drop failing files

* fix issue pointed out by mike

* clean up

* Drop logger

* drop unused imports

docs/concepts/llms.mdx

@@ -243,6 +243,9 @@ There are three ways to configure LLMs in CrewAI. Choose the method that best fi
         # llm: bedrock/amazon.titan-text-express-v1
         # llm: bedrock/meta.llama2-70b-chat-v1
 
+        # Amazon SageMaker Models - Enterprise-grade
+        # llm: sagemaker/<my-endpoint>
+
         # Mistral Models - Open source alternative
         # llm: mistral/mistral-large-latest
         # llm: mistral/mistral-medium-latest
@@ -506,6 +509,21 @@ Learn how to get the most out of your LLM configuration:
     )
     ```
   </Accordion>
+  
+  <Accordion title="Amazon SageMaker">
+    ```python Code
+    AWS_ACCESS_KEY_ID=<your-access-key>
+    AWS_SECRET_ACCESS_KEY=<your-secret-key>
+    AWS_DEFAULT_REGION=<your-region>
+    ```
+
+    Example usage:
+    ```python Code
+    llm = LLM(
+        model="sagemaker/<my-endpoint>"
+    )
+    ```
+  </Accordion>
 
   <Accordion title="Mistral">
     ```python Code

docs/installation.mdx

@@ -139,7 +139,6 @@ Now let's get you set up! 🚀
             │   └── __init__.py
             └── config/
                 ├── agents.yaml
-                ├── config.yaml
                 └── tasks.yaml
     ```
     </Frame>

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crewai"
-version = "0.98.0"
+version = "0.100.0"
 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"
@@ -36,6 +36,7 @@ dependencies = [
     "tomli-w>=1.1.0",
     "tomli>=2.0.2",
     "blinker>=1.9.0",
+    "json5>=0.10.0",
 ]
 
 [project.urls]

src/crewai/__init__.py

@@ -14,7 +14,7 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.98.0"
+__version__ = "0.100.0"
 __all__ = [
     "Agent",
     "Crew",

src/crewai/agent.py

@@ -1,4 +1,3 @@
-import os
 import shutil
 import subprocess
 from typing import Any, Dict, List, Literal, Optional, Union
@@ -8,7 +7,6 @@ from pydantic import Field, InstanceOf, PrivateAttr, model_validator
 from crewai.agents import CacheHandler
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.agents.crew_agent_executor import CrewAgentExecutor
-from crewai.cli.constants import ENV_VARS, LITELLM_PARAMS
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.utils.knowledge_utils import extract_knowledge_context
@@ -261,6 +259,9 @@ class Agent(BaseAgent):
                 }
             )["output"]
         except Exception as e:
+            if e.__class__.__module__.startswith("litellm"):
+                # Do not retry on litellm errors
+                raise e
             self._times_executed += 1
             if self._times_executed > self.max_retry_limit:
                 raise e

src/crewai/agents/crew_agent_executor.py

@@ -13,6 +13,7 @@ from crewai.agents.parser import (
     OutputParserException,
 )
 from crewai.agents.tools_handler import ToolsHandler
+from crewai.llm import LLM
 from crewai.tools.base_tool import BaseTool
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
 from crewai.utilities import I18N, Printer
@@ -54,7 +55,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         callbacks: List[Any] = [],
     ):
         self._i18n: I18N = I18N()
-        self.llm = llm
+        self.llm: LLM = llm
         self.task = task
         self.agent = agent
         self.crew = crew
@@ -80,10 +81,8 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         self.tool_name_to_tool_map: Dict[str, BaseTool] = {
             tool.name: tool for tool in self.tools
         }
-        if self.llm.stop:
-            self.llm.stop = list(set(self.llm.stop + self.stop))
-        else:
-            self.llm.stop = self.stop
+        self.stop = stop_words
+        self.llm.stop = list(set(self.llm.stop + self.stop))
 
     def invoke(self, inputs: Dict[str, str]) -> Dict[str, Any]:
         if "system" in self.prompt:
@@ -98,7 +97,16 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         self._show_start_logs()
 
         self.ask_for_human_input = bool(inputs.get("ask_for_human_input", False))
-        formatted_answer = self._invoke_loop()
+
+        try:
+            formatted_answer = self._invoke_loop()
+        except Exception as e:
+            if e.__class__.__module__.startswith("litellm"):
+                # Do not retry on litellm errors
+                raise e
+            else:
+                self._handle_unknown_error(e)
+                raise e
 
         if self.ask_for_human_input:
             formatted_answer = self._handle_human_feedback(formatted_answer)
@@ -124,7 +132,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                 self._enforce_rpm_limit()
 
                 answer = self._get_llm_response()
-
                 formatted_answer = self._process_llm_response(answer)
 
                 if isinstance(formatted_answer, AgentAction):
@@ -142,13 +149,32 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                 formatted_answer = self._handle_output_parser_exception(e)
 
             except Exception as e:
+                if e.__class__.__module__.startswith("litellm"):
+                    # Do not retry on litellm errors
+                    raise e
                 if self._is_context_length_exceeded(e):
                     self._handle_context_length()
                     continue
+                else:
+                    self._handle_unknown_error(e)
+                    raise e
+            finally:
+                self.iterations += 1
 
         self._show_logs(formatted_answer)
         return formatted_answer
 
+    def _handle_unknown_error(self, exception: Exception) -> None:
+        """Handle unknown errors by informing the user."""
+        self._printer.print(
+            content="An unknown error occurred. Please check the details below.",
+            color="red",
+        )
+        self._printer.print(
+            content=f"Error details: {exception}",
+            color="red",
+        )
+
     def _has_reached_max_iterations(self) -> bool:
         """Check if the maximum number of iterations has been reached."""
         return self.iterations >= self.max_iter
@@ -160,10 +186,17 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
 
     def _get_llm_response(self) -> str:
         """Call the LLM and return the response, handling any invalid responses."""
-        answer = self.llm.call(
-            self.messages,
-            callbacks=self.callbacks,
-        )
+        try:
+            answer = self.llm.call(
+                self.messages,
+                callbacks=self.callbacks,
+            )
+        except Exception as e:
+            self._printer.print(
+                content=f"Error during LLM call: {e}",
+                color="red",
+            )
+            raise e
 
         if not answer:
             self._printer.print(
@@ -184,7 +217,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                 if FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE in e.error:
                     answer = answer.split("Observation:")[0].strip()
 
-        self.iterations += 1
         return self._format_answer(answer)
 
     def _handle_agent_action(

src/crewai/cli/cli.py

@@ -350,7 +350,10 @@ def chat():
     Start a conversation with the Crew, collecting user-supplied inputs,
     and using the Chat LLM to generate responses.
     """
-    click.echo("Starting a conversation with the Crew")
+    click.secho(
+        "\nStarting a conversation with the Crew\n" "Type 'exit' or Ctrl+C to quit.\n",
+    )
+
     run_chat()
 
 

src/crewai/cli/crew_chat.py

@@ -1,17 +1,52 @@
 import json
+import platform
 import re
 import sys
+import threading
+import time
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Set, Tuple
 
 import click
 import tomli
+from packaging import version
 
+from crewai.cli.utils import read_toml
+from crewai.cli.version import get_crewai_version
 from crewai.crew import Crew
 from crewai.llm import LLM
 from crewai.types.crew_chat import ChatInputField, ChatInputs
 from crewai.utilities.llm_utils import create_llm
 
+MIN_REQUIRED_VERSION = "0.98.0"
+
+
+def check_conversational_crews_version(
+    crewai_version: str, pyproject_data: dict
+) -> bool:
+    """
+    Check if the installed crewAI version supports conversational crews.
+
+    Args:
+        crewai_version: The current version of crewAI.
+        pyproject_data: Dictionary containing pyproject.toml data.
+
+    Returns:
+        bool: True if version check passes, False otherwise.
+    """
+    try:
+        if version.parse(crewai_version) < version.parse(MIN_REQUIRED_VERSION):
+            click.secho(
+                "You are using an older version of crewAI that doesn't support conversational crews. "
+                "Run 'uv upgrade crewai' to get the latest version.",
+                fg="red",
+            )
+            return False
+    except version.InvalidVersion:
+        click.secho("Invalid crewAI version format detected.", fg="red")
+        return False
+    return True
+
 
 def run_chat():
     """
@@ -19,20 +54,47 @@ def run_chat():
     Incorporates crew_name, crew_description, and input fields to build a tool schema.
     Exits if crew_name or crew_description are missing.
     """
+    crewai_version = get_crewai_version()
+    pyproject_data = read_toml()
+
+    if not check_conversational_crews_version(crewai_version, pyproject_data):
+        return
+
     crew, crew_name = load_crew_and_name()
     chat_llm = initialize_chat_llm(crew)
     if not chat_llm:
         return
 
