_effect to capture context and return different responses
+        def side_effect(task, context=None, tools=None):
+            execution_contexts.append(context if context else "")
+            if len(execution_contexts) == 1:
+                return "This is a test response"
+            return "This is an IMPORTANT test response"
+
+        mock_execute_task.side_effect = side_effect
+
+        result = crew.kickoff()
+
+    # Verify that we had multiple executions
+    assert len(execution_contexts) > 1, "Task should have been executed multiple times"
+
+    # Verify that the second execution included the guardrail feedback
+    assert "Output must contain the keyword 'IMPORTANT'" in execution_contexts[1], \
+        "Guardrail feedback should be included in retry context"
+
+    # Verify final output meets guardrail requirements
+    assert "IMPORTANT" in result.raw, "Final output should contain required keyword"
+
+    # Verify task retry count
+    assert task.retry_count == 1, "Task should have been retried once"

tests/project_test.py

@@ -27,7 +27,7 @@ class SimpleCrew:
 
 
 @CrewBase
-class TestCrew:
+class InternalCrew:
     agents_config = "config/agents.yaml"
     tasks_config = "config/tasks.yaml"
 
@@ -84,7 +84,7 @@ def test_task_memoization():
 
 
 def test_crew_memoization():
-    crew = TestCrew()
+    crew = InternalCrew()
     first_call_result = crew.crew()
     second_call_result = crew.crew()
 
@@ -107,7 +107,7 @@ def test_task_name():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_before_kickoff_modification():
-    crew = TestCrew()
+    crew = InternalCrew()
     inputs = {"topic": "LLMs"}
     result = crew.crew().kickoff(inputs=inputs)
     assert "bicycles" in result.raw, "Before kickoff function did not modify inputs"
@@ -115,7 +115,7 @@ def test_before_kickoff_modification():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_after_kickoff_modification():
-    crew = TestCrew()
+    crew = InternalCrew()
     # Assuming the crew execution returns a dict
     result = crew.crew().kickoff({"topic": "LLMs"})
 
@@ -126,7 +126,7 @@ def test_after_kickoff_modification():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_before_kickoff_with_none_input():
-    crew = TestCrew()
+    crew = InternalCrew()
     crew.crew().kickoff(None)
     # Test should pass without raising exceptions
 

tests/task_test.py

@@ -936,3 +936,29 @@ def test_output_file_validation():
             expected_output="Test output",
             output_file="{invalid-name}/output.txt",
         )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_task_execution_times():
+    researcher = Agent(
+        role="Researcher",
+        goal="Make the best research and analysis on content about AI and AI agents",
+        backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
+        allow_delegation=False,
+    )
+
+    task = Task(
+        description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
+        expected_output="Bullet point list of 5 interesting ideas.",
+        agent=researcher,
+    )
+
+    assert task.start_time is None
+    assert task.end_time is None
+    assert task.execution_duration is None
+
+    task.execute_sync(agent=researcher)
+
+    assert task.start_time is not None
+    assert task.end_time is not None
+    assert task.execution_duration == (task.end_time - task.start_time).total_seconds()

tests/test_manager_llm_delegation.py

@@ -6,7 +6,7 @@ from crewai import Agent, Task
 from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
 
 
-class TestAgentTool(BaseAgentTool):
+class InternalAgentTool(BaseAgentTool):
     """Concrete implementation of BaseAgentTool for testing."""
 
     def _run(self, *args, **kwargs):
@@ -39,7 +39,7 @@ def test_agent_tool_role_matching(role_name, should_match):
     )
 
     # Create test agent tool
-    agent_tool = TestAgentTool(
+    agent_tool = InternalAgentTool(
         name="test_tool", description="Test tool", agents=[test_agent]
     )
 

tests/tools/test_base_tool.py

@@ -15,7 +15,7 @@ def test_creating_a_tool_using_annotation():
         my_tool.description
         == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
     )
-    assert my_tool.args_schema.schema()["properties"] == {
+    assert my_tool.args_schema.model_json_schema()["properties"] == {
         "question": {"title": "Question", "type": "string"}
     }
     assert (
@@ -29,7 +29,7 @@ def test_creating_a_tool_using_annotation():
         converted_tool.description
         == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
     )
-    assert converted_tool.args_schema.schema()["properties"] == {
+    assert converted_tool.args_schema.model_json_schema()["properties"] == {
         "question": {"title": "Question", "type": "string"}
     }
     assert (
@@ -54,7 +54,7 @@ def test_creating_a_tool_using_baseclass():
         my_tool.description
         == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
     )
-    assert my_tool.args_schema.schema()["properties"] == {
+    assert my_tool.args_schema.model_json_schema()["properties"] == {
         "question": {"title": "Question", "type": "string"}
     }
     assert my_tool.run("What is the meaning of life?") == "What is the meaning of life?"
@@ -66,7 +66,7 @@ def test_creating_a_tool_using_baseclass():
         converted_tool.description
         == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
     )
-    assert converted_tool.args_schema.schema()["properties"] == {
+    assert converted_tool.args_schema.model_json_schema()["properties"] == {
         "question": {"title": "Question", "type": "string"}
     }
     assert (

tests/tools/test_structured_tool.py

@@ -25,7 +25,7 @@ def schema_class():
     return TestSchema
 
 
-class TestCrewStructuredTool:
+class InternalCrewStructuredTool:
     def test_initialization(self, basic_function, schema_class):
         """Test basic initialization of CrewStructuredTool"""
         tool = CrewStructuredTool(

tests/utilities/evaluators/test_crew_evaluator_handler.py

@@ -12,7 +12,7 @@ from crewai.utilities.evaluators.crew_evaluator_handler import (
 )
 
 
-class TestCrewEvaluator:
+class InternalCrewEvaluator:
     @pytest.fixture
     def crew_planner(self):
         agent = Agent(role="Agent 1", goal="Goal 1", backstory="Backstory 1")

tests/utilities/test_planning_handler.py

@@ -16,7 +16,7 @@ from crewai.utilities.planning_handler import (
 )
 
 
-class TestCrewPlanner:
+class InternalCrewPlanner:
     @pytest.fixture
     def crew_planner(self):
         tasks = [
@@ -115,13 +115,13 @@ class TestCrewPlanner:
             def __init__(self, name: str, description: str):
                 tool_data = {"name": name, "description": description}
                 super().__init__(**tool_data)
-            
+
             def __str__(self):
                 return self.name
-            
+
             def __repr__(self):
                 return self.name
-            
+
             def to_structured_tool(self):
                 return self
 
@@ -149,11 +149,11 @@ class TestCrewPlanner:
                 ]
             )
         )
-        
+
         # Create planner with the new task
         planner = CrewPlanner([task], None)
         tasks_summary = planner._create_tasks_summary()
-        
+
         # Verify task summary content
         assert isinstance(tasks_summary, str)
         assert task.description in tasks_summary

tests/utilities/test_training_handler.py

@@ -4,7 +4,7 @@ import unittest
 from crewai.utilities.training_handler import CrewTrainingHandler
 
 
-class TestCrewTrainingHandler(unittest.TestCase):
+class InternalCrewTrainingHandler(unittest.TestCase):
     def setUp(self):
         self.handler = CrewTrainingHandler("trained_data.pkl")
 

uv.lock

@@ -631,7 +631,7 @@ wheels = [
 
 [[package]]
 name = "crewai"
-version = "0.86.0"
+version = "0.95.0"
 source = { editable = "." }
 dependencies = [
     { name = "appdirs" },