fix: sort imports using ruff --fix

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

README.md

@@ -1,10 +1,18 @@
 <div align="center">
 
-![Logo of CrewAI, two people rowing on a boat](./docs/crewai_logo.png)
+![Logo of CrewAI](./docs/crewai_logo.png)
 
 # **CrewAI**
 
-🤖 **CrewAI**: Production-grade framework for orchestrating sophisticated AI agent systems. From simple automations to complex real-world applications, CrewAI provides precise control and deep customization. By fostering collaborative intelligence through flexible, production-ready architecture, CrewAI empowers agents to work together seamlessly, tackling complex business challenges with predictable, consistent results.
+**CrewAI**: Production-grade framework for orchestrating sophisticated AI agent systems. From simple automations to complex real-world applications, CrewAI provides precise control and deep customization. By fostering collaborative intelligence through flexible, production-ready architecture, CrewAI empowers agents to work together seamlessly, tackling complex business challenges with predictable, consistent results.
+
+**CrewAI Enterprise**
+Want to plan, build (+ no code), deploy, monitor and interare your agents: [CrewAI Enterprise](https://www.crewai.com/enterprise). Designed for complex, real-world applications, our enterprise solution offers:
+
+- **Seamless Integrations**
+- **Scalable & Secure Deployment**
+- **Actionable Insights**
+- **24/7 Support**
 
 <h3>
 
@@ -392,7 +400,7 @@ class AdvancedAnalysisFlow(Flow[MarketState]):
             goal="Gather and validate supporting market data",
             backstory="You excel at finding and correlating multiple data sources"
         )
-        
+
         analysis_task = Task(
             description="Analyze {sector} sector data for the past {timeframe}",
             expected_output="Detailed market analysis with confidence score",
@@ -403,7 +411,7 @@ class AdvancedAnalysisFlow(Flow[MarketState]):
             expected_output="Corroborating evidence and potential contradictions",
             agent=researcher
         )
-        
+
         # Demonstrate crew autonomy
         analysis_crew = Crew(
             agents=[analyst, researcher],

docs/concepts/llms.mdx

@@ -463,26 +463,32 @@ Learn how to get the most out of your LLM configuration:
 
   <Accordion title="Google">
     ```python Code
-    # Option 1. Gemini accessed with an API key.
+    # Option 1: Gemini accessed with an API key.
     # https://ai.google.dev/gemini-api/docs/api-key
     GEMINI_API_KEY=<your-api-key>
 
-    # Option 2. Vertex AI IAM credentials for Gemini, Anthropic, and anything in the Model Garden.
+    # Option 2: Vertex AI IAM credentials for Gemini, Anthropic, and Model Garden.
     # https://cloud.google.com/vertex-ai/generative-ai/docs/overview
     ```
 
-    ## GET CREDENTIALS 
+    Get credentials:
+    ```python Code
+    import json
+
     file_path = 'path/to/vertex_ai_service_account.json'
 
     # Load the JSON file
     with open(file_path, 'r') as file:
         vertex_credentials = json.load(file)
 
-    # Convert to JSON string
+    # Convert the credentials to a JSON string
     vertex_credentials_json = json.dumps(vertex_credentials)
+    ```
 
     Example usage:
     ```python Code
+    from crewai import LLM
+
     llm = LLM(
         model="gemini/gemini-1.5-pro-latest",
         temperature=0.7,

docs/concepts/memory.mdx

@@ -58,41 +58,107 @@ my_crew = Crew(
 ### Example: Use Custom Memory Instances e.g FAISS as the VectorDB
 
 ```python Code
-from crewai import Crew, Agent, Task, Process
+from crewai import Crew, Process
+from crewai.memory import LongTermMemory, ShortTermMemory, EntityMemory
+from crewai.memory.storage import LTMSQLiteStorage, RAGStorage
+from typing import List, Optional
 
 # Assemble your crew with memory capabilities
-my_crew = Crew(
-    agents=[...],
-    tasks=[...],
-    process="Process.sequential",
-    memory=True,
-    long_term_memory=EnhanceLongTermMemory(
+my_crew: Crew = Crew(
+    agents = [...],
+    tasks = [...],
+    process = Process.sequential,
+    memory = True,
+    # Long-term memory for persistent storage across sessions
+    long_term_memory = LongTermMemory(
         storage=LTMSQLiteStorage(
-            db_path="/my_data_dir/my_crew1/long_term_memory_storage.db"
+            db_path="/my_crew1/long_term_memory_storage.db"
         )
     ),
-    short_term_memory=EnhanceShortTermMemory(
-        storage=CustomRAGStorage(
-            crew_name="my_crew",
-            storage_type="short_term",
-            data_dir="//my_data_dir",
-            model=embedder["model"],
-            dimension=embedder["dimension"],
+    # Short-term memory for current context using RAG
+    short_term_memory = ShortTermMemory(
+        storage = RAGStorage(
+                embedder_config={
+                    "provider": "openai",
+                    "config": {
+                        "model": 'text-embedding-3-small'
+                    }
+                },
+                type="short_term",
+                path="/my_crew1/"
+            )
         ),
     ),
-    entity_memory=EnhanceEntityMemory(
-        storage=CustomRAGStorage(
-            crew_name="my_crew",
-            storage_type="entities",
-            data_dir="//my_data_dir",
-            model=embedder["model"],
-            dimension=embedder["dimension"],
-        ),
+    # Entity memory for tracking key information about entities
+    entity_memory = EntityMemory(
+        storage=RAGStorage(
+            embedder_config={
+                "provider": "openai",
+                "config": {
+                    "model": 'text-embedding-3-small'
+                }
+            },
+            type="short_term",
+            path="/my_crew1/"
+        )
     ),
     verbose=True,
 )
 ```
 
+## Security Considerations
+
+When configuring memory storage:
+- Use environment variables for storage paths (e.g., `CREWAI_STORAGE_DIR`)
+- Never hardcode sensitive information like database credentials
+- Consider access permissions for storage directories
+- Use relative paths when possible to maintain portability
+
+Example using environment variables:
+```python
+import os
+from crewai import Crew
+from crewai.memory import LongTermMemory
+from crewai.memory.storage import LTMSQLiteStorage
+
+# Configure storage path using environment variable
+storage_path = os.getenv("CREWAI_STORAGE_DIR", "./storage")
+crew = Crew(
+    memory=True,
+    long_term_memory=LongTermMemory(
+        storage=LTMSQLiteStorage(
+            db_path="{storage_path}/memory.db".format(storage_path=storage_path)
+        )
+    )
+)
+```
+
+## Configuration Examples
+
+### Basic Memory Configuration
+```python
+from crewai import Crew
+from crewai.memory import LongTermMemory
+
+# Simple memory configuration
+crew = Crew(memory=True)  # Uses default storage locations
+```
+
+### Custom Storage Configuration
+```python
+from crewai import Crew
+from crewai.memory import LongTermMemory
+from crewai.memory.storage import LTMSQLiteStorage
+
+# Configure custom storage paths
+crew = Crew(
+    memory=True,
+    long_term_memory=LongTermMemory(
+        storage=LTMSQLiteStorage(db_path="./memory.db")
+    )
+)
+```
+
 ## Integrating Mem0 for Enhanced User Memory
 
 [Mem0](https://mem0.ai/) is a self-improving memory layer for LLM applications, enabling personalized AI experiences. 
@@ -368,6 +434,33 @@ my_crew = Crew(
 )
 ```
 
+### Adding Custom Embedding Function
+
+```python Code
+from crewai import Crew, Agent, Task, Process
+from chromadb import Documents, EmbeddingFunction, Embeddings
+
+# Create a custom embedding function
+class CustomEmbedder(EmbeddingFunction):
+    def __call__(self, input: Documents) -> Embeddings:
+        # generate embeddings
+        return [1, 2, 3] # this is a dummy embedding
+
+my_crew = Crew(
+    agents=[...],
+    tasks=[...],
+    process=Process.sequential,
+    memory=True,
+    verbose=True,
+    embedder={
+        "provider": "custom",
+        "config": {
+            "embedder": CustomEmbedder()
+        }
+    }
+)
+```
+
 ### Resetting Memory
 
 ```shell

docs/tools/filewritetool.mdx

@@ -8,9 +8,9 @@ icon: file-pen
 
 ## Description
 
-The `FileWriterTool` is a component of the crewai_tools package, designed to simplify the process of writing content to files. 
+The `FileWriterTool` is a component of the crewai_tools package, designed to simplify the process of writing content to files with cross-platform compatibility (Windows, Linux, macOS). 
 It is particularly useful in scenarios such as generating reports, saving logs, creating configuration files, and more. 
-This tool supports creating new directories if they don't exist, making it easier to organize your output.
+This tool handles path differences across operating systems, supports UTF-8 encoding, and automatically creates directories if they don't exist, making it easier to organize your output reliably across different platforms.
 