-    crew_chat_inputs = generate_crew_chat_inputs(crew, crew_name, chat_llm)
-    crew_tool_schema = generate_crew_tool_schema(crew_chat_inputs)
-    system_message = build_system_message(crew_chat_inputs)
-
-    # Call the LLM to generate the introductory message
-    introductory_message = chat_llm.call(
-        messages=[{"role": "system", "content": system_message}]
+    # Indicate that the crew is being analyzed
+    click.secho(
+        "\nAnalyzing crew and required inputs - this may take 3 to 30 seconds "
+        "depending on the complexity of your crew.",
+        fg="white",
     )
-    click.secho(f"\nAssistant: {introductory_message}\n", fg="green")
+
+    # Start loading indicator
+    loading_complete = threading.Event()
+    loading_thread = threading.Thread(target=show_loading, args=(loading_complete,))
+    loading_thread.start()
+
+    try:
+        crew_chat_inputs = generate_crew_chat_inputs(crew, crew_name, chat_llm)
+        crew_tool_schema = generate_crew_tool_schema(crew_chat_inputs)
+        system_message = build_system_message(crew_chat_inputs)
+
+        # Call the LLM to generate the introductory message
+        introductory_message = chat_llm.call(
+            messages=[{"role": "system", "content": system_message}]
+        )
+    finally:
+        # Stop loading indicator
+        loading_complete.set()
+        loading_thread.join()
+
+    # Indicate that the analysis is complete
+    click.secho("\nFinished analyzing crew.\n", fg="white")
+
+    click.secho(f"Assistant: {introductory_message}\n", fg="green")
 
     messages = [
         {"role": "system", "content": system_message},
@@ -43,15 +105,17 @@ def run_chat():
         crew_chat_inputs.crew_name: create_tool_function(crew, messages),
     }
 
-    click.secho(
-        "\nEntering an interactive chat loop with function-calling.\n"
-        "Type 'exit' or Ctrl+C to quit.\n",
-        fg="cyan",
-    )
-
     chat_loop(chat_llm, messages, crew_tool_schema, available_functions)
 
 
+def show_loading(event: threading.Event):
+    """Display animated loading dots while processing."""
+    while not event.is_set():
+        print(".", end="", flush=True)
+        time.sleep(1)
+    print()
+
+
 def initialize_chat_llm(crew: Crew) -> Optional[LLM]:
     """Initializes the chat LLM and handles exceptions."""
     try:
@@ -85,7 +149,7 @@ def build_system_message(crew_chat_inputs: ChatInputs) -> str:
         "Please keep your responses concise and friendly. "
         "If a user asks a question outside the crew's scope, provide a brief answer and remind them of the crew's purpose. "
         "After calling the tool, be prepared to take user feedback and make adjustments as needed. "
-        "If you are ever unsure about a user's request or need clarification, ask the user for more information."
+        "If you are ever unsure about a user's request or need clarification, ask the user for more information. "
         "Before doing anything else, introduce yourself with a friendly message like: 'Hey! I'm here to help you with [crew's purpose]. Could you please provide me with [inputs] so we can get started?' "
         "For example: 'Hey! I'm here to help you with uncovering and reporting cutting-edge developments through thorough research and detailed analysis. Could you please provide me with a topic you're interested in? This will help us generate a comprehensive research report and detailed analysis.'"
         f"\nCrew Name: {crew_chat_inputs.crew_name}"
@@ -102,25 +166,33 @@ def create_tool_function(crew: Crew, messages: List[Dict[str, str]]) -> Any:
     return run_crew_tool_with_messages
 
 
+def flush_input():
+    """Flush any pending input from the user."""
+    if platform.system() == "Windows":
+        # Windows platform
+        import msvcrt
+
+        while msvcrt.kbhit():
+            msvcrt.getch()
+    else:
+        # Unix-like platforms (Linux, macOS)
+        import termios
+
+        termios.tcflush(sys.stdin, termios.TCIFLUSH)
+
+
 def chat_loop(chat_llm, messages, crew_tool_schema, available_functions):
     """Main chat loop for interacting with the user."""
     while True:
         try:
-            user_input = click.prompt("You", type=str)
-            if user_input.strip().lower() in ["exit", "quit"]:
-                click.echo("Exiting chat. Goodbye!")
-                break
+            # Flush any pending input before accepting new input
+            flush_input()
 
-            messages.append({"role": "user", "content": user_input})
-            final_response = chat_llm.call(
-                messages=messages,
-                tools=[crew_tool_schema],
-                available_functions=available_functions,
+            user_input = get_user_input()
+            handle_user_input(
+                user_input, chat_llm, messages, crew_tool_schema, available_functions
             )
 
-            messages.append({"role": "assistant", "content": final_response})
-            click.secho(f"\nAssistant: {final_response}\n", fg="green")
-
         except KeyboardInterrupt:
             click.echo("\nExiting chat. Goodbye!")
             break
@@ -129,6 +201,55 @@ def chat_loop(chat_llm, messages, crew_tool_schema, available_functions):
             break
 
 
+def get_user_input() -> str:
+    """Collect multi-line user input with exit handling."""
+    click.secho(
+        "\nYou (type your message below. Press 'Enter' twice when you're done):",
+        fg="blue",
+    )
+    user_input_lines = []
+    while True:
+        line = input()
+        if line.strip().lower() == "exit":
+            return "exit"
+        if line == "":
+            break
+        user_input_lines.append(line)
+    return "\n".join(user_input_lines)
+
+
+def handle_user_input(
+    user_input: str,
+    chat_llm: LLM,
+    messages: List[Dict[str, str]],
+    crew_tool_schema: Dict[str, Any],
+    available_functions: Dict[str, Any],
+) -> None:
+    if user_input.strip().lower() == "exit":
+        click.echo("Exiting chat. Goodbye!")
+        return
+
+    if not user_input.strip():
+        click.echo("Empty message. Please provide input or type 'exit' to quit.")
+        return
+
+    messages.append({"role": "user", "content": user_input})
+
+    # Indicate that assistant is processing
+    click.echo()
+    click.secho("Assistant is processing your input. Please wait...", fg="green")
+
+    # Process assistant's response
+    final_response = chat_llm.call(
+        messages=messages,
+        tools=[crew_tool_schema],
+        available_functions=available_functions,
+    )
+
+    messages.append({"role": "assistant", "content": final_response})
+    click.secho(f"\nAssistant: {final_response}\n", fg="green")
+
+
 def generate_crew_tool_schema(crew_inputs: ChatInputs) -> dict:
     """
     Dynamically build a Littellm 'function' schema for the given crew.
@@ -323,10 +444,10 @@ def generate_input_description_with_ai(input_name: str, crew: Crew, chat_llm) ->
         ):
             # Replace placeholders with input names
             task_description = placeholder_pattern.sub(
-                lambda m: m.group(1), task.description
+                lambda m: m.group(1), task.description or ""
             )
             expected_output = placeholder_pattern.sub(
-                lambda m: m.group(1), task.expected_output
+                lambda m: m.group(1), task.expected_output or ""
             )
             context_texts.append(f"Task Description: {task_description}")
             context_texts.append(f"Expected Output: {expected_output}")
@@ -337,10 +458,10 @@ def generate_input_description_with_ai(input_name: str, crew: Crew, chat_llm) ->
             or f"{{{input_name}}}" in agent.backstory
         ):
             # Replace placeholders with input names
-            agent_role = placeholder_pattern.sub(lambda m: m.group(1), agent.role)
-            agent_goal = placeholder_pattern.sub(lambda m: m.group(1), agent.goal)
+            agent_role = placeholder_pattern.sub(lambda m: m.group(1), agent.role or "")
+            agent_goal = placeholder_pattern.sub(lambda m: m.group(1), agent.goal or "")
             agent_backstory = placeholder_pattern.sub(
-                lambda m: m.group(1), agent.backstory
+                lambda m: m.group(1), agent.backstory or ""
             )
             context_texts.append(f"Agent Role: {agent_role}")
             context_texts.append(f"Agent Goal: {agent_goal}")
@@ -381,18 +502,20 @@ def generate_crew_description_with_ai(crew: Crew, chat_llm) -> str:
     for task in crew.tasks:
         # Replace placeholders with input names
         task_description = placeholder_pattern.sub(
-            lambda m: m.group(1), task.description
+            lambda m: m.group(1), task.description or ""
         )
         expected_output = placeholder_pattern.sub(
-            lambda m: m.group(1), task.expected_output
+            lambda m: m.group(1), task.expected_output or ""
         )
         context_texts.append(f"Task Description: {task_description}")
         context_texts.append(f"Expected Output: {expected_output}")
     for agent in crew.agents:
         # Replace placeholders with input names
-        agent_role = placeholder_pattern.sub(lambda m: m.group(1), agent.role)
-        agent_goal = placeholder_pattern.sub(lambda m: m.group(1), agent.goal)
-        agent_backstory = placeholder_pattern.sub(lambda m: m.group(1), agent.backstory)
+        agent_role = placeholder_pattern.sub(lambda m: m.group(1), agent.role or "")
+        agent_goal = placeholder_pattern.sub(lambda m: m.group(1), agent.goal or "")
+        agent_backstory = placeholder_pattern.sub(
+            lambda m: m.group(1), agent.backstory or ""
+        )
         context_texts.append(f"Agent Role: {agent_role}")
         context_texts.append(f"Agent Goal: {agent_goal}")
         context_texts.append(f"Agent Backstory: {agent_backstory}")

src/crewai/cli/templates/crew/.gitignore

@@ -1,2 +1,3 @@
 .env
 __pycache__/
+.DS_Store

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]>=0.98.0,<1.0.0"
+    "crewai[tools]>=0.100.0,<1.0.0"
 ]
 
 [project.scripts]

src/crewai/cli/templates/flow/.gitignore

@@ -1,3 +1,4 @@
 .env
 __pycache__/
 lib/
+.DS_Store

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]>=0.98.0,<1.0.0",
+    "crewai[tools]>=0.100.0,<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]>=0.98.0"
+    "crewai[tools]>=0.100.0"
 ]
 
 [tool.crewai]

src/crewai/llm.py

@@ -142,7 +142,6 @@ class LLM:
         self.temperature = temperature
         self.top_p = top_p
         self.n = n
-        self.stop = stop
         self.max_completion_tokens = max_completion_tokens
         self.max_tokens = max_tokens
         self.presence_penalty = presence_penalty
@@ -160,37 +159,63 @@ class LLM:
 
         litellm.drop_params = True
 
+        # Normalize self.stop to always be a List[str]
+        if stop is None:
+            self.stop: List[str] = []
+        elif isinstance(stop, str):
+            self.stop = [stop]
+        else:
+            self.stop = stop
+
         self.set_callbacks(callbacks)
         self.set_env_callbacks()
 
     def call(
         self,
-        messages: List[Dict[str, str]],
+        messages: Union[str, List[Dict[str, str]]],
         tools: Optional[List[dict]] = None,
         callbacks: Optional[List[Any]] = None,
         available_functions: Optional[Dict[str, Any]] = None,
     ) -> str:
         """
-        High-level call method that:
-          1) Calls litellm.completion
-          2) Checks for function/tool calls
-          3) If a tool call is found:
-               a) executes the function
-               b) returns the result
-          4) If no tool call, returns the text response
+        High-level llm call method that:
+          1) Accepts either a string or a list of messages
+          2) Converts string input to the required message format
+          3) Calls litellm.completion
+          4) Handles function/tool calls if any
+          5) Returns the final text response or tool result
 
-        :param messages: The conversation messages
-        :param tools: Optional list of function schemas for function calling
-        :param callbacks: Optional list of callbacks
-        :param available_functions: A dictionary mapping function_name -> actual Python function
-        :return: Final text response from the LLM or the tool result
+        Parameters:
+        - messages (Union[str, List[Dict[str, str]]]): The input messages for the LLM.
+          - If a string is provided, it will be converted into a message list with a single entry.
+          - If a list of dictionaries is provided, each dictionary should have 'role' and 'content' keys.
+        - tools (Optional[List[dict]]): A list of tool schemas for function calling.
+        - callbacks (Optional[List[Any]]): A list of callback functions to be executed.
+        - available_functions (Optional[Dict[str, Any]]): A dictionary mapping function names to actual Python functions.
+
+        Returns:
+        - str: The final text response from the LLM or the result of a tool function call.
+
+        Examples:
+        ---------
+        # Example 1: Using a string input
+        response = llm.call("Return the name of a random city in the world.")
+        print(response)
+
+        # Example 2: Using a list of messages
+        messages = [{"role": "user", "content": "What is the capital of France?"}]
+        response = llm.call(messages)
+        print(response)
         """
+        if isinstance(messages, str):
+            messages = [{"role": "user", "content": messages}]
+
         with suppress_warnings():
             if callbacks and len(callbacks) > 0:
                 self.set_callbacks(callbacks)
 
             try:
-                # --- 1) Make the completion call
+                # --- 1) Prepare the parameters for the completion call
                 params = {
                     "model": self.model,
                     "messages": messages,
@@ -211,19 +236,21 @@ class LLM:
                     "api_version": self.api_version,
                     "api_key": self.api_key,
                     "stream": False,
-                    "tools": tools,  # pass the tool schema
+                    "tools": tools,
                 }
 
+                # Remove None values from params
                 params = {k: v for k, v in params.items() if v is not None}
 
+                # --- 2) Make the completion call
                 response = litellm.completion(**params)
                 response_message = cast(Choices, cast(ModelResponse, response).choices)[
                     0
                 ].message
                 text_response = response_message.content or ""
                 tool_calls = getattr(response_message, "tool_calls", [])
-                
-                # Ensure callbacks get the full response object with usage info
+
+                # --- 3) Handle callbacks with usage info
                 if callbacks and len(callbacks) > 0:
                     for callback in callbacks:
                         if hasattr(callback, "log_success_event"):
@@ -236,11 +263,11 @@ class LLM:
                                     end_time=0,
                                 )
 
-                # --- 2) If no tool calls, return the text response
+                # --- 4) If no tool calls, return the text response
                 if not tool_calls or not available_functions:
                     return text_response
 
-                # --- 3) Handle the tool call
+                # --- 5) Handle the tool call
                 tool_call = tool_calls[0]
                 function_name = tool_call.function.name
 
@@ -255,7 +282,6 @@ class LLM:
                     try:
                         # Call the actual tool function
                         result = fn(**function_args)
-
                         return result
 
                     except Exception as e:

src/crewai/tools/tool_usage.py

@@ -1,12 +1,13 @@
 import ast
 import datetime
 import json
-import re
 import time
 from difflib import SequenceMatcher
+from json import JSONDecodeError
 from textwrap import dedent
-from typing import Any, Dict, List, Union
+from typing import Any, Dict, List, Optional, Union
 
+import json5
 from json_repair import repair_json
 
 import crewai.utilities.events as events
@@ -407,28 +408,55 @@ class ToolUsage:
                 )
             return self._tool_calling(tool_string)
 
-    def _validate_tool_input(self, tool_input: str) -> Dict[str, Any]:
+    def _validate_tool_input(self, tool_input: Optional[str]) -> Dict[str, Any]:
+        if tool_input is None:
+            return {}
+
+        if not isinstance(tool_input, str) or not tool_input.strip():
+            raise Exception(
+                "Tool input must be a valid dictionary in JSON or Python literal format"
+            )
+
+        # Attempt 1: Parse as JSON
         try:
-            # Replace Python literals with JSON equivalents
-            replacements = {
-                r"'": '"',
-                r"None": "null",
-                r"True": "true",
-                r"False": "false",
-            }
-            for pattern, replacement in replacements.items():
-                tool_input = re.sub(pattern, replacement, tool_input)
-
             arguments = json.loads(tool_input)
-        except json.JSONDecodeError:
-            # Attempt to repair JSON string
-            repaired_input = repair_json(tool_input)
-            try:
-                arguments = json.loads(repaired_input)
-            except json.JSONDecodeError as e:
-                raise Exception(f"Invalid tool input JSON: {e}")
+            if isinstance(arguments, dict):
+                return arguments
+        except (JSONDecodeError, TypeError):
+            pass  # Continue to the next parsing attempt
 
-        return arguments
+        # Attempt 2: Parse as Python literal
+        try:
+            arguments = ast.literal_eval(tool_input)
+            if isinstance(arguments, dict):
+                return arguments
+        except (ValueError, SyntaxError):
+            pass  # Continue to the next parsing attempt
+
+        # Attempt 3: Parse as JSON5
+        try:
+            arguments = json5.loads(tool_input)
+            if isinstance(arguments, dict):
+                return arguments
+        except (JSONDecodeError, ValueError, TypeError):
+            pass  # Continue to the next parsing attempt
+
+        # Attempt 4: Repair JSON
+        try:
+            repaired_input = repair_json(tool_input)
+            self._printer.print(
+                content=f"Repaired JSON: {repaired_input}", color="blue"
+            )
+            arguments = json.loads(repaired_input)
+            if isinstance(arguments, dict):
+                return arguments
+        except Exception as e:
+            self._printer.print(content=f"Failed to repair JSON: {e}", color="red")
+
+        # If all parsing attempts fail, raise an error
+        raise Exception(
+            "Tool input must be a valid dictionary in JSON or Python literal format"
+        )
 
     def on_tool_error(self, tool: Any, tool_calling: ToolCalling, e: Exception) -> None:
         event_data = self._prepare_event_data(tool, tool_calling)

src/crewai/utilities/evaluators/task_evaluator.py

@@ -96,9 +96,9 @@ class TaskEvaluator:
         final_aggregated_data = ""
         for _, data in output_training_data.items():
             final_aggregated_data += (
-                f"Initial Output:\n{data['initial_output']}\n\n"
-                f"Human Feedback:\n{data['human_feedback']}\n\n"
-                f"Improved Output:\n{data['improved_output']}\n\n"
+                f"Initial Output:\n{data.get('initial_output', '')}\n\n"
+                f"Human Feedback:\n{data.get('human_feedback', '')}\n\n"
+                f"Improved Output:\n{data.get('improved_output', '')}\n\n"
             )
 
         evaluation_query = (

src/crewai/utilities/llm_utils.py

@@ -24,12 +24,10 @@ def create_llm(
 
     # 1) If llm_value is already an LLM object, return it directly
     if isinstance(llm_value, LLM):
-        print("LLM value is already an LLM object")
         return llm_value
 