 ## Installation
 
@@ -43,6 +43,8 @@ print(result)
 
 ## Conclusion
 
-By integrating the `FileWriterTool` into your crews, the agents can execute the process of writing content to files and creating directories. 
-This tool is essential for tasks that require saving output data, creating structured file systems, and more. By adhering to the setup and usage guidelines provided, 
-incorporating this tool into projects is straightforward and efficient.
+By integrating the `FileWriterTool` into your crews, the agents can reliably write content to files across different operating systems. 
+This tool is essential for tasks that require saving output data, creating structured file systems, and handling cross-platform file operations. 
+It's particularly recommended for Windows users who may encounter file writing issues with standard Python file operations.
+
+By adhering to the setup and usage guidelines provided, incorporating this tool into projects is straightforward and ensures consistent file writing behavior across all platforms.

src/crewai/agent.py

@@ -16,7 +16,6 @@ from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.task import Task
 from crewai.tools import BaseTool
 from crewai.tools.agent_tools.agent_tools import AgentTools
-from crewai.tools.base_tool import Tool
 from crewai.utilities import Converter, Prompts
 from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
 from crewai.utilities.converter import generate_model_description
@@ -146,7 +145,7 @@ class Agent(BaseAgent):
     def _set_knowledge(self):
         try:
             if self.knowledge_sources:
-                full_pattern = re.compile(r'[^a-zA-Z0-9\-_\r\n]|(\.\.)')
+                full_pattern = re.compile(r"[^a-zA-Z0-9\-_\r\n]|(\.\.)")
                 knowledge_agent_name = f"{re.sub(full_pattern, '_', self.role)}"
                 if isinstance(self.knowledge_sources, list) and all(
                     isinstance(k, BaseKnowledgeSource) for k in self.knowledge_sources

src/crewai/cli/reset_memories_command.py

@@ -3,11 +3,6 @@ import subprocess
 import click
 
 from crewai.cli.utils import get_crew
-from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
-from crewai.memory.entity.entity_memory import EntityMemory
-from crewai.memory.long_term.long_term_memory import LongTermMemory
-from crewai.memory.short_term.short_term_memory import ShortTermMemory
-from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
 
 
 def reset_memories_command(

src/crewai/crew.py

@@ -1,7 +1,6 @@
 import asyncio
 import json
 import re
-import sys
 import uuid
 import warnings
 from concurrent.futures import Future
@@ -381,6 +380,22 @@ class Crew(BaseModel):
 
         return self
 
+    @model_validator(mode="after")
+    def validate_must_have_non_conditional_task(self) -> "Crew":
+        """Ensure that a crew has at least one non-conditional task."""
+        if not self.tasks:
+            return self
+        non_conditional_count = sum(
+            1 for task in self.tasks if not isinstance(task, ConditionalTask)
+        )
+        if non_conditional_count == 0:
+            raise PydanticCustomError(
+                "only_conditional_tasks",
+                "Crew must include at least one non-conditional task",
+                {},
+            )
+        return self
+
     @model_validator(mode="after")
     def validate_first_task(self) -> "Crew":
         """Ensure the first task is not a ConditionalTask."""
@@ -441,6 +456,7 @@ class Crew(BaseModel):
         return self
 
 
+
     @property
     def key(self) -> str:
         source = [agent.key for agent in self.agents] + [
@@ -743,6 +759,7 @@ class Crew(BaseModel):
                     task, task_outputs, futures, task_index, was_replayed
                 )
                 if skipped_task_output:
+                    task_outputs.append(skipped_task_output)
                     continue
 
             if task.async_execution:
@@ -766,7 +783,7 @@ class Crew(BaseModel):
                     context=context,
                     tools=tools_for_task,
                 )
-                task_outputs = [task_output]
+                task_outputs.append(task_output)
                 self._process_task_result(task, task_output)
                 self._store_execution_log(task, task_output, task_index, was_replayed)
 
@@ -787,7 +804,7 @@ class Crew(BaseModel):
             task_outputs = self._process_async_tasks(futures, was_replayed)
             futures.clear()
 
-        previous_output = task_outputs[task_index - 1] if task_outputs else None
+        previous_output = task_outputs[-1] if task_outputs else None
         if previous_output is not None and not task.should_execute(previous_output):
             self._logger.log(
                 "debug",
@@ -909,11 +926,15 @@ class Crew(BaseModel):
             )
 
     def _create_crew_output(self, task_outputs: List[TaskOutput]) -> CrewOutput:
-        if len(task_outputs) != 1:
-            raise ValueError(
-                "Something went wrong. Kickoff should return only one task output."
-            )
-        final_task_output = task_outputs[0]
+        if not task_outputs:
+            raise ValueError("No task outputs available to create crew output.")
+            
+        # Filter out empty outputs and get the last valid one as the main output
+        valid_outputs = [t for t in task_outputs if t.raw]
+        if not valid_outputs:
+            raise ValueError("No valid task outputs available to create crew output.")
+        final_task_output = valid_outputs[-1]
+            
         final_string_output = final_task_output.raw
         self._finish_execution(final_string_output)
         token_usage = self.calculate_usage_metrics()
@@ -922,7 +943,7 @@ class Crew(BaseModel):
             raw=final_task_output.raw,
             pydantic=final_task_output.pydantic,
             json_dict=final_task_output.json_dict,
-            tasks_output=[task.output for task in self.tasks if task.output],
+            tasks_output=task_outputs,
             token_usage=token_usage,
         )
 
@@ -1126,20 +1147,32 @@ class Crew(BaseModel):
 
     def test(
         self,
-        n_iterations: int,
+        n_iterations: int = 1,
         openai_model_name: Optional[str] = None,
+        llm: Optional[Union[str, LLM]] = None,
         inputs: Optional[Dict[str, Any]] = None,
     ) -> None:
-        """Test and evaluate the Crew with the given inputs for n iterations concurrently using concurrent.futures."""
+        """Test and evaluate the Crew with the given inputs for n iterations.
+
+        Args:
+            n_iterations: Number of iterations to run the test
+            openai_model_name: OpenAI model name to use for evaluation (deprecated)
+            llm: LLM instance or model name to use for evaluation
+            inputs: Optional dictionary of inputs to pass to the crew
+        """
+        if not llm and not openai_model_name:
+            raise ValueError("Must provide either 'llm' or 'openai_model_name' parameter")
+        
+        model_to_use = self._get_llm_instance(llm, openai_model_name)
         test_crew = self.copy()
 
         self._test_execution_span = test_crew._telemetry.test_execution_span(
             test_crew,
             n_iterations,
             inputs,
-            openai_model_name,  # type: ignore[arg-type]
-        )  # type: ignore[arg-type]
-        evaluator = CrewEvaluator(test_crew, openai_model_name)  # type: ignore[arg-type]
+            str(model_to_use.model),
+        )
+        evaluator = CrewEvaluator(test_crew, model_to_use)
 
         for i in range(1, n_iterations + 1):
             evaluator.set_iteration(i)
@@ -1147,6 +1180,28 @@ class Crew(BaseModel):
 
         evaluator.print_crew_evaluation_result()
 
+    def _get_llm_instance(self, llm: Optional[Union[str, LLM]], openai_model_name: Optional[str]) -> LLM:
+        """Get an LLM instance from either llm or openai_model_name parameter.
+        
+        Args:
+            llm: LLM instance or model name
+            openai_model_name: OpenAI model name (deprecated)
+            
+        Returns:
+            LLM instance
+            
+        Raises:
+            ValueError: If neither llm nor openai_model_name is provided
+        """
+        model = llm if llm is not None else openai_model_name
+        if model is None:
+            raise ValueError("Must provide either 'llm' or 'openai_model_name' parameter")
+        if isinstance(model, str):
+            return LLM(model=model)
+        if not isinstance(model, LLM):
+            raise ValueError("Model must be either a string or an LLM instance")
+        return model
+
     def __repr__(self):
         return f"Crew(id={self.id}, process={self.process}, number_of_agents={len(self.agents)}, number_of_tasks={len(self.tasks)})"
 

src/crewai/llm.py

@@ -164,6 +164,7 @@ class LLM:
         self.context_window_size = 0
         self.reasoning_effort = reasoning_effort
         self.additional_params = kwargs
+        self.is_anthropic = self._is_anthropic_model(model)
 
         litellm.drop_params = True
 
@@ -178,42 +179,62 @@ class LLM:
         self.set_callbacks(callbacks)
         self.set_env_callbacks()
 