     # 2) If llm_value is a string (model name)
     if isinstance(llm_value, str):
-        print("LLM value is a string")
         try:
             created_llm = LLM(model=llm_value)
             return created_llm
@@ -39,12 +37,10 @@ def create_llm(
 
     # 3) If llm_value is None, parse environment variables or use default
     if llm_value is None:
-        print("LLM value is None")
         return _llm_via_environment_or_fallback()
 
     # 4) Otherwise, attempt to extract relevant attributes from an unknown object
     try:
-        print("LLM value is an unknown object")
         # Extract attributes with explicit types
         model = (
             getattr(llm_value, "model_name", None)

tests/agent_test.py

@@ -16,7 +16,7 @@ from crewai.tools import tool
 from crewai.tools.tool_calling import InstructorToolCalling
 from crewai.tools.tool_usage import ToolUsage
 from crewai.tools.tool_usage_events import ToolUsageFinished
-from crewai.utilities import RPMController
+from crewai.utilities import Printer, RPMController
 from crewai.utilities.events import Emitter
 
 
@@ -1600,3 +1600,142 @@ def test_agent_with_knowledge_sources():
 
         # Assert that the agent provides the correct information
         assert "red" in result.raw.lower()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_litellm_auth_error_handling():
+    """Test that LiteLLM authentication errors are handled correctly and not retried."""
+    from litellm import AuthenticationError as LiteLLMAuthenticationError
+
+    # Create an agent with a mocked LLM and max_retry_limit=0
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        llm=LLM(model="gpt-4"),
+        max_retry_limit=0,  # Disable retries for authentication errors
+    )
+
+    # Create a task
+    task = Task(
+        description="Test task",
+        expected_output="Test output",
+        agent=agent,
+    )
+
+    # Mock the LLM call to raise AuthenticationError
+    with (
+        patch.object(LLM, "call") as mock_llm_call,
+        pytest.raises(LiteLLMAuthenticationError, match="Invalid API key"),
+    ):
+        mock_llm_call.side_effect = LiteLLMAuthenticationError(
+            message="Invalid API key", llm_provider="openai", model="gpt-4"
+        )
+        agent.execute_task(task)
+
+    # Verify the call was only made once (no retries)
+    mock_llm_call.assert_called_once()
+
+
+def test_crew_agent_executor_litellm_auth_error():
+    """Test that CrewAgentExecutor handles LiteLLM authentication errors by raising them."""
+    from litellm.exceptions import AuthenticationError
+
+    from crewai.agents.tools_handler import ToolsHandler
+    from crewai.utilities import Printer
+
+    # Create an agent and executor
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        llm=LLM(model="gpt-4", api_key="invalid_api_key"),
+    )
+    task = Task(
+        description="Test task",
+        expected_output="Test output",
+        agent=agent,
+    )
+
+    # Create executor with all required parameters
+    executor = CrewAgentExecutor(
+        agent=agent,
+        task=task,
+        llm=agent.llm,
+        crew=None,
+        prompt={"system": "You are a test agent", "user": "Execute the task: {input}"},
+        max_iter=5,
+        tools=[],
+        tools_names="",
+        stop_words=[],
+        tools_description="",
+        tools_handler=ToolsHandler(),
+    )
+
+    # Mock the LLM call to raise AuthenticationError
+    with (
+        patch.object(LLM, "call") as mock_llm_call,
+        patch.object(Printer, "print") as mock_printer,
+        pytest.raises(AuthenticationError) as exc_info,
+    ):
+        mock_llm_call.side_effect = AuthenticationError(
+            message="Invalid API key", llm_provider="openai", model="gpt-4"
+        )
+        executor.invoke(
+            {
+                "input": "test input",
+                "tool_names": "",
+                "tools": "",
+            }
+        )
+
+    # Verify error handling messages
+    error_message = f"Error during LLM call: {str(mock_llm_call.side_effect)}"
+    mock_printer.assert_any_call(
+        content=error_message,
+        color="red",
+    )
+
+    # Verify the call was only made once (no retries)
+    mock_llm_call.assert_called_once()
+
+    # Assert that the exception was raised and has the expected attributes
+    assert exc_info.type is AuthenticationError
+    assert "Invalid API key".lower() in exc_info.value.message.lower()
+    assert exc_info.value.llm_provider == "openai"
+    assert exc_info.value.model == "gpt-4"
+
+
+def test_litellm_anthropic_error_handling():
+    """Test that AnthropicError from LiteLLM is handled correctly and not retried."""
+    from litellm.llms.anthropic.common_utils import AnthropicError
+
+    # Create an agent with a mocked LLM that uses an Anthropic model
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        llm=LLM(model="claude-3.5-sonnet-20240620"),
+        max_retry_limit=0,
+    )
+
+    # Create a task
+    task = Task(
+        description="Test task",
+        expected_output="Test output",
+        agent=agent,
+    )
+
+    # Mock the LLM call to raise AnthropicError
+    with (
+        patch.object(LLM, "call") as mock_llm_call,
+        pytest.raises(AnthropicError, match="Test Anthropic error"),
+    ):
+        mock_llm_call.side_effect = AnthropicError(
+            status_code=500,
+            message="Test Anthropic error",
+        )
+        agent.execute_task(task)
+
+    # Verify the LLM call was only made once (no retries)
+    mock_llm_call.assert_called_once()

tests/cassettes/test_agent_error_on_parsing_tool.yaml

@@ -2,21 +2,21 @@ interactions:
 - request:
     body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
       personal goal is: test goal\nYou ONLY have access to the following tools, and
-      should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
-      Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
-      answer but don''t give it yet, just re-use this         tool non-stop. \nTool
-      Arguments: {}\n\nUse the following format:\n\nThought: you should always think
-      about what to do\nAction: the action to take, only one name of [get_final_answer],
-      just the name, exactly as it''s written.\nAction Input: the input to the action,
-      just a simple python dictionary, enclosed in curly braces, using \" to wrap
-      keys and values.\nObservation: the result of the action\n\nOnce all necessary
-      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
-      the final answer to the original input question\n"}, {"role": "user", "content":
-      "\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect criteria
-      for your final answer: The final answer\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"}'
+      should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool
+      Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
+      just re-use this\n        tool non-stop.\n\nIMPORTANT: Use the following format
+      in your response:\n\n```\nThought: you should always think about what to do\nAction:
+      the action to take, only one name of [get_final_answer], just the name, exactly
+      as it''s written.\nAction Input: the input to the action, just a simple JSON
+      object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
+      the result of the action\n```\n\nOnce all necessary information is gathered,
+      return the following format:\n\n```\nThought: I now know the final answer\nFinal
+      Answer: the final answer to the original input question\n```"}, {"role": "user",
+      "content": "\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect
+      criteria for your final answer: The final answer\nyou MUST return the actual
+      complete content as the final answer, not a summary.\n\nBegin! This is VERY
+      important to you, use the tools available and give your best Final Answer, your
+      job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
     headers:
       accept:
       - application/json
@@ -25,16 +25,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1325'
+      - '1367'
       content-type:
       - application/json
-      cookie:
-      - _cfuvid=ePJSDFdHag2D8lj21_ijAMWjoA6xfnPNxN4uekvC728-1727226247743-0.0.1.1-604800000;
-        __cf_bm=3giyBOIM0GNudFELtsBWYXwLrpLBTNLsh81wfXgu2tg-1727226247-1.0.1.1-ugUDz0c5EhmfVpyGtcdedlIWeDGuy2q0tXQTKVpv83HZhvxgBcS7SBL1wS4rapPM38yhfEcfwA79ARt3HQEzKA
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.47.0
+      - OpenAI/Python 1.59.6
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -44,30 +41,35 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.47.0
+      - 1.59.6
       x-stainless-raw-response:
       - 'true'
+      x-stainless-retry-count:
+      - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.7
+      - 3.12.7
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-ABAtOWmVjvzQ9X58tKAUcOF4gmXwx\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1727226842,\n  \"model\": \"gpt-4o-2024-05-13\",\n
+    content: "{\n  \"id\": \"chatcmpl-AsXdf4OZKCZSigmN4k0gyh67NciqP\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1737562383,\n  \"model\": \"gpt-4o-2024-08-06\",\n
       \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Thought: I need to use the get_final_answer
-      tool to determine the final answer.\\nAction: get_final_answer\\nAction Input:
-      {}\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 274,\n    \"completion_tokens\":
-      27,\n    \"total_tokens\": 301,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
-      0\n    }\n  },\n  \"system_fingerprint\": \"fp_e375328146\"\n}\n"
+      \"assistant\",\n        \"content\": \"```\\nThought: I have to use the available
+      tool to get the final answer. Let's proceed with executing it.\\nAction: get_final_answer\\nAction
+      Input: {}\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      274,\n    \"completion_tokens\": 33,\n    \"total_tokens\": 307,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_50cad350e4\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8c8727b3492f31e6-MIA
+      - 9060d43e3be1d690-IAD
       Connection:
       - keep-alive
       Content-Encoding:
@@ -75,19 +77,27 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 25 Sep 2024 01:14:03 GMT
+      - Wed, 22 Jan 2025 16:13:03 GMT
       Server:
       - cloudflare
+      Set-Cookie:
+      - __cf_bm=_Jcp7wnO_mXdvOnborCN6j8HwJxJXbszedJC1l7pFUg-1737562383-1.0.1.1-pDSLXlg.nKjG4wsT7mTJPjUvOX1UJITiS4MqKp6yfMWwRSJINsW1qC48SAcjBjakx2H5I1ESVk9JtUpUFDtf4g;
+        path=/; expires=Wed, 22-Jan-25 16:43:03 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=x3SYvzL2nq_PTBGtE8R9cl5CkeaaDzZFQIrYfo91S2s-1737562383916-0.0.1.1-604800000;
+        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:
-      - '348'
+      - '791'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -99,45 +109,59 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '29999682'
+      - '29999680'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_be929caac49706f487950548bdcdd46e
+      - req_eeed99acafd3aeb1e3d4a6c8063192b0
     http_version: HTTP/1.1
     status_code: 200
 - request:
     body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
       personal goal is: test goal\nYou ONLY have access to the following tools, and
-      should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
-      Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
-      answer but don''t give it yet, just re-use this         tool non-stop. \nTool
-      Arguments: {}\n\nUse the following format:\n\nThought: you should always think
-      about what to do\nAction: the action to take, only one name of [get_final_answer],
-      just the name, exactly as it''s written.\nAction Input: the input to the action,
-      just a simple python dictionary, enclosed in curly braces, using \" to wrap
-      keys and values.\nObservation: the result of the action\n\nOnce all necessary
-      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
-      the final answer to the original input question\n"}, {"role": "user", "content":
-      "\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect criteria
-      for your final answer: The final answer\nyou MUST return the actual complete
-      content as the final answer, not a summary.\n\nBegin! This is VERY important
-      to you, use the tools available and give your best Final Answer, your job depends
-      on it!\n\nThought:"}, {"role": "user", "content": "Thought: I need to use the
-      get_final_answer tool to determine the final answer.\nAction: get_final_answer\nAction
+      should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool
+      Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
+      just re-use this\n        tool non-stop.\n\nIMPORTANT: Use the following format
+      in your response:\n\n```\nThought: you should always think about what to do\nAction:
+      the action to take, only one name of [get_final_answer], just the name, exactly
+      as it''s written.\nAction Input: the input to the action, just a simple JSON
+      object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
+      the result of the action\n```\n\nOnce all necessary information is gathered,
+      return the following format:\n\n```\nThought: I now know the final answer\nFinal
+      Answer: the final answer to the original input question\n```"}, {"role": "user",
+      "content": "\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect
+      criteria for your final answer: The final answer\nyou MUST return the actual
+      complete content as the final answer, not a summary.\n\nBegin! This is VERY
+      important to you, use the tools available and give your best Final Answer, your
+      job depends on it!\n\nThought:"}, {"role": "assistant", "content": "```\nThought:
+      I have to use the available tool to get the final answer. Let''s proceed with
+      executing it.\nAction: get_final_answer\nAction Input: {}\nObservation: I encountered
+      an error: Error on parsing tool.\nMoving on then. I MUST either use a tool (use
+      one at time) OR give my best final answer not both at the same time. When responding,
+      I must use the following format:\n\n```\nThought: you should always think about
+      what to do\nAction: the action to take, should be one of [get_final_answer]\nAction
+      Input: the input to the action, dictionary enclosed in curly braces\nObservation:
+      the result of the action\n```\nThis Thought/Action/Action Input/Result can repeat
+      N times. Once I know the final answer, I must return the following format:\n\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\n```"}, {"role":
+      "assistant", "content": "```\nThought: I have to use the available tool to get
+      the final answer. Let''s proceed with executing it.\nAction: get_final_answer\nAction
       Input: {}\nObservation: I encountered an error: Error on parsing tool.\nMoving
       on then. I MUST either use a tool (use one at time) OR give my best final answer
-      not both at the same time. To Use the following format:\n\nThought: you should
-      always think about what to do\nAction: the action to take, should be one of
-      [get_final_answer]\nAction Input: the input to the action, dictionary enclosed
-      in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action
-      Input/Result can repeat N times)\nThought: I now can give a great answer\nFinal
+      not both at the same time. When responding, I must use the following format:\n\n```\nThought:
+      you should always think about what to do\nAction: the action to take, should
+      be one of [get_final_answer]\nAction Input: the input to the action, dictionary
+      enclosed in curly braces\nObservation: the result of the action\n```\nThis Thought/Action/Action
+      Input/Result can repeat N times. Once I know the final answer, I must return
+      the following format:\n\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\n \nNow it''s time you MUST give your absolute
+      it must be outcome described\n\n```\nNow it''s time you MUST give your absolute
       best final answer. You''ll ignore all previous instructions, stop using any
-      tools, and just return your absolute BEST Final answer."}], "model": "gpt-4o"}'
+      tools, and just return your absolute BEST Final answer."}], "model": "gpt-4o",
+      "stop": ["\nObservation:"]}'
     headers:
       accept:
       - application/json
@@ -146,16 +170,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '2320'
+      - '3445'
       content-type:
       - application/json
       cookie:
-      - _cfuvid=ePJSDFdHag2D8lj21_ijAMWjoA6xfnPNxN4uekvC728-1727226247743-0.0.1.1-604800000;
-        __cf_bm=3giyBOIM0GNudFELtsBWYXwLrpLBTNLsh81wfXgu2tg-1727226247-1.0.1.1-ugUDz0c5EhmfVpyGtcdedlIWeDGuy2q0tXQTKVpv83HZhvxgBcS7SBL1wS4rapPM38yhfEcfwA79ARt3HQEzKA
+      - __cf_bm=_Jcp7wnO_mXdvOnborCN6j8HwJxJXbszedJC1l7pFUg-1737562383-1.0.1.1-pDSLXlg.nKjG4wsT7mTJPjUvOX1UJITiS4MqKp6yfMWwRSJINsW1qC48SAcjBjakx2H5I1ESVk9JtUpUFDtf4g;
+        _cfuvid=x3SYvzL2nq_PTBGtE8R9cl5CkeaaDzZFQIrYfo91S2s-1737562383916-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.47.0
+      - OpenAI/Python 1.59.6
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -165,29 +189,36 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.47.0
+      - 1.59.6
       x-stainless-raw-response:
       - 'true'
+      x-stainless-retry-count:
+      - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.7
+      - 3.12.7
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-ABAtPaaeRfdNsZ3k06CfAmrEW8IJu\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1727226843,\n  \"model\": \"gpt-4o-2024-05-13\",\n
+    content: "{\n  \"id\": \"chatcmpl-AsXdg9UrLvAiqWP979E6DszLsQ84k\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1737562384,\n  \"model\": \"gpt-4o-2024-08-06\",\n
       \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Final Answer: The final answer\",\n        \"refusal\":
-      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
-      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 483,\n    \"completion_tokens\":
-      6,\n    \"total_tokens\": 489,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
-      0\n    }\n  },\n  \"system_fingerprint\": \"fp_e375328146\"\n}\n"
+      \"assistant\",\n        \"content\": \"```\\nThought: I now know the final answer\\nFinal
+      Answer: The final answer must be the great and the most complete as possible,
+      it must be outcome described.\\n```\",\n        \"refusal\": null\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 719,\n    \"completion_tokens\": 35,\n
+      \   \"total_tokens\": 754,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_50cad350e4\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8c8727b9da1f31e6-MIA
+      - 9060d4441edad690-IAD
       Connection:
       - keep-alive
       Content-Encoding:
@@ -195,7 +226,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 25 Sep 2024 01:14:03 GMT
+      - Wed, 22 Jan 2025 16:13:05 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -209,7 +240,7 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '188'
+      - '928'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -221,13 +252,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '29999445'
+      - '29999187'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
       - 1ms
       x-request-id:
-      - req_d8e32538689fe064627468bad802d9a8
+      - req_61fc7506e6db326ec572224aec81ef23
     http_version: HTTP/1.1
     status_code: 200
 version: 1

tests/cassettes/test_agent_tool_role_matching[ "Futel Official Infopoint" -True].yaml