+    def _is_anthropic_model(self, model: str) -> bool:
+        """Determine if the model is from Anthropic provider.
+        
+        Args:
+            model: The model identifier string.
+            
+        Returns:
+            bool: True if the model is from Anthropic, False otherwise.
+        """
+        ANTHROPIC_PREFIXES = ('anthropic/', 'claude-', 'claude/')
+        return any(prefix in model.lower() for prefix in ANTHROPIC_PREFIXES)
+
     def call(
         self,
         messages: Union[str, List[Dict[str, str]]],
         tools: Optional[List[dict]] = None,
         callbacks: Optional[List[Any]] = None,
         available_functions: Optional[Dict[str, Any]] = None,
-    ) -> str:
-        """
-        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
-
-        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.
-
+    ) -> Union[str, Any]:
+        """High-level LLM call method.
+        
+        Args:
+            messages: Input messages for the LLM.
+                     Can be a string or list of message dictionaries.
+                     If string, it will be converted to a single user message.
+                     If list, each dict must have 'role' and 'content' keys.
+            tools: Optional list of tool schemas for function calling.
+                  Each tool should define its name, description, and parameters.
+            callbacks: Optional list of callback functions to be executed
+                      during and after the LLM call.
+            available_functions: Optional dict mapping function names to callables
+                               that can be invoked by the LLM.
+        
         Returns:
-        - str: The final text response from the LLM or the result of a tool function call.
-
+            Union[str, Any]: Either a text response from the LLM (str) or
+                           the result of a tool function call (Any).
+        
+        Raises:
+            TypeError: If messages format is invalid
+            ValueError: If response format is not supported
+            LLMContextLengthExceededException: If input exceeds model's context limit
+        
         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)
+            # Example 1: Simple string input
+            >>> response = llm.call("Return the name of a random city.")
+            >>> print(response)
+            "Paris"
+            
+            # Example 2: Message list with system and user messages
+            >>> messages = [
+            ...     {"role": "system", "content": "You are a geography expert"},
+            ...     {"role": "user", "content": "What is France's capital?"}
+            ... ]
+            >>> response = llm.call(messages)
+            >>> print(response)
+            "The capital of France is Paris."
         """
         # Validate parameters before proceeding with the call.
         self._validate_call_params()
@@ -233,10 +254,13 @@ class LLM:
                 self.set_callbacks(callbacks)
 
             try:
-                # --- 1) Prepare the parameters for the completion call
+                # --- 1) Format messages according to provider requirements
+                formatted_messages = self._format_messages_for_provider(messages)
+
+                # --- 2) Prepare the parameters for the completion call
                 params = {
                     "model": self.model,
-                    "messages": messages,
+                    "messages": formatted_messages,
                     "timeout": self.timeout,
                     "temperature": self.temperature,
                     "top_p": self.top_p,
@@ -324,6 +348,38 @@ class LLM:
                     logging.error(f"LiteLLM call failed: {str(e)}")
                 raise
 
+    def _format_messages_for_provider(self, messages: List[Dict[str, str]]) -> List[Dict[str, str]]:
+        """Format messages according to provider requirements.
+        
+        Args:
+            messages: List of message dictionaries with 'role' and 'content' keys.
+                     Can be empty or None.
+        
+        Returns:
+            List of formatted messages according to provider requirements.
+            For Anthropic models, ensures first message has 'user' role.
+        
+        Raises:
+            TypeError: If messages is None or contains invalid message format.
+        """
+        if messages is None:
+            raise TypeError("Messages cannot be None")
+            
+        # Validate message format first
+        for msg in messages:
+            if not isinstance(msg, dict) or "role" not in msg or "content" not in msg:
+                raise TypeError("Invalid message format. Each message must be a dict with 'role' and 'content' keys")
+            
+        if not self.is_anthropic:
+            return messages
+            
+        # Anthropic requires messages to start with 'user' role
+        if not messages or messages[0]["role"] == "system":
+            # If first message is system or empty, add a placeholder user message
+            return [{"role": "user", "content": "."}, *messages]
+                
+        return messages
+
     def _get_custom_llm_provider(self) -> str:
         """
         Derives the custom_llm_provider from the model string.

src/crewai/memory/entity/entity_memory.py

@@ -1,4 +1,4 @@
-from typing import Any, Optional
+from typing import Optional
 
 from pydantic import PrivateAttr
 

src/crewai/memory/memory.py

@@ -1,15 +1,15 @@
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Optional
 
 from pydantic import BaseModel
 
-from crewai.memory.storage.rag_storage import RAGStorage
-
 
 class Memory(BaseModel):
     """
     Base class for memory, now supporting agent tags and generic metadata.
     """
 
+    embedder_config: Optional[Dict[str, Any]] = None
+
     storage: Any
 
     def __init__(self, storage: Any, **data: Any):

src/crewai/memory/storage/base_rag_storage.py

@@ -13,7 +13,7 @@ class BaseRAGStorage(ABC):
         self,
         type: str,
         allow_reset: bool = True,
-        embedder_config: Optional[Any] = None,
+        embedder_config: Optional[Dict[str, Any]] = None,
         crew: Any = None,
     ):
         self.type = type

src/crewai/task.py

@@ -674,19 +674,32 @@ class Task(BaseModel):
             return OutputFormat.PYDANTIC
         return OutputFormat.RAW
 
-    def _save_file(self, result: Any) -> None:
+    def _save_file(self, result: Union[Dict, str, Any]) -> None:
         """Save task output to a file.
 
+        Note:
+            For cross-platform file writing, especially on Windows, consider using FileWriterTool
+            from the crewai_tools package:
+                pip install 'crewai[tools]'
+                from crewai_tools import FileWriterTool
+
         Args:
             result: The result to save to the file. Can be a dict or any stringifiable object.
 
         Raises:
             ValueError: If output_file is not set
-            RuntimeError: If there is an error writing to the file
+            RuntimeError: If there is an error writing to the file. For cross-platform
+                compatibility, especially on Windows, use FileWriterTool from crewai_tools
+                package.
         """
         if self.output_file is None:
             raise ValueError("output_file is not set.")
 
+        FILEWRITER_RECOMMENDATION = (
+            "For cross-platform file writing, especially on Windows, "
+            "use FileWriterTool from crewai_tools package."
+        )
+
         try:
             resolved_path = Path(self.output_file).expanduser().resolve()
             directory = resolved_path.parent
@@ -702,7 +715,12 @@ class Task(BaseModel):
                 else:
                     file.write(str(result))
         except (OSError, IOError) as e:
-            raise RuntimeError(f"Failed to save output file: {e}")
+            raise RuntimeError(
+                "\n".join([
+                    f"Failed to save output file: {e}",
+                    FILEWRITER_RECOMMENDATION
+                ])
+            )
         return None
 
     def __repr__(self):

src/crewai/utilities/embedding_configurator.py

@@ -1,5 +1,5 @@
 import os
-from typing import Any, Dict, cast
+from typing import Any, Dict, Optional, cast
 
 from chromadb import Documents, EmbeddingFunction, Embeddings
 from chromadb.api.types import validate_embedding_function
@@ -18,11 +18,12 @@ class EmbeddingConfigurator:
             "bedrock": self._configure_bedrock,
             "huggingface": self._configure_huggingface,
             "watson": self._configure_watson,
+            "custom": self._configure_custom,
         }
 
     def configure_embedder(
         self,
-        embedder_config: Dict[str, Any] | None = None,
+        embedder_config: Optional[Dict[str, Any]] = None,
     ) -> EmbeddingFunction:
         """Configures and returns an embedding function based on the provided config."""
         if embedder_config is None:
@@ -30,20 +31,19 @@ class EmbeddingConfigurator:
 
         provider = embedder_config.get("provider")
         config = embedder_config.get("config", {})
-        model_name = config.get("model")
-
-        if isinstance(provider, EmbeddingFunction):
-            try:
-                validate_embedding_function(provider)
-                return provider
-            except Exception as e:
-                raise ValueError(f"Invalid custom embedding function: {str(e)}")
+        model_name = config.get("model") if provider != "custom" else None
 
         if provider not in self.embedding_functions:
             raise Exception(
                 f"Unsupported embedding provider: {provider}, supported providers: {list(self.embedding_functions.keys())}"
             )
-        return self.embedding_functions[provider](config, model_name)
+
+        embedding_function = self.embedding_functions[provider]
+        return (
+            embedding_function(config)
+            if provider == "custom"
+            else embedding_function(config, model_name)
+        )
 
     @staticmethod
     def _create_default_embedding_function():
@@ -64,6 +64,13 @@ class EmbeddingConfigurator:
         return OpenAIEmbeddingFunction(
             api_key=config.get("api_key") or os.getenv("OPENAI_API_KEY"),
             model_name=model_name,
+            api_base=config.get("api_base", None),
+            api_type=config.get("api_type", None),
+            api_version=config.get("api_version", None),
+            default_headers=config.get("default_headers", None),
+            dimensions=config.get("dimensions", None),
+            deployment_id=config.get("deployment_id", None),
+            organization_id=config.get("organization_id", None),
         )
 
     @staticmethod
@@ -78,6 +85,10 @@ class EmbeddingConfigurator:
             api_type=config.get("api_type", "azure"),
             api_version=config.get("api_version"),
             model_name=model_name,
+            default_headers=config.get("default_headers"),
+            dimensions=config.get("dimensions"),
+            deployment_id=config.get("deployment_id"),
+            organization_id=config.get("organization_id"),
         )
 