@@ -1,117 +0,0 @@
-interactions:
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
-      Futel Football Club info\nYour personal goal is: Answer questions about Futel\nTo
-      give my best complete final answer to the task respond using 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: Test task\n\nThis is the expect criteria for your
-      final answer: Your best answer to your coworker asking you this, accounting
-      for the context shared.\nyou MUST return the actual complete content as the
-      final answer, not a summary.\n\nBegin! This is VERY important to you, use the
-      tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
-      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '939'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
-        _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
-      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:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-AnuRlxiTxduAVoXHHY58Fvfbll5IS\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1736458417,\n  \"model\": \"gpt-4o-2024-08-06\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
-      Answer: This is a test task, and the context or question from the coworker is
-      not specified. Therefore, my best effort would be to affirm my readiness to
-      answer accurately and in detail any question about Futel Football Club based
-      on the context described. If provided with specific information or questions,
-      I will ensure to respond comprehensively as required by my job directives.\",\n
-      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 177,\n    \"completion_tokens\":
-      82,\n    \"total_tokens\": 259,\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_703d4ff298\"\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8ff78bf7bd6cc002-ATL
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 09 Jan 2025 21:33:40 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:
-      - '2263'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '30000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '29999786'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_7c1a31da73cd103e9f410f908e59187f
-    http_version: HTTP/1.1
-    status_code: 200
-version: 1

tests/cassettes/test_agent_tool_role_matching[ FUTEL\nOFFICIAL INFOPOINT -True].yaml

@@ -1,119 +0,0 @@
-interactions:
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
-      Futel Football Club info\nYour personal goal is: Answer questions about Futel\nTo
-      give my best complete final answer to the task respond using 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: Test task\n\nThis is the expect criteria for your
-      final answer: Your best answer to your coworker asking you this, accounting
-      for the context shared.\nyou MUST return the actual complete content as the
-      final answer, not a summary.\n\nBegin! This is VERY important to you, use the
-      tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
-      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '939'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
-        _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
-      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:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-AnuRrFJZGKw8cIEshvuW1PKwFZFKs\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1736458423,\n  \"model\": \"gpt-4o-2024-08-06\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
-      Answer: Although you mentioned this being a \\\"Test task\\\" and haven't provided
-      a specific question regarding Futel Football Club, your request appears to involve
-      ensuring accuracy and detail in responses. For a proper answer about Futel,
-      I'd be ready to provide details about the club's history, management, players,
-      match schedules, and recent performance statistics. Remember to ask specific
-      questions to receive a targeted response. If this were a real context where
-      information was shared, I would respond precisely to what's been asked regarding
-      Futel Football Club.\",\n        \"refusal\": null\n      },\n      \"logprobs\":
-      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-      177,\n    \"completion_tokens\": 113,\n    \"total_tokens\": 290,\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_703d4ff298\"\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8ff78c1d0ecdc002-ATL
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 09 Jan 2025 21:33:47 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:
-      - '3097'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '30000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '29999786'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_179e1d56e2b17303e40480baffbc7b08
-    http_version: HTTP/1.1
-    status_code: 200
-version: 1

tests/cassettes/test_agent_tool_role_matching["Futel Official Infopoint"-True].yaml

@@ -1,114 +0,0 @@
-interactions:
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
-      Futel Football Club info\nYour personal goal is: Answer questions about Futel\nTo
-      give my best complete final answer to the task respond using 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: Test task\n\nThis is the expect criteria for your
-      final answer: Your best answer to your coworker asking you this, accounting
-      for the context shared.\nyou MUST return the actual complete content as the
-      final answer, not a summary.\n\nBegin! This is VERY important to you, use the
-      tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
-      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '939'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
-        _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
-      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:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-AnuRqgg7eiHnDi2DOqdk99fiqOboz\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1736458422,\n  \"model\": \"gpt-4o-2024-08-06\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
-      Answer: Your best answer to your coworker asking you this, accounting for the
-      context shared. You MUST return the actual complete content as the final answer,
-      not a summary.\",\n        \"refusal\": null\n      },\n      \"logprobs\":
-      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-      177,\n    \"completion_tokens\": 44,\n    \"total_tokens\": 221,\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_703d4ff298\"\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8ff78c164ad2c002-ATL
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 09 Jan 2025 21:33:43 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:
-      - '899'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '30000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '29999786'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_9f5226208edb90a27987aaf7e0ca03d3
-    http_version: HTTP/1.1
-    status_code: 200
-version: 1

tests/cassettes/test_agent_tool_role_matching[Futel Official Infopoint-True].yaml

@@ -1,119 +0,0 @@
-interactions:
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
-      Futel Football Club info\nYour personal goal is: Answer questions about Futel\nTo
-      give my best complete final answer to the task respond using 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: Test task\n\nThis is the expect criteria for your
-      final answer: Your best answer to your coworker asking you this, accounting
-      for the context shared.\nyou MUST return the actual complete content as the
-      final answer, not a summary.\n\nBegin! This is VERY important to you, use the
-      tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
-      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '939'
-      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-AnuRjmwH5mrykLxQhFwTqqTiDtuTf\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1736458415,\n  \"model\": \"gpt-4o-2024-08-06\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
-      Answer: As this is a test task, please note that Futel Football Club is fictional
-      and any specific details about it would not be available. However, if you have
-      specific questions or need information about a particular aspect of Futel or
-      any general football club inquiry, feel free to ask, and I'll do my best to
-      assist you with your query!\",\n        \"refusal\": null\n      },\n      \"logprobs\":
-      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-      177,\n    \"completion_tokens\": 79,\n    \"total_tokens\": 256,\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_703d4ff298\"\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8ff78be5eebfc002-ATL
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 09 Jan 2025 21:33:37 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
-        path=/; expires=Thu, 09-Jan-25 22:03:37 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000;
-        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:
-      - '2730'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '30000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '29999786'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_014478ba748f860d10ac250ca0ba824a
-    http_version: HTTP/1.1
-    status_code: 200
-version: 1

tests/cassettes/test_agent_tool_role_matching[Futel Official Infopoint\n-True].yaml

@@ -1,119 +0,0 @@
-interactions:
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
-      Futel Football Club info\nYour personal goal is: Answer questions about Futel\nTo
-      give my best complete final answer to the task respond using 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: Test task\n\nThis is the expect criteria for your
-      final answer: Your best answer to your coworker asking you this, accounting
-      for the context shared.\nyou MUST return the actual complete content as the
-      final answer, not a summary.\n\nBegin! This is VERY important to you, use the
-      tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
-      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '939'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
-        _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
-      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:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-AnuRofLgmzWcDya5LILqYwIJYgFoq\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1736458420,\n  \"model\": \"gpt-4o-2024-08-06\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
-      Answer: As an official Futel Football Club infopoint, my responsibility is to
-      provide detailed and accurate information about the club. This includes answering
-      questions regarding team statistics, player performances, upcoming fixtures,
-      ticketing and fan zone details, club history, and community initiatives. Our
-      focus is to ensure that fans and stakeholders have access to the latest and
-      most precise information about the club's on and off-pitch activities. If there's
-      anything specific you need to know, just let me know, and I'll be more than
-      happy to assist!\",\n        \"refusal\": null\n      },\n      \"logprobs\":
-      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-      177,\n    \"completion_tokens\": 115,\n    \"total_tokens\": 292,\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_703d4ff298\"\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8ff78c066f37c002-ATL
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 09 Jan 2025 21:33:42 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:
-      - '2459'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '30000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '29999786'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_a146dd27f040f39a576750970cca0f52
-    http_version: HTTP/1.1
-    status_code: 200
-version: 1

tests/cassettes/test_llm_call_with_message_list.yaml

@@ -0,0 +1,102 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "What is the capital of France?"}],
+      "model": "gpt-4o-mini"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '101'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=8NrWEBP3dDmc8p2.csR.EdsSwS8zFvzWI1kPICaK_fM-1737568015338-0.0.1.1-604800000;
+        __cf_bm=pKr3NwXmTZN9rMSlKvEX40VPKbrxF93QwDNHunL2v8Y-1737568015-1.0.1.1-nR0EA7hYIwWpIBYUI53d9xQrUnl5iML6lgz4AGJW4ZGPBDxFma3PZ2cBhlr_hE7wKa5fV3r32eMu_rNWMXD.eA
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.59.6
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.59.6
+      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-AsZ6WjNfEOrHwwEEdSZZCRBiTpBMS\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1737568016,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The capital of France is Paris.\",\n
+      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 14,\n    \"completion_tokens\":
+      8,\n    \"total_tokens\": 22,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 90615dc63b805cb1-RDU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 22 Jan 2025 17:46:56 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:
+      - '355'
+      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:
+      - '149999974'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_cdbed69c9c63658eb552b07f1220df19
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_llm_call_with_string_input.yaml

@@ -0,0 +1,108 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "Return the name of a random
+      city in the world."}], "model": "gpt-4o-mini"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '117'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=3UeEmz_rnmsoZxrVUv32u35gJOi766GDWNe5_RTjiPk-1736537376739-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.59.6
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.59.6
+      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-AsZ6UtbaNSMpNU9VJKxvn52t5eJTq\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1737568014,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"How about \\\"Lisbon\\\"? It\u2019s the
+      capital city of Portugal, known for its rich history and vibrant culture.\",\n
+      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 18,\n    \"completion_tokens\":
+      24,\n    \"total_tokens\": 42,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 90615dbcaefb5cb1-RDU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 22 Jan 2025 17:46:55 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=pKr3NwXmTZN9rMSlKvEX40VPKbrxF93QwDNHunL2v8Y-1737568015-1.0.1.1-nR0EA7hYIwWpIBYUI53d9xQrUnl5iML6lgz4AGJW4ZGPBDxFma3PZ2cBhlr_hE7wKa5fV3r32eMu_rNWMXD.eA;
+        path=/; expires=Wed, 22-Jan-25 18:16:55 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=8NrWEBP3dDmc8p2.csR.EdsSwS8zFvzWI1kPICaK_fM-1737568015338-0.0.1.1-604800000;
+        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:
+      - '449'
+      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:
+      - '149999971'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_898373758d2eae3cd84814050b2588e3
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_llm_call_with_string_input_and_callbacks.yaml

@@ -0,0 +1,102 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "Tell me a joke."}], "model":
+      "gpt-4o-mini"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '86'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=8NrWEBP3dDmc8p2.csR.EdsSwS8zFvzWI1kPICaK_fM-1737568015338-0.0.1.1-604800000;
+        __cf_bm=pKr3NwXmTZN9rMSlKvEX40VPKbrxF93QwDNHunL2v8Y-1737568015-1.0.1.1-nR0EA7hYIwWpIBYUI53d9xQrUnl5iML6lgz4AGJW4ZGPBDxFma3PZ2cBhlr_hE7wKa5fV3r32eMu_rNWMXD.eA
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.59.6
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.59.6
+      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-AsZ6VyjuUcXYpChXmD8rUSy6nSGq8\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1737568015,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Why did the scarecrow win an award?  \\n\\nBecause
+      he was outstanding in his field!\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      12,\n    \"completion_tokens\": 19,\n    \"total_tokens\": 31,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 90615dc03b6c5cb1-RDU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 22 Jan 2025 17:46:56 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:
+      - '825'
+      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:
+      - '149999979'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_4c1485d44e7461396d4a7316a63ff353
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_llm_call_with_tool_and_message_list.yaml

@@ -0,0 +1,111 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "What is the square of 5?"}],
+      "model": "gpt-4o-mini", "tools": [{"type": "function", "function": {"name":
+      "square_number", "description": "Returns the square of a number.", "parameters":
+      {"type": "object", "properties": {"number": {"type": "integer", "description":
+      "The number to square"}}, "required": ["number"]}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '361'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.59.6
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.59.6
+      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-AsZL5nGOaVpcGnDOesTxBZPHhMoaS\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1737568919,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+      \           \"id\": \"call_i6JVJ1KxX79A4WzFri98E03U\",\n            \"type\":
+      \"function\",\n            \"function\": {\n              \"name\": \"square_number\",\n
+      \             \"arguments\": \"{\\\"number\\\":5}\"\n            }\n          }\n
+      \       ],\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"tool_calls\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      58,\n    \"completion_tokens\": 15,\n    \"total_tokens\": 73,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 906173d229b905f6-IAD
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 22 Jan 2025 18:02:00 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=BYDpIoqfPZyRxl9xcFxkt4IzTUGe8irWQlZ.aYLt8Xc-1737568920-1.0.1.1-Y_cVFN7TbguWRBorSKZynVY02QUtYbsbHuR2gR1wJ8LHuqOF4xIxtK5iHVCpWWgIyPDol9xOXiqUkU8xRV_vHA;
+        path=/; expires=Wed, 22-Jan-25 18:32:00 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=etTqqA9SBOnENmrFAUBIexdW0v2ZeO1x9_Ek_WChlfU-1737568920137-0.0.1.1-604800000;
+        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:
+      - '642'
+      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:
+      - '149999976'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_388e63f9b8d4edc0dd153001f25388e5
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_llm_call_with_tool_and_string_input.yaml

@@ -0,0 +1,107 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "What is the current year?"}],
+      "model": "gpt-4o-mini", "tools": [{"type": "function", "function": {"name":
+      "get_current_year", "description": "Returns the current year as a string.",
+      "parameters": {"type": "object", "properties": {}, "required": []}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '295'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=8NrWEBP3dDmc8p2.csR.EdsSwS8zFvzWI1kPICaK_fM-1737568015338-0.0.1.1-604800000;
+        __cf_bm=pKr3NwXmTZN9rMSlKvEX40VPKbrxF93QwDNHunL2v8Y-1737568015-1.0.1.1-nR0EA7hYIwWpIBYUI53d9xQrUnl5iML6lgz4AGJW4ZGPBDxFma3PZ2cBhlr_hE7wKa5fV3r32eMu_rNWMXD.eA
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.59.6
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.59.6
+      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-AsZJ8HKXQU9nTB7xbGAkKxqrg9BZ2\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1737568798,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+      \           \"id\": \"call_mfvEs2jngeFloVZpZOHZVaKY\",\n            \"type\":
+      \"function\",\n            \"function\": {\n              \"name\": \"get_current_year\",\n
+      \             \"arguments\": \"{}\"\n            }\n          }\n        ],\n
+      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"tool_calls\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 46,\n    \"completion_tokens\":
+      12,\n    \"total_tokens\": 58,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 906170e038281775-IAD
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 22 Jan 2025 17:59:59 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:
+      - '416'
+      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:
+      - '149999975'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_4039a5e5772d1790a3131f0b1ea06139
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/llm_test.py

@@ -4,6 +4,7 @@ import pytest
 
 from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
 from crewai.llm import LLM
+from crewai.tools import tool
 from crewai.utilities.token_counter_callback import TokenCalcHandler
 
 
@@ -37,3 +38,119 @@ def test_llm_callback_replacement():
     assert usage_metrics_1.successful_requests == 1
     assert usage_metrics_2.successful_requests == 1
     assert usage_metrics_1 == calc_handler_1.token_cost_process.get_summary()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_llm_call_with_string_input():
+    llm = LLM(model="gpt-4o-mini")
+
+    # Test the call method with a string input
+    result = llm.call("Return the name of a random city in the world.")
+    assert isinstance(result, str)
+    assert len(result.strip()) > 0  # Ensure the response is not empty
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_llm_call_with_string_input_and_callbacks():
+    llm = LLM(model="gpt-4o-mini")
+    calc_handler = TokenCalcHandler(token_cost_process=TokenProcess())
+
+    # Test the call method with a string input and callbacks
+    result = llm.call(
+        "Tell me a joke.",
+        callbacks=[calc_handler],
+    )
+    usage_metrics = calc_handler.token_cost_process.get_summary()
+
+    assert isinstance(result, str)
+    assert len(result.strip()) > 0
+    assert usage_metrics.successful_requests == 1
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_llm_call_with_message_list():
+    llm = LLM(model="gpt-4o-mini")
+    messages = [{"role": "user", "content": "What is the capital of France?"}]
+
+    # Test the call method with a list of messages
+    result = llm.call(messages)
+    assert isinstance(result, str)
+    assert "Paris" in result
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_llm_call_with_tool_and_string_input():
+    llm = LLM(model="gpt-4o-mini")
+
+    def get_current_year() -> str:
+        """Returns the current year as a string."""
+        from datetime import datetime
+
+        return str(datetime.now().year)
+
+    # Create tool schema
+    tool_schema = {
+        "type": "function",
+        "function": {
+            "name": "get_current_year",
+            "description": "Returns the current year as a string.",
+            "parameters": {
+                "type": "object",
+                "properties": {},
+                "required": [],
+            },
+        },
+    }
+
+    # Available functions mapping
+    available_functions = {"get_current_year": get_current_year}
+
+    # Test the call method with a string input and tool
+    result = llm.call(
+        "What is the current year?",
+        tools=[tool_schema],
+        available_functions=available_functions,
+    )
+
+    assert isinstance(result, str)
+    assert result == get_current_year()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_llm_call_with_tool_and_message_list():
+    llm = LLM(model="gpt-4o-mini")
+
+    def square_number(number: int) -> int:
+        """Returns the square of a number."""
+        return number * number
+
+    # Create tool schema
+    tool_schema = {
+        "type": "function",
+        "function": {
+            "name": "square_number",
+            "description": "Returns the square of a number.",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "number": {"type": "integer", "description": "The number to square"}
+                },
+                "required": ["number"],
+            },
+        },
+    }
+
+    # Available functions mapping
+    available_functions = {"square_number": square_number}
+
+    messages = [{"role": "user", "content": "What is the square of 5?"}]
+
+    # Test the call method with messages and tool
+    result = llm.call(
+        messages,
+        tools=[tool_schema],
+        available_functions=available_functions,
+    )
+
+    assert isinstance(result, int)
+    assert result == 25