     @staticmethod
@@ -100,6 +111,8 @@ class EmbeddingConfigurator:
         return GoogleVertexEmbeddingFunction(
             model_name=model_name,
             api_key=config.get("api_key"),
+            project_id=config.get("project_id"),
+            region=config.get("region"),
         )
 
     @staticmethod
@@ -111,6 +124,7 @@ class EmbeddingConfigurator:
         return GoogleGenerativeAiEmbeddingFunction(
             model_name=model_name,
             api_key=config.get("api_key"),
+            task_type=config.get("task_type"),
         )
 
     @staticmethod
@@ -195,3 +209,28 @@ class EmbeddingConfigurator:
                     raise e
 
         return WatsonEmbeddingFunction()
+
+    @staticmethod
+    def _configure_custom(config):
+        custom_embedder = config.get("embedder")
+        if isinstance(custom_embedder, EmbeddingFunction):
+            try:
+                validate_embedding_function(custom_embedder)
+                return custom_embedder
+            except Exception as e:
+                raise ValueError(f"Invalid custom embedding function: {str(e)}")
+        elif callable(custom_embedder):
+            try:
+                instance = custom_embedder()
+                if isinstance(instance, EmbeddingFunction):
+                    validate_embedding_function(instance)
+                    return instance
+                raise ValueError(
+                    "Custom embedder does not create an EmbeddingFunction instance"
+                )
+            except Exception as e:
+                raise ValueError(f"Error instantiating custom embedder: {str(e)}")
+        else:
+            raise ValueError(
+                "Custom embedder must be an instance of `EmbeddingFunction` or a callable that creates one"
+            )

src/crewai/utilities/evaluators/crew_evaluator_handler.py

@@ -1,4 +1,5 @@
 from collections import defaultdict
+from typing import Union
 
 from pydantic import BaseModel, Field
 from rich.box import HEAVY_EDGE
@@ -6,6 +7,7 @@ from rich.console import Console
 from rich.table import Table
 
 from crewai.agent import Agent
+from crewai.llm import LLM
 from crewai.task import Task
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry import Telemetry
@@ -32,9 +34,9 @@ class CrewEvaluator:
     run_execution_times: defaultdict = defaultdict(list)
     iteration: int = 0
 
-    def __init__(self, crew, openai_model_name: str):
+    def __init__(self, crew, llm: Union[str, LLM]):
         self.crew = crew
-        self.openai_model_name = openai_model_name
+        self.llm = LLM(model=llm) if isinstance(llm, str) else llm
         self._telemetry = Telemetry()
         self._setup_for_evaluating()
 
@@ -51,7 +53,7 @@ class CrewEvaluator:
             ),
             backstory="Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in the crew based on the tasks they have performed",
             verbose=False,
-            llm=self.openai_model_name,
+            llm=self.llm,
         )
 
     def _evaluation_task(
@@ -181,7 +183,7 @@ class CrewEvaluator:
                 self.crew,
                 evaluation_result.pydantic.quality,
                 current_task.execution_duration,
-                self.openai_model_name,
+                self.llm.model,
             )
             self.tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
             self.run_execution_times[self.iteration].append(

tests/crew_test.py

@@ -49,6 +49,39 @@ writer = Agent(
 )
 
 
+def test_crew_with_only_conditional_tasks_raises_error():
+    """Test that creating a crew with only conditional tasks raises an error."""
+    def condition_func(task_output: TaskOutput) -> bool:
+        return True
+
+    conditional1 = ConditionalTask(
+        description="Conditional task 1",
+        expected_output="Output 1",
+        agent=researcher,
+        condition=condition_func,
+    )
+    conditional2 = ConditionalTask(
+        description="Conditional task 2",
+        expected_output="Output 2",
+        agent=researcher,
+        condition=condition_func,
+    )
+    conditional3 = ConditionalTask(
+        description="Conditional task 3",
+        expected_output="Output 3",
+        agent=researcher,
+        condition=condition_func,
+    )
+
+    with pytest.raises(
+        pydantic_core._pydantic_core.ValidationError,
+        match="Crew must include at least one non-conditional task",
+    ):
+        Crew(
+            agents=[researcher],
+            tasks=[conditional1, conditional2, conditional3],
+        )
+
 def test_crew_config_conditional_requirement():
     with pytest.raises(ValueError):
         Crew(process=Process.sequential)
@@ -2060,6 +2093,195 @@ def test_tools_with_custom_caching():
             assert result.raw == "3"
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_conditional_task_uses_last_output():
+    """Test that conditional tasks use the last task output for condition evaluation."""
+    task1 = Task(
+        description="First task",
+        expected_output="First output",
+        agent=researcher,
+    )
+    def condition_fails(task_output: TaskOutput) -> bool:
+        # This condition will never be met
+        return "never matches" in task_output.raw.lower()
+    
+    def condition_succeeds(task_output: TaskOutput) -> bool:
+        # This condition will match first task's output
+        return "first success" in task_output.raw.lower()
+    
+    conditional_task1 = ConditionalTask(
+        description="Second task - conditional that fails condition",
+        expected_output="Second output",
+        agent=researcher,
+        condition=condition_fails,
+    )
+    
+    conditional_task2 = ConditionalTask(
+        description="Third task - conditional that succeeds using first task output",
+        expected_output="Third output",
+        agent=writer,
+        condition=condition_succeeds,
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[task1, conditional_task1, conditional_task2],
+    )
+
+    # Mock outputs for tasks
+    mock_first = TaskOutput(
+        description="First task output",
+        raw="First success output",  # Will be used by third task's condition
+        agent=researcher.role,
+    )
+    mock_skipped = TaskOutput(
+        description="Second task output",
+        raw="",  # Empty output since condition fails
+        agent=researcher.role,
+    )
+    mock_third = TaskOutput(
+        description="Third task output",
+        raw="Third task executed",  # Output when condition succeeds using first task output
+        agent=writer.role,
+    )
+    
+    # Set up mocks for task execution and conditional logic
+    with patch.object(ConditionalTask, "should_execute") as mock_should_execute:
+        # First conditional fails, second succeeds
+        mock_should_execute.side_effect = [False, True]
+        
+        with patch.object(Task, "execute_sync") as mock_execute:
+            mock_execute.side_effect = [mock_first, mock_third]
+            result = crew.kickoff()
+            
+            # Verify execution behavior
+            assert mock_execute.call_count == 2  # Only first and third tasks execute
+            assert mock_should_execute.call_count == 2  # Both conditionals checked
+            
+            # Verify outputs collection
+            assert len(result.tasks_output) == 3
+            assert result.tasks_output[0].raw == "First success output"  # First task succeeded
+            assert result.tasks_output[1].raw == ""  # Second task skipped (condition failed)
+            assert result.tasks_output[2].raw == "Third task executed"  # Third task used first task's output
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_conditional_tasks_result_collection():
+    """Test that task outputs are properly collected based on execution status."""
+    task1 = Task(
+        description="Normal task that always executes",
+        expected_output="First output",
+        agent=researcher,
+    )
+    
+    def condition_never_met(task_output: TaskOutput) -> bool:
+        return "never matches" in task_output.raw.lower()
+    
+    def condition_always_met(task_output: TaskOutput) -> bool:
+        return "success" in task_output.raw.lower()
+    
+    task2 = ConditionalTask(
+        description="Conditional task that never executes",
+        expected_output="Second output",
+        agent=researcher,
+        condition=condition_never_met,
+    )
+    
+    task3 = ConditionalTask(
+        description="Conditional task that always executes",
+        expected_output="Third output",
+        agent=writer,
+        condition=condition_always_met,
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[task1, task2, task3],
+    )
+
+    # Mock outputs for different execution paths
+    mock_success = TaskOutput(
+        description="Success output",
+        raw="Success output",  # Triggers third task's condition
+        agent=researcher.role,
+    )
+    mock_skipped = TaskOutput(
+        description="Skipped output",
+        raw="",  # Empty output for skipped task
+        agent=researcher.role,
+    )
+    mock_conditional = TaskOutput(
+        description="Conditional output",
+        raw="Conditional task executed",
+        agent=writer.role,
+    )
+    
+    # Set up mocks for task execution and conditional logic
+    with patch.object(ConditionalTask, "should_execute") as mock_should_execute:
+        # First conditional fails, second succeeds
+        mock_should_execute.side_effect = [False, True]
+        
+        with patch.object(Task, "execute_sync") as mock_execute:
+            mock_execute.side_effect = [mock_success, mock_conditional]
+            result = crew.kickoff()
+            
+            # Verify execution behavior
+            assert mock_execute.call_count == 2  # Only first and third tasks execute
+            assert mock_should_execute.call_count == 2  # Both conditionals checked
+            
+            # Verify task output collection
+            assert len(result.tasks_output) == 3
+            assert result.tasks_output[0].raw == "Success output"      # Normal task executed
+            assert result.tasks_output[1].raw == ""                    # Second task skipped
+            assert result.tasks_output[2].raw == "Conditional task executed"  # Third task executed
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_multiple_conditional_tasks():
+    """Test that having multiple conditional tasks in sequence works correctly."""
+    task1 = Task(
+        description="Initial research task",
+        expected_output="Research output",
+        agent=researcher,
+    )
+    
+    def condition1(task_output: TaskOutput) -> bool:
+        return "success" in task_output.raw.lower()
+    
+    def condition2(task_output: TaskOutput) -> bool:
+        return "proceed" in task_output.raw.lower()
+    
+    task2 = ConditionalTask(
+        description="First conditional task",
+        expected_output="Conditional output 1",
+        agent=writer,
+        condition=condition1,
+    )
+    
+    task3 = ConditionalTask(
+        description="Second conditional task",
+        expected_output="Conditional output 2",
+        agent=writer,
+        condition=condition2,
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[task1, task2, task3],
+    )
+
+    # Mock different task outputs to test conditional logic
+    mock_success = TaskOutput(
+        description="Mock success",
+        raw="Success and proceed output",
+        agent=researcher.role,
+    )
+    
+    # Set up mocks for task execution
+    with patch.object(Task, "execute_sync", return_value=mock_success) as mock_execute:
+        result = crew.kickoff()
+        # Verify all tasks were executed (no IndexError)
+        assert mock_execute.call_count == 3
+        assert len(result.tasks_output) == 3
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_using_contextual_memory():
     from unittest.mock import patch
@@ -3084,8 +3306,7 @@ def test_conditional_should_execute():
 
 @mock.patch("crewai.crew.CrewEvaluator")
 @mock.patch("crewai.crew.Crew.copy")
-@mock.patch("crewai.crew.Crew.kickoff")
-def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
+def test_crew_testing_function(copy_mock, crew_evaluator_mock):
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
         expected_output="5 bullet points with a paragraph for each idea.",
@@ -3097,25 +3318,28 @@ def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
         tasks=[task],
     )
 
-    # Create a mock for the copied crew
-    copy_mock.return_value = crew
+    # Create a mock for the copied crew with a mock kickoff method
+    copied_crew = MagicMock()
+    copy_mock.return_value = copied_crew
+
+    # Create a mock for the CrewEvaluator instance
+    evaluator_instance = MagicMock()
+    crew_evaluator_mock.return_value = evaluator_instance
 
     n_iterations = 2
     crew.test(n_iterations, openai_model_name="gpt-4o-mini", inputs={"topic": "AI"})
 
     # Ensure kickoff is called on the copied crew
-    kickoff_mock.assert_has_calls(
+    copied_crew.kickoff.assert_has_calls(
         [mock.call(inputs={"topic": "AI"}), mock.call(inputs={"topic": "AI"})]
     )
 
-    crew_evaluator.assert_has_calls(
-        [
-            mock.call(crew, "gpt-4o-mini"),
-            mock.call().set_iteration(1),
-            mock.call().set_iteration(2),
-            mock.call().print_crew_evaluation_result(),
-        ]
-    )
+    # Verify CrewEvaluator interactions
+    # We don't check the exact LLM object since it's created internally
+    assert len(crew_evaluator_mock.mock_calls) == 4
+    assert crew_evaluator_mock.mock_calls[1] == mock.call().set_iteration(1)
+    assert crew_evaluator_mock.mock_calls[2] == mock.call().set_iteration(2)
+    assert crew_evaluator_mock.mock_calls[3] == mock.call().print_crew_evaluation_result()
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])

tests/llm_test.py

@@ -286,6 +286,79 @@ def test_o3_mini_reasoning_effort_medium():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.fixture
+def anthropic_llm():
+    """Fixture providing an Anthropic LLM instance."""
+    return LLM(model="anthropic/claude-3-sonnet")
+
+@pytest.fixture
+def system_message():
+    """Fixture providing a system message."""
+    return {"role": "system", "content": "test"}
+
+@pytest.fixture
+def user_message():
+    """Fixture providing a user message."""
+    return {"role": "user", "content": "test"}
+
+def test_anthropic_message_formatting_edge_cases(anthropic_llm):
+    """Test edge cases for Anthropic message formatting."""
+    # Test None messages
+    with pytest.raises(TypeError, match="Messages cannot be None"):
+        anthropic_llm._format_messages_for_provider(None)
+        
+    # Test empty message list
+    formatted = anthropic_llm._format_messages_for_provider([])
+    assert len(formatted) == 1
+    assert formatted[0]["role"] == "user"
+    assert formatted[0]["content"] == "."
+    
+    # Test invalid message format
+    with pytest.raises(TypeError, match="Invalid message format"):
+        anthropic_llm._format_messages_for_provider([{"invalid": "message"}])
+
+def test_anthropic_model_detection():
+    """Test Anthropic model detection with various formats."""
+    models = [
+        ("anthropic/claude-3", True),
+        ("claude-instant", True),
+        ("claude/v1", True),
+        ("gpt-4", False),
+        ("", False),
+        ("anthropomorphic", False),  # Should not match partial words
+    ]
+    
+    for model, expected in models:
+        llm = LLM(model=model)
+        assert llm.is_anthropic == expected, f"Failed for model: {model}"
+
+def test_anthropic_message_formatting(anthropic_llm, system_message, user_message):
+    """Test Anthropic message formatting with fixtures."""
+    # Test when first message is system
+    formatted = anthropic_llm._format_messages_for_provider([system_message])
+    assert len(formatted) == 2
+    assert formatted[0]["role"] == "user"
+    assert formatted[0]["content"] == "."
+    assert formatted[1] == system_message
+
+    # Test when first message is already user
+    formatted = anthropic_llm._format_messages_for_provider([user_message])
+    assert len(formatted) == 1
+    assert formatted[0] == user_message
+
+    # Test with empty message list
+    formatted = anthropic_llm._format_messages_for_provider([])
+    assert len(formatted) == 1
+    assert formatted[0]["role"] == "user"
+    assert formatted[0]["content"] == "."
+
+    # Test with non-Anthropic model (should not modify messages)
+    non_anthropic_llm = LLM(model="gpt-4")
+    formatted = non_anthropic_llm._format_messages_for_provider([system_message])
+    assert len(formatted) == 1
+    assert formatted[0] == system_message
+
+
 def test_deepseek_r1_with_open_router():
     if not os.getenv("OPEN_ROUTER_API_KEY"):
         pytest.skip("OPEN_ROUTER_API_KEY not set; skipping test.")