tests/test_manager_llm_delegation.py

@@ -1,51 +0,0 @@
-import pytest
-
-from crewai import Agent
-from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
-
-
-class InternalAgentTool(BaseAgentTool):
-    """Concrete implementation of BaseAgentTool for testing."""
-
-    def _run(self, *args, **kwargs):
-        """Implement required _run method."""
-        return "Test response"
-
-
-@pytest.mark.parametrize(
-    "role_name,should_match",
-    [
-        ("Futel Official Infopoint", True),  # exact match
-        ('  "Futel Official Infopoint"  ', True),  # extra quotes and spaces
-        ("Futel Official Infopoint\n", True),  # trailing newline
-        ('"Futel Official Infopoint"', True),  # embedded quotes
-        (" FUTEL\nOFFICIAL   INFOPOINT ", True),  # multiple whitespace and newline
-    ],
-)
-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_agent_tool_role_matching(role_name, should_match):
-    """Test that agent tools can match roles regardless of case, whitespace, and special characters."""
-    # Create test agent
-    test_agent = Agent(
-        role="Futel Official Infopoint",
-        goal="Answer questions about Futel",
-        backstory="Futel Football Club info",
-        allow_delegation=False,
-    )
-
-    # Create test agent tool
-    agent_tool = InternalAgentTool(
-        name="test_tool", description="Test tool", agents=[test_agent]
-    )
-
-    # Test role matching
-    result = agent_tool._execute(agent_name=role_name, task="Test task", context=None)
-
-    if should_match:
-        assert (
-            "coworker mentioned not found" not in result.lower()
-        ), f"Should find agent with role name: {role_name}"
-    else:
-        assert (
-            "coworker mentioned not found" in result.lower()
-        ), f"Should not find agent with role name: {role_name}"

tests/tools/test_tool_usage.py

@@ -231,3 +231,255 @@ def test_validate_tool_input_with_special_characters():
 
     arguments = tool_usage._validate_tool_input(tool_input)
     assert arguments == expected_arguments
+
+
+def test_validate_tool_input_none_input():
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=None,
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    arguments = tool_usage._validate_tool_input(None)
+    assert arguments == {}
+
+
+def test_validate_tool_input_valid_json():
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=None,
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    tool_input = '{"key": "value", "number": 42, "flag": true}'
+    expected_arguments = {"key": "value", "number": 42, "flag": True}
+
+    arguments = tool_usage._validate_tool_input(tool_input)
+    assert arguments == expected_arguments
+
+
+def test_validate_tool_input_python_dict():
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=None,
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    tool_input = "{'key': 'value', 'number': 42, 'flag': True}"
+    expected_arguments = {"key": "value", "number": 42, "flag": True}
+
+    arguments = tool_usage._validate_tool_input(tool_input)
+    assert arguments == expected_arguments
+
+
+def test_validate_tool_input_json5_unquoted_keys():
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=None,
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    tool_input = "{key: 'value', number: 42, flag: true}"
+    expected_arguments = {"key": "value", "number": 42, "flag": True}
+
+    arguments = tool_usage._validate_tool_input(tool_input)
+    assert arguments == expected_arguments
+
+
+def test_validate_tool_input_with_trailing_commas():
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=None,
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    tool_input = '{"key": "value", "number": 42, "flag": true,}'
+    expected_arguments = {"key": "value", "number": 42, "flag": True}
+
+    arguments = tool_usage._validate_tool_input(tool_input)
+    assert arguments == expected_arguments
+
+
+def test_validate_tool_input_invalid_input():
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=None,
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    invalid_inputs = [
+        "Just a string",
+        "['list', 'of', 'values']",
+        "12345",
+        "",
+    ]
+
+    for invalid_input in invalid_inputs:
+        with pytest.raises(Exception) as e_info:
+            tool_usage._validate_tool_input(invalid_input)
+        assert (
+            "Tool input must be a valid dictionary in JSON or Python literal format"
+            in str(e_info.value)
+        )
+
+    # Test for None input separately
+    arguments = tool_usage._validate_tool_input(None)
+    assert arguments == {}  # Expecting an empty dictionary
+
+
+def test_validate_tool_input_complex_structure():
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=None,
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    tool_input = """
+    {
+        "user": {
+            "name": "Alice",
+            "age": 30
+        },
+        "items": [
+            {"id": 1, "value": "Item1"},
+            {"id": 2, "value": "Item2",}
+        ],
+        "active": true,
+    }
+    """
+    expected_arguments = {
+        "user": {"name": "Alice", "age": 30},
+        "items": [
+            {"id": 1, "value": "Item1"},
+            {"id": 2, "value": "Item2"},
+        ],
+        "active": True,
+    }
+
+    arguments = tool_usage._validate_tool_input(tool_input)
+    assert arguments == expected_arguments
+
+
+def test_validate_tool_input_code_content():
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=None,
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    tool_input = '{"filename": "script.py", "content": "def hello():\\n    print(\'Hello, world!\')"}'
+    expected_arguments = {
+        "filename": "script.py",
+        "content": "def hello():\n    print('Hello, world!')",
+    }
+
+    arguments = tool_usage._validate_tool_input(tool_input)
+    assert arguments == expected_arguments
+
+
+def test_validate_tool_input_with_escaped_quotes():
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=None,
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    tool_input = '{"text": "He said, \\"Hello, world!\\""}'
+    expected_arguments = {"text": 'He said, "Hello, world!"'}
+
+    arguments = tool_usage._validate_tool_input(tool_input)
+    assert arguments == expected_arguments
+
+
+def test_validate_tool_input_large_json_content():
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=None,
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    # Simulate a large JSON content
+    tool_input = (
+        '{"data": ' + json.dumps([{"id": i, "value": i * 2} for i in range(1000)]) + "}"
+    )
+    expected_arguments = {"data": [{"id": i, "value": i * 2} for i in range(1000)]}
+
+    arguments = tool_usage._validate_tool_input(tool_input)
+    assert arguments == expected_arguments
+
+
+def test_validate_tool_input_none_input():
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=None,
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    arguments = tool_usage._validate_tool_input(None)
+    assert arguments == {}  # Expecting an empty dictionary

uv.lock

@@ -649,7 +649,7 @@ wheels = [
 
 [[package]]
 name = "crewai"
-version = "0.98.0"
+version = "0.100.0"
 source = { editable = "." }
 dependencies = [
     { name = "appdirs" },
@@ -659,6 +659,7 @@ dependencies = [
     { name = "click" },
     { name = "instructor" },
     { name = "json-repair" },
+    { name = "json5" },
     { name = "jsonref" },
     { name = "litellm" },
     { name = "openai" },
@@ -737,6 +738,7 @@ requires-dist = [
     { name = "fastembed", marker = "extra == 'fastembed'", specifier = ">=0.4.1" },
     { name = "instructor", specifier = ">=1.3.3" },
     { name = "json-repair", specifier = ">=0.25.2" },
+    { name = "json5", specifier = ">=0.10.0" },
     { name = "jsonref", specifier = ">=1.1.0" },
     { name = "litellm", specifier = "==1.57.4" },
     { name = "mem0ai", marker = "extra == 'mem0'", specifier = ">=0.1.29" },
@@ -2077,6 +2079,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/23/38/34cb843cee4c5c27aa5c822e90e99bf96feb3dfa705713b5b6e601d17f5c/json_repair-0.30.0-py3-none-any.whl", hash = "sha256:bda4a5552dc12085c6363ff5acfcdb0c9cafc629989a2112081b7e205828228d", size = 17641 },
 ]
 
+[[package]]
+name = "json5"
+version = "0.10.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/85/3d/bbe62f3d0c05a689c711cff57b2e3ac3d3e526380adb7c781989f075115c/json5-0.10.0.tar.gz", hash = "sha256:e66941c8f0a02026943c52c2eb34ebeb2a6f819a0be05920a6f5243cd30fd559", size = 48202 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/aa/42/797895b952b682c3dafe23b1834507ee7f02f4d6299b65aaa61425763278/json5-0.10.0-py3-none-any.whl", hash = "sha256:19b23410220a7271e8377f81ba8aacba2fdd56947fbb137ee5977cbe1f5e8dfa", size = 34049 },
+]
+
 [[package]]
 name = "jsonlines"
 version = "3.1.0"