tests/utilities/evaluators/cassettes/test_crew_test_with_custom_llm.yaml

@@ -0,0 +1,942 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are test. test\nYour personal
+      goal is: test\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\n\nThis is the expected
+      criteria for your final answer: test output\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-4", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      authorization:
+      - Bearer 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
+      connection:
+      - keep-alive
+      content-length:
+      - '780'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      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-AzAMqMWFX8hC1szIKxWNSyXm0SPFi\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1739141224,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I am prepared to conduct the test efficiently.\\n\\nFinal
+      Answer: The test output that aligns with the given criteria is a detailed description
+      of the testing process, providing a thorough understanding for anyone reviewing
+      it. The output not only contains the raw data or results but also includes step-by-step
+      documentation of the process employed, thoughts and reasoning behind each step,
+      deviations if any from the original plan, and how these deviations impacted
+      the results. In addition, it captures any errors or unexpected occurrences during
+      the course of the test, and proposes possible explanations or solutions for
+      these. It is detailed yet comprehensible, catering to both technical and non-technical
+      audiences. It is a result of meticulous planning, diligent execution, and robust
+      post-test analysis, making it a complete content.\",\n        \"refusal\": null\n
+      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 149,\n    \"completion_tokens\":
+      151,\n    \"total_tokens\": 300,\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\": null\n}\n"
+    headers:
+      CF-RAY:
+      - 90f7662cab11ba33-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 09 Feb 2025 22:47:09 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=p1aGVyahvfLAvEwvbX0FMmrN5o18PpVAu2dG_dTgMSU-1739141229-1.0.1.1-_q7aCslZTr11IMFZ81VgyuqsGiqTARFPANUvBEWM_0dZdb97Py78KE1omxdNv5F1pFKoWUqA1kEF2wzQ2wz4aA;
+        path=/; expires=Sun, 09-Feb-25 23:17:09 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=bsF0jwE67cS.ywAaQU59jKPFC03S1dvynClHm_wTQik-1739141229143-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '4585'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '1000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '999822'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 10ms
+      x-request-id:
+      - req_1ba81a80018602119b871a7a42d7becf
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      Ct8LCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkStgsKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRL5AQoQT8uAOJ+suOhFs22RW56o6BII0Ob64+TP3XQqE0NyZXcgVGVzdCBFeGVjdXRp
+      b24wATk1IlKguqsiGEGGgWOguqsiGEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjEwMC4xSi4KCGNy
+      ZXdfa2V5EiIKIGZlYjFlMjFiMzI1NmM1OWE2NDcxNTJhZmRkNjYzMjJlSjEKB2NyZXdfaWQSJgok
+      M2Q1MGJkYWItZDI1NS00MjFiLThkMzMtZjZmOTAzMThhOWQwShEKCml0ZXJhdGlvbnMSAwoBMUoV
+      Cgptb2RlbF9uYW1lEgcKBWdwdC00egIYAYUBAAEAABKSBwoQgzrB2KxaHe9FwPNktJHbFRIIT8gM
+      r7rSvJUqDENyZXcgQ3JlYXRlZDABOW4kaqC6qyIYQe+yeaC6qyIYShsKDmNyZXdhaV92ZXJzaW9u
+      EgkKBzAuMTAwLjFKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMi43Si4KCGNyZXdfa2V5EiIKIGZl
+      YjFlMjFiMzI1NmM1OWE2NDcxNTJhZmRkNjYzMjJlSjEKB2NyZXdfaWQSJgokM2Q1MGJkYWItZDI1
+      NS00MjFiLThkMzMtZjZmOTAzMThhOWQwShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEK
+      C2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1i
+      ZXJfb2ZfYWdlbnRzEgIYAUrFAgoLY3Jld19hZ2VudHMStQIKsgJbeyJrZXkiOiAiOTc2ZjhmNTBh
+      Y2NmZWJhMjIzZTQ5YzQyYjE2ZTk5ZTYiLCAiaWQiOiAiN2E3NmZjNmYtZTI5YS00MDBlLWI0NGEt
+      NzAyMDNlMzg1Y2RmIiwgInJvbGUiOiAidGVzdCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0
+      ZXIiOiAyNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxs
+      bSI6ICJncHQtNCIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4
+      ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtd
+      fV1K+QEKCmNyZXdfdGFza3MS6gEK5wFbeyJrZXkiOiAiZGE5NWViZGIzNmU0Y2RmOTJkZjZhNmRk
+      MTZiY2VlMGUiLCAiaWQiOiAiNTcwYmJlYjQtYzkzNi00NTNkLTg2MjktYzhjMDM0ODA5NDhjIiwg
+      ImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRf
+      cm9sZSI6ICJ0ZXN0IiwgImFnZW50X2tleSI6ICI5NzZmOGY1MGFjY2ZlYmEyMjNlNDljNDJiMTZl
+      OTllNiIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChAus8hZAJcezzXdP2XqhVyF
+      Egi1wnliqIdQdSoMVGFzayBDcmVhdGVkMAE5nneIoLqrIhhBKDyJoLqrIhhKLgoIY3Jld19rZXkS
+      IgogZmViMWUyMWIzMjU2YzU5YTY0NzE1MmFmZGQ2NjMyMmVKMQoHY3Jld19pZBImCiQzZDUwYmRh
+      Yi1kMjU1LTQyMWItOGQzMy1mNmY5MDMxOGE5ZDBKLgoIdGFza19rZXkSIgogZGE5NWViZGIzNmU0
+      Y2RmOTJkZjZhNmRkMTZiY2VlMGVKMQoHdGFza19pZBImCiQ1NzBiYmViNC1jOTM2LTQ1M2QtODYy
+      OS1jOGMwMzQ4MDk0OGN6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1506'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Sun, 09 Feb 2025 22:47:09 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Task Execution Evaluator.
+      Evaluator agent for crew evaluation with precise capabilities to evaluate the
+      performance of the agents in the crew based on the tasks they have performed\nYour
+      personal goal is: Your goal is to evaluate the performance of the agents in
+      the crew based on the tasks they have performed using score from 1 to 10 evaluating
+      on completion, quality, and overall performance.\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:
+      Based on the task description and the expected output, compare and evaluate
+      the performance of the agents in the crew based on the Task Output they have
+      performed using score from 1 to 10 evaluating on completion, quality, and overall
+      performance.task_description: test task_expected_output: test output agent:
+      test agent_goal: test Task Output: The test output that aligns with the given
+      criteria is a detailed description of the testing process, providing a thorough
+      understanding for anyone reviewing it. The output not only contains the raw
+      data or results but also includes step-by-step documentation of the process
+      employed, thoughts and reasoning behind each step, deviations if any from the
+      original plan, and how these deviations impacted the results. In addition, it
+      captures any errors or unexpected occurrences during the course of the test,
+      and proposes possible explanations or solutions for these. It is detailed yet
+      comprehensible, catering to both technical and non-technical audiences. It is
+      a result of meticulous planning, diligent execution, and robust post-test analysis,
+      making it a complete content.\n\nThis is the expected criteria for your final
+      answer: Evaluation Score from 1 to 10 based on the performance of the agents
+      on the tasks\nyou MUST return the actual complete content as the final answer,
+      not a summary.\nEnsure your final answer contains only the content in the following
+      format: {\n  \"quality\": float\n}\n\nEnsure the final output does not include
+      any code block markers like ```json or ```python.\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-4", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      authorization:
+      - Bearer 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
+      connection:
+      - keep-alive
+      content-length:
+      - '2523'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=p1aGVyahvfLAvEwvbX0FMmrN5o18PpVAu2dG_dTgMSU-1739141229-1.0.1.1-_q7aCslZTr11IMFZ81VgyuqsGiqTARFPANUvBEWM_0dZdb97Py78KE1omxdNv5F1pFKoWUqA1kEF2wzQ2wz4aA;
+        _cfuvid=bsF0jwE67cS.ywAaQU59jKPFC03S1dvynClHm_wTQik-1739141229143-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      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-AzAMvAOSw5847reo2vh61focjnyK2\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1739141229,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Based on the given task output, I can
+      determine that the test agent has performed impressively well. Their work is
+      comprehensive, catering to both non-technical and technical audiences and includes
+      complete and detailed process documentation. Further, the way they detect and
+      elaborate deviances and errors shows their meticulousness and efficiency. Their
+      planning, execution, and analysis are sound.\\n\\nFinal Answer: The quality
+      of this task is admirable, paying attention to details and meticulously planning
+      and reasoning behind each step. Considering all these, on a scale from 1 to
+      10, I would rate the task performed by the test agent as follows:\\n\\n{\\n
+      \ \\\"quality\\\": 9.5\\n}\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      471,\n    \"completion_tokens\": 133,\n    \"total_tokens\": 604,\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\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 90f7664a581eba33-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 09 Feb 2025 22:47:14 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:
+      - '4884'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '1000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '999388'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 36ms
+      x-request-id:
+      - req_0335ff13c1777c1bcdbee89879bc132c
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CvsNCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS0g0KEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKZAgoQJQy0LAglHxA7Ok+n0Gmi9hIIybabc5KDQlkqG0NyZXcgSW5kaXZpZHVhbCBU
+      ZXN0IFJlc3VsdDABOQK5tem8qyIYQVTw0+m8qyIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTAw
+      LjFKLgoIY3Jld19rZXkSIgogZmViMWUyMWIzMjU2YzU5YTY0NzE1MmFmZGQ2NjMyMmVKMQoHY3Jl
+      d19pZBImCiQzZDUwYmRhYi1kMjU1LTQyMWItOGQzMy1mNmY5MDMxOGE5ZDBKEAoHcXVhbGl0eRIF
+      CgM5LjVKFwoJZXhlY190aW1lEgoKCDQuODA5MTc4ShUKCm1vZGVsX25hbWUSBwoFZ3B0LTR6AhgB
+      hQEAAQAAEvkBChCnePSvJJg/cFeYF3HlEvyVEgh3YAewpHkssyoTQ3JldyBUZXN0IEV4ZWN1dGlv
+      bjABOeiBSOq8qyIYQQWTV+q8qyIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTAwLjFKLgoIY3Jl
+      d19rZXkSIgogZmViMWUyMWIzMjU2YzU5YTY0NzE1MmFmZGQ2NjMyMmVKMQoHY3Jld19pZBImCiQ2
+      YzYyNmEyZi05OGRlLTQ2ODAtOWJhNC01NWVkYzdmODhiZTNKEQoKaXRlcmF0aW9ucxIDCgExShUK
+      Cm1vZGVsX25hbWUSBwoFZ3B0LTR6AhgBhQEAAQAAEpIHChB0Gz3vlppAjams1hbMI/RQEggPCufR
+      e9thfSoMQ3JldyBDcmVhdGVkMAE5X3td6ryrIhhBWNhr6ryrIhhKGwoOY3Jld2FpX3ZlcnNpb24S
+      CQoHMC4xMDAuMUoaCg5weXRob25fdmVyc2lvbhIICgYzLjEyLjdKLgoIY3Jld19rZXkSIgogZmVi
+      MWUyMWIzMjU2YzU5YTY0NzE1MmFmZGQ2NjMyMmVKMQoHY3Jld19pZBImCiQ2YzYyNmEyZi05OGRl
+      LTQ2ODAtOWJhNC01NWVkYzdmODhiZTNKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoL
+      Y3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJl
+      cl9vZl9hZ2VudHMSAhgBSsUCCgtjcmV3X2FnZW50cxK1AgqyAlt7ImtleSI6ICI5NzZmOGY1MGFj
+      Y2ZlYmEyMjNlNDljNDJiMTZlOTllNiIsICJpZCI6ICJkYTA4M2Q5ZS0xOWU5LTQyMzAtYjZmNC0y
+      NjlhNzM1NzViOWQiLCAicm9sZSI6ICJ0ZXN0IiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRl
+      ciI6IDI1LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxt
+      IjogImdwdC00IiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhl
+      Y3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119
+      XUr5AQoKY3Jld190YXNrcxLqAQrnAVt7ImtleSI6ICJkYTk1ZWJkYjM2ZTRjZGY5MmRmNmE2ZGQx
+      NmJjZWUwZSIsICJpZCI6ICJhNGUwYjM1Ny0zMDBlLTQ0MjMtYTU1My0yZTZlMWQxODg1M2MiLCAi
+      YXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9y
+      b2xlIjogInRlc3QiLCAiYWdlbnRfa2V5IjogIjk3NmY4ZjUwYWNjZmViYTIyM2U0OWM0MmIxNmU5
+      OWU2IiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEC5jZek+sSlZP8lSwF5zTSYS
+      CIHcVJhIpsWuKgxUYXNrIENyZWF0ZWQwATl9vnrqvKsiGEFgjnvqvKsiGEouCghjcmV3X2tleRIi
+      CiBmZWIxZTIxYjMyNTZjNTlhNjQ3MTUyYWZkZDY2MzIyZUoxCgdjcmV3X2lkEiYKJDZjNjI2YTJm
+      LTk4ZGUtNDY4MC05YmE0LTU1ZWRjN2Y4OGJlM0ouCgh0YXNrX2tleRIiCiBkYTk1ZWJkYjM2ZTRj
+      ZGY5MmRmNmE2ZGQxNmJjZWUwZUoxCgd0YXNrX2lkEiYKJGE0ZTBiMzU3LTMwMGUtNDQyMy1hNTUz
+      LTJlNmUxZDE4ODUzY3oCGAGFAQABAAA=
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1790'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Sun, 09 Feb 2025 22:47:14 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are test. test\nYour personal
+      goal is: test\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\n\nThis is the expected
+      criteria for your final answer: test output\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-4", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      authorization:
+      - Bearer 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
+      connection:
+      - keep-alive
+      content-length:
+      - '780'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=p1aGVyahvfLAvEwvbX0FMmrN5o18PpVAu2dG_dTgMSU-1739141229-1.0.1.1-_q7aCslZTr11IMFZ81VgyuqsGiqTARFPANUvBEWM_0dZdb97Py78KE1omxdNv5F1pFKoWUqA1kEF2wzQ2wz4aA;
+        _cfuvid=bsF0jwE67cS.ywAaQU59jKPFC03S1dvynClHm_wTQik-1739141229143-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      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-AzAN0cgAktzQnGukedPNpZsTy461c\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1739141234,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I have an understanding of the task at
+      hand and am ready to provide an in-depth and comprehensive answer.\\n\\nFinal
+      Answer: As per the requirement of the task to provide a complete output, I am
+      returning this test output as my final answer. It is not a summary, but rather
+      a full and comprehensive response that fully addresses the question and expectations
+      set forth. Your test output is ready.\",\n        \"refusal\": null\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 149,\n    \"completion_tokens\": 77,\n
+      \   \"total_tokens\": 226,\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\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 90f76669bd9eba33-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 09 Feb 2025 22:47:17 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:
+      - '3379'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '1000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '999822'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 10ms
+      x-request-id:
+      - req_977371ae262154885689d766016ed132
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Task Execution Evaluator.
+      Evaluator agent for crew evaluation with precise capabilities to evaluate the
+      performance of the agents in the crew based on the tasks they have performed\nYour
+      personal goal is: Your goal is to evaluate the performance of the agents in
+      the crew based on the tasks they have performed using score from 1 to 10 evaluating
+      on completion, quality, and overall performance.\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:
+      Based on the task description and the expected output, compare and evaluate
+      the performance of the agents in the crew based on the Task Output they have
+      performed using score from 1 to 10 evaluating on completion, quality, and overall
+      performance.task_description: test task_expected_output: test output agent:
+      test agent_goal: test Task Output: As per the requirement of the task to provide
+      a complete output, I am returning this test output as my final answer. It is
+      not a summary, but rather a full and comprehensive response that fully addresses
+      the question and expectations set forth. Your test output is ready.\n\nThis
+      is the expected criteria for your final answer: Evaluation Score from 1 to 10
+      based on the performance of the agents on the tasks\nyou MUST return the actual
+      complete content as the final answer, not a summary.\nEnsure your final answer
+      contains only the content in the following format: {\n  \"quality\": float\n}\n\nEnsure
+      the final output does not include any code block markers like ```json or ```python.\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-4", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      authorization:
+      - Bearer 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
+      connection:
+      - keep-alive
+      content-length:
+      - '2017'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=p1aGVyahvfLAvEwvbX0FMmrN5o18PpVAu2dG_dTgMSU-1739141229-1.0.1.1-_q7aCslZTr11IMFZ81VgyuqsGiqTARFPANUvBEWM_0dZdb97Py78KE1omxdNv5F1pFKoWUqA1kEF2wzQ2wz4aA;
+        _cfuvid=bsF0jwE67cS.ywAaQU59jKPFC03S1dvynClHm_wTQik-1739141229143-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      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-AzAN3PPgDvH836sMJBXCVRc3im99S\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1739141237,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Based on the information provided, the
+      agent appears to have completed the task, providing an output that they have
+      defined as 'full and comprehensive'. It appears that the agent has attempted
+      to meet all the expectations of the task description and has reached the goal
+      of returning a 'test output' as the final answer.\\n\\nFinal Answer: Considering
+      these aspects, for task completion, the agent receives a 10 as they have successfully
+      generated an output. For quality, the agent again receives a significant score
+      of 10, because the full and comprehensive nature of the output matches the task's
+      expectations. Finally, taking into account both the completion and quality aspects,
+      the overall performance evaluation is also 10, recognizing the perfect alignment
+      between the task's expected output and the output delivered by the agent. \\nTherefore,
+      the final evaluation score can be summarized in the below format:\\n{\\n\\\"completion\\\":
+      10,\\n\\\"quality\\\": 10,\\n\\\"overall performance\\\": 10\\n}\",\n        \"refusal\":
+      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 385,\n    \"completion_tokens\":
+      190,\n    \"total_tokens\": 575,\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\": null\n}\n"
+    headers:
+      CF-RAY:
+      - 90f7667f9bfdba33-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 09 Feb 2025 22:47:24 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '6909'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '1000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '999515'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 29ms
+      x-request-id:
+      - req_3e283ae8c1cd132001ecf2d96198bbd6
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are test. test\nYour personal
+      goal is: test\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\n\nThis is the expected
+      criteria for your final answer: test output\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-4", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      authorization:
+      - Bearer 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
+      connection:
+      - keep-alive
+      content-length:
+      - '780'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=p1aGVyahvfLAvEwvbX0FMmrN5o18PpVAu2dG_dTgMSU-1739141229-1.0.1.1-_q7aCslZTr11IMFZ81VgyuqsGiqTARFPANUvBEWM_0dZdb97Py78KE1omxdNv5F1pFKoWUqA1kEF2wzQ2wz4aA;
+        _cfuvid=bsF0jwE67cS.ywAaQU59jKPFC03S1dvynClHm_wTQik-1739141229143-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      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-AzANAznjrZdppuFIsRnEouHG8WuM0\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1739141244,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I am ready to prepare my final answer
+      based on the test output criteria provided\\nFinal Answer: I have followed all
+      the instructions provided in the task to the best of my ability, and the outcome
+      of the test is as described in the final answer. It is complete, detailed, and
+      accurate.\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      149,\n    \"completion_tokens\": 59,\n    \"total_tokens\": 208,\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\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 90f766abaaa3ba33-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 09 Feb 2025 22:47:27 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:
+      - '2533'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '1000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '999822'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 10ms
+      x-request-id:
+      - req_6ea4c81627695f58de56727aa8d8cc59
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CvwNCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS0w0KEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKaAgoQGJwIgEdh/Dq2y8ue+Gl/XxIInTNNpEL8yjQqG0NyZXcgSW5kaXZpZHVhbCBU
+      ZXN0IFJlc3VsdDABOaAPzl6/qyIYQYnY6V6/qyIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTAw
+      LjFKLgoIY3Jld19rZXkSIgogZmViMWUyMWIzMjU2YzU5YTY0NzE1MmFmZGQ2NjMyMmVKMQoHY3Jl
+      d19pZBImCiQ2YzYyNmEyZi05OGRlLTQ2ODAtOWJhNC01NWVkYzdmODhiZTNKEQoHcXVhbGl0eRIG
+      CgQxMC4wShcKCWV4ZWNfdGltZRIKCggzLjUwMzUyNkoVCgptb2RlbF9uYW1lEgcKBWdwdC00egIY
+      AYUBAAEAABL5AQoQsfCFg6/ZkEo2LShWV3X+WhII4I9o90lQzxMqE0NyZXcgVGVzdCBFeGVjdXRp
+      b24wATmWhUlfv6siGEFeYlZfv6siGEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjEwMC4xSi4KCGNy
+      ZXdfa2V5EiIKIGZlYjFlMjFiMzI1NmM1OWE2NDcxNTJhZmRkNjYzMjJlSjEKB2NyZXdfaWQSJgok
+      ZDU2ZjljMWEtYmRkMS00MDI3LWI1ZjctMzg1ZGVlMWU2YjljShEKCml0ZXJhdGlvbnMSAwoBMUoV
+      Cgptb2RlbF9uYW1lEgcKBWdwdC00egIYAYUBAAEAABKSBwoQlucrHD/mwnCU8Dl9QKzgYhIIGyix
+      8K7RcoAqDENyZXcgQ3JlYXRlZDABOTQxXF+/qyIYQamXaV+/qyIYShsKDmNyZXdhaV92ZXJzaW9u
+      EgkKBzAuMTAwLjFKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMi43Si4KCGNyZXdfa2V5EiIKIGZl
+      YjFlMjFiMzI1NmM1OWE2NDcxNTJhZmRkNjYzMjJlSjEKB2NyZXdfaWQSJgokZDU2ZjljMWEtYmRk
+      MS00MDI3LWI1ZjctMzg1ZGVlMWU2YjljShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEK
+      C2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1i
+      ZXJfb2ZfYWdlbnRzEgIYAUrFAgoLY3Jld19hZ2VudHMStQIKsgJbeyJrZXkiOiAiOTc2ZjhmNTBh
+      Y2NmZWJhMjIzZTQ5YzQyYjE2ZTk5ZTYiLCAiaWQiOiAiMzcwMzA5YTQtMDU5OS00MWVlLWFiMTgt
+      YWE1ZmQ1Mjg2ZGQ1IiwgInJvbGUiOiAidGVzdCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0
+      ZXIiOiAyNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxs
+      bSI6ICJncHQtNCIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4
+      ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtd
+      fV1K+QEKCmNyZXdfdGFza3MS6gEK5wFbeyJrZXkiOiAiZGE5NWViZGIzNmU0Y2RmOTJkZjZhNmRk
+      MTZiY2VlMGUiLCAiaWQiOiAiZTBmNDgzNjAtYzNjNS00ZGY1LThkZjEtNDg2ZTc4OWNiZWUyIiwg
+      ImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRf
+      cm9sZSI6ICJ0ZXN0IiwgImFnZW50X2tleSI6ICI5NzZmOGY1MGFjY2ZlYmEyMjNlNDljNDJiMTZl
+      OTllNiIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChA4OLnKHp32b0EUM2g5rs+r
+      EgjifMpu5dQ6xCoMVGFzayBDcmVhdGVkMAE5x1d3X7+rIhhBMxF4X7+rIhhKLgoIY3Jld19rZXkS
+      IgogZmViMWUyMWIzMjU2YzU5YTY0NzE1MmFmZGQ2NjMyMmVKMQoHY3Jld19pZBImCiRkNTZmOWMx
+      YS1iZGQxLTQwMjctYjVmNy0zODVkZWUxZTZiOWNKLgoIdGFza19rZXkSIgogZGE5NWViZGIzNmU0
+      Y2RmOTJkZjZhNmRkMTZiY2VlMGVKMQoHdGFza19pZBImCiRlMGY0ODM2MC1jM2M1LTRkZjUtOGRm
+      MS00ODZlNzg5Y2JlZTJ6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1791'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Sun, 09 Feb 2025 22:47:29 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Task Execution Evaluator.
+      Evaluator agent for crew evaluation with precise capabilities to evaluate the
+      performance of the agents in the crew based on the tasks they have performed\nYour
+      personal goal is: Your goal is to evaluate the performance of the agents in
+      the crew based on the tasks they have performed using score from 1 to 10 evaluating
+      on completion, quality, and overall performance.\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:
+      Based on the task description and the expected output, compare and evaluate
+      the performance of the agents in the crew based on the Task Output they have
+      performed using score from 1 to 10 evaluating on completion, quality, and overall
+      performance.task_description: test task_expected_output: test output agent:
+      test agent_goal: test Task Output: I have followed all the instructions provided
+      in the task to the best of my ability, and the outcome of the test is as described
+      in the final answer. It is complete, detailed, and accurate.\n\nThis is the
+      expected criteria for your final answer: Evaluation Score from 1 to 10 based
+      on the performance of the agents on the tasks\nyou MUST return the actual complete
+      content as the final answer, not a summary.\nEnsure your final answer contains
+      only the content in the following format: {\n  \"quality\": float\n}\n\nEnsure
+      the final output does not include any code block markers like ```json or ```python.\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-4", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      authorization:
+      - Bearer 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
+      connection:
+      - keep-alive
+      content-length:
+      - '1935'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=p1aGVyahvfLAvEwvbX0FMmrN5o18PpVAu2dG_dTgMSU-1739141229-1.0.1.1-_q7aCslZTr11IMFZ81VgyuqsGiqTARFPANUvBEWM_0dZdb97Py78KE1omxdNv5F1pFKoWUqA1kEF2wzQ2wz4aA;
+        _cfuvid=bsF0jwE67cS.ywAaQU59jKPFC03S1dvynClHm_wTQik-1739141229143-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      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-AzANDGSiRIu1XO56ZMfLuO2SuL4l0\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1739141247,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Looking at the task output provided by
+      the agent, the agent has expressed a high level of confidence in their ability
+      to follow the instructions provided to the best of their ability. The agent
+      seems to have executed the task with detailed attention and accuracy.\\n\\nI
+      need to evaluate both the quality and the overall performance of the agent keeping
+      in mind the task description and the expected output. Given the agent's output
+      and goal, I can deduce the quality of their work as well as their overall performance.\\n\\nFinal
+      Answer: \\n{\\n  \\\"quality\\\": 8.5\\n}\",\n        \"refusal\": null\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 372,\n    \"completion_tokens\": 112,\n
+      \   \"total_tokens\": 484,\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\": null\n}\n"
+    headers:
+      CF-RAY:
+      - 90f766bc4d87ba33-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 09 Feb 2025 22:47:32 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '5056'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '1000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '999535'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 27ms
+      x-request-id:
+      - req_ff2926b015823a70e2173c71f8d63209
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/utilities/evaluators/test_custom_llm_support.py

@@ -0,0 +1,71 @@
+from unittest.mock import MagicMock
+
+import pytest
+
+from crewai.agent import Agent
+from crewai.crew import Crew
+from crewai.llm import LLM
+from crewai.task import Task
+from crewai.utilities.evaluators.crew_evaluator_handler import CrewEvaluator
+
+
+@pytest.mark.vcr()
+def test_crew_test_with_custom_llm():
+    """Test Crew.test() with both string model name and LLM instance."""
+
+    # Setup
+    agent = Agent(
+        role="test",
+        goal="test",
+        backstory="test",
+        llm=LLM(model="gpt-4"),
+    )
+    task = Task(
+        description="test",
+        expected_output="test output",
+        agent=agent,
+    )
+    crew = Crew(agents=[agent], tasks=[task])
+
+    # Test with string model name
+    crew.test(n_iterations=1, llm="gpt-4")
+
+    # Test with LLM instance
+    custom_llm = LLM(model="gpt-4")
+    crew.test(n_iterations=1, llm=custom_llm)
+
+    # Test backward compatibility
+    crew.test(n_iterations=1, openai_model_name="gpt-4")
+
+    # Test error when neither parameter is provided
+    with pytest.raises(ValueError, match="Must provide either 'llm' or 'openai_model_name' parameter"):
+        crew.test(n_iterations=1)
+
+def test_crew_evaluator_with_custom_llm():
+    # Setup
+    agent = Agent(
+        role="test",
+        goal="test",
+        backstory="test",
+        llm=LLM(model="gpt-4"),
+    )
+    task = Task(
+        description="test",
+        expected_output="test output",
+        agent=agent,
+    )
+    crew = Crew(agents=[agent], tasks=[task])
+
+    # Test with string model name
+    evaluator = CrewEvaluator(crew, "gpt-4")
+    assert isinstance(evaluator.llm, LLM)
+    assert evaluator.llm.model == "gpt-4"
+
+    # Test with LLM instance
+    custom_llm = LLM(model="gpt-4")
+    evaluator = CrewEvaluator(crew, custom_llm)
+    assert evaluator.llm == custom_llm
+
+    # Test that evaluator agent uses the correct LLM
+    evaluator_agent = evaluator._evaluator_agent()
+    assert evaluator_agent.llm == evaluator.llm